diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Dataset/UniversalBank.csv b/Loan Status Prediction/Bank Loan Approval Prediction/Dataset/UniversalBank.csv new file mode 100644 index 00000000..1cb9db73 --- /dev/null +++ b/Loan Status Prediction/Bank Loan Approval Prediction/Dataset/UniversalBank.csv @@ -0,0 +1,5001 @@ +ID,Age,Experience,Income,ZIP Code,Family,CCAvg,Education,Mortgage,Personal Loan,Securities Account,CD Account,Online,CreditCard +1,25,1,49,91107,4,1.60,1,0,0,1,0,0,0 +2,45,19,34,90089,3,1.50,1,0,0,1,0,0,0 +3,39,15,11,94720,1,1.00,1,0,0,0,0,0,0 +4,35,9,100,94112,1,2.70,2,0,0,0,0,0,0 +5,35,8,45,91330,4,1.00,2,0,0,0,0,0,1 +6,37,13,29,92121,4,0.40,2,155,0,0,0,1,0 +7,53,27,72,91711,2,1.50,2,0,0,0,0,1,0 +8,50,24,22,93943,1,0.30,3,0,0,0,0,0,1 +9,35,10,81,90089,3,0.60,2,104,0,0,0,1,0 +10,34,9,180,93023,1,8.90,3,0,1,0,0,0,0 +11,65,39,105,94710,4,2.40,3,0,0,0,0,0,0 +12,29,5,45,90277,3,0.10,2,0,0,0,0,1,0 +13,48,23,114,93106,2,3.80,3,0,0,1,0,0,0 +14,59,32,40,94920,4,2.50,2,0,0,0,0,1,0 +15,67,41,112,91741,1,2.00,1,0,0,1,0,0,0 +16,60,30,22,95054,1,1.50,3,0,0,0,0,1,1 +17,38,14,130,95010,4,4.70,3,134,1,0,0,0,0 +18,42,18,81,94305,4,2.40,1,0,0,0,0,0,0 +19,46,21,193,91604,2,8.10,3,0,1,0,0,0,0 +20,55,28,21,94720,1,0.50,2,0,0,1,0,0,1 +21,56,31,25,94015,4,0.90,2,111,0,0,0,1,0 +22,57,27,63,90095,3,2.00,3,0,0,0,0,1,0 +23,29,5,62,90277,1,1.20,1,260,0,0,0,1,0 +24,44,18,43,91320,2,0.70,1,163,0,1,0,0,0 +25,36,11,152,95521,2,3.90,1,159,0,0,0,0,1 +26,43,19,29,94305,3,0.50,1,97,0,0,0,1,0 +27,40,16,83,95064,4,0.20,3,0,0,0,0,0,0 +28,46,20,158,90064,1,2.40,1,0,0,0,0,1,1 +29,56,30,48,94539,1,2.20,3,0,0,0,0,1,1 +30,38,13,119,94104,1,3.30,2,0,1,0,1,1,1 +31,59,35,35,93106,1,1.20,3,122,0,0,0,1,0 +32,40,16,29,94117,1,2.00,2,0,0,0,0,1,0 +33,53,28,41,94801,2,0.60,3,193,0,0,0,0,0 +34,30,6,18,91330,3,0.90,3,0,0,0,0,0,0 +35,31,5,50,94035,4,1.80,3,0,0,0,0,1,0 +36,48,24,81,92647,3,0.70,1,0,0,0,0,0,0 +37,59,35,121,94720,1,2.90,1,0,0,0,0,0,1 +38,51,25,71,95814,1,1.40,3,198,0,0,0,0,0 +39,42,18,141,94114,3,5.00,3,0,1,1,1,1,0 +40,38,13,80,94115,4,0.70,3,285,0,0,0,1,0 +41,57,32,84,92672,3,1.60,3,0,0,1,0,0,0 +42,34,9,60,94122,3,2.30,1,0,0,0,0,0,0 +43,32,7,132,90019,4,1.10,2,412,1,0,0,1,0 +44,39,15,45,95616,1,0.70,1,0,0,0,0,1,0 +45,46,20,104,94065,1,5.70,1,0,0,0,0,1,1 +46,57,31,52,94720,4,2.50,1,0,0,0,0,0,1 +47,39,14,43,95014,3,0.70,2,153,0,0,0,1,0 +48,37,12,194,91380,4,0.20,3,211,1,1,1,1,1 +49,56,26,81,95747,2,4.50,3,0,0,0,0,0,1 +50,40,16,49,92373,1,1.80,1,0,0,0,0,0,1 +51,32,8,8,92093,4,0.70,2,0,0,1,0,1,0 +52,61,37,131,94720,1,2.90,1,0,0,0,0,1,0 +53,30,6,72,94005,1,0.10,1,207,0,0,0,0,0 +54,50,26,190,90245,3,2.10,3,240,1,0,0,1,0 +55,29,5,44,95819,1,0.20,3,0,0,0,0,1,0 +56,41,17,139,94022,2,8.00,1,0,0,0,0,1,0 +57,55,30,29,94005,3,0.10,2,0,0,1,1,1,0 +58,56,31,131,95616,2,1.20,3,0,1,0,0,0,0 +59,28,2,93,94065,2,0.20,1,0,0,0,0,0,0 +60,31,5,188,91320,2,4.50,1,455,0,0,0,0,0 +61,49,24,39,90404,3,1.70,2,0,0,1,0,1,0 +62,47,21,125,93407,1,5.70,1,112,0,1,0,0,0 +63,42,18,22,90089,1,1.00,1,0,0,0,0,0,0 +64,42,17,32,94523,4,0.00,2,0,0,0,0,1,0 +65,47,23,105,90024,2,3.30,1,0,0,0,0,0,0 +66,59,35,131,91360,1,3.80,1,0,0,0,0,1,1 +67,62,36,105,95670,2,2.80,1,336,0,0,0,0,0 +68,53,23,45,95123,4,2.00,3,132,0,1,0,0,0 +69,47,21,60,93407,3,2.10,1,0,0,0,0,1,1 +70,53,29,20,90045,4,0.20,1,0,0,0,0,1,0 +71,42,18,115,91335,1,3.50,1,0,0,0,0,0,1 +72,53,29,69,93907,4,1.00,2,0,0,0,0,1,0 +73,44,20,130,92007,1,5.00,1,0,0,0,0,0,1 +74,41,16,85,94606,1,4.00,3,0,0,0,0,1,1 +75,28,3,135,94611,2,3.30,1,0,0,0,0,0,1 +76,31,7,135,94901,4,3.80,2,0,1,0,1,1,1 +77,58,32,12,91320,3,0.30,3,0,0,0,0,0,0 +78,46,20,29,92220,3,0.50,2,0,0,0,0,0,0 +79,54,30,133,93305,2,2.60,3,0,1,0,0,0,0 +80,50,26,19,94720,2,0.40,1,118,0,0,0,1,0 +81,60,36,41,95134,4,1.30,1,174,0,0,0,1,1 +82,47,22,40,94612,3,2.70,2,0,0,0,0,1,0 +83,41,16,82,92507,1,4.00,3,0,0,0,0,1,0 +84,33,9,50,94305,1,2.40,2,0,0,0,0,0,0 +85,46,22,18,91730,1,0.90,3,0,0,0,0,1,0 +86,27,2,109,94005,4,1.80,3,0,0,0,0,0,0 +87,40,16,42,94501,4,2.20,2,126,0,0,0,0,0 +88,48,22,78,94305,3,1.10,1,0,0,0,0,1,0 +89,65,41,51,94117,2,1.10,1,0,0,0,0,1,0 +90,25,-1,113,94303,4,2.30,3,0,0,0,0,0,1 +91,55,30,118,90277,4,5.60,2,0,1,0,0,1,0 +92,35,10,29,94105,4,1.10,3,0,0,0,0,1,0 +93,43,19,34,94305,3,0.60,2,0,0,0,0,0,0 +94,60,34,64,94550,2,1.70,3,236,0,1,0,1,0 +95,65,39,121,92612,1,2.00,1,0,0,0,0,0,0 +96,38,12,48,95617,4,0.20,3,0,0,0,0,1,0 +97,41,15,80,95014,1,5.20,1,0,0,0,0,0,0 +98,54,28,161,92121,1,2.90,1,0,0,0,0,1,0 +99,49,23,94,92374,1,0.30,1,0,0,0,0,1,0 +100,66,41,15,91711,3,0.10,3,0,0,0,0,1,0 +101,48,23,74,94080,1,1.20,1,0,0,0,0,1,0 +102,61,36,30,94608,3,1.30,2,0,0,0,0,0,0 +103,53,23,44,93555,3,1.00,3,198,0,0,0,1,1 +104,43,18,22,95670,2,0.30,2,0,0,0,0,1,0 +105,56,32,38,93311,4,1.30,1,166,0,0,0,1,1 +106,24,0,35,94704,3,0.10,2,0,0,1,0,1,0 +107,43,17,69,92717,4,2.90,1,0,0,0,0,1,1 +108,42,18,43,92037,1,0.70,1,136,0,0,0,0,0 +109,33,7,32,95136,1,0.60,3,166,0,0,0,1,0 +110,43,17,49,94542,1,2.80,1,0,0,0,0,1,0 +111,41,14,9,91330,3,1.00,2,0,0,0,0,0,0 +112,62,38,45,94143,4,1.30,2,0,0,0,0,1,0 +113,40,15,82,91775,3,1.00,1,309,0,0,0,0,0 +114,58,34,92,92703,2,2.80,1,103,0,0,0,0,0 +115,39,14,39,92354,3,0.50,3,0,0,0,0,1,0 +116,65,40,81,92024,3,1.80,2,0,0,0,0,1,0 +117,54,29,35,92831,1,1.50,2,0,0,0,0,1,0 +118,58,33,61,92833,2,2.30,3,193,0,0,0,1,0 +119,41,16,73,92647,3,3.00,1,0,0,0,0,1,0 +120,32,7,112,94304,1,4.60,1,366,0,0,0,0,0 +121,54,29,12,90057,2,0.20,3,0,0,0,0,1,0 +122,52,26,38,91711,3,0.90,3,0,0,0,0,1,0 +123,58,32,73,94523,2,0.70,2,0,0,0,0,1,1 +124,37,13,84,92130,1,3.60,2,0,0,1,0,0,0 +125,39,15,78,92121,4,2.40,1,118,0,0,0,1,0 +126,60,35,80,91301,3,0.50,1,0,0,0,0,1,0 +127,31,5,115,92096,2,1.30,1,101,0,0,0,1,1 +128,34,8,82,92646,1,2.70,2,251,0,0,0,1,0 +129,38,14,74,92182,2,0.00,1,0,0,1,0,1,0 +130,41,16,70,92131,3,0.50,3,0,0,0,0,0,1 +131,28,4,81,94801,3,1.50,1,276,0,0,0,1,0 +132,58,34,149,93720,4,7.20,2,0,1,0,1,1,1 +133,31,1,51,90840,2,1.75,3,0,0,0,0,0,0 +134,30,4,39,90245,3,1.10,2,0,0,0,0,1,0 +135,53,29,98,95035,3,1.80,2,0,0,0,0,0,0 +136,58,33,45,93010,4,2.10,1,0,0,0,0,1,1 +137,59,32,49,95035,4,2.50,2,0,0,0,0,1,0 +138,49,25,128,95054,2,0.40,1,0,0,0,0,0,0 +139,59,34,42,94928,3,1.50,1,0,0,1,1,0,1 +140,59,35,18,93305,1,1.20,3,0,0,0,0,1,0 +141,51,25,31,90245,2,0.40,3,161,0,0,0,1,1 +142,35,11,58,95831,3,2.00,1,149,0,0,0,1,1 +143,33,9,48,91770,1,2.10,3,0,0,0,0,0,1 +144,25,1,54,94117,4,1.60,1,0,0,0,0,1,1 +145,49,23,70,92093,2,1.50,2,0,0,0,0,0,0 +146,59,35,124,90007,1,7.40,1,0,0,0,0,0,1 +147,46,19,84,94102,1,2.67,2,0,0,0,0,1,1 +148,50,25,83,94542,4,3.60,3,188,0,0,0,1,0 +149,52,28,163,91423,2,0.40,1,116,0,0,0,1,0 +150,48,22,42,93955,3,2.20,2,0,0,0,0,0,0 +151,46,22,118,94107,2,7.50,1,0,0,0,1,1,1 +152,26,0,132,92834,3,6.50,3,0,1,0,0,0,1 +153,57,32,24,93117,1,1.30,1,0,0,0,0,1,1 +154,60,36,22,94551,2,1.00,1,0,0,1,1,1,1 +155,54,29,58,92612,4,1.30,3,0,0,0,0,0,0 +156,24,0,60,94596,4,1.60,1,0,0,0,0,1,0 +157,26,0,15,92131,4,0.40,1,0,0,0,0,0,1 +158,41,17,83,94025,4,2.67,1,0,0,0,0,1,1 +159,32,6,79,94720,2,1.50,3,0,0,0,0,1,1 +160,61,35,41,94545,4,1.70,2,0,0,1,0,1,0 +161,29,0,134,95819,4,6.50,3,0,1,0,0,0,0 +162,61,35,80,95053,2,2.80,1,0,0,0,0,1,0 +163,38,12,52,90036,1,2.00,1,0,0,0,0,0,0 +164,28,4,70,91125,4,2.60,1,0,0,0,0,1,0 +165,53,27,92,95120,2,1.10,1,0,0,1,0,0,0 +166,27,1,43,94706,1,1.50,1,0,0,0,0,1,0 +167,25,1,21,95827,3,1.00,2,0,0,0,0,0,0 +168,33,9,23,94305,3,0.90,3,0,0,0,0,1,1 +169,50,26,13,91320,4,1.00,1,0,0,0,0,1,0 +170,27,1,112,90503,4,2.10,3,0,0,0,0,0,1 +171,27,1,138,90250,2,2.00,1,0,0,0,0,1,0 +172,52,28,11,95817,3,0.40,1,0,0,1,0,0,0 +173,38,13,171,92717,2,7.80,1,0,0,0,0,1,0 +174,58,34,42,90095,4,1.50,1,0,0,0,0,1,1 +175,42,17,168,95503,2,7.90,2,0,1,0,0,1,0 +176,45,20,85,91711,4,1.10,2,0,0,1,0,1,0 +177,52,25,44,93111,3,1.00,2,135,0,0,0,1,0 +178,29,3,65,94132,4,1.80,2,244,0,0,0,0,0 +179,53,29,24,95818,4,0.20,1,0,0,0,0,1,1 +180,62,37,11,91942,1,0.10,1,0,0,0,0,1,0 +181,51,27,38,90401,2,1.00,3,164,0,0,0,1,0 +182,36,12,10,93524,4,0.70,2,81,0,0,0,0,0 +183,24,0,135,95133,1,1.50,1,0,0,0,0,1,0 +184,29,3,148,92173,3,4.10,1,0,1,0,0,1,0 +185,52,26,63,92717,2,1.50,2,0,0,1,0,1,0 +186,39,14,115,91320,1,1.00,3,0,0,0,0,1,0 +187,48,23,45,95616,1,0.30,1,0,0,0,0,1,1 +188,46,21,159,94305,3,1.90,3,315,1,0,0,1,0 +189,64,40,169,91320,2,2.10,1,122,0,0,0,1,0 +190,55,29,112,94043,2,1.40,1,0,0,0,0,1,0 +191,60,36,93,92521,1,4.30,1,0,0,0,0,1,0 +192,51,25,29,90404,1,0.30,3,140,0,0,0,0,0 +193,50,23,85,92122,1,2.67,2,0,0,0,0,1,0 +194,48,24,21,93118,4,0.60,1,0,0,0,0,1,1 +195,53,29,144,92697,2,6.80,1,0,0,0,0,1,0 +196,34,10,13,94577,4,1.00,1,95,0,1,0,1,0 +197,48,24,165,93407,1,5.00,1,0,0,0,0,0,1 +198,55,31,9,91345,4,0.70,1,89,0,0,0,1,0 +199,27,3,59,94123,4,0.00,1,90,0,1,0,1,0 +200,36,11,158,92152,1,5.10,3,0,1,0,1,1,1 +201,32,6,29,91355,1,1.90,3,0,0,0,0,1,1 +202,35,9,20,94609,2,1.40,3,0,0,0,0,1,1 +203,30,3,68,94306,4,2.00,2,0,0,0,0,1,0 +204,58,34,65,95747,4,2.20,1,0,0,0,0,1,0 +205,56,31,61,96150,2,1.90,2,105,0,0,0,0,0 +206,38,12,91,95616,4,1.40,2,100,0,0,0,0,1 +207,49,25,31,91355,1,1.00,1,0,0,1,0,1,0 +208,34,10,71,94115,4,0.10,2,0,0,0,0,0,0 +209,40,16,73,94110,4,2.67,1,0,0,0,0,1,1 +210,64,39,172,94707,4,3.10,1,282,1,0,1,1,1 +211,51,26,20,92131,2,0.00,1,0,0,0,0,0,0 +212,44,18,55,94720,1,0.20,1,0,0,0,0,0,0 +213,46,22,69,91604,2,1.70,1,209,0,0,0,0,0 +214,57,33,155,91326,1,7.40,1,0,0,0,0,1,0 +215,54,28,94,90291,1,1.90,2,0,0,0,0,0,0 +216,38,14,92,95818,2,0.00,1,249,0,0,0,1,1 +217,27,3,125,95521,2,0.60,1,0,0,0,0,0,0 +218,39,14,74,94305,3,3.00,1,0,0,0,0,0,0 +219,44,20,72,92807,3,0.30,3,0,0,0,0,1,0 +220,56,30,61,94707,1,2.20,3,0,0,0,0,1,1 +221,32,6,25,92130,2,0.30,1,0,0,0,0,0,1 +222,45,19,83,95051,2,1.70,2,0,0,0,0,1,0 +223,26,2,104,94306,3,2.50,1,0,0,0,0,0,0 +224,55,25,41,95014,3,1.00,3,0,0,0,0,1,0 +225,52,27,58,94305,4,1.80,3,91,0,0,0,0,0 +226,39,13,93,94720,1,1.50,3,0,0,0,0,0,1 +227,24,-1,39,94085,2,1.70,2,0,0,0,0,0,0 +228,47,23,148,94551,2,7.50,1,0,0,0,1,1,1 +229,47,22,53,92677,4,1.90,3,98,0,1,1,0,1 +230,48,24,71,93117,2,1.70,1,145,0,0,0,0,1 +231,47,22,92,94720,1,2.80,2,0,0,0,0,1,0 +232,35,10,61,94304,4,2.10,3,0,0,0,0,1,0 +233,46,19,38,94122,3,2.50,2,135,0,0,0,0,0 +234,62,37,58,91320,4,1.70,1,0,0,0,0,1,0 +235,26,1,80,95616,1,0.80,2,150,0,0,0,0,0 +236,38,8,71,94720,4,1.80,3,0,0,0,0,1,0 +237,43,18,89,93407,3,0.50,3,0,0,0,0,1,1 +238,62,38,83,92521,1,1.80,3,0,0,0,0,1,0 +239,57,32,28,95831,3,0.20,1,0,0,0,0,1,1 +240,28,3,52,94112,4,1.70,2,0,0,0,0,0,0 +241,51,26,70,90089,1,1.20,1,169,0,0,0,0,0 +242,48,22,71,91711,1,1.40,3,0,0,0,0,0,1 +243,41,16,75,94005,1,3.70,3,280,0,0,0,0,0 +244,65,39,170,90095,3,7.90,3,99,1,0,1,1,0 +245,41,17,78,94025,4,0.80,1,78,0,0,0,1,0 +246,35,11,25,92614,2,1.00,2,0,0,0,0,0,0 +247,38,14,60,94025,2,0.60,3,0,0,0,0,1,1 +248,53,29,120,92626,4,2.70,2,111,1,1,1,1,0 +249,55,29,99,92121,2,1.40,1,264,0,0,0,1,1 +250,26,1,55,90089,3,2.60,3,113,0,0,0,0,1 +251,30,6,29,94305,3,1.00,2,117,0,0,0,0,0 +252,54,28,170,92182,2,6.20,2,325,1,0,0,1,0 +253,65,40,53,91711,3,2.20,1,0,0,0,0,0,1 +254,47,21,138,94583,1,0.00,1,0,0,0,0,0,0 +255,65,41,134,91942,3,3.90,3,121,1,0,0,1,0 +256,66,40,42,92103,2,0.70,3,138,0,0,0,0,1 +257,26,0,99,92697,4,2.30,3,0,0,0,0,0,1 +258,66,41,18,92691,3,0.50,1,0,0,0,0,0,1 +259,35,9,24,95747,4,0.30,1,0,0,0,0,1,0 +260,56,30,55,94107,1,1.40,1,77,0,0,0,1,0 +261,51,27,58,92407,1,0.00,1,0,0,0,0,0,1 +262,42,16,111,93106,2,1.20,3,251,1,0,0,1,0 +263,49,23,33,90245,1,0.30,3,0,0,0,1,1,1 +264,27,1,74,92121,4,1.80,2,112,0,0,0,1,1 +265,45,19,38,90840,2,0.70,1,0,0,0,0,0,0 +266,49,23,23,94305,4,0.60,3,98,0,1,0,0,0 +267,63,38,61,94720,2,1.50,1,0,0,0,0,1,0 +268,47,22,81,90504,1,2.90,1,138,0,0,0,0,0 +269,64,39,129,94002,1,2.50,1,0,0,0,0,1,0 +270,43,13,33,95039,1,0.75,3,0,0,0,0,0,0 +271,60,36,63,94063,4,2.20,1,0,0,0,0,1,0 +272,40,14,70,94923,4,1.40,2,0,0,0,0,1,0 +273,29,3,45,95023,4,0.20,1,158,0,0,0,1,1 +274,41,16,65,90095,3,0.50,3,0,0,0,0,1,0 +275,30,5,74,95616,4,2.20,1,0,0,1,0,0,1 +276,49,24,50,94706,4,1.80,3,0,0,1,0,0,0 +277,30,5,22,90058,4,0.50,3,109,0,0,0,1,0 +278,29,2,30,92126,4,1.00,3,0,0,0,0,0,0 +279,50,26,21,91125,4,1.00,1,0,0,0,0,1,0 +280,39,14,155,94577,2,3.90,1,0,0,0,0,1,0 +281,33,8,64,92121,4,2.10,3,164,0,0,0,1,0 +282,57,31,65,94118,4,2.60,3,0,0,0,0,0,1 +283,34,9,71,91711,4,0.70,3,0,0,0,0,1,0 +284,61,36,40,90029,3,0.50,2,0,0,1,0,1,0 +285,44,19,69,92806,3,0.50,3,0,0,0,0,1,0 +286,40,13,69,94305,3,2.33,2,0,0,0,0,0,0 +287,51,25,45,94806,3,0.60,2,131,0,0,0,1,0 +288,37,12,62,92110,3,0.70,2,0,0,0,0,0,1 +289,44,19,172,94306,2,4.30,3,391,1,1,1,1,0 +290,42,15,24,92121,3,1.00,2,0,0,0,0,1,1 +291,51,25,80,92373,1,4.90,1,0,0,0,0,0,0 +292,43,16,8,90089,3,0.67,2,88,0,0,0,1,0 +293,30,5,38,94542,4,0.80,1,129,0,0,0,1,1 +294,45,19,93,90095,4,2.60,3,0,0,0,0,0,0 +295,35,9,55,94536,1,2.00,1,0,0,0,0,1,0 +296,60,34,64,94304,2,1.70,3,0,0,0,0,0,1 +297,34,9,122,90623,1,0.00,1,0,0,0,0,1,0 +298,55,25,70,93720,3,1.40,3,0,0,0,0,1,0 +299,43,19,81,92069,2,3.20,1,0,0,0,0,0,0 +300,41,15,159,90057,1,5.50,3,0,1,0,1,1,0 +301,34,9,70,92843,4,1.30,1,0,0,1,0,0,0 +302,65,39,150,92120,2,6.90,1,196,0,0,0,0,0 +303,45,21,152,94550,2,7.50,1,0,0,0,0,1,0 +304,49,25,195,95605,4,3.00,1,617,1,0,0,0,0 +305,48,23,22,90740,1,0.10,1,0,0,0,0,0,0 +306,60,35,22,91207,1,1.30,1,123,0,0,0,1,0 +307,55,29,79,92373,3,0.80,1,0,0,0,0,1,1 +308,42,18,33,90401,1,1.40,3,0,0,0,0,1,0 +309,32,8,128,94720,2,4.33,1,0,0,0,1,1,1 +310,62,38,91,95929,1,3.80,1,0,0,1,0,1,0 +311,57,32,39,90277,4,0.90,1,0,0,0,0,1,1 +312,52,26,121,94550,1,7.30,1,167,0,0,0,1,0 +313,36,6,21,91741,1,0.67,3,0,0,1,0,1,0 +314,34,9,41,93720,3,2.30,1,0,0,0,0,0,1 +315,63,37,45,93437,2,0.70,3,0,0,0,0,1,0 +316,24,-2,51,90630,3,0.30,3,0,0,0,0,1,0 +317,57,31,165,95054,1,1.60,2,0,1,0,0,1,0 +318,40,16,119,91335,2,4.20,2,0,1,0,0,1,0 +319,27,2,110,95670,4,1.80,3,190,0,0,0,1,0 +320,65,39,20,90034,3,0.70,2,0,0,0,0,0,1 +321,60,34,64,90266,1,0.80,2,248,0,0,0,0,0 +322,44,20,101,92717,3,4.40,2,82,1,0,0,0,0 +323,63,39,101,92007,1,3.90,1,0,1,1,1,1,0 +324,59,34,99,90034,1,4.40,1,0,1,0,0,0,0 +325,56,30,158,90089,4,6.10,1,0,1,0,0,0,0 +326,54,28,89,95039,1,1.90,2,0,0,0,0,1,1 +327,52,27,80,95616,1,1.30,3,0,0,0,1,1,1 +328,58,32,114,91330,2,2.00,1,402,0,0,0,1,0 +329,60,35,49,94110,3,0.50,2,0,0,0,0,1,1 +330,28,4,191,90064,1,6.33,1,0,0,0,0,1,0 +331,54,30,78,92374,4,1.00,2,0,0,0,0,1,0 +332,32,6,28,94115,3,1.00,1,0,0,0,0,0,0 +333,59,33,42,95630,1,0.80,2,0,0,0,0,1,0 +334,63,38,140,92407,1,2.50,1,0,0,0,0,0,0 +335,48,23,45,95053,1,1.30,2,0,0,0,0,1,0 +336,56,32,122,95827,2,0.30,1,360,0,0,1,1,1 +337,36,12,65,95051,3,2.60,2,0,0,0,0,1,0 +338,57,27,68,94117,1,1.40,3,0,0,0,0,1,0 +339,29,3,153,93657,2,2.00,1,392,0,0,0,0,0 +340,39,13,89,92110,4,1.40,2,0,0,0,0,0,0 +341,59,34,91,93524,1,2.60,1,0,0,0,0,1,1 +342,31,6,55,92038,4,2.00,2,185,0,0,0,1,0 +343,43,19,118,91304,2,3.30,1,0,0,0,0,0,1 +344,35,5,22,93407,1,0.67,3,103,0,0,0,0,0 +345,54,24,63,92606,3,1.40,3,138,0,0,0,1,1 +346,51,27,12,92192,4,0.50,2,78,0,1,0,1,0 +347,44,19,50,90745,3,2.70,2,0,0,0,0,1,0 +348,25,0,43,94305,2,1.60,3,0,0,1,1,1,1 +349,40,15,173,95060,4,6.60,1,0,1,0,1,1,1 +350,26,2,60,93407,2,3.00,1,132,1,0,0,0,0 +351,39,14,113,94301,1,1.00,3,0,0,1,0,1,0 +352,28,4,155,92182,4,5.30,2,0,1,0,0,1,0 +353,52,28,91,92692,4,1.00,2,0,0,0,0,0,1 +354,53,29,55,95818,4,1.10,2,0,0,0,0,1,0 +355,44,20,173,90277,2,1.40,1,419,0,0,0,1,0 +356,43,19,71,92101,3,0.30,3,0,0,0,0,0,1 +357,56,30,24,94704,2,0.40,3,88,0,0,0,0,0 +358,38,14,42,94610,1,2.00,2,81,0,0,0,1,0 +359,30,6,141,94539,2,4.33,1,0,0,0,0,1,0 +360,32,6,32,93106,1,1.90,3,0,0,0,0,1,0 +361,35,10,55,94539,4,1.30,1,0,0,0,0,0,0 +362,43,19,153,90254,2,7.50,1,0,0,0,0,1,0 +363,58,32,113,94590,2,1.40,1,270,0,0,0,0,1 +364,25,0,30,92691,2,1.70,2,0,0,0,0,0,0 +365,54,24,29,92028,3,1.00,3,148,0,0,0,0,1 +366,57,32,174,90089,1,6.80,2,466,1,0,0,1,0 +367,50,24,35,92717,1,0.30,3,0,0,0,0,1,0 +368,32,8,98,95054,2,2.00,2,175,0,0,0,1,0 +369,63,37,30,92054,2,1.00,3,159,0,0,0,1,0 +370,31,6,58,95051,2,2.50,1,0,0,0,0,0,1 +371,36,12,25,92101,4,1.00,1,147,0,0,0,0,0 +372,58,34,19,92029,4,0.70,1,0,0,0,0,0,0 +373,56,30,44,93105,4,0.70,2,174,0,0,0,1,0 +374,49,25,20,90291,4,1.00,1,111,0,0,0,1,1 +375,30,5,98,91941,2,3.10,1,220,0,0,0,1,0 +376,33,7,90,92346,3,1.60,1,0,0,0,0,1,0 +377,45,21,61,94304,3,0.70,1,0,0,0,0,0,0 +378,30,5,40,94402,4,2.00,2,0,0,0,0,1,0 +379,47,23,38,94618,2,2.10,3,0,0,0,0,0,0 +380,25,0,28,92093,2,1.70,2,0,0,0,0,0,0 +381,63,33,34,94305,1,1.50,3,0,0,0,0,1,1 +382,55,29,73,95616,2,2.30,3,0,0,0,0,1,1 +383,65,41,133,94904,4,2.00,1,0,1,0,0,0,1 +384,44,18,53,94608,1,0.20,1,0,0,0,0,1,0 +385,51,25,21,9307,4,0.60,3,0,0,0,0,1,1 +386,35,9,40,93943,3,0.90,1,0,0,0,0,1,0 +387,30,5,41,95051,4,1.70,2,0,0,0,0,1,0 +388,31,5,82,95482,4,1.80,2,0,0,0,0,1,0 +389,54,30,100,95814,4,3.40,3,0,1,0,0,0,0 +390,45,20,155,90024,1,7.00,1,0,0,0,0,1,1 +391,45,19,45,92521,1,0.20,1,0,0,0,0,1,0 +392,58,32,9,94080,3,0.30,3,0,0,0,0,0,1 +393,54,29,48,91709,4,1.80,3,0,0,0,0,1,0 +394,53,28,18,90095,4,0.10,3,109,0,1,1,1,1 +395,33,9,80,91311,4,3.40,1,0,0,0,0,1,1 +396,60,35,64,94509,2,2.80,1,0,0,0,0,0,0 +397,50,24,29,93023,4,0.10,1,0,0,0,0,0,0 +398,26,2,48,90503,3,0.70,2,0,0,0,0,1,0 +399,54,30,23,94608,2,0.40,1,0,0,0,0,0,0 +400,28,3,84,90024,4,0.20,1,0,0,0,0,1,1 +401,36,10,179,94542,3,6.60,1,0,1,0,0,1,0 +402,29,2,30,95747,4,1.50,2,112,0,0,0,0,1 +403,54,28,93,91604,1,4.90,1,133,0,0,1,1,1 +404,55,30,39,92647,2,1.90,2,0,0,0,0,0,0 +405,61,36,60,92866,3,0.50,2,182,0,0,0,0,0 +406,36,11,133,90245,1,3.80,1,290,0,1,1,1,1 +407,45,19,125,92354,1,2.40,1,0,0,0,0,0,0 +408,64,40,58,93437,1,1.80,3,0,0,0,0,1,0 +409,60,36,89,91745,2,2.80,1,0,0,0,0,1,0 +410,49,22,82,90019,1,2.67,2,125,0,0,0,1,0 +411,47,23,110,94111,2,3.30,1,0,0,0,0,1,1 +412,60,36,54,92182,4,2.30,3,0,0,1,0,0,0 +413,45,20,89,93311,4,1.90,3,0,0,0,0,1,0 +414,32,7,42,92407,3,2.30,1,0,0,0,0,1,0 +415,52,28,41,94309,3,1.90,2,0,0,0,0,0,1 +416,35,8,38,93106,4,1.00,2,124,0,0,0,1,0 +417,40,15,85,94304,2,0.40,1,0,0,0,0,1,0 +418,53,29,83,90073,4,1.00,2,0,0,0,0,1,0 +419,27,0,33,90089,4,1.00,3,0,0,0,0,0,0 +420,58,33,50,94501,4,2.10,1,0,0,0,0,0,1 +421,47,22,58,93105,4,3.60,3,0,0,0,0,1,1 +422,28,3,115,92333,4,3.10,2,0,1,0,0,0,0 +423,46,20,145,91380,2,6.30,1,0,0,1,1,1,0 +424,43,19,161,95616,2,7.50,1,0,0,0,0,0,0 +425,56,30,38,92029,1,0.20,1,0,0,0,0,0,0 +426,28,3,28,90505,4,0.80,1,0,0,0,0,1,0 +427,42,18,75,92182,3,2.33,1,0,0,0,0,0,1 +428,32,7,35,92521,3,1.30,1,116,0,0,0,0,1 +429,62,38,24,94720,2,1.00,1,116,0,0,0,0,1 +430,37,13,78,94998,4,0.10,2,0,0,0,0,1,0 +431,51,26,113,94086,1,1.30,3,161,0,0,0,1,0 +432,39,13,75,94305,3,2.10,1,224,0,0,0,1,0 +433,43,17,91,91311,1,5.70,1,0,0,0,0,1,0 +434,52,28,31,91330,4,0.20,1,141,0,0,0,1,1 +435,30,6,45,95819,1,1.80,2,0,0,0,0,1,0 +436,52,26,80,94709,3,0.80,1,0,0,0,0,0,0 +437,61,35,50,92122,3,1.40,3,112,0,0,0,1,0 +438,36,9,31,95825,4,1.00,2,0,0,1,0,1,0 +439,58,32,113,93943,2,3.80,2,119,1,0,1,1,1 +440,47,23,29,94304,4,0.60,1,0,0,0,0,1,0 +441,64,39,59,92626,2,1.50,1,139,0,0,0,1,0 +442,52,27,43,93555,1,1.30,2,0,0,1,0,1,0 +443,58,28,122,95136,1,3.00,3,115,1,0,0,1,0 +444,48,24,29,90509,1,1.00,1,0,0,0,0,0,0 +445,64,40,91,93106,2,0.00,3,0,0,0,0,1,1 +446,58,32,65,94590,3,2.20,3,0,0,0,0,1,0 +447,47,23,22,93108,1,1.00,1,0,0,0,0,0,1 +448,49,23,71,95134,1,1.40,3,0,0,0,0,0,0 +449,31,4,60,94588,4,2.00,2,0,0,0,0,1,1 +450,61,37,60,91706,3,2.00,3,0,0,0,0,1,0 +451,51,25,69,95747,1,0.30,1,0,0,0,0,1,1 +452,28,-2,48,94132,2,1.75,3,89,0,0,0,1,0 +453,39,13,21,94022,3,0.20,2,0,0,0,0,0,0 +454,54,28,53,92109,4,2.80,2,0,0,1,0,0,0 +455,50,24,29,94110,3,0.90,3,0,0,0,0,0,0 +456,30,4,60,91107,4,2.20,2,0,0,0,0,1,0 +457,64,39,42,92068,3,0.50,2,116,0,0,0,1,0 +458,29,3,69,94303,3,0.30,3,0,0,0,0,0,0 +459,48,24,20,95841,1,1.00,1,0,0,0,0,1,1 +460,35,10,200,91107,2,3.00,1,458,0,0,0,0,0 +461,60,36,141,90277,2,2.10,1,0,0,0,0,1,1 +462,55,30,81,92123,2,3.70,1,0,0,1,0,0,0 +463,29,4,183,91423,3,8.30,3,0,1,0,0,1,0 +464,48,22,149,94928,2,5.50,2,0,1,1,1,1,0 +465,43,19,83,94305,4,3.60,3,0,1,0,0,0,1 +466,66,42,35,94305,1,1.90,2,172,0,0,0,1,0 +467,25,0,13,91342,2,0.90,3,0,0,0,0,1,0 +468,45,20,39,90232,1,2.40,1,0,0,0,0,0,1 +469,34,10,21,92634,1,0.50,3,0,0,0,0,1,0 +470,48,23,10,94609,2,0.70,3,0,0,0,0,1,1 +471,32,6,84,91006,4,1.80,2,0,0,0,0,0,0 +472,50,24,30,91768,4,0.10,1,161,0,0,0,1,1 +473,43,19,31,90007,4,0.30,1,156,0,0,0,1,0 +474,64,39,182,93955,1,1.20,2,547,1,0,0,1,0 +475,60,34,114,90028,2,6.90,1,0,0,0,0,1,0 +476,43,19,152,92008,3,6.10,2,0,1,0,0,0,0 +477,60,34,53,92717,1,0.80,2,0,0,1,0,0,1 +478,64,39,24,95112,4,0.40,2,78,0,0,0,1,0 +479,44,20,150,95060,2,3.30,1,0,0,0,0,0,1 +480,60,36,132,92154,2,6.00,1,470,0,0,0,1,1 +481,54,29,68,94998,3,1.60,3,0,0,0,0,1,1 +482,33,9,53,94063,1,1.20,1,0,0,0,0,0,1 +483,56,32,173,94022,1,4.60,2,88,1,0,1,1,0 +484,29,5,30,90095,3,1.00,2,0,0,0,0,0,0 +485,25,1,113,95023,2,0.20,1,0,0,0,0,1,1 +486,60,34,15,95014,1,0.80,2,0,0,0,0,1,0 +487,55,30,84,92173,2,3.70,1,304,0,1,0,1,0 +488,39,13,88,94117,4,1.40,2,0,0,0,0,1,1 +489,37,13,43,94122,3,2.80,1,0,0,0,0,1,0 +490,53,28,43,91380,2,2.10,3,0,0,0,1,1,1 +491,34,10,90,94303,2,2.70,1,0,0,0,0,1,0 +492,42,18,34,92115,4,0.30,1,104,0,1,0,1,0 +493,60,36,38,94596,4,1.30,1,0,0,0,0,1,0 +494,50,24,173,94720,1,1.00,1,0,0,0,0,1,1 +495,41,17,160,92647,2,8.00,1,0,0,0,0,1,0 +496,25,0,44,94545,4,0.60,2,0,0,0,0,1,1 +497,50,24,83,94301,2,0.40,3,0,0,0,0,1,0 +498,48,22,94,90623,4,2.60,3,0,0,0,0,1,0 +499,32,8,43,95023,1,2.10,3,0,0,0,0,0,1 +500,50,25,42,93108,3,1.70,2,0,0,0,0,1,0 +501,59,33,34,92177,2,0.30,1,0,0,0,0,0,0 +502,50,26,39,90640,3,1.90,2,0,0,0,0,1,0 +503,44,19,70,92833,1,0.10,2,0,0,0,0,0,0 +504,31,5,39,94022,4,1.80,3,185,0,0,0,0,1 +505,40,10,44,94720,3,2.00,3,0,0,0,0,1,0 +506,36,12,69,94305,3,3.10,2,0,1,0,0,1,0 +507,51,25,44,94608,3,0.90,3,0,0,0,0,0,0 +508,64,40,32,91380,3,0.10,3,0,0,0,0,1,0 +509,47,22,15,95521,2,0.70,3,0,0,0,0,0,0 +510,52,28,118,90503,2,6.80,1,112,0,0,0,1,0 +511,51,26,62,95136,1,1.30,2,221,0,0,0,1,0 +512,31,5,82,94143,4,2.20,2,0,0,0,0,0,0 +513,39,14,54,95035,3,3.00,1,108,0,0,0,0,1 +514,30,6,48,94607,1,2.10,3,0,0,0,0,0,0 +515,27,1,74,91730,3,0.30,3,0,0,0,0,1,0 +516,41,16,113,92780,1,1.00,3,211,0,0,0,0,1 +517,53,27,81,90009,3,1.70,2,0,0,0,0,0,0 +518,54,27,43,92834,3,1.00,2,169,0,0,0,0,0 +519,28,4,34,92677,1,1.80,2,0,0,0,0,1,0 +520,34,9,48,95616,1,2.50,3,105,0,0,0,1,0 +521,61,37,54,90024,4,1.20,2,129,0,0,0,1,1 +522,48,24,75,92518,4,1.40,2,0,0,0,0,1,0 +523,36,11,72,91007,1,2.80,1,224,0,0,0,0,0 +524,56,31,39,93023,4,0.90,1,0,0,0,0,0,0 +525,24,-1,75,93014,4,0.20,1,0,0,0,0,1,0 +526,64,38,79,94024,2,2.80,1,179,0,0,0,0,0 +527,26,2,205,93106,1,6.33,1,271,0,0,0,0,1 +528,33,8,65,90027,2,0.10,1,89,0,0,0,1,0 +529,64,39,122,90089,4,0.20,1,378,1,0,0,1,0 +530,39,15,82,95207,1,0.80,2,0,0,0,0,1,0 +531,54,30,21,91706,2,0.20,1,0,0,0,0,0,1 +532,32,6,50,90401,4,2.10,3,0,0,1,1,1,1 +533,62,37,39,94305,2,2.80,1,113,0,0,1,1,1 +534,27,2,101,92807,1,1.90,1,0,0,0,0,0,0 +535,53,28,41,93117,2,0.60,3,0,0,1,0,0,0 +536,51,25,132,94143,1,0.30,1,0,0,0,0,1,0 +537,25,-1,43,92173,3,2.40,2,176,0,0,0,1,0 +538,44,20,131,90717,1,4.90,3,0,1,0,0,1,0 +539,31,5,11,94534,1,0.40,2,76,0,0,0,0,1 +540,57,32,21,94720,1,0.30,3,117,0,0,0,0,0 +541,25,-1,109,94010,4,2.30,3,314,0,0,0,1,0 +542,30,6,141,95014,2,4.33,1,0,0,0,0,0,0 +543,40,14,81,94709,3,0.10,1,0,0,0,0,1,0 +544,63,38,54,94704,3,2.40,1,90,0,0,0,0,1 +545,35,10,164,91614,2,7.80,1,0,0,0,0,1,0 +546,43,19,28,94303,4,0.30,1,87,0,0,0,0,0 +547,27,2,68,94025,3,2.60,3,203,0,1,0,0,0 +548,44,14,44,94132,3,2.00,3,180,0,1,1,1,1 +549,49,23,61,94117,1,1.40,3,0,0,0,0,1,1 +550,61,36,35,94110,3,1.30,2,0,0,0,0,0,1 +551,60,34,54,94301,3,0.30,2,0,0,0,0,1,1 +552,59,34,14,93118,1,0.10,1,0,0,0,0,1,1 +553,28,3,52,90024,4,2.20,1,230,0,0,0,1,0 +554,52,28,101,91330,2,0.30,1,0,0,0,0,0,0 +555,28,2,149,94720,2,7.20,1,0,0,0,0,1,0 +556,34,8,35,92037,4,0.80,1,137,0,0,1,1,1 +557,60,34,21,93105,3,0.30,3,129,0,0,0,1,0 +558,39,15,118,95039,2,1.90,1,0,0,0,0,0,1 +559,30,5,38,95064,4,2.00,2,0,0,1,0,0,0 +560,49,25,24,95818,4,0.20,1,138,0,0,0,1,0 +561,43,18,59,93943,1,3.70,3,0,0,0,0,1,0 +562,63,33,41,94234,4,1.67,3,0,0,0,0,1,0 +563,28,3,85,94035,1,0.80,2,0,0,0,0,1,1 +564,51,27,12,94608,4,1.00,1,0,0,0,0,1,0 +565,33,7,32,94904,1,0.60,3,152,0,0,0,0,0 +566,55,29,79,90210,3,0.80,1,0,0,0,0,1,0 +567,53,28,175,95060,3,3.60,3,0,1,0,1,1,1 +568,34,8,28,95112,3,0.90,1,0,0,0,0,0,0 +569,34,9,41,92101,2,0.10,1,161,0,0,0,1,1 +570,40,14,70,95136,3,2.10,1,185,0,0,0,0,0 +571,49,25,161,94928,3,6.50,2,485,1,1,1,0,0 +572,35,9,53,94143,4,2.20,2,0,0,0,0,1,0 +573,39,15,128,92333,1,3.40,1,0,0,0,0,0,0 +574,55,28,50,95020,3,1.00,2,0,0,0,0,1,1 +575,29,5,80,94709,2,2.00,2,0,0,0,0,1,1 +576,54,30,93,91107,1,2.70,2,0,0,0,0,1,0 +577,25,-1,48,92870,3,0.30,3,0,0,0,0,0,1 +578,52,28,149,94043,2,6.80,1,0,0,0,0,1,0 +579,46,19,49,92124,3,2.50,2,0,0,0,0,1,1 +580,57,33,88,93524,1,2.70,2,0,0,0,0,1,0 +581,52,22,22,90049,4,0.40,3,0,0,0,0,1,1 +582,28,3,55,94521,4,2.20,1,0,0,0,0,1,1 +583,44,18,72,95678,1,0.70,3,155,0,0,0,0,0 +584,24,-1,38,95045,2,1.70,2,0,0,0,0,1,0 +585,40,16,114,91604,1,3.40,1,300,0,0,0,1,0 +586,34,4,83,92653,4,4.00,3,0,0,0,0,1,0 +587,39,14,101,94305,2,0.40,1,0,0,0,0,1,1 +588,50,24,94,93305,1,4.90,1,272,0,0,0,1,0 +589,41,17,40,93117,2,2.50,1,0,0,0,1,1,1 +590,31,7,128,92821,1,6.00,1,0,0,0,0,0,0 +591,29,3,39,94612,4,2.10,3,0,0,0,0,1,0 +592,30,5,51,92037,1,1.00,1,0,0,0,0,1,0 +593,44,20,79,95051,4,2.00,3,0,0,1,1,1,1 +594,33,7,48,90025,4,2.20,2,0,0,0,0,1,0 +595,50,26,85,94143,1,0.00,1,144,0,0,0,0,0 +596,42,18,41,92121,1,1.80,1,94,0,0,0,1,0 +597,48,22,152,94022,1,3.50,3,0,1,0,0,1,0 +598,24,-2,125,92835,2,7.20,1,0,0,1,0,0,1 +599,56,31,11,92374,2,0.20,3,90,0,0,0,0,0 +600,28,4,103,94720,2,2.50,1,0,0,0,0,1,1 +601,56,30,141,94143,2,0.50,1,0,0,0,0,1,0 +602,58,32,38,91320,1,1.40,1,0,0,0,0,1,1 +603,29,5,135,95035,2,0.60,1,0,0,0,0,0,0 +604,63,38,28,94720,2,0.50,2,89,0,0,0,1,0 +605,28,3,70,90245,4,2.20,1,240,0,0,0,0,1 +606,57,31,41,91330,1,0.20,1,0,0,0,0,1,1 +607,34,8,81,91741,3,0.90,2,208,0,0,0,1,0 +608,28,3,170,95014,1,0.10,3,0,1,0,0,0,0 +609,27,2,55,91910,4,1.70,2,0,0,0,0,1,0 +610,37,11,24,91770,4,1.50,3,0,0,0,0,0,0 +611,52,28,81,94132,3,1.80,2,275,0,0,0,0,0 +612,49,23,32,94701,4,1.80,1,83,0,0,0,0,0 +613,65,40,129,90095,1,1.30,1,0,0,0,0,1,1 +614,60,35,108,94904,1,0.90,1,0,0,1,0,0,0 +615,37,12,180,90034,1,8.60,1,0,0,0,0,1,1 +616,63,37,139,93943,2,6.90,1,0,0,0,0,0,0 +617,40,14,33,94025,2,1.40,3,0,0,0,0,1,1 +618,46,20,74,94024,4,2.60,3,0,0,0,0,1,0 +619,63,37,42,91320,2,0.70,3,115,0,0,0,1,0 +620,57,27,73,93106,1,3.00,3,0,0,0,0,0,0 +621,33,8,115,91129,4,2.90,2,0,1,0,0,1,0 +622,41,17,114,91125,2,1.80,2,0,0,0,0,1,0 +623,41,17,92,93555,2,1.90,1,131,0,0,0,1,0 +624,44,19,34,95616,1,0.30,3,78,0,0,0,1,0 +625,33,6,54,92821,2,1.67,2,122,0,0,0,1,0 +626,52,28,64,95605,2,1.00,3,211,0,0,0,1,0 +627,30,6,42,94305,1,0.20,3,100,0,0,0,0,1 +628,45,19,70,92677,3,2.10,1,0,0,0,0,1,0 +629,49,24,51,90071,1,1.30,2,0,0,0,0,0,0 +630,45,19,71,91711,4,2.90,1,218,0,0,1,1,1 +631,32,7,35,96651,3,1.30,1,108,0,0,0,0,1 +632,45,18,40,94960,3,1.00,2,0,0,0,0,1,0 +633,57,32,165,94720,4,2.70,3,0,1,0,0,1,0 +634,61,31,18,94583,1,1.50,3,0,0,0,0,1,1 +635,57,31,32,90034,3,1.40,1,0,0,1,1,1,1 +636,60,35,35,90509,3,0.20,1,169,0,0,0,1,0 +637,40,16,120,92037,2,6.10,1,196,0,0,0,1,0 +638,53,28,31,90245,4,0.10,3,0,0,0,0,1,0 +639,42,16,35,92054,3,1.50,1,0,0,0,0,0,0 +640,62,36,32,92646,2,0.20,3,0,0,0,0,1,1 +641,43,18,85,94960,1,3.70,3,327,0,1,0,1,0 +642,35,10,139,95060,2,7.80,1,0,0,0,0,0,0 +643,50,24,103,94132,1,0.30,1,0,0,0,0,1,0 +644,45,21,152,91902,2,1.40,1,0,0,0,0,1,0 +645,52,27,33,92121,2,2.00,2,0,0,0,0,1,0 +646,35,9,84,95120,4,2.20,2,322,0,0,0,0,0 +647,58,33,61,90033,4,1.70,1,0,0,0,0,0,0 +648,62,38,64,95064,4,2.20,1,123,0,1,1,1,1 +649,50,25,34,95621,1,1.30,2,0,0,0,0,1,0 +650,25,-1,82,92677,4,2.10,3,0,0,0,0,1,0 +651,47,22,122,90037,1,5.10,3,163,1,1,0,0,0 +652,28,4,58,92121,3,1.50,1,131,0,0,0,0,0 +653,34,9,92,90005,1,2.80,1,0,0,0,0,1,0 +654,49,23,78,92691,2,2.40,2,205,0,0,0,0,1 +655,54,29,129,93940,4,4.20,3,0,1,0,0,0,0 +656,50,25,13,91109,2,0.70,3,0,0,0,0,0,0 +657,37,11,81,94539,1,2.80,3,145,0,0,0,0,0 +658,38,8,23,95207,1,0.67,3,0,0,0,0,0,0 +659,52,26,35,91711,3,0.90,3,0,0,0,0,0,0 +660,63,39,79,93009,4,1.70,2,0,0,0,0,1,1 +661,39,14,165,92126,2,3.30,1,0,0,0,0,1,0 +662,63,38,52,94720,2,2.80,1,0,0,0,0,1,0 +663,65,41,185,93561,3,2.00,2,0,1,0,0,0,0 +664,46,20,49,90503,3,2.20,2,0,0,0,0,0,0 +665,54,30,64,95126,1,1.80,3,227,0,0,0,0,1 +666,54,24,61,92866,4,2.00,3,0,0,1,0,1,0 +667,52,26,112,92120,1,2.40,1,0,0,1,1,1,1 +668,63,39,72,93106,3,2.00,3,190,0,1,0,1,0 +669,66,41,18,94010,3,0.50,1,0,0,0,0,0,0 +670,56,29,41,94109,4,2.50,2,0,0,0,0,0,0 +671,23,-1,61,92374,4,2.60,1,239,0,0,0,1,0 +672,65,41,105,92612,1,3.00,2,282,1,1,1,1,0 +673,51,27,23,96651,1,0.20,1,0,0,0,0,1,0 +674,34,10,22,95670,1,0.50,3,85,0,0,0,0,0 +675,49,23,59,95827,3,2.10,1,0,0,0,0,0,0 +676,29,2,33,91711,1,2.00,2,160,0,0,0,0,0 +677,47,23,11,94063,1,0.90,3,103,0,0,0,0,1 +678,46,21,204,92780,2,2.80,1,0,0,0,0,1,0 +679,52,27,61,92101,4,1.80,3,207,0,0,0,0,0 +680,55,31,103,92093,3,1.80,2,364,0,0,0,0,0 +681,61,36,51,94706,3,1.50,1,0,0,0,0,0,1 +682,34,9,164,94720,1,6.00,3,0,1,0,0,1,0 +683,58,34,12,90504,1,0.10,2,0,0,0,0,0,1 +684,40,16,82,91311,1,3.60,2,0,0,0,0,0,0 +685,43,17,164,90266,1,2.40,1,449,0,0,0,1,0 +686,35,8,48,93107,2,1.67,2,0,0,0,0,1,0 +687,24,-1,38,92612,4,0.60,2,0,0,0,0,1,0 +688,48,22,65,92120,2,1.50,2,0,0,0,0,1,0 +689,44,20,71,94304,4,1.90,1,207,0,0,0,1,0 +690,54,30,18,94591,1,0.30,1,0,0,1,1,1,0 +691,59,34,52,94115,2,1.60,3,75,0,0,0,1,0 +692,45,18,48,90025,3,2.50,2,113,0,0,0,1,1 +693,26,2,30,94720,1,1.00,3,111,0,0,0,0,0 +694,40,15,40,92096,2,2.20,3,107,0,0,0,1,0 +695,32,7,112,90740,1,3.80,1,81,0,0,0,1,0 +696,29,4,115,92717,1,1.90,1,0,0,0,0,0,0 +697,51,27,63,92251,2,1.00,3,82,0,0,0,1,0 +698,42,17,85,92648,1,3.70,3,0,0,0,0,1,0 +699,64,38,59,92028,1,2.50,3,220,0,0,0,0,0 +700,44,20,68,95060,1,0.80,3,91,0,0,0,0,0 +701,37,11,84,90089,2,1.80,1,0,0,0,0,1,1 +702,44,19,62,93106,3,0.80,3,0,0,0,0,0,1 +703,35,9,109,92709,3,4.00,1,0,1,0,0,0,0 +704,41,17,141,94022,2,7.60,1,92,0,0,0,0,0 +705,56,32,129,94065,1,7.40,1,0,0,0,0,0,0 +706,62,36,30,94720,3,0.70,2,0,0,0,0,1,0 +707,58,34,148,95819,1,4.70,1,0,0,0,0,1,0 +708,47,20,25,95064,3,0.67,2,0,0,0,0,1,1 +709,35,10,21,92182,3,1.30,1,115,0,0,0,0,0 +710,29,4,72,95841,4,2.20,1,0,0,0,0,1,0 +711,43,17,59,94085,3,0.90,3,87,0,0,0,1,1 +712,62,37,83,91754,3,1.80,2,187,0,1,0,0,0 +713,41,16,10,94123,2,0.30,2,0,0,0,0,1,0 +714,34,9,84,92009,3,0.60,2,0,0,0,0,1,0 +715,50,23,98,92068,3,2.00,2,0,0,0,0,0,0 +716,47,23,32,92130,1,1.00,1,0,0,1,1,1,1 +717,29,5,31,96064,4,0.40,2,161,0,0,0,1,1 +718,59,34,94,93940,3,0.50,1,0,0,0,0,0,1 +719,56,31,21,90024,2,0.20,3,137,0,0,1,1,1 +720,61,35,110,92521,3,4.40,1,0,0,1,0,1,0 +721,58,32,38,94025,1,2.20,3,0,0,0,0,0,0 +722,49,24,39,92717,1,1.40,3,0,0,0,0,1,0 +723,45,21,132,91103,3,1.20,2,0,1,0,1,1,1 +724,50,24,61,94301,4,2.60,1,0,0,0,0,1,0 +725,64,38,92,94086,1,2.00,1,0,0,0,0,1,0 +726,39,15,119,92037,2,6.10,1,0,0,0,0,0,0 +727,58,33,53,91030,4,2.10,1,0,0,0,0,1,0 +728,62,37,18,92037,3,1.30,2,0,0,0,0,1,0 +729,45,20,114,94720,2,4.40,2,0,1,0,0,0,0 +730,58,28,90,93106,1,3.00,3,0,0,0,0,0,1 +731,43,18,140,95616,1,7.00,1,205,0,0,0,1,0 +732,28,3,90,90066,2,3.30,1,0,0,0,0,1,1 +733,26,1,85,90064,1,1.90,1,0,0,0,0,1,0 +734,49,24,80,92009,1,1.20,1,0,0,0,0,1,0 +735,66,42,53,92182,2,1.10,1,0,0,0,0,1,1 +736,33,7,49,95403,4,2.20,2,0,0,0,0,1,0 +737,61,35,152,91016,3,3.30,3,0,1,0,0,1,0 +738,64,37,138,94709,2,2.80,2,0,1,0,0,1,0 +739,36,10,80,94596,4,2.20,2,0,0,0,0,1,0 +740,49,23,82,91902,2,2.40,2,0,0,0,0,0,0 +741,52,27,195,90266,1,8.10,1,0,0,0,0,0,0 +742,61,37,22,94590,1,1.20,3,0,0,0,0,1,0 +743,32,6,81,92626,1,2.50,1,0,0,0,0,1,0 +744,61,37,40,94539,4,2.20,1,0,0,1,1,1,1 +745,45,20,154,94720,2,2.80,1,0,0,1,0,1,0 +746,30,4,49,93955,3,1.10,2,0,0,0,0,0,1 +747,62,37,85,95051,4,3.40,2,0,0,0,0,1,0 +748,57,32,21,94112,3,0.10,2,0,0,1,1,1,0 +749,41,17,14,91330,1,1.00,1,0,0,0,0,0,0 +750,58,34,60,92008,4,1.60,2,0,0,0,0,0,1 +751,29,5,138,93106,2,4.33,1,0,0,0,0,1,0 +752,53,28,98,90210,1,1.30,3,355,0,0,0,1,0 +753,64,39,22,90071,4,0.60,2,0,0,0,0,0,0 +754,49,23,49,94720,1,1.20,2,0,0,0,0,1,1 +755,38,14,102,95020,2,1.90,1,0,0,0,1,1,1 +756,56,30,45,91103,4,0.70,2,0,0,0,0,0,1 +757,56,31,82,95348,4,1.30,3,0,0,0,0,1,0 +758,52,28,81,91745,3,1.80,2,0,0,1,0,0,0 +759,64,39,35,90266,1,1.50,2,0,0,1,0,0,0 +760,53,28,59,91950,2,1.90,2,0,0,0,0,1,0 +761,29,3,52,92122,3,1.10,2,0,0,0,0,1,0 +762,48,24,84,92152,3,0.70,1,166,0,0,0,1,0 +763,32,6,85,90504,1,2.70,2,100,0,0,0,1,0 +764,54,28,65,94122,1,0.20,1,0,0,0,0,0,1 +765,37,13,89,95051,2,1.70,2,314,0,0,0,0,1 +766,47,21,109,95822,4,1.80,1,0,1,0,0,0,0 +767,37,12,81,94538,1,2.80,1,0,0,0,0,0,0 +768,64,39,38,92024,1,1.10,3,108,0,0,0,0,0 +769,43,19,72,90024,2,1.70,1,0,0,0,0,1,0 +770,33,6,78,90250,4,2.00,2,119,0,1,0,1,0 +771,26,2,172,94551,2,6.90,2,0,1,0,0,1,0 +772,42,18,71,91614,3,2.33,1,106,0,1,0,1,0 +773,54,28,165,92093,1,4.10,3,0,1,0,1,1,1 +774,41,16,120,92612,2,3.90,1,0,0,0,0,1,1 +775,55,29,39,92154,1,0.20,1,0,0,0,0,0,1 +776,65,39,23,92835,3,0.70,2,0,0,0,0,0,1 +777,50,26,135,92121,2,4.60,3,91,1,0,0,1,0 +778,55,31,12,95060,2,0.20,1,76,0,0,0,1,1 +779,62,36,92,94801,2,0.70,2,0,0,0,0,1,0 +780,53,28,192,94304,2,6.40,3,0,1,0,0,0,0 +781,32,7,42,92634,4,0.80,1,0,0,0,0,1,1 +782,56,32,158,94588,3,3.70,3,0,1,0,0,1,0 +783,54,30,194,92056,3,6.00,3,587,1,1,1,1,1 +784,44,20,160,94606,2,7.60,1,0,0,1,0,0,0 +785,48,22,98,94115,2,6.30,1,0,0,0,0,0,0 +786,46,22,164,94122,2,7.60,1,0,0,0,1,1,1 +787,45,21,42,94305,2,2.50,1,0,0,1,0,1,0 +788,45,15,202,91380,3,10.00,3,0,1,0,0,0,0 +789,58,34,10,92521,4,0.70,1,0,0,0,0,0,0 +790,29,3,31,92126,4,0.30,2,0,0,0,0,1,0 +791,55,30,58,92028,4,0.90,1,0,0,0,0,1,1 +792,55,29,65,94501,4,2.80,2,0,0,0,0,1,0 +793,41,16,98,93117,1,4.00,3,0,0,0,0,0,1 +794,24,-2,150,94720,2,2.00,1,0,0,0,0,1,0 +795,54,29,44,91301,2,2.30,3,0,0,0,0,1,0 +796,57,32,15,92806,2,0.20,3,0,0,0,0,0,1 +797,30,6,82,93657,2,2.50,1,0,0,0,0,0,0 +798,42,17,61,94998,3,0.50,3,0,0,0,0,1,0 +799,29,2,38,93063,1,2.00,2,0,0,0,0,0,0 +800,29,3,39,95051,4,2.10,3,0,0,0,0,1,0 +801,31,7,173,91040,1,6.00,1,0,0,0,0,1,0 +802,47,23,8,92612,4,0.20,1,0,0,0,0,1,0 +803,36,12,51,92521,3,2.00,1,214,0,0,0,1,0 +804,52,27,62,92661,4,1.80,3,82,0,0,0,0,0 +805,54,28,34,94061,4,0.70,2,0,0,0,0,1,0 +806,55,29,132,95758,3,5.90,2,307,1,0,0,0,0 +807,53,27,44,94542,4,1.50,3,0,0,0,0,0,0 +808,52,27,162,92096,1,8.10,1,0,0,0,0,1,0 +809,64,39,64,92068,3,2.20,1,0,0,0,0,1,0 +810,54,29,111,94304,1,0.10,3,0,0,0,0,0,1 +811,32,6,41,92182,2,2.00,3,0,0,0,0,0,0 +812,63,33,52,94720,4,1.67,3,0,0,0,0,0,0 +813,36,10,65,90089,4,2.20,2,0,0,0,0,0,0 +814,50,25,130,94720,1,1.10,2,0,1,0,0,1,0 +815,33,8,45,93943,2,0.10,1,0,0,0,0,0,1 +816,62,38,35,94596,1,1.90,2,118,0,0,0,0,0 +817,49,23,65,94035,3,0.70,2,263,0,0,0,1,1 +818,41,15,38,90291,2,0.70,1,91,0,0,0,1,0 +819,51,27,42,95039,4,1.10,2,0,0,0,0,1,1 +820,56,30,45,90024,4,1.50,3,0,0,0,0,0,0 +821,51,25,145,90740,1,0.30,1,0,0,0,0,1,0 +822,39,13,33,92093,4,1.50,3,0,0,0,0,0,0 +823,61,35,60,96091,3,1.40,3,0,0,0,0,0,0 +824,35,9,45,90509,1,2.00,1,0,0,0,0,1,1 +825,39,15,72,94801,4,2.40,1,0,0,1,0,1,0 +826,37,11,34,95616,3,0.20,2,0,0,0,0,0,0 +827,48,21,23,93555,3,0.67,2,0,0,0,0,1,0 +828,63,37,45,94542,2,1.00,3,88,0,0,0,1,1 +829,35,9,28,94542,4,1.00,1,75,0,0,0,1,0 +830,55,30,81,90254,4,3.80,2,0,0,0,0,1,0 +831,29,5,72,92407,3,0.70,2,81,0,0,0,0,0 +832,61,31,49,94066,4,1.67,3,0,0,0,0,1,0 +833,36,10,31,90630,4,1.20,2,0,0,0,0,0,0 +834,61,35,63,94939,3,2.20,3,0,0,0,0,0,0 +835,36,12,150,95138,4,5.40,1,0,1,1,1,1,0 +836,58,33,142,92691,2,3.90,1,193,0,0,0,1,1 +837,42,17,74,92123,3,3.00,1,0,0,0,0,0,1 +838,30,4,24,92096,1,0.40,2,81,0,0,0,1,0 +839,45,20,29,92507,4,1.90,3,0,0,0,0,0,0 +840,39,15,79,92646,4,2.40,1,0,0,0,0,0,0 +841,27,3,94,92373,2,0.20,1,310,0,0,0,0,1 +842,57,33,121,94542,1,4.30,1,0,0,1,0,0,0 +843,34,10,54,92101,3,2.00,1,0,0,0,0,0,0 +844,64,39,73,94720,3,2.40,1,0,0,0,0,1,0 +845,47,23,71,95762,1,0.80,3,127,0,0,0,1,0 +846,44,17,29,94706,3,1.00,2,0,0,0,0,1,1 +847,51,27,93,92154,1,2.70,1,0,0,0,0,1,0 +848,40,14,73,94539,1,1.50,3,252,0,0,0,1,0 +849,57,32,19,94720,4,0.90,2,0,0,0,0,1,0 +850,33,8,58,94305,2,0.10,1,0,0,1,1,1,1 +851,46,20,39,95054,1,0.20,1,0,0,0,0,0,0 +852,41,16,23,94521,2,1.40,2,0,0,1,0,1,0 +853,33,7,29,92064,1,0.60,3,127,0,0,0,0,1 +854,27,2,155,95138,1,0.80,1,0,0,0,0,0,0 +855,52,28,90,95814,1,2.60,2,0,0,1,0,1,0 +856,59,33,113,92152,2,2.00,1,77,0,0,0,1,0 +857,62,38,42,94025,1,1.80,3,0,0,0,0,0,0 +858,49,25,30,95616,4,0.20,1,0,0,0,1,1,1 +859,45,19,19,94720,3,0.50,2,0,0,0,0,1,0 +860,63,37,124,92182,3,5.00,2,170,1,0,0,0,0 +861,57,31,30,95841,2,0.70,2,145,0,0,0,0,0 +862,60,30,28,92354,1,1.50,3,124,0,1,0,1,0 +863,50,23,15,94025,2,1.00,2,101,0,0,0,0,0 +864,54,30,70,90095,1,1.60,3,265,0,0,0,0,0 +865,28,2,10,94080,1,0.10,2,0,0,0,0,1,0 +866,60,34,22,92037,3,0.30,3,139,0,0,0,1,1 +867,44,20,70,94611,4,1.90,1,0,0,0,0,1,0 +868,61,35,61,94708,1,1.60,1,0,0,0,0,0,0 +869,40,15,161,94596,2,3.30,1,0,0,1,0,0,1 +870,54,30,29,93014,2,0.80,1,0,0,0,0,0,1 +871,43,19,35,92106,3,0.50,1,0,0,0,0,1,0 +872,54,28,48,96091,4,2.80,2,0,0,0,0,1,0 +873,32,7,44,90095,4,0.80,1,0,0,0,0,1,0 +874,24,0,88,90740,3,0.80,1,134,0,0,0,0,0 +875,30,4,40,92056,4,2.10,3,0,0,0,0,1,1 +876,61,36,21,95616,4,0.40,2,123,0,0,0,0,0 +877,40,14,58,94025,2,2.80,1,0,0,0,0,1,0 +878,35,11,59,95123,4,0.10,2,0,0,0,0,0,0 +879,33,3,74,95616,4,4.00,3,0,0,0,0,0,0 +880,63,37,84,91768,4,1.90,2,0,0,0,0,1,0 +881,57,31,58,91604,1,0.20,1,177,0,0,0,1,0 +882,44,19,154,92116,2,8.80,1,0,0,0,0,1,0 +883,51,25,185,94117,1,1.70,1,0,0,0,0,0,0 +884,51,26,78,92703,1,1.20,1,305,0,0,0,1,0 +885,38,13,55,91709,2,1.10,2,0,0,0,0,1,0 +886,31,5,30,94304,4,0.30,2,0,0,0,0,1,0 +887,54,29,74,93907,3,2.00,2,0,0,0,0,0,0 +888,41,16,118,94720,2,3.30,1,0,0,0,0,1,0 +889,57,33,182,94114,2,3.30,3,372,1,0,0,0,0 +890,24,-2,82,91103,2,1.60,3,0,0,0,0,1,1 +891,55,29,29,92780,4,1.50,3,79,0,0,0,1,0 +892,32,6,120,94102,4,5.40,1,301,1,0,1,1,1 +893,38,12,53,95616,2,2.40,2,0,0,0,0,1,0 +894,58,32,43,93943,3,1.40,1,0,0,0,0,0,1 +895,29,4,59,95064,4,2.20,1,232,0,0,0,1,1 +896,43,17,84,94608,4,2.60,3,289,0,1,1,1,1 +897,50,24,161,95133,3,3.40,1,212,1,0,0,1,0 +898,62,37,21,92691,4,0.40,2,137,0,0,0,1,1 +899,57,32,63,94111,4,0.70,1,0,0,0,0,1,0 +900,30,3,172,91302,3,3.40,2,0,1,0,0,0,1 +901,30,4,51,94709,4,0.20,1,172,0,0,0,0,1 +902,57,33,24,95616,4,0.70,1,0,0,0,0,1,0 +903,57,33,95,95054,2,1.60,1,0,0,0,0,0,0 +904,43,18,59,90048,1,2.40,1,250,0,0,0,1,0 +905,28,2,51,90503,4,1.80,2,0,0,1,0,0,0 +906,46,22,28,94720,1,1.00,1,84,0,0,0,1,1 +907,29,3,154,94720,2,2.00,1,130,0,0,0,0,0 +908,64,40,15,91711,2,0.30,3,115,0,0,0,1,1 +909,66,36,55,93023,4,1.67,3,0,0,0,0,0,1 +910,23,-1,149,91709,1,6.33,1,305,0,0,0,0,1 +911,60,36,79,92120,1,1.80,3,0,0,0,0,0,1 +912,47,21,68,94538,4,2.60,3,0,0,0,0,0,0 +913,35,10,78,94105,1,2.60,2,0,0,0,0,1,0 +914,57,32,34,92507,2,2.00,2,0,0,1,0,0,0 +915,65,41,195,91711,3,0.40,1,0,1,1,1,0,1 +916,53,28,184,94550,1,8.10,1,303,0,0,0,1,0 +917,44,20,85,92192,2,3.20,1,0,0,0,0,1,0 +918,45,20,200,90405,2,8.80,1,0,0,0,0,1,1 +919,41,16,64,92325,3,0.50,3,0,0,0,0,0,0 +920,51,27,88,91116,1,2.60,2,0,0,1,0,0,1 +921,27,1,42,94501,3,2.40,2,0,0,0,0,0,0 +922,31,5,91,92096,3,1.60,1,126,0,0,0,1,1 +923,32,6,38,92868,1,0.30,1,0,0,1,1,1,0 +924,55,30,28,95123,1,1.50,2,0,0,0,0,0,0 +925,55,30,32,91330,4,0.10,3,0,0,1,0,0,0 +926,42,18,31,94720,1,0.30,3,0,0,0,0,0,1 +927,33,9,22,93940,4,0.40,2,103,0,0,0,1,0 +928,65,40,95,95014,3,3.70,2,138,1,0,0,0,1 +929,35,10,74,90638,4,1.30,1,0,0,0,0,1,0 +930,55,30,22,92121,1,1.50,2,91,0,0,0,0,1 +931,28,4,43,92103,3,0.10,2,0,0,0,0,1,0 +932,27,3,43,91302,1,1.00,3,0,0,0,0,1,0 +933,51,27,112,94720,3,1.80,2,0,0,1,1,1,1 +934,50,23,9,92064,2,1.00,2,0,0,0,0,1,0 +935,58,33,81,91320,2,0.00,3,0,0,0,0,1,0 +936,46,20,131,95929,1,5.70,1,256,0,0,0,0,1 +937,62,32,19,92109,1,1.50,3,0,0,1,0,0,0 +938,38,13,62,92093,3,0.70,2,0,0,1,0,1,0 +939,62,37,19,95818,4,0.40,2,124,0,1,0,0,0 +940,56,32,8,93943,2,0.30,1,0,0,0,0,1,1 +941,61,36,193,94303,1,4.70,3,203,1,0,0,1,0 +942,38,13,129,92093,4,4.40,1,140,1,0,0,0,0 +943,55,29,30,91320,4,0.70,2,0,0,0,0,0,1 +944,30,4,80,94701,4,1.80,2,0,0,0,0,0,0 +945,41,15,22,90503,4,1.50,3,0,0,0,0,0,1 +946,57,32,33,91745,1,1.50,2,0,0,0,0,1,0 +947,36,11,64,91355,4,2.10,3,0,0,0,0,0,0 +948,55,29,60,94305,3,2.20,3,84,0,0,0,1,0 +949,30,4,81,92037,1,2.90,3,259,0,0,0,1,1 +950,40,16,45,94720,3,0.60,2,204,0,0,0,1,0 +951,32,6,112,95054,4,1.80,2,0,0,0,0,1,0 +952,59,34,83,94105,2,3.40,3,0,1,0,0,1,0 +953,44,20,180,93943,2,7.60,1,524,0,0,0,0,1 +954,51,26,28,92130,4,0.20,2,0,0,1,0,1,0 +955,37,12,169,91107,2,5.20,3,249,1,0,0,1,0 +956,59,35,14,90840,4,0.70,1,0,0,0,0,1,0 +957,37,11,43,90250,1,2.00,1,0,0,0,0,1,0 +958,56,32,88,94309,2,0.30,1,0,0,0,0,1,0 +959,55,29,78,90747,4,2.60,3,0,0,0,0,0,1 +960,49,24,68,94143,1,0.20,2,163,0,0,0,0,0 +961,46,22,144,93611,2,3.30,1,0,0,0,0,1,1 +962,35,9,30,94114,4,1.00,1,163,0,0,0,1,0 +963,47,21,120,95833,1,0.00,1,135,0,0,0,0,0 +964,39,14,24,94305,2,0.30,2,0,0,0,0,0,0 +965,27,1,78,92037,4,2.30,3,157,0,1,0,1,0 +966,62,36,135,94301,2,5.20,2,0,1,0,0,1,0 +967,57,32,44,91605,2,1.60,3,0,0,0,0,0,0 +968,55,30,73,92675,4,3.80,2,0,0,0,0,1,0 +969,55,31,90,92868,1,2.70,2,0,0,0,0,1,1 +970,41,15,58,94704,3,0.50,3,0,0,0,0,1,0 +971,57,32,75,94928,2,3.70,1,236,0,0,0,1,0 +972,43,19,174,92028,3,1.70,3,231,1,0,1,1,1 +973,40,16,50,92093,2,1.70,1,174,0,0,0,0,0 +974,43,18,85,92703,1,4.00,3,287,0,0,0,1,0 +975,63,38,54,90401,3,2.20,1,0,0,0,0,1,0 +976,63,38,83,92122,2,3.40,1,0,1,0,0,0,0 +977,54,30,24,94109,4,0.20,1,0,0,1,0,0,0 +978,54,30,45,95134,4,1.10,2,205,0,0,0,1,0 +979,52,26,68,92068,1,0.80,3,0,0,0,0,1,1 +980,50,26,48,94720,4,0.10,3,0,0,0,0,0,1 +981,38,13,114,92697,1,1.00,3,0,0,0,0,1,1 +982,36,12,142,90064,3,2.30,2,0,1,0,1,1,1 +983,58,33,52,94402,3,0.50,2,0,0,0,0,0,1 +984,46,22,142,92220,2,3.30,1,0,0,0,0,0,0 +985,50,25,15,92173,1,0.40,3,0,0,0,0,0,0 +986,46,22,118,92120,1,4.70,1,159,0,0,0,0,1 +987,53,27,101,90245,4,4.90,1,0,0,0,0,1,0 +988,62,36,84,94609,2,2.80,1,0,0,0,0,1,0 +989,63,39,32,94998,1,1.90,2,100,0,0,0,0,0 +990,42,16,64,94607,3,0.50,3,247,0,0,0,0,0 +991,34,10,81,94002,4,3.40,1,0,0,0,0,1,0 +992,40,14,28,94025,4,1.50,3,0,0,0,0,0,1 +993,34,9,93,94608,1,0.00,1,0,0,0,0,1,0 +994,41,15,185,91775,1,3.60,2,0,1,0,0,0,0 +995,32,8,42,90650,1,1.80,2,0,0,0,0,0,0 +996,28,3,45,94305,2,1.60,3,0,0,0,0,1,1 +997,33,6,49,92037,2,1.67,2,214,0,0,0,0,0 +998,46,20,69,92780,3,2.10,1,0,0,0,0,0,0 +999,52,27,94,93106,1,2.80,2,333,0,0,0,1,0 +1000,60,35,18,92120,1,1.50,2,0,0,0,0,1,1 +1001,59,35,8,92691,4,0.70,1,91,0,1,0,0,0 +1002,57,32,55,90717,4,2.10,1,108,0,0,0,1,0 +1003,46,20,85,95617,2,0.40,3,0,0,0,0,0,0 +1004,25,1,62,94720,4,0.00,1,229,0,0,0,1,0 +1005,53,23,65,95054,4,2.00,3,0,0,0,0,1,0 +1006,38,12,138,95112,2,0.00,1,0,0,1,0,1,0 +1007,63,38,103,91103,1,2.50,1,0,0,0,0,1,0 +1008,44,19,99,95064,3,3.50,3,357,1,0,0,0,0 +1009,50,24,152,92220,1,7.30,1,0,0,0,0,1,0 +1010,28,3,25,91330,2,0.90,3,140,0,0,0,1,0 +1011,27,3,98,95616,2,2.50,1,361,0,1,1,1,1 +1012,52,27,39,94304,2,0.70,2,166,0,0,0,1,0 +1013,50,25,40,95820,1,1.30,2,0,0,0,0,1,1 +1014,39,13,58,94551,3,2.10,1,169,0,0,0,1,0 +1015,50,26,192,90245,2,1.80,3,301,1,0,1,1,1 +1016,60,34,62,94303,1,0.80,2,0,0,0,0,0,0 +1017,30,5,69,94720,1,0.80,2,0,0,1,0,1,0 +1018,31,5,40,94305,4,1.30,3,170,0,0,0,0,0 +1019,39,15,61,90018,2,0.60,3,127,0,0,0,0,0 +1020,29,3,30,91745,4,0.30,2,157,0,0,0,0,0 +1021,54,29,29,90071,1,1.50,2,97,0,0,0,1,0 +1022,35,8,41,92612,2,1.00,2,0,0,0,0,1,1 +1023,27,3,118,95605,1,3.30,2,0,1,0,0,1,0 +1024,45,20,109,94117,1,7.00,1,366,0,0,0,1,0 +1025,58,33,122,93711,4,0.20,2,0,1,0,1,1,0 +1026,62,37,50,94545,3,1.50,1,169,0,0,0,1,0 +1027,28,4,43,95616,3,0.10,2,0,0,0,0,1,0 +1028,32,7,108,94550,1,4.60,1,0,0,1,0,0,0 +1029,29,4,110,92096,4,2.50,3,0,1,0,0,0,0 +1030,41,17,20,94720,1,1.40,3,0,0,0,0,1,0 +1031,61,35,112,90024,4,1.70,3,0,0,0,0,0,1 +1032,56,32,25,95403,1,0.10,2,136,0,0,0,1,0 +1033,37,12,42,94720,3,0.70,2,0,0,0,0,1,1 +1034,60,34,29,95973,2,0.30,1,0,0,0,0,1,0 +1035,49,23,84,90095,3,2.10,1,134,0,1,0,1,0 +1036,43,17,81,94720,4,2.60,3,0,0,1,0,1,0 +1037,53,28,55,94720,4,0.90,1,119,0,0,0,1,1 +1038,35,11,40,93106,1,2.40,2,0,0,1,0,1,0 +1039,56,30,145,95831,4,5.70,2,0,1,0,1,1,1 +1040,41,16,175,94304,2,1.10,3,0,1,0,0,1,0 +1041,36,6,78,91107,4,1.80,3,163,0,0,0,0,0 +1042,56,32,51,92780,4,1.50,1,0,0,0,0,0,0 +1043,64,34,50,95616,4,1.67,3,0,0,0,0,1,0 +1044,51,27,21,95630,3,0.40,1,0,0,0,0,1,0 +1045,49,24,79,95827,1,0.20,2,83,0,0,0,1,1 +1046,43,18,84,92096,1,4.00,3,0,0,0,0,0,0 +1047,51,26,34,94105,4,0.40,2,0,0,0,0,0,0 +1048,55,31,73,94143,4,1.60,2,0,0,0,0,0,0 +1049,62,37,90,95747,3,0.50,1,0,0,0,0,1,0 +1050,35,10,23,94501,4,0.20,3,0,0,0,0,1,0 +1051,53,27,145,90095,2,6.10,3,294,1,0,1,1,1 +1052,33,7,54,92886,4,0.20,1,141,0,1,0,0,0 +1053,43,17,49,95812,3,2.20,2,103,0,0,0,1,1 +1054,58,32,51,95819,1,2.80,2,0,0,0,0,1,0 +1055,63,38,8,95136,4,0.60,2,0,0,0,0,1,0 +1056,31,6,62,95630,1,1.00,1,0,0,1,0,1,0 +1057,36,6,25,95020,1,0.67,3,0,0,0,0,1,0 +1058,30,0,63,95503,2,1.75,3,0,0,0,0,1,0 +1059,59,34,24,94105,2,0.20,3,86,0,0,0,1,0 +1060,28,2,11,91203,1,0.10,2,0,0,0,0,1,1 +1061,59,34,23,93111,1,0.10,1,0,0,0,0,0,1 +1062,47,22,33,91105,1,1.40,3,0,0,0,0,1,0 +1063,47,21,83,92220,1,3.80,1,97,1,0,0,0,0 +1064,56,30,39,90024,3,1.40,1,131,0,0,0,0,1 +1065,41,17,138,95008,3,6.90,2,0,1,0,0,1,0 +1066,25,1,113,90401,3,2.50,1,0,0,0,0,0,1 +1067,30,5,125,90016,4,0.50,3,0,1,0,1,1,0 +1068,50,24,195,95035,1,1.70,1,0,0,0,0,0,0 +1069,34,9,105,90035,3,1.20,3,0,0,1,0,0,0 +1070,44,18,75,91203,2,3.50,1,0,1,0,0,1,0 +1071,36,9,40,90840,2,1.00,2,0,0,0,0,1,0 +1072,39,14,61,94005,3,0.50,3,137,0,0,0,1,0 +1073,54,24,75,90089,2,4.50,3,0,0,0,0,0,0 +1074,33,8,122,94583,1,0.00,1,0,0,0,0,1,1 +1075,39,14,75,95762,3,3.00,1,0,0,0,0,0,1 +1076,41,15,59,90024,4,0.20,3,0,0,0,0,0,0 +1077,40,13,24,94608,3,1.00,2,0,0,0,0,1,0 +1078,29,3,175,90095,3,3.30,3,329,1,0,0,1,0 +1079,51,27,39,92709,2,0.80,1,182,0,0,0,0,1 +1080,54,30,145,94591,2,6.80,1,0,0,1,0,0,0 +1081,47,22,24,90717,4,0.40,2,142,0,0,0,1,0 +1082,53,28,20,94080,3,0.10,2,0,0,0,0,0,0 +1083,30,5,85,94115,1,2.60,2,0,0,0,0,1,0 +1084,28,3,65,95014,3,2.60,3,0,0,1,0,0,0 +1085,60,35,191,93407,4,5.60,3,0,1,0,0,0,0 +1086,51,26,11,92612,2,0.00,1,0,0,1,0,0,0 +1087,63,37,40,94024,2,1.00,3,167,0,0,0,0,0 +1088,38,13,54,92028,3,0.70,2,196,0,0,0,0,0 +1089,59,35,95,95521,1,3.80,1,0,0,0,0,1,1 +1090,53,29,94,92103,4,1.00,2,0,0,0,0,1,0 +1091,31,5,79,94720,4,2.20,2,0,0,0,0,0,0 +1092,41,17,48,94720,3,0.30,3,0,0,0,0,1,1 +1093,25,1,70,92120,4,2.60,1,0,0,1,0,1,0 +1094,27,3,40,94550,3,0.10,2,111,0,0,0,1,0 +1095,50,24,44,94086,4,1.80,1,0,0,0,0,1,1 +1096,50,25,43,92129,1,1.40,3,137,0,0,0,1,0 +1097,43,18,29,90245,1,0.30,3,0,0,0,0,1,0 +1098,50,24,188,92007,3,1.30,1,184,1,0,0,0,1 +1099,46,20,114,90720,1,0.00,1,0,0,0,0,1,1 +1100,30,6,52,92717,3,0.70,2,0,0,0,0,1,0 +1101,42,16,13,91711,1,0.20,1,0,0,0,0,1,0 +1102,42,17,95,90095,3,0.50,3,0,0,0,0,0,0 +1103,29,3,84,95023,1,2.90,3,0,0,0,0,1,0 +1104,38,14,49,90037,1,1.80,1,0,0,0,0,0,0 +1105,51,25,181,93106,1,1.70,1,0,0,0,0,1,1 +1106,35,10,182,95051,1,0.30,2,229,1,0,1,1,1 +1107,37,13,70,92101,2,2.70,1,0,0,0,0,0,0 +1108,47,21,79,94110,3,1.10,1,185,0,0,0,1,1 +1109,55,29,61,95051,4,2.80,2,0,0,0,0,1,1 +1110,65,41,121,92126,2,2.10,1,0,0,0,0,1,0 +1111,58,33,34,92028,3,0.20,1,83,0,0,0,1,0 +1112,54,28,183,90071,1,1.00,1,442,0,0,0,0,0 +1113,52,28,51,94949,1,1.60,3,0,0,1,0,0,1 +1114,28,2,70,90630,3,0.30,3,0,0,0,0,0,1 +1115,32,8,39,95827,1,1.70,1,0,0,0,0,1,1 +1116,51,24,84,94117,3,2.00,2,0,0,0,0,0,0 +1117,43,18,122,92056,1,7.00,1,0,0,0,0,1,1 +1118,42,18,145,94709,1,1.70,1,132,0,0,0,1,1 +1119,42,17,98,95670,2,0.40,1,0,0,0,0,1,1 +1120,41,16,79,96064,1,1.00,3,233,0,0,0,1,0 +1121,34,8,38,94304,2,2.00,3,0,0,0,0,1,1 +1122,30,6,49,91330,3,0.70,2,196,0,0,0,0,1 +1123,32,7,38,90041,1,1.00,1,0,0,0,0,1,0 +1124,46,20,91,92521,4,2.60,3,0,0,0,0,0,0 +1125,38,12,29,94022,4,0.20,1,0,0,0,0,0,1 +1126,37,13,172,95003,2,6.50,1,0,0,0,0,0,0 +1127,32,8,104,95192,2,3.70,1,0,1,0,0,0,1 +1128,35,9,58,91101,1,2.50,1,0,0,0,0,1,1 +1129,30,5,171,94025,2,1.90,2,0,1,0,0,0,0 +1130,30,4,73,94305,3,3.30,1,0,1,0,1,1,1 +1131,58,32,191,94402,1,2.90,1,0,0,0,0,0,0 +1132,57,27,90,91709,2,4.50,3,0,0,0,0,1,0 +1133,34,9,55,94920,3,2.30,1,0,0,1,1,1,1 +1134,31,4,28,94126,1,2.00,2,0,0,0,0,0,0 +1135,39,14,42,95616,1,2.50,3,0,0,0,0,1,0 +1136,57,33,9,93106,1,0.10,2,91,0,1,0,1,0 +1137,47,21,65,94086,1,1.50,2,0,0,1,0,1,0 +1138,51,26,134,90230,4,4.50,3,0,1,1,1,1,0 +1139,30,6,83,93101,4,3.40,1,0,0,1,0,1,0 +1140,55,28,38,95616,3,1.00,2,0,0,0,0,1,0 +1141,32,6,13,94611,4,0.30,1,0,0,0,0,1,1 +1142,32,7,143,91365,3,2.90,3,0,1,0,0,1,0 +1143,44,20,75,91335,4,1.90,1,0,0,0,0,0,0 +1144,33,7,120,94022,1,3.20,3,0,1,0,0,1,0 +1145,49,24,91,95822,1,2.80,2,0,0,0,0,0,0 +1146,32,6,99,92101,2,1.50,3,0,0,0,0,0,1 +1147,31,7,71,90034,1,0.10,1,78,0,1,0,0,0 +1148,37,13,111,91367,1,0.80,2,0,0,0,0,0,0 +1149,41,15,108,90034,1,5.20,1,0,0,0,0,0,0 +1150,56,32,158,91763,1,7.40,1,0,0,0,0,0,0 +1151,55,31,81,95521,3,2.67,1,0,0,0,0,1,0 +1152,49,23,12,94720,2,0.10,3,0,0,1,1,1,0 +1153,63,37,21,95831,2,0.40,1,0,0,0,0,1,0 +1154,55,30,55,92821,4,0.90,1,215,0,0,0,1,1 +1155,59,35,42,93555,1,1.80,3,0,0,0,0,1,0 +1156,41,16,81,92653,2,0.40,1,0,0,0,0,0,1 +1157,49,25,13,94305,4,0.20,1,87,0,0,0,0,0 +1158,48,23,132,94998,1,0.60,1,157,0,0,0,0,0 +1159,41,16,99,92660,1,1.00,3,0,0,0,0,1,0 +1160,50,26,23,92028,4,0.20,1,0,0,0,0,0,1 +1161,28,1,40,95134,1,2.00,2,0,0,1,0,1,0 +1162,36,11,181,94309,3,1.40,1,0,1,0,0,0,0 +1163,38,14,112,94501,2,2.20,1,394,0,0,0,0,0 +1164,34,9,138,94720,2,7.80,1,227,0,0,0,1,0 +1165,41,17,94,90071,3,3.80,2,327,1,1,1,1,0 +1166,43,19,113,91203,1,1.70,1,0,0,0,0,0,0 +1167,30,5,112,91711,4,5.00,2,0,1,0,0,0,1 +1168,37,12,190,92354,2,3.00,1,475,0,0,0,1,0 +1169,62,37,38,91706,1,1.10,3,0,0,0,0,1,0 +1170,40,16,32,92110,1,1.40,3,158,0,0,0,1,0 +1171,35,10,104,91320,3,0.60,2,0,0,0,0,0,1 +1172,64,40,43,95014,1,1.90,2,0,0,0,0,1,0 +1173,49,24,45,92104,3,1.70,2,0,0,1,0,1,0 +1174,24,-1,35,94305,2,1.70,2,0,0,0,0,0,0 +1175,36,10,42,93106,4,1.20,2,0,0,0,0,1,1 +1176,29,4,58,91006,1,0.80,2,0,0,0,0,1,1 +1177,29,3,103,90049,4,3.40,1,0,1,0,0,1,0 +1178,28,3,71,90405,1,3.30,2,149,1,1,1,1,0 +1179,33,7,14,94025,1,0.40,2,98,0,0,0,1,0 +1180,36,11,98,90291,3,1.20,3,0,0,1,0,0,1 +1181,42,17,90,90504,1,0.10,2,0,0,0,0,0,1 +1182,25,0,65,90095,4,0.20,1,0,0,1,0,0,0 +1183,28,2,19,94720,4,0.40,1,0,0,0,0,1,1 +1184,50,25,35,94105,3,1.70,2,0,0,0,0,1,1 +1185,34,9,71,90041,4,1.30,1,0,0,0,0,1,0 +1186,43,19,31,94025,3,0.50,1,0,0,0,0,0,0 +1187,62,38,43,94928,4,1.20,2,0,0,0,0,1,0 +1188,61,36,24,94309,1,1.50,2,87,0,1,0,0,0 +1189,45,19,58,94305,2,0.40,3,0,0,1,0,0,1 +1190,42,17,115,92717,2,0.40,1,0,0,0,0,1,0 +1191,39,15,168,93117,2,8.00,1,152,0,1,0,0,0 +1192,29,5,128,94111,1,1.50,1,0,0,0,0,1,1 +1193,45,20,138,92870,1,7.00,1,0,0,0,0,0,1 +1194,58,32,81,92121,3,1.70,2,0,0,0,0,1,1 +1195,29,3,41,94305,4,1.30,3,0,0,0,0,1,0 +1196,32,7,123,92407,2,2.90,2,0,1,0,0,1,0 +1197,37,13,71,94609,2,2.70,1,94,0,0,0,1,0 +1198,48,23,8,92866,1,0.40,3,0,0,0,0,0,1 +1199,40,14,42,94801,2,0.70,1,101,0,0,0,1,0 +1200,29,4,62,92064,2,2.50,1,184,0,0,0,1,0 +1201,36,12,22,92507,4,1.00,1,91,0,1,0,1,0 +1202,35,8,38,95060,4,1.00,2,0,0,0,0,1,0 +1203,35,11,24,95521,4,0.40,2,0,0,0,0,0,0 +1204,62,37,50,91311,3,2.40,1,0,0,0,0,1,0 +1205,26,1,190,91604,4,1.30,2,197,1,0,0,1,0 +1206,32,7,94,91361,2,3.10,1,0,0,0,0,1,0 +1207,63,37,165,95035,4,5.10,3,0,1,0,0,0,0 +1208,38,12,43,94301,4,1.20,2,0,0,0,0,0,1 +1209,50,26,48,91711,1,1.60,2,0,0,0,0,0,1 +1210,46,21,52,91304,3,2.70,2,228,0,0,0,0,1 +1211,50,24,84,93943,4,4.90,1,0,0,0,0,1,0 +1212,61,36,131,92407,1,0.90,1,0,0,0,0,1,0 +1213,34,8,44,91101,4,0.20,1,0,0,0,0,0,0 +1214,27,2,78,93943,4,0.20,1,87,0,0,0,0,0 +1215,61,36,15,92521,4,0.40,2,0,0,0,0,0,0 +1216,45,20,38,94550,4,1.90,3,144,0,0,0,1,1 +1217,50,25,84,91107,1,1.30,3,0,0,1,0,1,0 +1218,44,20,122,94305,1,0.30,1,0,0,0,0,1,0 +1219,62,36,98,92122,2,2.80,1,0,0,0,0,0,0 +1220,45,18,80,92407,3,2.67,2,0,0,0,0,0,0 +1221,41,17,165,94143,2,8.00,1,0,0,0,0,1,0 +1222,30,5,121,94132,2,3.30,1,0,0,0,0,0,1 +1223,61,37,20,90011,3,0.40,2,94,0,0,0,0,0 +1224,45,19,11,96150,1,0.20,1,91,0,0,0,0,0 +1225,59,35,45,94920,1,1.80,3,0,0,0,0,1,0 +1226,30,6,118,94534,2,2.80,2,0,1,0,0,0,0 +1227,60,36,14,90089,2,0.30,1,109,0,0,0,1,1 +1228,39,13,30,92122,3,0.20,2,0,0,0,0,0,0 +1229,56,30,45,92870,1,0.20,1,98,0,0,0,0,0 +1230,56,32,80,94596,3,2.67,1,0,0,0,0,1,0 +1231,27,1,25,94920,4,0.30,2,0,0,0,0,1,1 +1232,66,41,144,94306,1,2.50,1,0,0,1,1,1,1 +1233,43,19,84,92646,4,0.20,3,297,0,0,0,1,0 +1234,53,29,22,93943,2,0.40,1,0,0,0,0,1,0 +1235,44,18,33,90405,3,1.50,1,0,0,0,0,1,1 +1236,54,28,60,94110,4,2.60,3,0,0,0,0,0,0 +1237,31,6,81,95762,4,2.20,2,116,0,0,0,1,0 +1238,38,13,169,92093,1,6.80,3,0,1,0,1,1,1 +1239,28,2,63,91116,2,1.60,3,0,0,0,0,1,0 +1240,51,26,12,90245,2,0.70,3,109,0,0,0,1,1 +1241,52,27,15,91320,4,0.80,1,101,0,0,0,0,0 +1242,64,38,39,92120,1,0.50,3,0,0,1,1,1,1 +1243,29,4,44,91380,4,2.00,2,0,0,0,0,1,0 +1244,34,10,110,92697,1,4.00,1,0,0,0,0,1,0 +1245,33,8,130,94720,3,6.30,2,99,1,0,0,0,1 +1246,46,21,41,94025,1,1.40,3,128,0,0,0,1,0 +1247,48,22,59,91775,1,1.40,3,241,0,0,0,1,0 +1248,52,28,39,94606,2,0.80,1,0,0,0,0,1,0 +1249,44,19,35,94305,4,0.00,2,0,0,0,0,1,0 +1250,51,27,80,90032,1,2.60,2,0,0,0,0,1,1 +1251,47,20,81,94301,1,2.67,2,0,0,0,0,1,0 +1252,39,13,31,95120,2,0.80,3,0,0,0,0,0,0 +1253,42,17,93,92182,4,1.90,3,0,0,0,0,0,0 +1254,57,33,45,92346,4,1.50,1,204,0,0,0,1,0 +1255,36,12,40,91101,2,0.60,3,0,0,0,0,1,1 +1256,27,1,80,95354,2,1.60,3,185,0,0,0,1,1 +1257,31,7,20,92115,1,0.40,3,0,0,0,0,1,0 +1258,63,37,41,93014,1,0.50,3,0,0,0,0,0,1 +1259,34,8,31,91203,1,0.30,1,104,0,0,0,1,1 +1260,52,27,35,95616,4,0.20,2,0,0,0,0,1,0 +1261,57,31,40,91107,3,1.40,3,137,0,0,0,1,1 +1262,63,39,84,94901,1,1.80,3,0,0,0,0,0,0 +1263,26,1,53,94720,2,1.60,3,0,0,0,0,1,0 +1264,35,5,85,92870,4,4.00,3,0,0,0,0,1,0 +1265,58,33,138,94546,2,3.90,1,0,0,0,0,1,0 +1266,32,2,71,95014,2,1.75,3,108,0,0,0,0,0 +1267,64,39,113,92121,1,0.80,3,0,0,0,0,0,1 +1268,50,23,23,94720,2,1.00,2,0,0,1,0,0,0 +1269,34,9,62,92677,3,2.30,1,0,0,0,0,0,0 +1270,36,11,14,92673,4,0.20,3,100,0,0,0,1,1 +1271,43,18,60,91311,2,2.20,3,0,0,0,0,0,1 +1272,28,4,94,92115,3,0.80,1,236,0,0,0,1,0 +1273,64,39,83,95616,3,1.80,2,0,0,0,0,1,0 +1274,60,35,130,95741,3,6.30,3,437,1,0,1,1,1 +1275,62,37,61,93117,4,1.70,1,0,0,0,0,0,0 +1276,27,2,92,95616,2,3.10,1,178,0,0,0,1,0 +1277,42,16,20,95351,2,0.80,3,117,0,0,0,1,1 +1278,45,20,194,92110,2,8.80,1,428,0,0,0,0,0 +1279,36,10,74,94305,1,2.50,1,0,0,0,0,0,1 +1280,48,22,84,90024,2,0.40,3,145,0,0,0,0,0 +1281,65,40,98,95064,3,1.80,2,333,0,0,0,0,0 +1282,39,15,52,92093,3,2.33,1,0,0,0,0,1,0 +1283,51,26,55,93955,1,1.30,2,236,0,0,0,0,1 +1284,30,6,64,94305,4,3.40,1,117,0,0,0,0,0 +1285,65,40,128,90740,1,2.50,1,162,0,0,0,1,0 +1286,38,13,113,94720,4,1.70,2,0,1,0,0,0,1 +1287,29,3,50,94010,3,1.10,2,0,0,0,0,0,1 +1288,42,18,54,94010,4,2.20,2,0,0,0,0,0,0 +1289,63,38,129,91326,1,0.90,1,366,0,0,0,1,0 +1290,46,21,82,94523,4,0.40,1,0,0,0,0,0,0 +1291,62,38,100,90277,4,1.70,2,0,0,0,0,1,0 +1292,58,34,44,94111,4,2.20,1,0,0,1,0,0,0 +1293,56,30,164,94610,4,0.50,2,234,1,0,1,1,1 +1294,56,31,81,92373,2,3.70,1,121,0,0,0,1,1 +1295,34,10,71,95003,1,0.10,1,257,0,0,0,1,1 +1296,42,17,28,92866,1,0.50,3,90,0,0,0,0,0 +1297,30,6,80,92399,3,1.50,1,219,0,0,0,1,0 +1298,61,35,90,95814,4,1.90,2,0,0,0,0,1,0 +1299,38,14,74,90274,1,3.60,2,0,0,0,0,1,1 +1300,50,25,14,95762,2,0.70,3,0,0,1,0,1,0 +1301,61,36,23,91754,2,0.50,2,103,0,0,0,1,0 +1302,41,17,153,92121,1,1.70,1,337,0,0,0,0,1 +1303,42,16,38,94087,3,0.90,3,0,0,0,0,0,0 +1304,29,5,112,94720,2,2.00,2,382,0,1,0,0,0 +1305,51,26,145,90025,1,8.10,1,397,0,0,0,0,1 +1306,32,6,28,94025,2,0.30,2,88,0,0,0,1,0 +1307,34,9,31,94115,4,1.10,3,0,0,0,0,1,1 +1308,26,2,195,94546,1,6.33,1,0,0,0,0,1,1 +1309,54,24,50,92037,3,2.00,3,0,0,0,0,1,1 +1310,38,14,71,95136,4,2.00,3,0,0,0,0,0,0 +1311,62,36,21,95616,3,0.30,3,0,0,0,0,0,0 +1312,37,11,35,90044,2,0.80,3,125,0,0,0,0,0 +1313,46,21,42,92691,1,2.40,1,0,0,0,0,1,1 +1314,52,27,78,92008,4,3.60,3,141,0,0,0,1,0 +1315,32,6,73,94305,4,2.20,2,0,0,0,0,0,0 +1316,49,25,53,95134,2,1.00,3,181,0,0,0,0,0 +1317,28,3,51,94086,2,1.60,3,123,0,0,0,0,0 +1318,55,30,40,95521,2,2.30,3,0,0,0,0,1,0 +1319,52,26,178,94234,1,1.00,1,0,0,0,0,0,0 +1320,32,6,35,94005,2,0.30,1,0,0,0,0,0,1 +1321,31,7,192,90250,1,0.00,2,0,1,0,0,1,0 +1322,27,3,123,95138,1,5.40,1,0,0,0,0,0,0 +1323,32,5,48,94022,2,1.67,2,0,0,1,1,1,1 +1324,52,26,45,91604,3,0.60,2,0,0,0,0,0,0 +1325,52,28,15,95064,1,0.20,1,0,0,0,0,1,0 +1326,50,24,79,94304,1,0.30,1,120,0,0,0,1,0 +1327,32,5,63,90024,4,2.00,2,0,0,1,0,1,0 +1328,61,35,30,94720,2,0.20,3,0,0,0,0,1,0 +1329,60,36,145,95616,4,6.90,1,380,1,0,0,0,1 +1330,28,4,32,90095,3,1.00,2,0,0,0,0,0,0 +1331,34,9,64,92346,2,0.10,1,224,0,0,0,1,1 +1332,31,7,84,92692,1,0.10,1,0,0,0,0,1,0 +1333,31,5,21,94309,1,0.40,2,0,0,0,0,1,0 +1334,62,38,99,95014,4,1.70,2,0,0,0,0,1,0 +1335,47,22,35,94304,2,1.30,1,0,0,0,0,1,0 +1336,50,24,180,94539,1,1.70,1,0,0,0,0,1,1 +1337,36,12,42,93555,1,1.33,1,0,0,0,0,1,0 +1338,26,0,179,92028,4,2.10,2,0,1,0,0,0,0 +1339,51,27,42,90245,4,0.10,3,0,0,0,0,0,0 +1340,52,25,180,94545,2,9.00,2,297,1,0,0,1,0 +1341,35,11,82,94131,4,3.40,1,0,0,0,0,0,0 +1342,42,16,55,91355,2,0.70,1,149,0,0,0,0,0 +1343,36,12,79,90041,2,2.20,1,0,0,0,0,1,0 +1344,41,17,48,92831,2,0.60,3,215,0,0,0,0,1 +1345,49,25,93,93117,1,2.70,1,0,0,1,0,1,0 +1346,57,32,23,92126,2,0.20,3,0,0,0,0,0,0 +1347,44,20,50,95670,3,2.33,1,200,0,0,0,0,0 +1348,60,34,85,91367,2,2.00,1,0,0,0,0,1,0 +1349,38,14,35,95051,1,1.50,2,97,0,0,0,1,0 +1350,26,2,171,93943,3,6.00,2,0,1,0,0,1,0 +1351,29,2,29,90266,4,1.50,2,0,0,0,0,0,1 +1352,59,35,84,94588,1,1.80,3,0,0,0,0,1,1 +1353,51,27,20,90401,4,0.50,2,0,0,0,0,1,0 +1354,50,25,14,94124,1,0.40,3,0,0,0,0,1,1 +1355,35,10,179,91942,1,8.60,1,357,0,0,0,0,0 +1356,61,37,48,91910,1,0.80,1,158,0,0,0,1,0 +1357,42,16,74,90066,1,2.80,1,0,0,0,0,1,0 +1358,55,29,53,95134,1,1.40,1,0,0,0,0,0,0 +1359,50,25,83,92007,1,2.80,2,0,0,0,0,1,1 +1360,64,40,171,90034,2,2.10,1,433,0,0,0,0,0 +1361,54,28,85,92028,4,4.90,1,0,0,0,0,1,0 +1362,50,26,38,95039,4,0.90,2,0,0,0,0,1,0 +1363,31,5,85,92130,3,1.60,1,157,0,0,0,1,1 +1364,32,8,79,92115,1,0.10,1,0,0,0,0,0,0 +1365,44,19,69,92129,4,0.40,1,0,0,0,0,0,0 +1366,60,35,43,94720,3,0.90,3,0,0,0,0,1,1 +1367,60,34,33,91107,2,0.30,1,101,0,0,0,1,0 +1368,62,38,42,95747,3,0.10,3,149,0,0,0,0,1 +1369,46,21,40,94025,4,1.90,3,122,0,0,0,1,0 +1370,57,33,43,91902,1,1.80,3,0,0,0,0,0,0 +1371,30,5,20,94545,4,0.50,3,117,0,0,0,0,0 +1372,58,32,65,95621,3,2.50,1,222,0,0,0,1,0 +1373,39,13,139,95616,3,3.40,1,483,1,0,0,1,0 +1374,60,35,135,92612,3,0.30,3,0,1,0,0,1,0 +1375,59,34,84,94043,3,1.60,3,0,0,0,0,1,0 +1376,50,26,179,92612,1,2.90,3,0,1,0,0,0,1 +1377,63,39,45,92870,4,1.30,2,86,0,0,0,0,0 +1378,27,3,109,93023,2,2.50,1,0,0,0,0,1,0 +1379,54,29,34,93305,4,0.10,3,0,0,0,0,1,0 +1380,62,37,162,95051,1,1.30,1,0,0,0,0,1,0 +1381,60,34,105,92103,2,1.40,1,0,0,0,0,1,0 +1382,38,12,22,91380,3,0.20,2,0,0,0,0,1,0 +1383,34,8,82,91775,2,1.80,1,178,0,0,0,1,1 +1384,65,41,105,95616,4,1.70,2,230,0,1,0,1,0 +1385,55,31,62,91711,1,1.80,3,0,0,0,0,1,0 +1386,57,31,82,95032,2,2.00,1,83,0,0,0,0,1 +1387,27,3,72,95616,4,0.00,1,0,0,0,0,1,0 +1388,35,10,38,95762,4,1.70,1,0,0,0,0,1,1 +1389,52,28,25,90212,4,1.00,1,0,0,0,0,0,0 +1390,45,15,20,94107,1,0.75,3,0,0,0,0,1,0 +1391,29,3,80,94305,4,1.80,2,0,0,0,0,1,1 +1392,44,18,84,91330,3,1.10,1,0,0,0,0,0,0 +1393,47,23,33,90095,1,1.00,1,0,0,0,0,1,1 +1394,62,37,55,95039,3,0.90,3,0,0,0,0,1,0 +1395,52,27,33,90095,2,0.70,2,0,0,0,0,0,1 +1396,47,23,190,92831,4,0.30,3,305,1,0,0,0,0 +1397,42,18,43,91107,1,0.30,3,158,0,0,0,0,0 +1398,65,41,45,95521,3,0.10,3,0,0,0,0,1,0 +1399,42,18,141,93407,1,3.50,1,0,0,0,0,0,0 +1400,40,16,69,92009,4,2.40,1,0,0,0,0,1,0 +1401,32,8,78,90401,4,0.10,2,0,0,0,0,1,0 +1402,40,15,84,94521,1,3.70,3,0,0,0,0,1,0 +1403,55,29,172,95064,1,5.20,2,0,1,0,0,0,0 +1404,32,6,51,93109,4,0.20,1,154,0,1,0,0,1 +1405,58,28,75,92121,1,1.40,3,0,0,0,0,1,0 +1406,46,22,183,91605,1,3.10,2,0,1,0,1,1,1 +1407,53,23,20,92123,4,0.40,3,0,0,0,0,1,1 +1408,63,39,101,94306,2,3.90,3,294,1,0,0,1,0 +1409,40,14,129,90089,1,5.90,3,0,1,0,0,1,0 +1410,41,17,63,90745,2,3.20,1,0,0,0,0,0,0 +1411,60,35,44,92126,4,2.10,1,0,0,0,0,0,0 +1412,65,39,184,91302,1,5.40,3,176,1,0,1,1,1 +1413,59,33,100,95064,2,2.00,1,127,0,0,0,0,0 +1414,48,24,12,90058,3,0.40,1,0,0,0,0,0,0 +1415,59,33,68,94105,2,2.30,3,128,0,1,0,1,0 +1416,33,8,48,94019,1,1.00,1,212,0,0,0,1,0 +1417,40,15,82,93101,2,0.40,1,0,0,0,0,0,0 +1418,42,18,52,94061,2,2.50,1,0,0,0,0,0,0 +1419,65,41,154,92008,2,4.60,2,0,1,1,1,1,1 +1420,30,4,39,91105,1,1.50,1,0,0,0,0,0,1 +1421,30,4,40,91605,1,0.30,1,0,0,0,1,1,1 +1422,42,17,54,94720,4,1.90,3,164,0,0,0,0,0 +1423,32,8,32,94143,2,1.00,2,103,0,0,1,1,1 +1424,55,30,64,90250,2,2.30,3,0,0,0,0,0,0 +1425,29,3,92,94539,2,1.30,1,287,0,0,0,1,0 +1426,64,38,40,91330,1,2.50,3,94,0,0,0,1,1 +1427,37,11,60,96651,3,0.50,3,0,0,0,0,1,0 +1428,31,5,85,95828,2,1.30,1,119,0,0,0,1,1 +1429,25,-1,21,94583,4,0.40,1,90,0,0,0,1,0 +1430,31,5,35,95064,1,0.60,3,171,0,0,0,0,0 +1431,32,7,52,92660,2,0.10,1,0,0,0,0,1,0 +1432,58,34,128,90058,1,7.40,1,0,0,0,0,0,0 +1433,26,2,195,90245,1,6.33,1,0,0,0,0,0,0 +1434,51,25,68,92647,2,1.50,2,117,0,0,0,0,1 +1435,65,41,55,93106,2,1.10,1,0,0,0,0,0,0 +1436,43,17,55,90266,1,0.20,1,0,0,0,0,1,0 +1437,46,21,80,95054,4,0.40,1,0,0,0,0,1,1 +1438,28,3,123,92007,1,0.80,1,146,0,0,0,0,0 +1439,63,37,90,94105,4,1.90,2,106,0,1,0,1,0 +1440,59,29,61,94025,1,1.40,3,0,0,0,0,0,0 +1441,42,15,41,94610,3,2.50,2,0,0,0,0,1,0 +1442,58,33,43,94720,2,1.60,3,0,0,0,0,1,0 +1443,39,13,71,95822,3,0.10,1,162,0,1,0,1,0 +1444,36,12,25,95051,4,1.00,1,0,0,0,0,1,0 +1445,60,33,154,90740,1,3.00,2,0,1,1,1,1,0 +1446,47,21,141,90095,1,2.40,1,0,0,0,0,0,0 +1447,29,4,22,92661,2,0.90,3,110,0,0,0,0,0 +1448,52,28,145,94131,2,6.80,1,0,0,0,0,1,0 +1449,41,16,49,92122,3,0.50,3,0,0,0,0,1,0 +1450,63,37,109,90740,1,2.00,1,0,0,0,0,1,0 +1451,59,34,80,90086,3,0.50,1,0,0,0,0,1,1 +1452,44,20,82,94555,4,1.40,2,201,0,0,0,1,1 +1453,54,28,52,94102,4,2.50,1,0,0,0,0,1,0 +1454,29,5,85,90232,3,2.50,1,0,0,0,0,1,1 +1455,51,25,148,90024,1,1.00,1,0,0,0,0,0,0 +1456,63,39,160,91330,2,2.10,1,0,0,0,0,0,1 +1457,36,11,39,90095,4,1.70,1,0,0,0,0,1,0 +1458,42,16,25,94304,2,0.80,3,0,0,0,0,0,1 +1459,51,25,33,93033,1,1.40,3,0,0,0,0,1,1 +1460,47,20,38,92115,3,2.50,2,0,0,0,0,0,0 +1461,40,16,85,92677,4,0.20,3,0,0,0,0,1,1 +1462,54,28,48,93022,1,0.20,1,0,0,0,0,1,0 +1463,47,21,15,95207,4,0.60,3,77,0,0,0,1,0 +1464,35,10,94,91343,1,0.00,1,174,0,0,0,1,0 +1465,28,4,120,92333,2,0.60,1,0,0,0,0,1,0 +1466,45,19,60,91911,1,0.70,3,159,0,0,0,1,0 +1467,33,9,145,94303,2,4.33,1,277,0,0,0,0,1 +1468,62,36,29,91107,2,0.70,3,0,0,0,0,0,0 +1469,45,18,78,92129,3,2.67,2,0,0,0,0,1,0 +1470,59,35,59,90005,4,1.20,2,0,0,0,0,1,0 +1471,58,28,80,91116,2,4.50,3,0,0,0,0,0,1 +1472,52,26,180,94305,1,1.00,1,0,0,0,0,1,1 +1473,34,8,8,94710,3,0.10,2,83,0,0,0,1,0 +1474,65,35,23,91711,1,1.50,3,0,0,0,0,1,0 +1475,48,23,79,92124,2,3.80,3,0,0,0,0,1,0 +1476,44,19,78,92064,2,3.80,3,268,0,0,0,0,0 +1477,61,37,64,92028,1,0.00,2,0,0,0,0,0,1 +1478,40,14,64,91320,4,0.20,3,0,0,0,0,1,1 +1479,65,39,160,94803,4,3.80,1,237,1,0,0,1,0 +1480,28,4,43,91304,1,1.00,3,102,0,0,0,0,0 +1481,67,42,32,93943,1,1.10,3,0,0,0,0,0,1 +1482,35,9,179,91125,2,0.00,1,76,0,1,0,1,0 +1483,60,35,8,94143,1,0.10,1,0,0,0,0,1,0 +1484,58,32,63,92717,1,1.60,1,0,0,1,0,1,0 +1485,55,30,40,94126,2,2.30,3,0,0,1,0,1,0 +1486,34,9,99,90245,4,2.20,2,155,0,0,0,1,0 +1487,35,9,141,93022,2,4.50,2,0,1,0,0,0,0 +1488,28,4,159,93907,1,1.50,1,0,0,0,0,1,1 +1489,38,12,39,95825,2,0.30,1,174,0,0,0,1,0 +1490,62,38,99,91604,4,1.70,2,0,0,0,0,0,0 +1491,30,4,18,95020,4,0.30,2,0,0,0,0,1,1 +1492,38,12,38,94553,2,0.30,1,0,0,0,0,1,1 +1493,33,8,133,90024,1,0.00,1,0,0,0,0,1,0 +1494,58,34,84,91380,2,2.80,1,0,0,0,0,1,1 +1495,59,35,60,90089,1,0.00,2,0,0,0,0,1,1 +1496,52,28,178,92647,3,5.40,3,147,1,0,0,1,0 +1497,36,12,18,91330,1,0.50,3,0,0,0,0,0,1 +1498,45,21,73,95020,1,0.80,3,0,0,0,0,1,0 +1499,49,23,125,94022,1,7.30,1,0,0,0,0,0,0 +1500,52,26,91,92173,1,4.30,2,0,1,0,1,1,1 +1501,54,28,74,95014,2,1.10,1,0,0,0,0,1,0 +1502,30,4,35,92130,2,0.30,2,0,0,1,0,0,1 +1503,65,39,113,90036,1,2.00,1,0,0,0,0,1,1 +1504,34,8,52,94720,4,2.20,2,0,0,0,0,0,0 +1505,30,6,191,92028,2,4.40,2,0,1,0,0,1,0 +1506,51,25,18,92109,1,0.30,3,93,0,0,0,0,1 +1507,52,27,25,95138,2,0.00,1,0,0,0,0,1,1 +1508,43,18,50,91006,4,1.90,3,0,0,0,0,0,0 +1509,35,10,75,93940,4,0.70,3,0,0,0,0,1,1 +1510,56,26,92,92647,2,4.50,3,0,0,1,0,0,1 +1511,57,32,33,95747,2,2.00,2,0,0,0,0,1,0 +1512,58,32,65,90266,3,2.20,3,0,0,0,0,0,0 +1513,53,28,44,91604,3,1.70,1,0,0,0,0,0,0 +1514,45,21,183,95211,2,1.40,1,354,0,0,0,0,0 +1515,44,20,175,96150,2,1.40,1,0,0,0,0,1,1 +1516,54,28,28,94305,4,1.50,3,0,0,0,0,1,1 +1517,41,17,49,92130,4,2.20,2,0,0,0,0,0,0 +1518,52,26,45,92697,4,1.80,1,0,0,0,0,1,0 +1519,43,17,64,95053,4,3.00,3,221,1,0,0,1,0 +1520,63,38,22,92115,3,0.10,3,90,0,0,0,1,0 +1521,54,30,120,95039,1,7.40,1,119,0,0,0,1,1 +1522,33,8,175,92354,2,6.70,1,102,0,0,0,1,0 +1523,25,-1,101,94720,4,2.30,3,256,0,0,0,0,1 +1524,41,16,104,92037,1,1.00,3,0,0,0,0,1,0 +1525,40,16,155,94002,4,0.10,3,0,1,0,1,1,1 +1526,43,18,58,95747,1,2.40,1,0,0,0,0,0,0 +1527,36,10,80,94608,4,2.20,2,0,0,0,0,1,0 +1528,57,33,45,94117,1,1.80,3,195,0,0,0,0,0 +1529,34,9,134,94550,1,4.60,1,164,0,1,0,1,0 +1530,38,14,58,91709,4,2.00,3,153,0,1,0,0,0 +1531,47,21,20,94066,1,0.20,1,0,0,0,0,1,1 +1532,39,13,25,90304,4,1.50,3,0,0,0,0,1,0 +1533,45,20,55,94588,1,0.30,1,0,0,0,0,1,1 +1534,62,37,155,93943,1,1.30,1,0,0,0,0,0,0 +1535,59,34,30,92084,1,1.30,1,0,0,0,0,1,1 +1536,61,37,39,92096,4,0.40,1,0,0,0,0,1,1 +1537,36,12,73,95617,4,2.00,3,188,0,0,0,1,0 +1538,58,34,41,94608,4,1.30,1,0,0,0,0,1,0 +1539,55,30,34,95820,4,0.10,3,157,0,0,0,1,0 +1540,29,5,21,90601,3,0.90,3,119,0,0,0,0,0 +1541,34,8,11,91320,4,0.30,1,0,0,1,1,1,1 +1542,61,35,154,92704,2,6.90,1,0,0,0,0,0,0 +1543,50,20,19,92612,4,0.40,3,0,0,0,0,0,0 +1544,52,26,101,93407,2,2.40,2,0,0,0,0,1,0 +1545,39,15,24,92123,1,1.00,1,116,0,0,0,1,1 +1546,55,29,131,92675,2,2.70,1,0,0,1,0,0,0 +1547,33,9,105,95136,1,4.00,1,0,0,0,0,1,0 +1548,47,21,52,94720,1,1.20,2,194,0,0,0,0,0 +1549,57,32,21,92037,4,0.90,2,113,0,1,0,0,0 +1550,57,31,45,94305,3,1.40,1,198,0,0,0,1,0 +1551,40,14,39,93117,1,2.00,1,0,0,0,0,1,0 +1552,50,25,192,94115,2,2.80,1,238,0,0,0,0,1 +1553,29,5,195,94301,1,4.30,1,0,0,0,0,0,0 +1554,46,22,83,95616,3,0.70,1,0,0,0,0,0,0 +1555,42,15,34,91302,3,1.00,2,0,0,1,0,1,0 +1556,59,33,49,93009,4,1.70,2,104,0,0,0,1,0 +1557,31,1,60,94143,4,4.00,3,244,0,0,0,0,0 +1558,51,25,41,94939,4,1.80,1,0,0,0,0,0,0 +1559,35,10,72,91320,3,2.30,1,285,0,0,0,0,0 +1560,59,35,102,92677,4,3.00,2,115,1,0,0,1,0 +1561,35,10,31,95605,3,1.30,1,0,0,0,0,0,0 +1562,46,20,73,93106,1,1.50,2,128,0,0,0,1,0 +1563,34,9,89,91763,1,0.00,1,0,0,0,0,1,0 +1564,55,29,19,92109,4,0.70,3,121,0,1,0,0,1 +1565,64,40,63,94706,4,1.20,2,0,0,0,0,1,0 +1566,34,9,104,95758,3,1.20,3,0,0,0,0,1,0 +1567,61,35,40,95064,1,0.80,2,128,0,0,0,1,0 +1568,63,39,92,94710,2,0.00,3,0,0,0,0,1,0 +1569,59,33,72,92350,2,0.70,2,226,0,0,0,0,0 +1570,51,27,44,94305,3,1.90,2,141,0,0,0,0,0 +1571,41,16,114,94705,4,3.50,1,0,1,0,0,0,1 +1572,37,13,73,95758,4,2.40,1,0,0,0,0,0,0 +1573,64,40,63,91711,4,1.20,2,0,0,1,0,0,1 +1574,44,20,69,92028,1,0.80,3,184,0,0,1,1,1 +1575,62,37,42,92106,3,1.50,1,0,0,0,0,1,0 +1576,50,26,88,90037,1,2.70,1,0,0,0,0,1,0 +1577,43,18,98,92131,2,0.40,1,0,0,0,0,1,0 +1578,34,8,65,92093,1,3.00,1,227,1,0,0,1,0 +1579,38,13,12,94143,2,0.30,2,104,0,1,0,1,0 +1580,29,5,122,94305,4,3.00,1,0,1,0,0,0,1 +1581,39,14,12,92093,2,0.00,3,0,0,0,0,0,0 +1582,53,29,24,94105,2,0.20,1,0,0,0,0,0,1 +1583,43,19,170,92037,4,4.25,1,318,1,0,1,1,1 +1584,61,36,184,92028,4,2.30,2,342,1,0,1,1,1 +1585,46,20,25,93401,4,0.60,3,125,0,0,0,0,0 +1586,57,31,131,90502,2,2.70,1,0,0,0,0,0,0 +1587,59,33,50,94122,2,2.30,3,0,0,0,0,0,1 +1588,52,28,21,94035,2,0.40,1,0,0,1,0,1,0 +1589,29,3,55,95616,3,1.10,2,0,0,0,0,1,0 +1590,57,32,124,90049,1,0.20,2,0,1,0,0,1,0 +1591,49,23,58,95819,4,2.60,1,188,0,0,0,0,0 +1592,39,13,72,95817,2,2.80,1,0,0,0,0,1,0 +1593,56,31,192,90089,1,7.00,3,0,1,0,1,1,0 +1594,63,38,83,91320,3,1.80,2,0,0,0,0,1,0 +1595,37,12,93,90025,1,2.80,1,0,0,1,0,1,0 +1596,56,26,38,94305,3,1.00,3,110,0,1,0,1,0 +1597,45,20,55,92606,4,1.90,3,164,0,1,0,0,0 +1598,66,41,11,92325,3,0.10,3,0,0,1,0,0,1 +1599,40,15,85,94550,2,0.40,1,0,0,1,0,0,0 +1600,50,24,124,93305,1,4.90,1,266,0,0,0,1,0 +1601,60,36,129,92028,2,6.00,1,0,0,0,0,1,0 +1602,31,7,180,93407,1,4.30,1,0,0,0,0,0,0 +1603,40,14,74,90245,4,1.40,2,0,0,0,0,1,0 +1604,36,6,138,92152,1,7.00,3,86,1,0,0,1,0 +1605,55,29,111,90502,2,3.60,3,0,1,0,0,0,1 +1606,54,28,83,93555,3,0.80,1,0,0,0,0,1,0 +1607,35,10,33,90266,4,1.70,1,87,0,0,0,1,0 +1608,55,29,21,92028,4,0.70,3,0,0,0,0,0,0 +1609,36,10,35,94608,2,0.30,1,98,0,0,0,1,0 +1610,66,41,105,93023,1,0.80,3,0,0,1,1,1,1 +1611,38,14,103,94305,1,0.80,2,0,0,0,0,0,1 +1612,58,32,75,92096,2,2.30,3,0,0,0,0,0,0 +1613,41,17,33,94550,1,0.70,1,104,0,0,0,0,0 +1614,60,34,52,94305,4,1.70,2,0,0,1,0,1,0 +1615,47,23,89,94920,1,2.60,2,0,0,1,1,1,1 +1616,62,36,63,93109,1,2.50,3,0,0,0,0,0,0 +1617,48,23,84,94402,4,3.10,2,0,1,1,1,1,0 +1618,61,36,44,91302,4,2.10,1,0,0,0,0,0,0 +1619,29,3,29,94720,3,1.00,1,0,0,0,0,1,1 +1620,45,21,29,90005,1,0.30,3,0,0,0,0,1,0 +1621,39,14,22,94035,2,0.30,2,0,0,0,0,1,0 +1622,31,6,53,92093,4,2.20,1,114,0,0,0,1,0 +1623,39,14,24,94611,2,0.30,2,0,0,0,0,1,0 +1624,63,38,153,90045,1,1.30,1,455,0,0,0,0,0 +1625,28,2,31,90024,2,0.30,2,0,0,1,0,1,0 +1626,56,30,21,94542,2,0.70,2,0,0,0,0,1,0 +1627,31,6,180,93108,2,6.70,1,0,0,0,0,0,0 +1628,46,20,82,91016,3,0.70,2,0,0,0,0,1,1 +1629,42,18,90,95064,4,0.80,1,245,0,1,0,0,0 +1630,53,29,154,93407,4,7.40,3,0,1,0,0,0,0 +1631,41,17,99,92096,2,1.80,2,0,0,0,0,1,1 +1632,61,36,153,91105,1,2.60,2,0,1,1,1,0,1 +1633,31,5,93,95032,2,3.10,2,0,1,0,0,1,0 +1634,62,38,53,92121,1,0.00,2,0,0,0,0,0,0 +1635,59,34,18,95814,3,1.30,2,104,0,0,1,1,1 +1636,49,24,70,91330,1,2.90,1,0,0,0,0,0,0 +1637,65,39,100,92122,4,1.70,3,0,0,0,0,0,1 +1638,30,6,193,94022,3,6.30,3,0,1,0,0,1,0 +1639,32,7,125,95133,1,0.00,1,0,0,0,0,1,1 +1640,56,31,68,94571,2,0.00,3,0,0,1,0,1,0 +1641,36,10,55,90009,1,2.00,1,95,0,0,0,1,0 +1642,58,34,152,92182,4,3.60,3,0,1,0,0,0,0 +1643,27,3,84,95814,3,1.50,1,0,0,0,0,1,1 +1644,41,16,13,91125,2,0.00,3,0,0,0,0,1,0 +1645,59,35,33,91355,4,0.40,1,131,0,0,0,0,1 +1646,56,32,89,92096,4,1.00,2,90,0,1,0,1,0 +1647,52,26,93,91745,1,2.40,1,0,0,0,0,1,0 +1648,35,5,68,90509,4,1.80,3,0,0,0,0,0,0 +1649,47,21,85,93106,2,1.70,2,0,0,0,0,0,1 +1650,29,4,73,95039,1,0.80,2,0,0,0,0,1,0 +1651,31,6,83,92131,4,2.20,2,106,0,0,0,1,0 +1652,62,36,158,94301,2,6.30,3,0,1,0,0,1,0 +1653,48,18,182,92626,4,6.00,3,0,1,0,0,1,0 +1654,26,1,24,96651,2,0.90,3,123,0,0,0,0,1 +1655,60,34,102,94305,2,2.00,1,0,0,0,0,1,1 +1656,35,11,53,91355,3,2.80,1,0,0,0,0,0,0 +1657,40,15,175,92646,2,3.30,1,0,0,0,0,1,0 +1658,31,5,28,94538,3,1.00,1,0,0,0,0,1,0 +1659,50,25,14,92037,4,0.80,1,0,0,0,0,1,0 +1660,33,7,139,95828,1,4.00,3,106,1,0,1,1,1 +1661,37,11,34,95747,3,0.90,1,0,0,0,0,1,0 +1662,38,14,64,92093,1,1.50,3,0,0,0,0,0,1 +1663,63,38,84,94607,4,0.10,2,0,0,0,0,0,0 +1664,57,32,42,95070,3,0.50,2,0,0,1,0,1,0 +1665,61,35,63,91605,1,1.60,1,0,0,0,0,1,0 +1666,37,12,100,92735,3,1.20,3,341,0,0,0,1,1 +1667,51,25,190,95138,2,4.20,2,0,1,0,0,1,0 +1668,44,20,22,90024,1,1.00,1,91,0,0,0,0,0 +1669,63,37,20,90066,1,0.80,2,0,0,1,0,0,1 +1670,43,18,21,95037,2,1.40,2,0,0,0,0,1,1 +1671,38,14,25,95135,4,0.40,2,101,0,0,0,1,0 +1672,34,9,20,92648,4,1.10,3,0,0,0,0,1,0 +1673,48,23,173,94546,3,0.20,1,0,1,0,1,1,1 +1674,29,5,81,94115,2,2.50,1,0,0,0,0,0,1 +1675,37,11,139,95814,2,0.80,2,421,1,0,0,1,0 +1676,60,35,119,90266,2,3.90,1,0,0,1,0,1,0 +1677,46,20,74,92821,4,2.60,3,104,0,0,0,1,0 +1678,34,10,42,92173,1,1.50,2,131,0,0,0,0,0 +1679,56,30,73,94035,2,1.10,1,0,0,0,0,0,0 +1680,57,31,114,94590,4,5.20,1,0,1,1,1,1,0 +1681,62,36,44,92093,2,1.00,3,0,0,0,0,0,0 +1682,32,8,141,90005,2,4.33,1,0,0,0,0,0,0 +1683,51,26,14,92182,2,0.00,1,103,0,0,0,1,0 +1684,55,29,33,92660,2,0.40,3,0,0,0,0,0,0 +1685,60,34,83,94028,2,2.00,1,249,0,0,0,0,0 +1686,40,16,89,90011,4,0.80,1,155,0,0,0,1,0 +1687,62,38,39,96003,4,2.20,1,0,0,1,0,1,0 +1688,63,39,83,90025,3,2.00,3,0,0,0,0,1,1 +1689,60,34,108,92152,2,2.00,1,359,0,0,0,1,0 +1690,59,34,21,92028,3,1.30,2,0,0,0,0,1,1 +1691,26,1,102,95521,1,1.90,1,0,0,0,0,0,0 +1692,56,32,48,94117,1,1.60,3,0,0,0,0,0,1 +1693,58,32,32,93014,3,1.40,1,0,0,0,0,1,0 +1694,57,31,43,95616,1,0.20,1,0,0,0,0,0,0 +1695,48,23,35,94025,4,0.40,2,118,0,0,0,0,0 +1696,30,6,184,91911,1,6.00,1,0,0,0,0,1,0 +1697,45,21,140,91024,2,7.60,1,132,0,0,0,0,0 +1698,64,38,32,90065,3,0.70,2,0,0,0,0,1,1 +1699,44,20,149,92121,1,1.70,1,0,0,0,0,1,0 +1700,51,25,15,94720,4,0.60,3,0,0,0,0,0,1 +1701,43,16,71,90089,3,2.33,2,0,0,0,0,0,0 +1702,29,3,108,94304,4,1.80,2,0,0,0,0,0,0 +1703,56,30,122,93555,2,0.50,1,0,0,0,0,0,1 +1704,65,41,40,94542,3,0.10,3,0,0,0,0,1,0 +1705,46,22,198,95521,2,6.67,1,0,0,0,0,0,1 +1706,48,24,79,90245,4,1.40,2,0,0,1,0,0,1 +1707,56,31,84,92672,1,0.10,3,0,0,0,0,1,0 +1708,61,37,31,92374,3,0.40,2,0,0,0,0,0,1 +1709,46,20,12,90250,4,0.60,3,0,0,0,0,0,1 +1710,58,34,88,93555,2,1.60,1,0,0,0,0,1,1 +1711,31,5,29,95405,2,0.30,2,131,0,0,0,1,1 +1712,27,3,201,95819,1,6.33,1,158,0,0,0,1,0 +1713,44,20,20,92780,1,1.40,3,0,0,0,0,0,0 +1714,44,20,15,90405,1,1.00,1,0,0,0,0,1,0 +1715,51,27,155,94720,2,0.40,1,107,0,0,0,0,1 +1716,39,13,25,95370,3,0.20,2,0,0,0,0,1,0 +1717,32,8,200,91330,2,6.50,1,565,0,0,0,1,0 +1718,33,7,101,93727,1,2.70,2,233,0,0,0,0,0 +1719,40,16,19,92028,4,0.40,2,0,0,0,0,1,1 +1720,36,12,188,91304,2,6.50,1,0,0,0,0,1,1 +1721,52,28,8,95060,1,0.30,1,0,0,0,0,1,0 +1722,54,29,59,92867,2,2.30,3,152,0,0,0,1,0 +1723,26,2,72,92647,4,2.60,1,0,0,1,1,1,0 +1724,39,15,55,95821,1,1.50,3,0,0,0,0,1,0 +1725,46,19,24,90025,3,0.67,2,0,0,0,0,1,0 +1726,57,32,19,95348,1,1.30,1,0,0,0,0,1,0 +1727,59,33,71,91335,2,2.30,3,150,0,0,0,1,1 +1728,52,26,54,90049,2,1.50,2,0,0,0,0,0,1 +1729,52,26,28,95405,1,0.30,3,0,0,0,0,1,0 +1730,50,20,25,91320,4,0.40,3,0,0,0,0,1,0 +1731,41,17,51,94402,2,0.60,3,0,0,0,0,0,1 +1732,43,19,125,92122,3,2.40,1,0,1,0,0,1,0 +1733,25,0,88,94566,2,1.80,2,319,0,0,0,1,1 +1734,40,16,125,95125,2,2.20,1,0,0,0,0,1,0 +1735,35,10,79,94720,4,2.10,3,182,0,0,0,1,0 +1736,60,36,31,95051,3,0.40,2,0,0,0,0,1,1 +1737,57,31,131,95133,2,2.70,1,394,0,0,0,0,1 +1738,44,19,70,92399,1,0.20,2,230,0,1,0,0,0 +1739,61,36,38,91129,3,0.90,3,82,0,0,0,1,1 +1740,33,7,83,95211,1,2.50,1,0,0,1,1,1,1 +1741,45,20,59,95008,1,2.40,1,0,0,1,1,1,0 +1742,45,21,121,94066,1,4.70,1,0,0,0,0,0,0 +1743,64,38,42,95929,2,0.70,3,137,0,0,0,1,0 +1744,50,24,32,94701,4,1.80,1,109,0,0,0,1,0 +1745,28,3,29,91105,4,0.80,1,135,0,0,0,1,0 +1746,37,12,40,90065,2,1.10,2,0,0,1,0,0,1 +1747,62,36,25,90740,3,0.30,3,0,0,0,0,1,1 +1748,29,5,21,90717,4,0.40,2,89,0,0,0,0,1 +1749,49,23,79,95819,3,0.70,2,151,0,0,0,1,0 +1750,46,22,52,95814,2,2.10,3,221,0,0,0,0,0 +1751,60,34,61,95521,4,1.70,2,229,0,0,0,0,0 +1752,55,31,25,94720,2,0.20,1,0,0,0,0,0,0 +1753,33,8,155,92717,1,7.40,3,0,1,0,0,0,0 +1754,53,29,25,92008,2,0.40,1,0,0,0,0,1,0 +1755,50,24,80,95616,4,4.90,1,0,0,0,0,1,0 +1756,28,3,55,92647,4,1.70,2,0,0,0,0,1,1 +1757,42,17,23,95053,2,0.00,3,0,0,0,0,0,0 +1758,33,9,60,90630,1,1.20,1,0,0,0,0,1,1 +1759,40,14,54,96003,2,0.70,1,0,0,0,0,0,0 +1760,31,6,44,94720,4,0.80,1,0,0,0,0,0,0 +1761,41,16,33,94309,4,0.00,2,0,0,0,0,1,0 +1762,52,27,45,94720,2,2.00,2,121,0,0,0,0,1 +1763,65,35,55,94526,4,1.67,3,89,0,0,0,1,1 +1764,48,24,134,94105,1,5.00,1,0,0,0,0,0,1 +1765,45,21,44,94596,3,0.60,2,0,0,0,0,1,0 +1766,26,0,149,95051,2,7.20,1,154,0,0,0,0,0 +1767,64,38,22,92697,2,0.20,3,0,0,1,0,0,0 +1768,41,14,74,92691,3,2.33,2,0,0,0,0,1,0 +1769,43,18,128,92093,4,5.30,1,84,1,0,0,0,0 +1770,60,36,62,94061,4,2.20,1,0,0,0,0,0,0 +1771,62,37,9,91320,1,0.10,1,94,0,0,0,0,0 +1772,46,21,9,95023,2,0.70,3,0,0,0,0,1,0 +1773,36,11,15,94720,2,0.30,2,119,0,0,0,0,0 +1774,31,5,28,92037,4,0.80,1,0,0,0,0,0,0 +1775,43,18,83,93109,3,0.50,3,0,0,0,0,0,1 +1776,46,22,73,91360,1,0.80,3,117,0,0,0,0,0 +1777,50,26,42,94080,4,1.10,2,151,0,0,0,1,0 +1778,52,27,34,93117,2,0.70,2,114,0,0,0,1,1 +1779,27,3,32,94710,3,1.00,2,0,0,0,0,0,0 +1780,34,9,68,94720,1,2.80,1,0,0,0,0,1,0 +1781,49,24,82,95051,1,2.90,1,267,0,0,0,1,0 +1782,52,26,19,90650,2,0.70,2,0,0,0,0,0,1 +1783,37,11,60,95825,2,2.80,1,181,0,0,0,0,1 +1784,53,27,192,94720,1,1.70,1,601,0,0,0,1,0 +1785,54,29,119,91355,3,2.00,1,0,1,1,1,0,0 +1786,29,3,190,94080,2,4.50,1,0,0,0,0,1,0 +1787,35,11,34,93117,1,1.50,2,0,0,0,0,0,0 +1788,32,6,44,94608,4,0.20,1,0,0,1,1,1,1 +1789,38,13,23,91116,4,0.20,3,0,0,0,0,1,0 +1790,44,20,171,91330,4,0.70,1,567,1,0,1,1,1 +1791,44,20,43,92124,1,0.30,3,0,0,1,0,0,1 +1792,48,22,139,94309,1,0.00,1,0,0,0,1,1,1 +1793,46,20,118,93009,1,5.70,1,0,0,0,1,1,1 +1794,35,9,113,94596,3,0.80,3,0,1,0,0,1,0 +1795,56,32,98,91355,3,3.90,3,0,1,0,0,0,0 +1796,49,24,70,90024,1,2.90,1,0,0,0,0,0,1 +1797,57,32,42,92831,2,2.10,3,0,0,0,0,1,0 +1798,35,10,143,91365,1,8.60,1,0,0,0,0,1,1 +1799,44,20,185,94086,3,2.70,1,0,1,0,0,1,0 +1800,38,14,28,95821,4,0.40,2,100,0,0,0,1,0 +1801,57,33,45,94080,3,1.50,1,181,0,1,1,1,1 +1802,35,10,78,92121,1,2.60,2,0,0,0,0,0,0 +1803,29,3,121,92806,2,1.30,1,0,0,0,0,0,0 +1804,58,32,59,94542,1,1.60,1,0,0,0,0,1,0 +1805,40,16,64,92661,4,2.67,1,0,0,1,0,1,0 +1806,51,26,15,92373,2,0.00,1,114,0,0,0,1,0 +1807,61,36,10,90740,1,0.10,1,0,0,0,0,0,0 +1808,46,20,61,90036,2,0.40,3,0,0,0,0,0,0 +1809,55,31,50,93010,4,1.50,1,0,0,0,0,1,0 +1810,35,10,79,95045,4,2.10,3,0,0,1,0,1,0 +1811,60,34,35,90025,1,0.20,1,0,0,0,0,1,0 +1812,28,3,11,94534,4,0.50,3,0,0,0,0,0,0 +1813,43,19,128,95054,1,4.70,1,0,0,0,0,1,0 +1814,61,36,55,90033,3,0.90,3,0,0,0,0,1,1 +1815,48,22,79,95747,3,0.70,2,0,0,0,0,1,0 +1816,65,39,18,94923,2,0.40,1,0,0,1,1,1,1 +1817,45,19,91,92373,2,1.70,2,0,0,1,0,1,0 +1818,36,11,9,94604,4,0.20,3,0,0,0,0,0,1 +1819,45,20,62,95818,2,2.20,3,0,0,0,0,1,0 +1820,60,34,59,94110,1,1.60,1,231,0,0,0,1,0 +1821,47,22,25,90404,1,0.10,1,148,0,0,0,1,0 +1822,32,7,54,96008,4,1.30,1,0,0,1,0,1,0 +1823,48,23,112,93014,1,5.10,2,86,1,1,1,1,0 +1824,33,8,125,91320,1,0.00,1,0,0,0,0,1,1 +1825,49,23,194,94022,4,8.30,2,0,1,0,0,0,1 +1826,56,32,161,94720,1,5.80,3,0,1,1,0,0,0 +1827,59,33,35,91105,1,0.20,1,171,0,0,0,0,0 +1828,56,30,113,92704,2,2.70,1,352,0,0,0,0,1 +1829,30,4,25,92123,2,0.30,2,0,0,0,0,0,0 +1830,59,29,45,95630,3,2.00,3,0,0,0,0,1,0 +1831,38,13,119,94571,2,7.80,1,221,0,0,0,0,0 +1832,47,22,30,94118,4,0.40,2,115,0,0,0,1,1 +1833,54,29,79,91330,4,3.80,2,0,0,1,0,1,0 +1834,34,9,178,94303,1,0.80,3,0,1,0,0,0,0 +1835,41,16,23,94143,2,0.30,2,118,0,0,0,0,0 +1836,47,23,171,94546,2,1.40,1,284,0,0,0,1,1 +1837,44,19,74,90041,4,1.90,3,0,0,0,0,0,0 +1838,43,18,103,90089,3,1.00,1,180,0,0,0,1,1 +1839,31,7,99,94720,1,4.00,1,0,0,0,0,1,0 +1840,28,2,43,95616,4,1.30,3,0,0,0,0,1,1 +1841,55,25,23,93106,4,0.40,3,88,0,0,0,0,0 +1842,42,17,91,94583,1,0.10,2,199,0,0,0,1,1 +1843,53,29,93,95051,1,2.70,2,256,0,0,0,1,0 +1844,30,6,154,90230,1,6.00,1,0,0,0,0,0,0 +1845,65,40,21,92717,3,0.10,3,0,0,0,0,0,1 +1846,43,18,65,93065,2,2.20,3,0,0,0,0,1,0 +1847,56,32,15,90089,1,0.10,2,0,0,0,0,1,0 +1848,25,0,52,95126,3,2.60,3,159,0,0,0,0,0 +1849,35,10,30,95032,3,1.30,1,0,0,1,1,1,1 +1850,50,26,42,90630,1,1.60,2,0,0,0,0,1,0 +1851,36,10,20,90033,4,0.30,1,97,0,0,0,1,0 +1852,34,8,60,94015,4,2.20,2,0,0,0,0,0,1 +1853,32,6,54,94596,4,1.80,3,167,0,0,0,0,0 +1854,51,25,60,90401,4,2.60,1,97,0,0,0,1,0 +1855,52,25,41,95403,3,1.00,2,0,0,0,0,1,0 +1856,65,39,30,94304,3,0.70,2,0,0,0,0,1,1 +1857,51,24,21,95014,2,1.00,2,0,0,0,0,1,0 +1858,37,13,105,94066,1,0.80,2,0,0,0,0,0,1 +1859,35,11,65,90747,3,2.80,1,240,0,0,0,1,0 +1860,67,41,20,91741,2,0.40,1,80,0,0,0,0,0 +1861,30,6,179,91103,3,4.90,1,142,1,0,0,1,0 +1862,62,38,161,90274,1,2.90,1,0,0,1,1,1,1 +1863,42,17,82,95616,1,3.70,3,0,0,0,0,1,0 +1864,48,22,43,94588,1,1.20,2,112,0,0,0,1,0 +1865,61,36,61,92103,2,2.80,1,0,0,0,0,0,0 +1866,36,6,90,91342,4,1.80,3,0,0,1,0,0,0 +1867,48,24,90,94523,1,2.60,2,334,0,0,0,1,0 +1868,65,39,21,94553,2,0.40,1,0,0,0,0,0,0 +1869,25,1,118,92833,1,5.40,1,0,0,0,0,1,1 +1870,55,30,44,94025,2,2.00,2,0,0,0,0,1,0 +1871,63,37,110,95032,1,4.10,3,0,1,0,0,0,0 +1872,31,5,99,94065,4,1.80,2,268,0,0,0,0,0 +1873,43,17,98,94402,3,1.10,1,0,0,0,0,0,0 +1874,28,4,69,94538,3,0.70,2,80,0,0,0,1,0 +1875,37,11,82,95819,3,0.90,2,218,0,0,0,1,1 +1876,27,3,112,90066,3,2.50,1,389,0,1,0,1,0 +1877,62,38,123,90210,1,2.90,1,0,0,0,0,0,0 +1878,51,24,78,90037,1,2.67,2,0,0,0,0,1,0 +1879,56,30,59,95833,3,0.80,1,159,0,1,0,1,0 +1880,56,30,78,90401,3,1.70,2,0,0,0,0,0,0 +1881,44,19,49,94720,4,1.90,3,89,0,0,0,1,0 +1882,46,19,82,91365,3,2.67,2,0,0,0,0,0,0 +1883,56,32,125,91330,3,0.60,1,342,1,0,1,1,1 +1884,56,30,185,91711,1,2.90,1,0,0,0,0,0,0 +1885,57,33,163,94132,1,7.40,1,0,0,0,0,1,0 +1886,31,6,19,96001,4,1.10,3,104,0,0,1,1,1 +1887,65,41,115,94105,4,1.70,2,0,0,0,0,0,0 +1888,31,7,81,95006,2,2.00,2,0,0,0,1,1,1 +1889,36,10,93,94305,1,2.80,3,0,0,0,0,1,0 +1890,56,30,111,93106,4,0.30,1,372,1,1,1,1,0 +1891,52,27,184,90630,1,8.10,1,0,0,0,0,0,0 +1892,42,18,50,95126,4,2.20,2,0,0,0,0,0,0 +1893,55,30,55,94110,3,1.70,1,0,0,0,0,0,1 +1894,49,24,13,94608,1,0.40,3,101,0,1,0,0,0 +1895,51,25,29,94303,4,0.10,1,0,0,0,0,1,1 +1896,26,2,72,95003,4,2.60,1,0,0,0,0,1,0 +1897,32,7,83,94304,1,2.60,2,0,0,1,0,0,1 +1898,54,29,98,93065,1,0.10,3,0,0,0,0,0,0 +1899,50,24,43,95630,4,0.10,1,0,0,0,0,1,0 +1900,59,33,34,94115,1,0.20,1,0,0,0,0,1,0 +1901,61,36,10,91365,4,0.40,2,0,0,0,0,1,0 +1902,43,19,201,94305,2,6.67,1,0,0,1,0,1,0 +1903,39,14,85,94005,3,1.20,3,107,0,0,0,1,1 +1904,56,26,50,90095,3,1.40,3,0,0,0,0,0,0 +1905,38,14,91,95060,2,0.00,1,0,0,0,0,1,0 +1906,25,-1,112,92507,2,2.00,1,241,0,0,0,1,0 +1907,42,17,98,92866,2,0.40,1,275,0,0,0,1,0 +1908,42,18,115,93711,1,0.30,1,0,0,0,0,0,0 +1909,50,26,22,92037,4,0.50,2,112,0,0,0,1,0 +1910,56,30,101,90048,3,1.70,2,0,0,0,0,0,1 +1911,43,18,83,95616,2,3.80,3,112,0,0,0,0,0 +1912,60,35,52,94709,3,0.50,2,0,0,0,0,0,0 +1913,42,16,191,94304,3,4.80,2,0,1,1,1,1,0 +1914,57,33,134,92110,4,0.90,1,198,1,0,0,1,0 +1915,48,24,54,95616,1,1.60,2,186,0,0,0,1,0 +1916,37,11,69,91911,3,2.10,1,0,0,1,0,0,0 +1917,57,32,64,95138,3,1.60,3,0,0,0,0,1,0 +1918,62,32,53,96001,4,1.67,3,142,0,0,0,0,0 +1919,39,9,118,93555,2,6.00,3,246,1,0,1,1,1 +1920,38,13,19,92069,2,1.40,2,120,0,0,0,0,1 +1921,54,28,31,92130,2,0.40,3,0,0,0,0,0,0 +1922,45,21,63,95621,1,0.80,3,245,0,0,0,1,1 +1923,39,15,25,93023,1,1.40,3,0,0,0,0,0,0 +1924,45,19,22,90639,1,0.20,1,0,0,0,0,1,0 +1925,62,38,78,92009,1,1.80,3,0,0,0,0,0,0 +1926,43,19,81,90245,1,0.30,1,218,0,0,0,1,0 +1927,30,6,41,90095,1,2.40,2,0,0,0,0,1,0 +1928,35,10,62,93106,3,2.30,1,0,0,0,0,0,0 +1929,58,34,35,94122,1,1.20,3,0,0,0,0,1,0 +1930,44,19,30,94501,1,0.60,3,0,0,0,0,1,0 +1931,56,29,51,94080,3,1.00,2,0,0,0,0,1,0 +1932,28,2,140,92122,2,2.00,1,0,0,0,0,1,0 +1933,64,39,73,90073,3,2.40,1,185,0,0,0,0,0 +1934,63,39,40,91311,4,1.20,2,0,0,0,0,1,0 +1935,44,20,69,95814,1,0.80,3,0,0,0,0,1,1 +1936,34,9,191,94086,1,4.80,3,0,1,0,1,1,1 +1937,50,24,82,90291,3,3.00,2,0,0,0,0,1,0 +1938,51,25,181,95051,1,3.30,3,589,1,1,1,1,0 +1939,30,4,38,90245,1,1.90,3,0,0,0,0,1,0 +1940,55,31,23,94122,2,0.20,1,0,0,0,0,1,0 +1941,57,33,55,92630,1,1.80,3,0,0,0,0,1,0 +1942,43,19,58,95307,2,3.20,1,0,0,0,0,1,0 +1943,61,36,29,90210,2,0.50,2,0,0,0,0,1,0 +1944,49,23,39,95521,4,2.60,1,0,0,0,0,0,0 +1945,52,28,39,90095,3,1.90,2,83,0,0,1,1,1 +1946,57,33,30,93106,3,1.50,1,151,0,1,0,1,0 +1947,53,23,58,94720,4,2.00,3,0,0,0,0,1,1 +1948,52,28,62,94111,1,1.80,3,231,0,0,0,1,0 +1949,39,15,62,93955,4,2.40,1,86,0,0,0,0,0 +1950,58,34,19,90504,1,1.20,3,0,0,0,0,0,0 +1951,36,12,38,94109,1,1.50,2,0,0,0,0,0,0 +1952,45,21,84,94550,4,2.00,3,0,0,0,0,1,1 +1953,30,5,78,92037,1,2.60,2,0,0,0,0,1,0 +1954,49,25,22,90058,4,0.20,1,83,0,0,0,1,0 +1955,44,20,81,90245,4,2.00,3,277,0,0,0,1,0 +1956,43,17,32,90401,3,0.50,2,0,0,0,0,1,0 +1957,42,18,89,94539,4,0.80,1,184,0,0,0,0,0 +1958,29,4,121,90028,2,3.30,1,0,0,0,0,1,0 +1959,28,2,42,95762,1,1.50,1,0,0,0,0,1,1 +1960,50,24,130,95833,1,1.00,1,0,0,0,0,0,0 +1961,44,19,30,95616,4,0.00,2,0,0,0,0,1,0 +1962,52,26,114,94304,1,4.90,1,0,0,0,0,0,0 +1963,28,4,155,90019,1,6.33,1,0,0,0,0,0,0 +1964,62,38,50,94539,2,1.10,1,0,0,0,0,0,1 +1965,34,10,34,95060,1,1.50,2,111,0,0,0,0,1 +1966,45,20,94,90095,3,0.50,3,0,0,0,0,1,0 +1967,52,26,114,91330,2,2.40,2,0,0,0,0,0,0 +1968,43,18,89,94303,3,0.50,3,108,0,0,0,0,1 +1969,54,24,49,91801,1,1.40,3,0,0,0,0,1,0 +1970,64,38,115,94105,1,2.00,1,0,0,0,0,1,1 +1971,27,3,148,92780,1,1.50,1,397,0,0,0,1,1 +1972,42,17,72,95616,4,1.10,2,203,0,0,0,0,1 +1973,28,2,114,94606,4,2.10,3,0,0,0,0,1,0 +1974,47,22,11,92192,2,0.00,1,78,0,0,0,0,0 +1975,39,13,63,90095,4,0.20,3,242,0,0,0,0,0 +1976,29,3,113,94132,2,0.20,1,0,0,0,0,1,1 +1977,39,13,80,95616,2,1.80,1,0,0,0,0,1,0 +1978,41,15,54,94303,3,0.50,3,0,0,0,0,1,1 +1979,37,11,32,94612,2,1.40,3,0,0,1,0,1,0 +1980,41,17,11,91330,1,1.00,1,0,0,0,0,0,0 +1981,45,19,141,94706,1,2.40,1,0,0,0,0,1,0 +1982,52,26,84,91768,3,3.00,2,0,0,0,0,1,0 +1983,58,33,18,94701,3,0.10,2,110,0,0,0,1,0 +1984,31,5,20,94720,2,0.30,1,0,0,0,0,0,0 +1985,26,1,55,92630,4,1.70,2,175,0,0,0,1,0 +1986,31,7,31,94920,4,0.40,2,79,0,0,0,0,0 +1987,42,17,114,90065,2,0.40,1,0,0,0,0,0,0 +1988,56,31,52,94118,3,2.00,2,0,0,1,1,1,1 +1989,52,28,18,91301,1,0.30,1,120,0,0,0,1,0 +1990,59,35,55,90274,1,1.80,3,0,0,1,0,0,0 +1991,32,8,29,92807,1,0.20,3,76,0,0,0,1,1 +1992,46,22,30,90747,3,0.50,1,0,0,0,0,0,0 +1993,52,28,38,94302,2,0.80,1,0,0,0,0,0,1 +1994,30,5,122,94545,2,3.10,1,0,0,0,0,0,0 +1995,32,8,183,94080,1,6.00,1,0,0,0,0,0,0 +1996,35,11,41,94720,1,2.40,2,0,0,0,0,0,0 +1997,49,24,38,94305,1,1.40,3,0,0,0,0,0,0 +1998,54,30,61,92093,1,1.80,3,0,0,0,0,1,0 +1999,56,32,103,94111,3,4.00,3,0,1,0,0,0,0 +2000,48,22,80,93940,2,2.40,2,0,0,0,0,1,0 +2001,28,2,22,95670,1,0.10,2,0,0,0,0,1,0 +2002,44,17,128,94928,2,3.25,2,0,1,0,0,0,1 +2003,30,4,142,92126,3,4.20,1,359,1,0,0,0,0 +2004,44,20,124,90277,1,4.70,1,0,0,0,0,1,1 +2005,30,4,44,92704,1,1.90,3,143,0,0,0,0,0 +2006,47,23,170,90254,2,6.50,2,0,1,0,1,1,1 +2007,64,39,75,94720,4,0.10,2,0,0,0,1,1,1 +2008,48,21,78,94010,3,2.00,2,0,0,0,0,1,1 +2009,63,38,31,92037,1,1.10,3,125,0,0,0,1,0 +2010,25,0,99,92735,1,1.90,1,323,0,0,0,0,0 +2011,61,36,41,96001,2,1.50,1,0,0,0,0,0,0 +2012,46,21,39,92507,4,0.00,2,0,0,0,0,1,0 +2013,57,31,51,93943,1,1.40,1,0,0,0,0,1,1 +2014,40,15,52,92691,3,0.80,3,113,0,0,0,1,0 +2015,49,19,169,95054,3,5.67,3,167,1,0,1,0,1 +2016,30,5,141,95747,1,0.80,1,0,0,0,0,1,0 +2017,41,17,93,92835,4,0.80,1,218,0,0,0,0,0 +2018,42,15,14,92064,3,1.00,2,0,0,1,0,0,0 +2019,63,39,160,90089,2,2.10,1,0,0,0,0,1,1 +2020,43,17,44,94611,1,0.20,1,0,0,1,1,1,0 +2021,59,34,33,94303,3,0.20,1,0,0,1,0,0,0 +2022,46,20,103,91380,4,4.80,3,0,1,0,0,1,0 +2023,33,3,71,93561,4,1.80,3,236,0,0,0,0,0 +2024,55,29,55,94720,1,0.20,1,151,0,0,0,1,0 +2025,36,12,113,94305,4,0.20,1,0,1,0,0,0,0 +2026,47,20,79,94720,3,2.00,2,185,0,1,0,0,0 +2027,59,33,80,93907,2,0.70,2,0,0,0,0,1,0 +2028,38,12,179,94596,2,0.00,1,380,0,0,0,0,0 +2029,42,17,9,91710,2,0.00,3,0,0,0,0,0,0 +2030,30,3,61,92152,4,2.00,2,0,0,0,0,1,0 +2031,63,38,111,95814,2,3.90,1,207,0,1,1,1,1 +2032,60,35,80,94608,3,0.50,1,0,0,0,0,1,0 +2033,62,37,32,90266,3,0.20,1,0,0,1,0,0,1 +2034,49,23,83,92126,1,0.30,1,0,0,0,0,1,1 +2035,59,33,91,92821,4,1.90,2,329,0,0,0,0,0 +2036,36,10,29,93065,4,1.00,1,0,0,0,0,1,1 +2037,46,19,19,94305,3,0.67,2,0,0,0,0,1,0 +2038,35,8,52,95616,2,1.00,2,0,0,0,0,0,1 +2039,50,24,150,94551,1,7.30,1,0,0,0,0,1,1 +2040,51,25,32,91605,2,0.40,3,0,0,0,0,1,0 +2041,41,16,91,94720,3,0.50,3,0,0,0,0,0,0 +2042,45,20,180,95403,3,8.50,2,535,1,0,0,0,0 +2043,41,17,121,94102,1,0.30,1,0,0,0,0,1,0 +2044,57,32,25,90049,2,0.20,3,0,0,0,0,1,1 +2045,51,25,102,92677,1,0.30,1,0,0,0,0,1,0 +2046,52,28,44,95051,4,0.90,2,107,0,0,0,1,0 +2047,43,16,161,95134,3,8.00,2,0,1,0,1,1,1 +2048,63,38,134,90640,3,4.00,2,0,1,0,0,0,1 +2049,28,4,43,94803,1,1.80,2,0,0,0,0,1,1 +2050,43,18,94,92717,4,1.10,2,0,0,0,0,1,0 +2051,41,15,29,94024,2,0.80,3,98,0,0,0,0,0 +2052,34,8,38,90018,4,0.20,1,0,0,0,0,0,0 +2053,28,3,120,94080,1,0.80,1,170,0,0,0,0,0 +2054,58,32,85,92110,2,2.00,1,161,0,1,1,1,1 +2055,39,15,89,92126,2,1.90,1,0,0,0,0,0,0 +2056,49,23,25,90274,1,1.40,3,0,0,0,0,1,0 +2057,33,8,20,92691,3,1.30,1,83,0,0,0,0,1 +2058,37,12,125,91754,2,3.90,1,0,0,0,0,1,1 +2059,33,7,18,92093,1,0.60,3,0,0,0,0,0,0 +2060,28,3,173,92121,2,6.70,1,222,0,0,0,1,0 +2061,54,29,34,92093,4,0.10,3,0,0,0,0,1,1 +2062,63,38,159,93950,4,4.90,2,111,1,0,0,0,0 +2063,57,31,55,92521,3,2.50,1,219,0,0,1,1,1 +2064,56,30,32,94080,2,0.40,3,0,0,0,0,1,0 +2065,54,29,65,94545,4,1.80,3,0,0,0,0,0,1 +2066,29,5,83,92354,3,1.50,1,0,0,0,0,1,1 +2067,41,16,30,95814,2,1.40,2,0,0,0,0,0,1 +2068,58,32,180,91770,1,2.90,1,0,0,0,0,0,1 +2069,61,37,13,90024,2,0.30,3,0,0,0,0,1,0 +2070,30,4,35,90059,4,0.80,1,0,0,0,0,1,1 +2071,62,37,95,91107,3,0.50,1,0,0,0,0,0,0 +2072,52,28,83,94705,1,0.00,1,0,0,0,0,1,0 +2073,29,3,39,95831,4,0.20,1,137,0,0,0,1,1 +2074,46,20,54,91107,1,0.70,3,154,0,0,0,1,1 +2075,52,27,81,91942,1,1.30,3,293,0,0,0,0,1 +2076,40,16,53,94123,4,2.00,3,0,0,0,0,0,0 +2077,49,23,119,91030,1,7.30,1,398,0,0,0,0,0 +2078,34,9,160,94108,4,8.00,3,0,1,0,0,0,1 +2079,35,11,21,95814,2,1.00,2,0,0,0,0,0,0 +2080,26,2,40,94132,1,1.00,3,0,0,0,0,1,0 +2081,65,40,69,91706,4,0.10,2,0,0,0,0,1,0 +2082,52,27,45,95006,1,1.30,2,0,0,0,0,0,0 +2083,32,7,55,91301,4,2.00,2,0,0,0,0,1,0 +2084,31,7,38,94025,1,0.20,3,0,0,0,0,1,0 +2085,36,9,44,93907,4,1.00,2,101,0,1,0,1,0 +2086,50,24,45,94105,3,0.60,2,117,0,0,0,1,0 +2087,36,12,84,90291,1,0.80,2,0,0,0,0,1,1 +2088,51,27,188,94305,2,6.90,2,343,1,0,0,1,0 +2089,39,9,29,94701,3,2.00,3,151,0,1,0,0,0 +2090,53,29,95,94304,1,2.70,2,0,0,0,0,1,0 +2091,50,25,79,95023,1,2.90,1,307,0,0,0,0,1 +2092,31,4,41,91360,1,2.00,2,0,0,1,0,1,0 +2093,53,23,19,92673,4,0.40,3,84,0,0,0,1,0 +2094,48,23,75,94111,4,3.60,3,0,0,0,0,1,1 +2095,57,31,64,90024,3,2.50,1,208,0,0,0,0,1 +2096,47,21,174,94025,4,3.20,3,0,1,0,0,0,0 +2097,55,29,54,95051,2,2.30,3,93,0,0,0,0,0 +2098,37,11,14,90740,3,0.10,2,113,0,0,0,1,0 +2099,59,35,94,90089,1,3.80,1,272,0,0,0,0,0 +2100,53,29,10,90095,2,0.40,1,0,0,0,0,0,0 +2101,31,6,145,93940,1,0.80,1,84,0,0,0,1,0 +2102,35,5,203,95032,1,10.00,3,0,1,0,0,0,0 +2103,25,-1,81,92647,2,1.60,3,0,0,0,0,1,1 +2104,37,13,153,90630,2,6.50,1,0,0,0,0,1,1 +2105,40,14,58,90245,4,0.20,3,0,0,0,0,1,0 +2106,31,5,49,94114,4,1.80,3,0,0,0,0,1,1 +2107,62,38,132,90210,1,2.90,1,0,0,0,0,0,0 +2108,41,17,85,90291,4,0.20,3,229,0,0,0,0,0 +2109,56,32,85,94132,3,2.67,1,0,0,1,0,1,0 +2110,47,23,178,93014,1,6.50,3,0,1,0,0,0,0 +2111,28,4,104,94301,3,2.50,1,0,0,0,0,0,0 +2112,60,34,40,94105,1,1.60,1,0,0,0,0,1,0 +2113,27,2,103,93117,1,1.90,1,120,0,0,0,1,0 +2114,57,33,25,92064,2,1.00,1,0,0,0,0,1,0 +2115,62,36,69,95039,2,1.70,3,0,0,0,0,1,0 +2116,57,31,30,95070,3,1.40,1,0,0,0,0,0,0 +2117,44,17,70,94920,3,2.67,2,0,0,0,0,0,0 +2118,31,7,15,91380,3,0.90,3,0,0,0,0,1,0 +2119,31,5,125,91320,2,1.30,1,0,0,0,0,1,1 +2120,39,13,50,94923,3,0.50,3,0,0,0,0,0,0 +2121,41,17,44,93106,1,0.30,3,0,0,0,0,1,0 +2122,41,17,38,92182,4,2.20,2,180,0,0,0,0,1 +2123,55,29,64,93437,3,0.80,1,119,0,0,0,0,1 +2124,28,2,9,95014,1,0.10,2,0,0,0,0,1,0 +2125,35,9,44,92054,3,0.90,1,89,0,0,0,0,0 +2126,44,20,93,91910,4,0.80,1,101,0,0,0,1,0 +2127,44,19,83,92121,4,0.40,1,141,0,0,0,0,0 +2128,40,14,179,94720,2,0.00,1,0,0,0,0,0,0 +2129,65,40,40,94104,1,1.10,3,0,0,0,0,0,0 +2130,35,10,58,91754,4,0.70,3,232,0,0,0,0,0 +2131,55,31,74,94607,3,2.67,1,0,0,0,0,0,1 +2132,55,31,15,95747,1,0.20,1,0,0,0,0,0,0 +2133,59,35,11,94949,2,1.00,1,0,0,0,0,0,1 +2134,39,15,41,95035,1,2.00,2,176,0,0,0,1,0 +2135,50,24,68,95821,1,1.50,2,120,0,0,0,1,1 +2136,45,15,28,95039,1,0.75,3,0,0,1,0,0,0 +2137,50,26,115,95008,1,1.20,3,0,1,0,0,0,1 +2138,65,40,83,92354,4,0.10,2,247,0,0,0,1,0 +2139,36,11,40,93611,2,1.10,2,166,0,1,0,0,0 +2140,57,32,113,91768,1,0.10,3,0,0,0,0,1,0 +2141,53,27,89,92130,1,0.80,3,0,0,1,0,1,0 +2142,28,4,38,92109,4,1.60,1,0,0,0,0,0,0 +2143,55,31,62,93943,4,1.50,1,0,0,0,0,1,0 +2144,56,31,65,92093,3,1.70,1,109,0,0,0,0,0 +2145,33,6,168,94720,3,5.67,2,0,1,1,1,1,0 +2146,57,32,40,94720,3,1.70,1,0,0,0,0,1,1 +2147,27,3,30,93108,1,1.00,3,80,0,0,0,0,0 +2148,27,3,20,92007,4,1.00,1,0,0,0,0,0,0 +2149,54,30,58,92007,2,3.20,3,0,0,0,0,0,0 +2150,48,22,150,95039,1,7.30,1,193,0,0,0,0,0 +2151,62,38,54,91320,1,0.80,1,0,0,1,0,0,1 +2152,41,16,19,91730,2,0.30,2,105,0,0,0,0,0 +2153,62,38,30,94304,3,0.10,3,128,0,0,0,1,0 +2154,40,14,123,90041,1,5.20,1,0,0,0,0,1,0 +2155,32,8,45,94558,1,2.40,2,0,0,0,0,0,0 +2156,62,38,154,94305,1,2.90,1,0,0,0,0,1,0 +2157,35,11,93,90747,2,2.70,1,0,0,0,0,1,1 +2158,25,0,71,93727,4,0.20,1,78,0,1,0,0,0 +2159,50,25,83,94720,4,3.10,1,0,1,0,0,0,1 +2160,61,35,99,94085,1,4.80,3,255,1,0,0,0,1 +2161,43,17,55,93933,3,2.20,2,0,0,0,0,0,0 +2162,52,28,38,94131,4,0.90,2,95,0,0,0,1,1 +2163,39,13,74,95008,3,0.90,2,155,0,0,0,1,0 +2164,33,3,69,92161,4,1.80,3,0,0,0,0,1,0 +2165,27,3,104,92007,2,2.50,1,184,0,1,0,1,0 +2166,27,0,38,95929,4,1.00,3,154,0,0,0,1,0 +2167,32,8,25,93524,3,0.90,3,0,0,0,0,1,1 +2168,65,40,162,94596,1,1.30,1,0,0,0,0,1,0 +2169,55,29,64,93063,4,2.60,3,0,0,0,0,1,0 +2170,52,27,30,94305,2,0.70,2,0,0,0,0,1,1 +2171,39,13,52,95039,3,0.50,3,0,0,1,0,0,1 +2172,35,11,42,93108,1,1.50,3,0,0,0,0,1,0 +2173,39,15,79,92028,2,1.80,2,219,0,0,0,0,0 +2174,34,10,34,93407,1,1.70,1,164,0,0,0,0,0 +2175,30,5,123,95605,2,3.10,1,0,0,0,0,1,0 +2176,37,12,160,94305,2,3.30,1,0,0,0,0,0,0 +2177,41,14,51,91320,3,2.33,2,0,0,0,0,1,0 +2178,31,7,108,94507,1,4.00,1,0,0,0,0,1,0 +2179,37,13,158,93943,2,2.30,2,0,1,0,1,1,1 +2180,49,23,68,90024,1,1.50,2,0,0,0,0,0,0 +2181,58,33,42,91380,2,1.60,3,0,0,0,0,1,0 +2182,45,15,32,94143,1,0.75,3,105,0,0,0,1,0 +2183,40,14,22,94566,2,1.40,3,0,0,0,0,0,0 +2184,34,8,29,90025,2,2.00,3,0,0,0,0,1,1 +2185,62,36,183,90095,2,3.40,3,0,1,0,0,0,0 +2186,54,30,69,92009,1,1.60,3,0,0,0,0,1,1 +2187,26,2,92,96001,2,0.20,1,0,0,0,0,1,0 +2188,54,30,40,90024,2,1.00,3,0,0,0,0,0,0 +2189,29,4,9,92037,4,0.50,3,86,0,0,0,1,1 +2190,48,23,128,94309,1,0.60,1,0,0,0,0,1,1 +2191,27,3,110,96150,2,0.20,1,294,0,1,0,0,1 +2192,42,18,171,90027,2,8.00,1,0,0,0,0,1,0 +2193,25,1,13,95814,4,1.00,1,95,0,0,0,0,1 +2194,45,19,25,94609,2,0.10,3,102,0,0,0,1,0 +2195,34,9,123,94553,1,1.60,2,0,1,0,0,1,0 +2196,51,27,33,92037,4,0.20,1,83,0,0,0,1,0 +2197,51,24,189,95211,4,4.75,2,0,1,0,0,1,0 +2198,60,35,34,94102,1,0.30,3,0,0,0,0,1,0 +2199,59,35,58,91355,1,0.00,2,0,0,0,0,1,0 +2200,49,24,51,91016,1,1.30,2,98,0,0,0,0,1 +2201,50,25,29,90095,2,1.30,1,0,0,0,0,0,0 +2202,41,16,111,92009,2,0.40,1,0,0,0,0,0,0 +2203,49,24,43,94709,4,1.90,3,0,0,0,0,1,0 +2204,50,25,130,91320,1,0.60,1,311,0,0,0,0,0 +2205,63,37,20,94704,2,0.40,1,76,0,0,0,0,0 +2206,63,37,101,95819,2,2.80,1,0,0,0,0,0,0 +2207,33,7,48,92831,4,2.20,2,207,0,0,0,0,0 +2208,38,12,180,90245,1,2.80,3,158,1,0,0,1,0 +2209,64,40,92,91109,2,0.00,3,185,0,1,0,1,0 +2210,36,10,33,94080,3,0.90,1,0,0,0,0,0,0 +2211,58,33,51,95006,2,1.90,2,0,0,0,0,0,0 +2212,39,14,31,92717,2,1.40,2,94,0,0,0,1,1 +2213,46,22,83,95060,1,2.70,1,0,0,0,0,1,0 +2214,61,37,45,94610,1,0.80,1,0,0,0,0,0,0 +2215,53,27,89,92735,1,0.80,3,146,0,0,0,1,1 +2216,28,3,193,94501,3,4.00,2,0,1,0,0,1,0 +2217,64,40,89,94707,1,3.80,1,0,0,0,0,0,0 +2218,48,24,162,91355,4,3.30,2,446,1,0,1,1,0 +2219,38,13,9,92634,2,0.30,2,0,0,0,0,0,0 +2220,52,22,58,93101,4,2.00,3,223,0,0,0,1,0 +2221,65,40,80,94105,1,0.80,3,0,0,0,0,1,0 +2222,59,33,73,92056,2,1.70,3,0,0,0,0,1,1 +2223,45,20,41,95008,1,0.30,1,0,0,0,0,1,0 +2224,53,28,74,91711,3,2.00,2,0,0,1,0,0,0 +2225,38,12,29,92084,2,1.40,3,0,0,0,0,1,0 +2226,54,24,25,90505,4,0.40,3,115,0,0,0,0,0 +2227,25,1,98,90717,1,5.40,1,0,0,0,0,1,0 +2228,61,35,59,90840,4,1.70,2,0,0,0,0,1,1 +2229,48,23,43,90254,4,1.90,3,0,0,0,0,1,0 +2230,46,22,72,91711,4,1.40,2,149,0,0,0,1,1 +2231,36,11,183,94704,1,3.00,3,0,1,0,1,1,1 +2232,46,20,134,94575,1,5.70,1,146,0,1,0,1,0 +2233,59,33,140,95035,2,0.50,1,262,0,0,0,1,0 +2234,59,35,39,92028,1,1.80,3,0,0,0,0,1,0 +2235,36,12,35,95812,4,0.40,2,0,0,0,0,1,0 +2236,63,37,141,92121,2,6.90,1,0,0,0,0,1,1 +2237,51,24,23,95616,1,0.50,2,0,0,0,0,1,0 +2238,30,5,134,92647,1,0.00,1,0,0,0,0,1,1 +2239,48,22,35,92709,1,1.40,3,0,0,0,0,1,0 +2240,55,29,42,95833,4,2.50,1,0,0,1,0,0,0 +2241,41,17,81,92868,4,0.20,3,167,0,1,0,0,0 +2242,26,0,14,94301,4,0.40,1,94,0,0,0,1,0 +2243,41,17,45,93437,1,1.80,1,172,0,1,0,1,0 +2244,54,28,79,91342,3,1.70,2,150,0,0,0,1,1 +2245,57,31,53,92806,1,0.80,2,120,0,0,0,0,0 +2246,54,28,33,94111,2,0.70,2,0,0,0,0,0,1 +2247,35,11,190,92093,3,3.10,2,266,1,0,0,0,0 +2248,60,34,60,95616,1,2.50,3,103,0,0,0,0,0 +2249,63,37,8,94618,1,0.80,2,97,0,0,0,1,0 +2250,41,14,38,95814,3,1.00,2,150,0,0,0,1,0 +2251,46,22,154,93109,1,5.00,1,0,0,0,0,1,0 +2252,31,5,54,92173,4,2.20,2,0,0,0,0,0,0 +2253,58,32,41,95819,3,1.40,1,0,0,0,0,1,0 +2254,59,35,25,95827,2,0.30,1,75,0,0,0,1,0 +2255,46,22,53,90025,2,1.70,1,109,0,0,0,0,0 +2256,33,9,79,94612,1,0.10,1,0,0,0,0,1,0 +2257,56,31,13,94305,4,0.90,2,76,0,0,1,1,1 +2258,47,23,130,91763,2,1.40,1,0,0,0,0,0,0 +2259,59,33,93,91320,2,0.70,2,0,0,0,0,0,0 +2260,24,0,82,90401,3,0.80,1,0,0,0,0,1,0 +2261,39,14,15,93561,2,0.30,2,92,0,0,0,0,0 +2262,30,3,150,94305,4,5.00,2,0,1,0,0,1,0 +2263,55,29,131,95070,2,0.70,2,0,1,0,0,0,1 +2264,47,21,28,92868,3,1.50,1,0,0,0,0,1,0 +2265,35,11,9,93106,4,0.70,2,0,0,0,0,1,0 +2266,47,23,88,94305,4,1.40,2,0,0,0,0,0,0 +2267,38,13,143,94550,1,4.10,1,0,0,0,0,0,0 +2268,38,13,168,92647,2,1.30,3,0,1,0,0,0,0 +2269,27,3,105,94304,1,3.00,2,0,1,1,0,0,0 +2270,42,18,62,94305,3,2.10,3,0,0,0,0,1,0 +2271,26,2,51,92103,4,2.60,1,0,0,0,0,1,0 +2272,60,34,101,94928,3,4.40,1,0,0,0,0,1,1 +2273,27,3,90,91365,3,0.80,1,0,0,0,0,1,0 +2274,27,1,83,91775,4,2.10,3,0,0,0,0,1,1 +2275,40,15,21,90034,2,0.00,3,0,0,0,0,1,0 +2276,40,16,115,94305,1,3.40,1,0,0,0,0,1,0 +2277,29,3,172,92093,4,4.40,1,0,1,0,0,0,0 +2278,30,6,32,91330,2,1.00,2,0,0,0,0,0,0 +2279,30,4,204,91107,2,4.50,1,0,0,0,0,1,0 +2280,47,23,34,91711,4,0.60,1,0,0,0,1,1,1 +2281,33,7,30,94920,2,2.00,3,132,0,0,0,0,0 +2282,57,32,31,95039,3,1.30,2,0,0,0,0,1,1 +2283,38,14,90,94110,2,2.70,1,0,0,0,0,1,1 +2284,54,28,79,92677,4,2.60,3,0,0,0,0,0,0 +2285,47,23,22,94901,4,0.60,1,0,0,0,0,1,1 +2286,48,22,114,92007,1,2.40,3,0,1,0,0,1,0 +2287,62,36,42,94122,1,0.50,3,128,0,0,0,1,0 +2288,30,6,29,92121,1,0.20,3,90,0,0,0,1,0 +2289,35,11,72,94706,3,2.60,2,0,0,0,0,1,0 +2290,59,35,68,93117,1,1.80,3,95,0,0,0,0,0 +2291,38,13,78,91942,4,0.70,3,0,0,0,0,1,0 +2292,47,23,90,95449,1,2.70,1,323,0,0,0,0,0 +2293,57,33,170,95051,2,2.10,2,0,1,0,0,0,0 +2294,42,17,14,91768,2,0.10,2,0,0,0,0,1,0 +2295,39,15,129,90035,2,1.90,1,0,0,0,0,0,0 +2296,53,23,39,92101,3,1.00,3,87,0,0,0,1,0 +2297,27,3,82,94305,2,0.20,1,0,0,0,0,0,1 +2298,59,35,31,94063,3,0.40,2,0,0,0,0,1,1 +2299,48,24,9,92630,4,0.50,2,0,0,0,0,0,1 +2300,62,37,15,94583,3,0.10,3,91,0,0,0,0,0 +2301,66,41,70,93711,3,2.20,1,0,0,0,0,0,0 +2302,38,13,84,93403,4,0.70,3,0,0,0,0,0,0 +2303,42,17,155,92806,1,7.00,1,0,0,0,0,0,1 +2304,47,21,89,94720,2,0.80,3,0,0,0,0,1,1 +2305,27,2,170,95818,3,4.70,1,0,1,0,0,1,0 +2306,32,7,185,92009,2,6.70,1,0,0,0,1,1,1 +2307,37,13,82,92373,2,2.20,1,0,0,0,0,0,0 +2308,56,31,60,92009,3,1.70,1,0,0,0,0,1,0 +2309,39,13,58,94590,2,2.40,2,0,0,0,0,1,0 +2310,36,12,29,94583,1,1.33,1,81,0,0,0,1,0 +2311,32,6,32,92806,2,0.30,1,0,0,0,0,0,0 +2312,62,37,115,90245,4,3.40,2,0,0,0,0,1,1 +2313,48,22,83,91345,2,2.40,2,0,0,0,0,1,0 +2314,58,32,54,94035,3,0.30,2,0,0,0,0,1,1 +2315,27,2,112,94501,4,1.80,3,0,0,1,0,1,0 +2316,52,26,182,95818,2,1.40,2,0,1,0,0,1,0 +2317,54,30,112,94920,2,6.80,1,0,0,0,0,1,0 +2318,31,5,129,95814,3,5.90,3,319,1,1,1,0,1 +2319,60,34,23,94803,1,0.80,2,112,0,0,0,1,0 +2320,34,9,198,95819,2,3.00,1,422,0,0,0,1,0 +2321,46,22,84,92692,4,2.00,3,0,0,0,0,1,0 +2322,41,15,39,91380,3,0.50,3,0,0,0,0,0,0 +2323,62,37,129,94143,1,1.30,1,0,0,0,0,1,0 +2324,31,7,113,94542,2,2.00,2,315,0,0,0,0,0 +2325,41,11,35,93107,1,0.75,3,114,0,0,0,1,0 +2326,55,30,85,94591,1,0.10,3,0,0,0,0,0,0 +2327,45,19,73,94086,4,2.90,1,0,0,0,0,0,0 +2328,51,25,70,90095,1,0.80,3,0,0,1,0,1,0 +2329,27,2,130,92182,3,4.40,1,192,1,0,0,1,0 +2330,30,4,39,94022,1,1.50,1,0,0,0,0,1,0 +2331,31,5,72,95133,4,1.80,2,242,0,0,0,1,1 +2332,61,37,68,90245,4,2.30,3,0,0,0,0,0,0 +2333,40,16,35,94022,1,1.40,3,0,0,0,0,1,1 +2334,45,21,61,95812,3,0.70,1,0,0,1,1,1,1 +2335,45,21,69,90025,4,1.90,1,0,0,0,0,0,0 +2336,37,13,59,93907,1,3.60,2,0,0,0,0,0,0 +2337,34,8,99,93460,2,4.50,3,217,0,0,0,0,0 +2338,43,16,201,95054,1,10.00,2,0,1,0,0,0,1 +2339,42,18,130,94611,2,7.50,1,0,0,0,0,0,1 +2340,56,31,72,90095,3,2.00,2,0,0,0,0,0,0 +2341,33,9,44,94112,1,1.20,1,0,0,0,0,0,0 +2342,36,10,91,92028,1,1.50,3,289,0,0,0,1,0 +2343,62,37,92,94608,3,0.50,1,310,0,0,0,1,0 +2344,58,34,55,90032,1,0.80,1,168,0,0,0,1,1 +2345,65,40,20,94608,3,0.50,1,102,0,0,0,1,1 +2346,65,40,89,90291,1,4.10,1,299,1,0,1,1,0 +2347,52,26,59,92660,2,1.50,2,239,0,0,0,0,1 +2348,64,39,8,92104,3,0.10,3,87,0,0,0,0,1 +2349,51,25,85,94015,4,4.90,1,0,0,0,0,1,1 +2350,59,35,94,94610,1,4.30,1,76,0,1,1,1,0 +2351,52,28,22,91711,2,0.40,1,0,0,0,0,1,1 +2352,55,31,74,94611,2,3.20,3,0,0,0,0,1,1 +2353,46,19,59,93555,3,2.67,2,0,0,0,0,0,0 +2354,61,36,12,93023,4,0.60,2,0,0,0,0,1,1 +2355,35,9,8,94043,1,0.40,2,0,0,0,0,1,0 +2356,56,31,74,94920,3,1.60,3,0,0,0,0,1,1 +2357,31,5,184,92064,4,3.40,2,0,1,0,1,1,1 +2358,44,19,34,95005,4,0.00,2,0,0,0,0,0,0 +2359,53,27,63,93109,2,0.80,3,0,0,1,0,1,0 +2360,36,12,123,95060,2,5.60,2,0,1,0,1,1,1 +2361,27,1,85,93302,2,1.60,3,0,0,0,0,0,0 +2362,36,12,109,94928,3,0.50,3,0,1,1,1,1,0 +2363,40,15,31,94720,1,0.60,3,0,0,0,0,1,0 +2364,39,13,61,90095,2,2.40,2,90,0,0,0,1,0 +2365,59,35,88,94923,2,1.60,1,0,0,0,0,0,1 +2366,43,18,22,91311,2,0.30,2,0,0,0,0,0,0 +2367,30,4,63,95008,4,2.20,2,0,0,1,0,1,0 +2368,26,1,80,95616,4,0.20,1,0,0,0,0,1,1 +2369,48,22,78,94588,3,2.10,1,0,0,0,0,1,1 +2370,50,24,45,94005,4,0.10,1,93,0,0,0,1,0 +2371,33,7,51,94040,4,2.10,3,0,0,0,0,0,1 +2372,32,6,111,95014,2,1.50,3,0,0,0,0,0,0 +2373,34,10,45,93943,3,2.80,1,153,0,0,0,1,1 +2374,33,9,184,94304,2,4.80,2,0,1,0,0,0,0 +2375,32,5,41,92008,2,1.00,2,112,0,1,0,1,0 +2376,55,30,69,91007,4,1.30,3,0,0,1,1,1,1 +2377,58,33,23,91768,3,0.20,1,0,0,0,0,0,0 +2378,47,23,160,92037,2,6.67,1,0,0,0,0,0,0 +2379,30,5,61,95605,1,0.80,2,251,0,1,1,1,0 +2380,42,18,110,94720,2,6.10,1,182,0,0,0,1,0 +2381,40,16,50,92606,2,0.60,3,0,0,0,0,0,0 +2382,33,9,49,94928,1,2.40,2,0,0,0,0,1,0 +2383,46,20,185,94131,4,7.50,2,428,1,0,0,0,1 +2384,63,39,52,90033,2,1.10,1,0,0,0,0,1,1 +2385,62,37,53,92028,2,2.80,1,0,0,0,0,1,0 +2386,43,17,125,94720,4,3.50,2,0,1,0,0,0,0 +2387,31,5,72,94542,3,1.60,1,0,0,0,0,1,0 +2388,28,2,51,94720,4,1.80,3,0,0,0,0,0,1 +2389,64,39,23,91768,3,0.50,1,0,0,1,0,0,0 +2390,27,1,41,90033,1,1.90,3,0,0,0,0,0,1 +2391,33,9,41,95814,3,2.00,1,108,0,0,0,1,0 +2392,39,12,138,92697,1,4.67,2,0,1,0,0,1,0 +2393,44,20,138,94143,2,3.30,1,0,0,0,0,0,1 +2394,53,28,14,94005,4,0.80,1,0,0,0,0,1,1 +2395,42,18,145,94065,2,8.00,1,505,0,0,0,0,0 +2396,44,17,25,95064,3,1.00,2,0,0,0,0,0,1 +2397,34,10,43,95014,1,1.70,1,142,0,0,0,0,1 +2398,47,22,93,90266,1,0.20,2,309,0,0,0,1,0 +2399,53,29,90,95053,2,0.30,1,217,0,1,0,0,1 +2400,62,36,41,90245,2,1.00,3,154,0,1,0,1,0 +2401,61,36,169,91380,2,6.10,3,106,1,0,1,1,1 +2402,42,17,63,95814,2,2.20,3,0,0,0,0,1,0 +2403,48,21,23,94720,3,0.67,2,95,0,0,0,0,0 +2404,38,13,140,90210,4,0.50,1,0,1,0,0,0,0 +2405,41,15,75,95010,1,1.50,3,0,0,0,0,1,0 +2406,57,32,13,94588,4,0.90,2,78,0,1,0,1,0 +2407,31,7,10,92354,1,0.50,3,81,0,0,0,1,0 +2408,39,15,100,94720,1,0.80,2,0,0,0,0,1,0 +2409,48,22,85,94105,3,1.10,1,203,0,0,0,1,0 +2410,55,31,73,95207,3,2.67,1,219,0,0,0,1,0 +2411,29,4,130,92630,2,6.70,1,0,0,0,0,0,1 +2412,47,22,65,91330,3,2.70,2,0,0,0,0,1,0 +2413,61,36,59,93118,4,1.70,1,148,0,0,0,0,0 +2414,60,34,31,91007,2,1.00,3,0,0,0,0,0,0 +2415,34,10,134,91775,1,4.00,1,0,0,0,0,0,0 +2416,45,21,11,94143,4,0.20,1,106,0,0,0,1,1 +2417,60,35,32,93611,1,0.30,3,80,0,0,0,1,0 +2418,25,0,53,90095,2,1.60,3,0,0,0,0,1,1 +2419,41,17,28,95616,1,0.70,1,0,0,0,0,0,1 +2420,63,37,44,94550,2,1.00,3,0,0,0,0,1,0 +2421,63,39,40,91304,1,0.80,1,118,0,0,0,0,1 +2422,43,19,40,94949,3,0.60,2,0,0,0,0,1,0 +2423,58,32,163,95014,2,0.50,1,400,0,0,0,0,0 +2424,50,25,82,91335,1,1.30,3,0,0,0,0,1,0 +2425,38,12,89,94583,4,1.40,2,0,0,0,0,0,0 +2426,54,30,78,92507,4,1.60,2,0,0,0,0,1,1 +2427,61,36,55,94132,3,0.90,3,197,0,0,0,0,0 +2428,29,5,34,92675,4,0.40,2,0,0,0,0,1,0 +2429,39,12,108,92717,4,3.67,2,301,1,0,0,0,1 +2430,33,7,58,95616,4,2.20,2,0,0,0,0,1,1 +2431,23,-1,73,92120,4,2.60,1,0,0,0,0,1,0 +2432,56,31,54,91380,4,2.10,1,0,0,0,0,1,0 +2433,54,30,45,92182,4,0.90,2,0,0,0,0,0,1 +2434,37,11,123,94720,1,2.30,2,0,1,1,1,1,0 +2435,38,12,93,95616,1,5.20,1,267,0,0,0,1,0 +2436,34,9,102,92115,4,2.20,2,0,0,0,0,1,0 +2437,53,29,39,92626,3,1.50,1,0,0,0,0,1,0 +2438,65,40,114,94608,4,3.40,2,0,0,0,0,0,1 +2439,62,37,29,91030,1,0.30,3,0,0,0,0,0,1 +2440,51,25,30,91116,3,0.60,2,144,0,0,0,0,1 +2441,31,5,22,91401,1,0.60,3,0,0,0,0,0,0 +2442,64,38,38,94305,2,0.30,1,186,0,0,0,1,1 +2443,39,15,41,90028,2,1.70,1,0,0,0,0,0,0 +2444,28,3,161,92646,4,1.70,3,422,1,0,1,1,1 +2445,60,35,38,94701,3,0.50,2,0,0,0,0,1,1 +2446,47,23,25,93106,1,0.90,3,0,0,0,0,1,0 +2447,25,1,70,93010,4,2.60,1,218,0,0,0,1,0 +2448,44,19,201,95819,2,8.80,1,0,0,0,0,1,1 +2449,51,26,42,92103,2,0.60,3,0,0,0,0,1,1 +2450,31,7,64,94720,1,1.20,1,0,0,0,0,1,0 +2451,32,7,28,90034,4,1.10,3,0,0,0,0,0,0 +2452,51,25,119,93940,1,4.90,1,208,0,0,0,1,1 +2453,25,1,28,94596,1,1.00,3,0,0,0,0,1,0 +2454,43,19,60,94104,3,2.10,3,0,0,0,0,1,0 +2455,54,29,23,93955,1,1.50,2,0,0,0,0,0,0 +2456,34,8,164,94720,4,7.40,3,0,1,0,0,1,0 +2457,54,30,39,95211,2,0.80,1,0,0,0,0,0,1 +2458,42,17,19,92115,2,0.00,3,85,0,0,0,1,1 +2459,46,20,72,93108,2,0.80,3,0,0,0,0,1,1 +2460,62,37,41,95060,3,0.90,3,0,0,0,0,1,1 +2461,31,5,32,92123,2,0.30,2,130,0,0,0,1,0 +2462,30,5,69,94302,1,0.80,2,0,0,0,0,1,0 +2463,52,28,23,95828,3,0.40,1,0,0,0,0,1,0 +2464,35,9,44,92009,4,0.20,1,0,0,0,0,1,0 +2465,60,36,32,92407,3,0.40,2,165,0,0,0,1,0 +2466,58,34,25,90059,2,0.30,1,123,0,0,0,1,0 +2467,24,-2,80,94105,2,1.60,3,0,0,0,0,1,0 +2468,40,16,83,92350,1,0.80,2,230,0,1,0,1,0 +2469,49,23,133,94304,1,7.30,1,0,0,0,0,1,1 +2470,43,18,89,92780,1,0.10,2,307,0,0,0,0,1 +2471,33,7,81,92122,2,4.50,3,187,0,0,1,1,1 +2472,36,11,44,91040,2,1.10,2,85,0,0,0,1,0 +2473,62,36,119,94720,2,2.00,1,0,0,0,0,0,0 +2474,57,32,39,92182,4,0.90,1,147,0,0,0,0,0 +2475,64,38,40,92122,2,1.00,3,0,0,0,0,0,0 +2476,52,26,79,95817,3,0.80,1,183,0,0,0,0,0 +2477,54,28,30,95616,4,0.70,2,0,0,0,0,1,0 +2478,40,14,179,90025,1,2.60,3,0,1,0,0,1,0 +2479,30,5,178,94063,2,6.70,1,0,0,0,0,0,0 +2480,55,30,82,94720,4,3.80,2,0,0,0,0,1,0 +2481,39,13,50,91768,2,2.40,2,0,0,0,0,0,0 +2482,55,30,64,94306,2,1.90,2,0,0,0,0,0,0 +2483,28,4,129,92115,1,1.50,1,0,0,0,0,0,1 +2484,44,18,68,93943,4,2.90,1,0,0,1,0,0,0 +2485,46,21,30,92697,1,1.40,3,112,0,1,0,0,0 +2486,61,36,48,94025,3,1.50,1,0,0,0,0,0,1 +2487,61,36,130,92717,1,1.30,1,257,0,0,0,0,0 +2488,45,20,40,92886,1,0.50,3,0,0,1,0,1,0 +2489,38,14,105,94708,2,1.90,1,0,0,0,0,1,0 +2490,29,3,41,92626,4,0.20,1,0,0,0,0,1,0 +2491,52,28,168,90404,3,6.50,3,118,1,0,0,1,0 +2492,38,14,80,92868,2,2.70,1,0,0,0,0,1,0 +2493,28,3,134,96091,2,3.10,1,0,0,0,0,1,0 +2494,34,9,49,94025,1,2.50,3,0,0,0,0,0,0 +2495,35,9,63,92697,2,1.80,1,0,0,0,0,1,0 +2496,46,22,70,94701,4,1.90,1,212,0,0,0,0,1 +2497,63,37,32,93117,3,0.70,2,141,0,0,0,0,0 +2498,33,9,14,95133,3,0.90,3,114,0,0,0,0,0 +2499,38,14,111,92028,2,6.10,1,326,0,0,0,0,0 +2500,53,27,38,94105,4,2.80,2,144,0,1,0,1,0 +2501,28,2,121,92096,2,2.00,1,341,0,0,0,1,0 +2502,44,18,90,95616,4,2.60,3,0,0,0,0,1,0 +2503,58,31,178,92009,2,6.00,2,0,1,0,0,1,0 +2504,38,14,20,94024,4,0.40,2,79,0,0,0,1,1 +2505,48,24,61,91380,2,1.70,1,229,0,0,0,0,1 +2506,33,7,43,96064,4,0.80,1,0,0,0,0,0,0 +2507,66,42,39,94590,1,1.90,2,0,0,0,0,1,1 +2508,59,34,60,90048,4,2.10,1,234,0,0,0,1,1 +2509,40,15,63,93407,3,3.00,1,0,0,1,0,1,0 +2510,36,11,8,93401,4,0.20,3,81,0,0,0,0,1 +2511,62,38,52,95616,4,1.30,2,0,0,0,0,1,1 +2512,51,27,92,92121,4,3.00,1,0,1,0,1,1,1 +2513,58,32,111,90212,2,1.40,1,298,0,0,0,1,0 +2514,52,26,71,92037,1,1.40,3,0,0,0,0,0,0 +2515,41,16,25,92182,2,0.10,2,91,0,1,0,0,0 +2516,31,5,34,94558,1,1.90,3,156,0,0,0,1,0 +2517,28,3,74,94720,3,2.60,3,0,0,0,0,0,0 +2518,57,31,120,95616,2,2.00,1,0,0,0,0,0,1 +2519,61,37,50,95125,4,1.30,2,0,0,0,0,0,1 +2520,60,36,10,92121,2,1.00,1,0,0,0,0,1,1 +2521,56,29,45,90095,4,2.50,2,113,0,0,0,1,0 +2522,49,23,29,94551,4,1.80,1,0,0,0,0,1,1 +2523,63,37,145,94025,2,6.90,1,0,0,0,0,1,0 +2524,49,23,100,95403,2,6.30,1,0,0,0,0,0,0 +2525,49,25,24,95678,3,0.40,1,0,0,0,0,1,0 +2526,32,8,60,95816,1,1.20,1,0,0,0,0,1,1 +2527,26,1,50,95616,4,0.60,2,0,0,0,0,0,0 +2528,27,1,43,95120,3,1.10,2,0,0,0,0,0,0 +2529,57,31,79,91335,3,4.40,1,0,0,0,0,0,1 +2530,29,5,44,95819,3,0.10,2,0,0,0,0,1,1 +2531,56,30,31,90024,4,1.50,3,0,0,0,0,1,0 +2532,59,35,14,94305,2,1.00,1,107,0,0,0,1,0 +2533,53,28,19,94608,4,0.80,1,106,0,0,0,0,1 +2534,54,29,111,93023,1,1.10,2,0,1,0,0,1,0 +2535,56,30,90,94402,1,1.90,2,0,0,0,0,1,0 +2536,50,25,21,90274,2,0.70,3,129,0,0,0,0,0 +2537,51,25,104,94949,1,4.20,2,0,1,0,0,1,0 +2538,53,27,75,94303,1,1.90,2,0,0,0,0,1,0 +2539,37,12,175,92037,2,7.80,1,297,0,0,0,1,1 +2540,32,7,98,95929,1,4.20,1,171,1,1,1,0,0 +2541,49,23,41,95521,4,0.10,1,153,0,0,0,1,0 +2542,34,8,171,90212,2,2.20,2,569,1,0,0,1,0 +2543,54,30,79,92630,4,1.60,2,0,0,0,0,1,0 +2544,64,39,24,94117,4,0.60,2,0,0,0,0,0,0 +2545,58,34,90,95039,1,3.60,2,0,1,0,0,0,0 +2546,25,-1,39,94720,3,2.40,2,0,0,0,0,1,0 +2547,50,25,9,91911,2,0.00,1,0,0,1,0,0,0 +2548,38,13,15,90245,2,0.10,2,90,0,0,0,1,0 +2549,48,24,80,91343,1,2.70,1,0,0,0,0,1,0 +2550,41,15,63,95060,1,0.70,3,79,0,0,0,0,1 +2551,32,8,20,93106,1,0.50,3,102,0,0,0,1,0 +2552,46,22,43,92120,2,2.10,3,0,0,1,1,1,1 +2553,39,15,65,95822,1,1.50,3,0,0,0,0,0,0 +2554,39,15,91,93907,2,1.70,2,151,0,0,0,0,0 +2555,63,39,53,93940,1,0.80,1,0,0,0,0,0,0 +2556,58,32,110,94143,3,1.70,2,0,0,0,0,0,0 +2557,28,4,82,92831,3,1.50,1,103,0,0,0,1,0 +2558,36,11,23,94553,4,0.20,3,0,0,0,0,1,0 +2559,43,19,172,95136,2,6.67,1,0,0,0,0,1,0 +2560,36,12,88,90212,2,2.70,1,0,0,0,0,1,0 +2561,44,18,71,93943,2,0.80,3,0,0,0,0,1,0 +2562,31,5,180,94720,1,2.90,3,144,1,1,0,0,0 +2563,45,21,39,92521,2,2.10,3,184,0,0,0,0,1 +2564,39,13,94,90401,1,1.50,3,0,0,0,0,0,1 +2565,43,16,25,94126,3,1.00,2,0,0,0,0,1,0 +2566,40,15,10,94708,2,0.00,3,102,0,0,0,1,0 +2567,30,5,42,94305,1,1.00,1,184,0,0,0,0,0 +2568,58,33,142,92333,2,3.90,1,0,0,0,0,0,1 +2569,46,21,34,92373,2,1.30,1,0,0,0,0,1,0 +2570,35,10,139,90024,1,4.60,1,0,0,0,0,0,0 +2571,30,4,154,95621,2,4.50,1,207,0,0,0,1,0 +2572,34,8,40,91768,2,2.00,3,89,0,0,0,0,0 +2573,62,32,33,93907,1,1.50,3,140,0,0,0,1,1 +2574,58,34,80,90095,2,1.60,1,0,0,0,0,1,1 +2575,45,18,10,92037,3,0.67,2,100,0,0,0,1,0 +2576,42,16,41,90401,3,0.50,3,0,0,0,0,1,0 +2577,60,36,30,93711,4,1.30,1,118,0,0,0,1,1 +2578,55,29,78,95521,1,0.80,3,190,0,0,0,1,0 +2579,45,21,164,90638,1,5.00,1,0,0,0,0,0,1 +2580,52,27,23,92780,1,0.40,3,0,0,0,0,0,0 +2581,31,7,149,92624,1,6.00,1,0,0,0,0,0,0 +2582,60,34,25,94132,4,0.70,3,0,0,0,0,1,0 +2583,33,9,42,95010,1,2.10,3,0,0,0,0,1,0 +2584,37,11,71,91302,1,2.50,1,185,0,0,0,1,1 +2585,59,34,114,94606,3,4.20,2,0,1,0,0,1,0 +2586,51,26,70,91320,1,2.80,2,0,0,0,0,1,1 +2587,47,23,149,92675,4,6.10,1,0,1,0,0,0,1 +2588,60,33,55,94998,4,2.50,2,0,0,0,0,1,0 +2589,61,36,29,93065,1,1.30,1,0,0,0,0,0,0 +2590,64,40,123,90840,1,3.80,1,0,0,0,0,1,1 +2591,46,20,152,95814,1,7.40,3,374,1,0,1,1,1 +2592,31,7,8,95131,4,0.70,2,0,0,0,0,0,0 +2593,57,32,69,94710,4,0.70,1,245,0,0,0,0,0 +2594,48,23,161,96003,4,7.90,3,310,1,0,0,0,0 +2595,48,23,79,94024,1,0.20,2,0,0,0,0,0,0 +2596,35,10,105,92780,1,4.60,1,0,0,0,0,0,0 +2597,33,8,39,95032,3,2.30,1,0,0,0,0,0,0 +2598,47,23,163,92653,1,5.00,1,0,0,0,0,0,0 +2599,46,20,9,94005,1,0.20,1,0,0,0,0,1,0 +2600,44,20,71,91006,4,2.00,3,0,0,0,0,0,1 +2601,42,18,51,92868,3,2.10,3,0,0,0,0,0,0 +2602,50,24,32,90277,1,1.40,3,167,0,0,0,0,0 +2603,52,26,161,93108,4,4.30,1,0,1,0,1,1,1 +2604,53,27,60,90049,1,0.20,1,0,0,0,0,1,0 +2605,37,10,35,92521,4,1.00,2,0,0,0,0,0,0 +2606,64,40,41,94305,4,1.20,2,0,0,0,0,1,0 +2607,46,22,73,92648,2,1.70,1,216,0,0,0,1,0 +2608,57,33,49,94305,4,1.50,1,214,0,1,1,1,1 +2609,61,35,79,94024,2,2.00,1,194,0,0,0,1,1 +2610,42,18,120,93407,2,7.50,1,0,0,1,0,0,0 +2611,40,16,60,94501,2,3.20,1,0,0,0,0,0,0 +2612,33,8,78,95051,3,0.60,2,0,0,0,0,1,0 +2613,50,26,40,95138,4,1.10,2,131,0,0,0,0,0 +2614,52,26,110,94501,2,5.40,3,204,1,1,1,1,0 +2615,35,11,160,92093,4,5.70,3,0,1,1,0,0,0 +2616,57,32,68,94542,4,0.70,1,191,0,0,0,1,1 +2617,56,31,49,92182,2,1.60,3,103,0,0,0,1,0 +2618,44,20,65,92037,2,2.50,1,0,0,0,0,1,0 +2619,23,-3,55,92704,3,2.40,2,145,0,0,0,1,0 +2620,33,8,62,92093,3,2.30,1,98,0,0,0,0,1 +2621,48,22,152,95616,1,0.00,1,0,0,0,0,0,0 +2622,45,18,42,95126,3,2.50,2,0,0,0,0,0,0 +2623,54,28,39,90245,4,0.70,2,0,0,0,0,1,0 +2624,42,17,111,94304,3,3.00,1,0,1,1,1,0,1 +2625,47,21,82,94109,3,2.10,1,0,0,0,0,0,0 +2626,61,36,108,93943,4,3.40,2,0,0,0,0,1,0 +2627,53,27,59,92038,2,0.80,3,0,0,0,0,1,0 +2628,56,30,61,93106,3,2.50,1,193,0,0,0,1,0 +2629,33,6,78,95819,4,2.00,2,0,0,1,0,1,0 +2630,44,18,18,93943,2,0.10,3,0,0,0,0,1,0 +2631,63,37,113,94611,4,1.70,3,0,0,0,0,1,1 +2632,47,20,62,92521,1,2.67,2,0,0,0,0,1,0 +2633,50,24,81,94720,1,4.90,1,248,0,0,0,1,0 +2634,49,25,13,95054,3,0.40,1,106,0,0,0,1,0 +2635,34,9,75,94303,1,2.80,1,194,0,0,0,0,0 +2636,40,14,33,95616,2,0.80,3,89,0,0,0,1,0 +2637,38,13,179,93943,1,4.10,1,0,0,0,0,1,0 +2638,51,26,69,94005,3,2.00,2,0,0,0,0,1,0 +2639,28,4,45,94025,1,1.00,3,0,0,0,0,1,0 +2640,52,26,59,95762,3,3.00,2,0,0,0,0,1,0 +2641,39,13,81,94309,2,2.80,1,0,0,0,0,1,0 +2642,29,5,133,90095,1,5.40,1,212,0,0,0,1,0 +2643,54,29,81,92096,2,0.00,3,0,0,0,0,1,0 +2644,63,38,14,92630,4,0.40,2,86,0,0,0,1,1 +2645,40,14,28,94061,2,0.80,3,0,0,0,0,0,0 +2646,36,12,93,95125,2,2.20,1,0,0,0,0,1,0 +2647,45,20,191,92007,3,2.60,3,123,1,0,0,0,0 +2648,61,37,155,91605,1,2.90,1,0,0,0,0,1,0 +2649,26,0,155,93105,2,7.20,1,0,0,0,0,0,0 +2650,33,8,68,92407,4,1.30,1,0,0,0,0,1,0 +2651,64,40,52,95060,2,1.10,1,226,0,0,0,0,0 +2652,43,17,51,94025,1,0.70,3,0,0,0,0,0,0 +2653,24,0,44,90089,4,1.60,1,180,0,0,0,1,0 +2654,30,5,121,94555,2,3.10,1,408,0,0,0,1,0 +2655,60,36,49,94965,4,2.20,1,204,0,1,0,1,0 +2656,50,26,42,91784,2,1.00,3,78,0,1,0,1,0 +2657,40,15,144,91040,1,4.10,1,0,0,0,0,0,0 +2658,31,6,72,94583,1,2.60,2,0,0,0,0,1,0 +2659,30,4,44,94304,1,1.50,1,109,0,0,0,0,0 +2660,60,35,43,91763,3,0.90,3,175,0,0,0,0,0 +2661,39,14,74,93063,1,0.10,2,144,0,1,0,1,0 +2662,66,41,145,90009,1,2.50,1,0,0,0,0,1,0 +2663,65,41,158,92346,2,2.10,1,0,0,0,0,0,0 +2664,54,28,78,91311,4,4.90,1,0,0,0,0,0,0 +2665,54,29,154,95014,1,2.40,2,352,1,0,0,1,0 +2666,35,9,105,90064,2,4.50,3,0,0,0,0,0,0 +2667,32,7,100,92126,3,0.60,2,0,0,0,0,1,0 +2668,63,39,58,94112,1,0.00,2,0,0,0,0,1,0 +2669,60,35,113,94507,1,0.90,1,406,0,0,0,1,0 +2670,43,18,10,91902,2,0.10,2,0,0,1,0,0,1 +2671,59,33,142,94080,2,2.70,1,0,0,0,0,0,0 +2672,62,37,128,92093,1,2.50,1,0,0,0,0,0,0 +2673,30,5,131,92068,3,0.50,3,0,1,0,0,0,0 +2674,54,30,88,92647,4,1.00,2,122,0,0,0,1,0 +2675,30,6,101,90245,2,0.60,1,0,0,0,0,1,0 +2676,31,1,70,92115,2,1.75,3,0,0,0,1,1,1 +2677,44,20,122,91765,1,0.30,1,0,0,1,0,1,0 +2678,32,8,70,91423,3,1.50,1,0,0,0,0,1,0 +2679,63,38,148,93023,2,4.30,3,0,1,0,0,1,0 +2680,57,32,43,92704,2,2.10,3,166,0,0,0,1,0 +2681,60,30,31,95060,1,1.50,3,0,0,0,0,1,0 +2682,37,11,35,94609,2,0.80,3,0,0,0,0,0,0 +2683,53,27,81,90032,4,2.60,3,0,0,0,0,1,0 +2684,51,25,19,95812,1,1.40,3,98,0,0,0,0,0 +2685,30,5,98,92028,4,1.80,3,129,0,1,1,1,1 +2686,28,2,101,90280,4,2.10,3,0,0,0,0,1,0 +2687,50,24,81,95053,2,0.40,3,0,0,0,0,0,0 +2688,52,27,135,93561,1,0.60,1,452,0,0,0,1,0 +2689,56,30,34,94542,2,0.70,2,0,0,0,0,1,0 +2690,40,16,104,91730,1,3.40,1,249,0,0,0,0,0 +2691,64,38,29,90245,3,0.70,2,0,0,0,0,1,0 +2692,61,36,119,95064,2,5.40,2,0,1,0,0,1,0 +2693,46,20,82,90230,2,1.70,2,0,0,0,0,1,1 +2694,55,29,62,90089,1,0.20,1,0,0,0,0,1,0 +2695,45,19,85,94720,3,2.10,1,0,0,0,0,1,1 +2696,40,15,8,94960,2,0.10,2,0,0,0,0,0,0 +2697,63,37,78,91711,4,1.70,3,0,0,0,0,1,0 +2698,57,32,44,93407,3,0.50,2,0,0,0,0,1,0 +2699,38,14,122,95819,2,8.00,1,0,0,0,0,1,1 +2700,37,11,22,90035,3,0.10,2,114,0,0,0,0,0 +2701,31,5,39,94590,4,2.20,2,0,0,0,0,1,1 +2702,50,26,55,94305,1,1.60,2,0,0,0,0,1,0 +2703,42,18,144,94063,2,6.10,1,158,0,0,0,0,0 +2704,51,27,71,92521,1,2.60,2,0,0,0,0,0,1 +2705,38,13,191,91710,2,3.00,1,0,0,0,0,1,0 +2706,53,26,22,92831,1,0.50,2,100,0,0,0,1,0 +2707,43,17,158,90740,1,2.40,1,0,0,0,0,1,0 +2708,35,9,131,90089,3,0.30,3,0,1,0,1,1,1 +2709,49,24,75,95670,1,2.80,2,160,0,0,0,0,1 +2710,28,4,69,94305,3,0.70,2,170,0,0,0,0,0 +2711,51,27,39,94304,2,0.80,1,0,0,0,0,0,0 +2712,39,14,34,94939,4,1.70,1,0,0,0,0,1,1 +2713,31,7,32,91320,1,1.70,1,0,0,0,0,1,0 +2714,44,18,129,92028,1,5.70,1,0,0,0,0,1,0 +2715,46,20,158,92870,3,5.40,1,432,1,0,0,0,1 +2716,42,18,54,90089,1,1.80,1,0,0,0,0,1,0 +2717,41,17,34,92182,1,2.00,2,0,0,0,0,0,0 +2718,23,-2,45,95422,4,0.60,2,0,0,0,0,1,1 +2719,59,33,68,95064,2,2.30,3,0,0,1,0,0,0 +2720,47,21,53,95929,1,1.50,2,0,0,0,0,1,0 +2721,48,23,32,93302,1,0.10,1,0,0,0,0,0,1 +2722,58,33,173,92121,2,7.20,3,0,1,0,0,1,0 +2723,58,34,31,92126,4,0.40,1,0,0,0,0,0,0 +2724,54,29,72,94558,2,3.70,1,144,0,0,0,1,0 +2725,49,24,30,90212,4,0.40,2,157,0,0,1,1,1 +2726,63,38,138,92675,1,2.50,1,0,0,0,0,1,0 +2727,62,37,18,92028,1,1.50,2,127,0,0,0,0,0 +2728,45,19,69,90840,1,2.80,1,220,0,0,0,1,1 +2729,39,13,58,94555,3,2.10,1,247,0,0,0,1,0 +2730,58,34,63,90007,4,1.50,1,0,0,0,0,1,0 +2731,56,30,43,90401,2,0.30,1,0,0,1,0,0,0 +2732,29,5,28,96651,1,0.20,3,0,0,0,0,1,0 +2733,33,9,38,93106,1,2.10,3,133,0,0,0,0,0 +2734,55,29,72,93107,3,0.30,2,147,0,0,0,0,0 +2735,56,31,64,94126,4,0.90,1,0,0,0,0,1,0 +2736,36,12,70,92131,3,2.60,2,165,0,0,0,1,0 +2737,53,29,12,95621,1,0.30,1,0,0,0,0,0,0 +2738,57,31,159,94577,2,0.50,1,0,0,0,0,0,0 +2739,35,9,103,95120,2,4.50,3,0,0,0,0,1,0 +2740,43,18,42,91330,1,0.30,3,0,0,0,0,1,0 +2741,54,29,48,92182,2,2.10,3,142,0,0,0,1,0 +2742,29,3,49,90266,1,1.50,1,0,0,0,0,0,0 +2743,39,14,89,95762,2,0.40,1,0,0,0,0,1,0 +2744,32,8,22,94583,4,0.70,2,0,0,0,0,1,1 +2745,51,27,10,92121,2,0.20,1,86,0,0,0,0,0 +2746,50,25,38,95616,1,1.30,2,120,0,0,0,0,1 +2747,54,29,49,92703,2,2.10,3,95,0,0,0,1,1 +2748,38,12,30,91765,2,1.40,3,0,0,0,0,0,1 +2749,32,7,82,94305,1,2.60,2,240,0,0,1,1,1 +2750,62,37,82,94086,1,0.80,3,312,0,0,0,1,0 +2751,57,33,24,94501,1,0.10,2,0,0,0,0,0,0 +2752,47,23,32,92251,4,0.60,1,156,0,0,0,1,1 +2753,51,25,34,95819,3,0.90,3,111,0,0,0,1,0 +2754,54,27,195,93117,2,4.75,2,477,1,0,0,0,0 +2755,26,1,61,93943,4,2.20,1,119,0,0,0,0,0 +2756,37,11,22,93711,3,0.10,2,0,0,0,0,1,1 +2757,27,0,40,91301,4,1.00,3,0,0,0,0,1,0 +2758,63,38,50,93943,2,2.80,1,205,0,0,0,0,0 +2759,62,36,35,94501,2,0.70,3,0,0,1,0,0,1 +2760,59,33,64,95617,3,0.30,2,0,0,0,0,0,0 +2761,32,7,49,94080,3,2.30,1,0,0,0,0,1,0 +2762,35,8,44,95045,4,1.00,2,192,0,0,0,0,1 +2763,56,31,65,93403,2,3.70,1,0,0,0,0,1,0 +2764,55,31,13,93943,4,0.70,1,0,0,0,0,1,0 +2765,31,5,84,91320,1,2.90,3,105,0,0,0,0,1 +2766,54,29,28,92093,4,0.20,2,101,0,0,0,1,0 +2767,58,32,108,95123,3,4.40,1,0,0,0,0,1,0 +2768,48,24,59,90401,1,0.00,1,144,0,0,0,1,0 +2769,48,22,163,95819,1,2.40,1,396,0,0,0,1,0 +2770,33,9,183,91320,2,8.80,3,582,1,0,0,1,0 +2771,36,6,69,90024,4,4.00,3,0,0,0,0,1,0 +2772,41,16,115,92333,1,7.00,1,0,0,0,0,0,0 +2773,55,31,130,92646,4,6.50,1,0,1,0,0,0,1 +2774,63,37,185,94309,2,7.90,2,358,1,0,0,1,0 +2775,53,29,118,94066,2,0.30,1,0,0,0,0,1,0 +2776,38,13,163,95039,1,4.10,1,0,0,0,0,0,0 +2777,46,20,140,93106,2,6.30,1,380,0,0,0,1,1 +2778,59,33,91,94122,2,0.70,2,0,0,0,0,1,1 +2779,56,31,61,92646,4,1.30,3,0,0,0,0,1,1 +2780,59,35,168,95521,4,4.10,2,0,1,0,0,1,0 +2781,39,13,69,90630,3,0.90,2,0,0,0,0,0,0 +2782,47,21,22,92037,1,0.20,1,104,0,0,0,0,0 +2783,47,22,53,92691,1,0.30,1,213,0,0,0,0,0 +2784,53,26,25,92123,2,1.00,2,0,0,0,1,1,1 +2785,36,9,115,91765,4,2.20,2,0,1,0,0,0,0 +2786,34,9,31,92521,4,1.10,3,85,0,1,1,1,1 +2787,36,10,83,94705,1,2.80,3,0,0,0,0,0,1 +2788,60,34,152,92807,2,6.90,1,0,0,0,0,0,0 +2789,45,20,30,96003,1,0.10,1,0,0,0,0,1,0 +2790,27,3,34,90065,1,0.20,3,0,0,0,0,1,1 +2791,47,22,44,95821,1,1.40,3,0,0,0,0,1,1 +2792,44,20,182,94710,2,7.60,1,0,0,0,0,0,0 +2793,54,30,44,95616,3,1.50,1,117,0,0,0,1,0 +2794,57,33,122,94301,2,6.00,1,153,0,1,1,1,1 +2795,52,26,35,94550,4,1.80,1,0,0,0,0,1,0 +2796,51,25,91,92407,1,0.80,3,0,0,0,0,0,0 +2797,57,32,30,94024,2,2.00,2,0,0,0,0,0,0 +2798,65,39,53,94608,1,2.50,3,0,0,0,0,1,0 +2799,58,33,28,94720,1,0.30,3,0,0,0,0,1,0 +2800,64,39,85,94720,4,3.40,2,200,0,0,0,1,0 +2801,52,26,28,93907,2,0.70,2,90,0,0,0,1,1 +2802,58,34,41,91016,4,0.40,1,177,0,0,0,1,0 +2803,52,22,154,90650,1,5.00,3,0,1,1,1,1,0 +2804,43,18,41,92831,1,0.30,3,0,0,0,0,1,0 +2805,56,32,33,95014,3,1.50,1,0,0,0,0,0,0 +2806,37,12,182,94523,3,5.80,3,0,1,0,0,1,0 +2807,53,27,59,90740,2,0.80,3,0,0,0,0,1,0 +2808,27,2,129,90009,2,3.30,1,0,0,1,0,0,0 +2809,53,27,35,94583,3,0.90,3,136,0,0,0,1,0 +2810,42,16,185,94705,3,2.20,2,0,1,1,1,1,1 +2811,58,34,45,93943,4,1.30,2,201,0,0,0,0,0 +2812,36,12,62,94065,4,0.10,2,145,0,0,0,0,0 +2813,53,28,183,96008,3,8.20,3,467,1,0,1,1,1 +2814,48,22,14,94303,2,0.10,3,0,0,0,0,1,0 +2815,54,28,53,94002,1,2.20,3,0,0,0,0,1,1 +2816,26,1,48,94019,3,2.60,3,169,0,0,0,0,0 +2817,50,26,128,92780,2,0.40,1,0,0,0,0,1,0 +2818,31,7,105,94025,1,4.00,1,331,0,0,0,1,0 +2819,35,9,40,93943,3,0.90,1,0,0,0,0,1,1 +2820,63,37,10,90095,2,0.40,1,0,0,0,0,1,0 +2821,29,4,102,90245,2,3.30,1,303,0,0,0,0,0 +2822,57,32,31,94143,3,0.10,2,0,0,0,0,1,0 +2823,30,5,30,90245,4,0.80,1,158,0,0,0,1,0 +2824,33,7,21,90095,1,0.60,3,0,0,1,0,0,0 +2825,62,36,44,92867,2,0.30,1,0,0,0,0,0,0 +2826,35,10,48,95060,1,2.50,3,164,0,0,0,1,0 +2827,37,11,21,94604,3,0.20,2,0,0,0,0,1,0 +2828,37,11,84,90266,4,2.20,2,0,0,0,0,1,1 +2829,35,10,64,94306,3,0.70,2,230,0,0,0,1,0 +2830,35,9,82,94720,1,2.50,1,138,0,0,0,0,0 +2831,59,35,39,95616,4,1.30,1,0,0,0,0,1,0 +2832,53,27,45,90405,2,0.80,3,0,0,0,0,1,1 +2833,45,21,133,92056,4,5.70,3,0,1,0,1,1,1 +2834,46,22,152,90009,2,1.40,1,0,0,0,0,1,0 +2835,40,16,12,90033,1,1.00,1,91,0,1,0,0,0 +2836,42,16,32,94112,3,1.50,1,149,0,0,0,1,0 +2837,25,1,74,94085,4,2.60,1,204,0,0,0,0,0 +2838,39,14,54,92037,2,1.10,2,159,0,0,0,0,1 +2839,30,6,181,94542,3,4.10,2,0,1,0,1,1,1 +2840,58,33,75,90034,2,0.00,3,0,0,0,0,1,0 +2841,41,15,95,91101,3,0.10,1,240,0,1,0,0,0 +2842,37,11,190,94305,4,7.30,2,565,1,0,1,1,0 +2843,36,11,90,94709,1,2.80,1,0,0,0,0,1,0 +2844,27,3,20,95616,4,1.00,1,134,0,0,0,1,1 +2845,60,34,64,95014,3,2.20,3,0,0,0,0,0,0 +2846,62,36,85,90019,2,1.70,3,98,0,0,0,0,0 +2847,67,43,105,93711,4,1.70,2,0,0,0,0,1,0 +2848,44,18,21,90840,1,0.20,1,0,0,0,0,1,0 +2849,24,-1,78,94720,2,1.80,2,0,0,0,0,0,0 +2850,45,21,158,94085,2,6.67,1,132,0,0,0,1,1 +2851,58,34,125,94720,1,4.30,1,219,0,0,0,0,0 +2852,61,36,81,95449,3,1.80,2,0,0,0,0,1,0 +2853,54,29,183,93105,1,8.10,1,0,0,0,0,1,1 +2854,28,3,54,94550,4,0.60,2,0,0,0,0,1,0 +2855,49,24,79,94025,4,3.60,3,212,0,0,0,1,0 +2856,35,11,38,91706,1,1.50,2,136,0,0,0,1,0 +2857,36,10,172,94704,4,1.00,2,295,1,0,0,1,0 +2858,34,8,184,93106,3,7.50,1,0,1,0,0,0,0 +2859,36,11,158,95054,2,7.80,1,114,0,0,0,1,1 +2860,35,11,188,94596,1,0.90,3,282,1,0,0,1,0 +2861,27,2,20,95064,4,0.50,3,0,0,0,0,1,0 +2862,42,18,60,92677,4,0.20,3,151,0,0,0,0,1 +2863,65,39,113,92096,4,2.40,3,0,0,0,0,1,0 +2864,29,5,70,93101,4,0.00,1,0,0,0,0,1,1 +2865,65,41,84,95762,2,0.00,3,0,0,0,0,1,1 +2866,59,33,23,94002,2,0.20,3,0,0,0,0,1,0 +2867,46,22,141,90089,2,3.30,1,0,0,1,1,1,1 +2868,59,33,110,90007,3,4.40,1,264,0,0,0,1,0 +2869,52,26,31,94923,4,1.80,1,0,0,0,0,1,1 +2870,60,35,22,92660,1,1.30,1,80,0,0,0,0,0 +2871,43,17,91,95134,1,5.20,1,0,0,1,0,0,0 +2872,65,39,82,94131,4,2.40,3,252,0,0,0,1,0 +2873,50,26,23,92630,1,0.30,1,0,0,0,0,0,0 +2874,48,23,35,93943,1,0.10,1,0,0,1,0,1,0 +2875,49,25,114,91380,1,2.50,3,0,1,0,0,1,0 +2876,58,33,18,94402,3,0.10,2,0,0,0,0,1,1 +2877,24,-2,80,91107,2,1.60,3,238,0,0,0,0,0 +2878,58,32,74,95817,2,2.30,3,0,0,0,0,0,1 +2879,45,19,122,94590,4,4.10,2,0,1,0,0,1,0 +2880,42,15,73,94545,3,2.33,2,0,0,0,0,0,0 +2881,64,40,40,96064,2,1.10,1,0,0,0,0,1,0 +2882,49,25,55,92103,4,0.10,3,0,0,0,0,1,0 +2883,55,31,69,90089,1,2.70,2,0,0,1,0,0,1 +2884,40,14,92,90024,4,1.40,2,0,0,0,0,1,0 +2885,28,2,48,93943,4,2.10,3,0,0,0,0,1,1 +2886,57,31,113,91711,4,0.60,3,327,1,0,0,1,0 +2887,50,25,58,93940,1,1.30,2,0,0,0,0,1,0 +2888,40,16,109,94025,2,2.20,1,0,0,0,0,1,0 +2889,55,28,39,94542,3,1.00,2,0,0,0,0,1,1 +2890,53,29,33,94591,3,1.90,2,144,0,0,0,0,0 +2891,48,24,18,94304,4,0.20,1,0,0,0,0,1,1 +2892,59,33,63,90044,1,1.60,1,0,0,0,0,1,1 +2893,58,32,43,92093,1,2.80,2,0,0,0,0,1,0 +2894,38,14,70,94022,4,2.00,3,0,0,0,0,1,0 +2895,49,25,19,94545,1,0.90,3,0,0,0,0,0,0 +2896,60,36,39,94501,4,1.30,2,140,0,0,0,1,0 +2897,54,28,81,94720,3,0.80,1,0,0,0,0,0,0 +2898,28,2,34,92161,4,1.30,3,0,0,0,0,0,0 +2899,27,1,140,91711,1,5.90,2,175,1,1,1,1,0 +2900,42,18,114,94305,1,0.30,1,0,0,0,0,0,0 +2901,52,28,55,91320,2,3.20,3,151,0,0,0,0,0 +2902,54,30,21,95351,1,0.10,2,76,0,0,0,1,0 +2903,56,30,50,94022,4,2.80,2,0,0,1,0,1,0 +2904,58,34,41,95833,3,1.50,1,0,0,0,0,1,1 +2905,56,32,190,90032,3,2.20,1,0,1,0,1,1,0 +2906,64,40,8,94110,2,0.30,3,0,0,0,0,1,0 +2907,35,8,55,92870,2,1.67,2,0,0,0,0,1,0 +2908,45,20,40,91763,2,1.30,1,0,0,0,0,0,1 +2909,57,32,22,95616,3,0.10,2,0,0,0,0,1,0 +2910,35,8,44,94590,2,1.67,2,0,0,1,0,0,1 +2911,46,22,102,95039,3,4.50,3,0,1,0,0,1,0 +2912,30,4,54,93033,4,1.80,3,235,0,0,0,1,0 +2913,44,20,130,90291,4,3.20,2,0,1,0,0,0,0 +2914,39,12,75,94501,3,2.33,2,0,0,0,0,1,1 +2915,42,18,42,95929,2,1.70,1,0,0,0,0,1,0 +2916,34,9,133,92110,1,3.80,1,0,0,0,0,1,0 +2917,46,20,40,92037,1,1.20,2,0,0,0,0,1,0 +2918,55,31,34,94305,3,1.50,1,101,0,0,0,1,0 +2919,28,3,142,93727,1,0.80,1,0,0,0,0,1,0 +2920,35,10,64,94542,3,2.30,1,0,0,0,1,1,1 +2921,60,35,44,94720,2,1.60,3,170,0,0,0,1,0 +2922,50,24,95,91401,1,0.30,1,262,0,0,0,1,0 +2923,52,26,49,90011,1,1.40,3,0,0,0,0,1,0 +2924,51,27,12,91007,2,0.20,1,0,0,0,0,0,0 +2925,51,26,98,90024,1,1.30,3,0,0,0,0,1,1 +2926,59,35,42,91711,4,0.40,1,0,0,0,0,1,0 +2927,53,28,44,92152,2,0.60,3,0,0,0,0,1,1 +2928,43,17,124,94117,1,5.20,1,0,0,0,0,0,0 +2929,31,6,175,95005,2,6.70,1,0,0,0,0,1,0 +2930,32,6,22,94061,4,0.30,1,0,0,0,0,0,0 +2931,41,17,78,95929,4,2.67,1,99,0,0,0,1,0 +2932,31,4,54,91741,2,1.00,2,109,0,0,0,0,1 +2933,41,16,154,92407,1,7.00,1,0,0,0,0,0,1 +2934,47,22,42,95820,3,2.70,2,0,0,0,0,1,0 +2935,37,13,195,91763,2,6.50,1,635,0,0,0,1,0 +2936,53,23,80,93023,1,3.00,3,0,0,0,0,1,1 +2937,49,22,81,94301,3,2.00,2,0,0,0,0,1,0 +2938,62,36,89,94022,2,2.00,1,0,0,0,0,1,1 +2939,33,9,61,93943,3,2.60,2,0,0,0,0,1,0 +2940,54,24,25,90016,4,0.40,3,0,0,0,0,0,1 +2941,27,3,43,90245,3,0.10,2,163,0,0,0,1,0 +2942,60,35,122,92606,1,2.60,1,352,0,0,0,0,0 +2943,29,5,160,90405,1,4.30,1,385,0,0,0,1,0 +2944,56,32,83,91320,4,1.60,2,0,0,0,0,0,0 +2945,55,30,79,92182,2,0.00,3,0,0,0,0,0,0 +2946,45,19,30,94305,3,0.50,2,0,0,0,0,1,1 +2947,33,9,145,94110,1,4.30,1,437,0,0,0,1,0 +2948,45,21,151,90024,2,3.30,1,328,0,0,0,0,0 +2949,44,18,14,94720,2,0.10,3,98,0,0,0,0,1 +2950,37,11,19,95054,3,0.20,2,0,0,0,0,1,0 +2951,42,16,55,95820,1,0.70,3,135,0,0,0,1,0 +2952,26,2,132,94720,2,2.40,3,0,1,0,0,0,1 +2953,33,8,182,94065,1,8.60,1,0,0,0,0,0,0 +2954,61,36,78,91330,3,0.50,1,0,0,0,0,1,1 +2955,31,7,42,95822,1,2.40,2,0,0,0,0,1,1 +2956,54,29,44,95518,2,2.30,3,187,0,0,0,1,0 +2957,62,38,195,91125,4,5.20,3,522,1,0,1,1,1 +2958,61,36,53,92717,3,0.50,2,0,0,0,0,1,0 +2959,66,41,65,92612,3,2.40,1,0,0,0,0,0,0 +2960,38,12,43,94305,4,0.20,1,0,0,0,0,0,0 +2961,55,29,38,90035,4,1.50,3,0,0,0,0,0,1 +2962,60,36,50,95741,1,1.80,3,0,0,0,0,1,0 +2963,23,-2,81,91711,2,1.80,2,0,0,0,0,0,0 +2964,29,3,41,94588,1,1.90,3,0,0,0,0,1,1 +2965,35,10,73,93943,3,2.30,1,0,0,0,0,1,0 +2966,53,27,31,91605,2,0.40,3,104,0,0,0,0,1 +2967,32,7,84,91320,3,0.60,2,0,0,0,0,1,1 +2968,38,14,95,94109,2,1.90,1,0,0,0,0,1,1 +2969,44,18,162,90840,4,1.30,1,301,1,0,0,0,0 +2970,43,18,60,95039,2,2.20,3,115,0,0,0,0,0 +2971,54,30,121,95039,2,1.10,3,0,1,1,0,0,0 +2972,52,25,43,91380,3,1.00,2,165,0,0,1,1,1 +2973,31,7,38,92182,1,1.80,2,182,0,0,1,1,1 +2974,47,22,82,92084,1,2.90,1,276,0,0,0,1,0 +2975,42,18,52,95008,4,1.90,1,0,0,0,0,1,0 +2976,57,33,43,91016,3,1.50,1,168,0,0,0,0,1 +2977,33,8,82,95747,1,2.60,2,0,0,1,1,1,1 +2978,35,10,161,94109,1,4.10,1,0,0,1,0,1,0 +2979,56,30,24,94550,2,0.70,2,0,0,0,0,1,0 +2980,57,32,102,90210,1,2.60,1,0,0,0,0,1,0 +2981,25,-1,53,94305,3,2.40,2,0,0,0,0,0,0 +2982,53,28,85,92037,1,1.20,1,0,0,0,0,0,0 +2983,59,33,111,95120,3,4.40,1,0,0,0,0,1,0 +2984,56,32,90,95054,2,0.30,1,0,0,0,0,1,1 +2985,54,28,94,92709,2,1.10,1,188,0,0,0,0,0 +2986,48,23,63,94606,4,3.60,3,0,0,0,0,0,0 +2987,55,30,153,94305,2,2.80,2,0,1,1,1,1,0 +2988,33,7,39,92037,2,2.00,3,0,0,0,0,0,0 +2989,46,21,205,95762,2,8.80,1,181,0,1,0,1,0 +2990,42,18,142,93106,1,3.40,1,496,0,0,0,1,0 +2991,49,25,163,94608,2,0.40,1,0,0,1,0,0,0 +2992,42,17,113,93014,3,1.00,1,0,0,1,0,1,0 +2993,46,21,64,92104,1,2.90,1,0,0,0,0,1,1 +2994,65,40,20,92647,3,0.10,3,0,0,0,0,0,1 +2995,50,24,179,94025,1,1.00,1,0,0,0,0,1,0 +2996,54,24,91,91101,2,4.50,3,90,0,0,0,1,0 +2997,42,18,103,91367,1,3.33,1,0,1,1,1,1,1 +2998,57,33,80,95053,4,1.60,2,0,0,0,0,0,0 +2999,61,35,38,93106,2,0.30,1,0,0,0,0,0,0 +3000,60,34,44,94143,1,0.20,1,0,0,0,0,0,1 +3001,40,14,164,94720,1,4.30,2,0,1,0,0,0,0 +3002,33,7,81,92647,3,1.60,1,0,0,0,0,1,1 +3003,37,13,95,90095,2,1.70,2,83,0,0,0,0,0 +3004,52,28,44,90747,3,1.90,2,0,0,0,0,0,1 +3005,33,7,88,94583,3,1.60,1,0,0,0,0,1,1 +3006,62,36,148,94111,3,7.00,2,0,1,0,0,1,0 +3007,62,37,169,95014,3,5.00,2,184,1,0,1,1,1 +3008,63,37,11,91711,1,0.80,2,102,0,0,0,0,1 +3009,55,25,92,94550,1,3.00,3,158,0,0,0,0,1 +3010,33,9,74,92120,3,2.60,2,0,0,0,0,1,0 +3011,25,1,72,94301,3,0.80,1,0,0,0,0,1,0 +3012,55,31,63,95616,3,2.67,1,0,0,0,0,1,0 +3013,29,3,172,92373,2,4.50,1,415,0,0,0,1,0 +3014,45,21,183,90029,2,1.40,1,0,0,0,0,1,1 +3015,60,34,40,91311,1,2.50,3,166,0,0,0,1,0 +3016,44,18,68,92673,4,2.90,1,0,0,1,0,0,1 +3017,48,23,78,91423,4,3.60,3,0,0,0,0,1,0 +3018,57,32,68,90041,2,3.70,1,184,0,0,0,0,0 +3019,58,32,49,94005,1,1.40,1,99,0,0,0,1,1 +3020,58,33,39,94132,2,2.30,3,0,0,0,0,1,0 +3021,44,20,151,95193,1,3.50,1,392,0,0,0,1,0 +3022,54,28,159,90245,2,0.50,1,461,0,0,0,1,0 +3023,59,33,89,94608,4,1.90,2,0,0,0,0,1,1 +3024,63,37,105,92694,4,1.70,3,244,0,0,0,0,1 +3025,61,35,78,90840,2,2.00,1,0,0,0,0,1,1 +3026,58,32,128,94609,2,2.70,1,344,0,0,0,0,0 +3027,44,20,81,90254,4,0.80,1,228,0,0,0,0,1 +3028,53,29,50,93305,4,0.10,3,152,0,0,0,1,0 +3029,63,39,38,92624,3,0.10,3,178,0,0,0,1,1 +3030,41,17,119,94960,2,6.10,1,263,0,1,0,1,0 +3031,50,26,110,94509,3,1.80,2,0,0,0,0,1,0 +3032,51,25,29,90212,1,1.40,3,102,0,0,0,0,1 +3033,47,22,19,94590,1,0.40,3,0,0,0,0,1,0 +3034,43,19,130,90630,2,4.70,3,221,1,0,0,0,1 +3035,46,21,38,90024,1,2.40,1,130,0,0,0,1,0 +3036,50,24,31,95054,1,0.30,3,0,0,0,0,0,0 +3037,33,9,14,91320,4,0.70,2,105,0,0,0,1,0 +3038,27,2,158,95060,3,0.40,2,0,1,0,1,1,0 +3039,34,8,39,92124,4,0.20,1,115,0,0,0,1,0 +3040,34,9,141,95616,2,4.90,3,0,1,0,0,0,1 +3041,28,2,33,95814,3,1.00,1,167,0,0,0,1,0 +3042,29,5,92,95006,2,0.60,1,0,0,0,0,1,0 +3043,52,26,78,94301,3,3.00,2,0,0,0,0,0,0 +3044,47,22,42,91754,3,2.70,2,0,0,0,0,1,1 +3045,41,16,15,94124,2,0.30,2,83,0,0,0,0,0 +3046,58,32,48,91768,1,2.80,2,0,0,0,0,1,0 +3047,37,12,63,95630,3,2.30,1,0,0,0,0,1,0 +3048,57,33,149,95060,1,4.70,1,0,0,1,0,0,0 +3049,63,39,49,90275,1,0.80,1,103,0,0,0,1,0 +3050,60,35,125,94720,2,3.90,1,0,0,0,0,0,0 +3051,50,25,58,92131,1,1.30,2,0,0,0,0,1,0 +3052,60,35,48,94538,3,1.50,1,0,0,0,0,1,0 +3053,54,30,75,94720,2,3.20,3,0,0,0,0,0,1 +3054,28,4,114,92521,2,0.20,1,0,0,0,0,1,0 +3055,45,21,134,92697,4,5.50,2,0,1,0,1,1,1 +3056,28,2,111,94305,4,2.30,3,0,0,0,0,1,0 +3057,54,29,62,94301,4,3.80,2,149,0,0,0,1,0 +3058,42,18,45,95616,1,0.70,1,0,0,1,0,1,0 +3059,30,4,113,90064,2,0.20,1,0,0,0,0,1,0 +3060,61,36,128,94550,1,2.60,1,0,0,0,0,1,0 +3061,64,38,168,94061,4,5.70,3,0,1,0,0,1,0 +3062,38,13,81,90095,1,4.00,3,206,0,1,0,1,0 +3063,39,14,75,92521,1,0.10,2,297,0,0,0,0,1 +3064,54,29,21,95841,4,0.10,3,0,0,0,0,0,0 +3065,59,33,83,94701,3,4.40,1,0,0,0,0,1,0 +3066,39,15,121,92354,1,3.50,1,368,0,1,0,1,0 +3067,63,33,40,91320,4,1.67,3,0,0,0,0,1,0 +3068,31,5,101,94501,1,2.90,3,170,0,1,0,0,0 +3069,56,26,90,92120,2,4.50,3,0,0,0,0,0,0 +3070,47,20,68,91320,1,2.67,2,0,0,0,0,1,1 +3071,28,3,74,91330,2,1.80,2,221,0,1,0,0,0 +3072,32,8,74,93023,4,0.10,2,257,0,0,0,0,1 +3073,54,30,51,92821,2,3.20,3,0,0,0,0,0,0 +3074,29,5,149,94611,1,1.50,1,0,0,0,0,1,0 +3075,39,15,31,95039,1,1.40,3,88,0,0,0,1,1 +3076,26,0,85,95616,2,1.60,3,0,0,0,0,0,0 +3077,29,-1,62,92672,2,1.75,3,0,0,0,0,0,1 +3078,46,21,44,95112,1,0.30,1,110,0,1,0,1,0 +3079,38,13,63,92325,3,0.50,3,190,0,1,1,1,1 +3080,55,31,23,95616,2,0.30,1,0,0,0,0,1,1 +3081,48,22,40,94063,3,2.20,2,87,0,0,0,1,0 +3082,36,10,78,95064,2,4.50,3,204,0,0,0,1,1 +3083,39,13,40,92122,3,0.90,3,129,0,0,0,1,0 +3084,40,16,78,90720,4,2.40,1,0,0,1,1,1,0 +3085,26,0,129,90028,3,0.70,2,0,1,0,0,0,0 +3086,55,29,71,91311,3,0.30,2,0,0,0,0,0,1 +3087,61,35,23,94720,3,0.30,3,0,0,0,0,1,0 +3088,57,33,15,94303,2,0.30,1,0,0,0,0,1,0 +3089,56,31,28,94720,1,1.30,1,138,0,0,0,0,1 +3090,31,5,23,94110,3,1.00,1,95,0,0,0,0,0 +3091,61,31,19,91109,1,1.50,3,0,0,0,0,1,0 +3092,58,32,42,95020,3,1.40,3,158,0,0,0,0,1 +3093,43,18,113,90036,2,0.40,1,325,0,1,0,0,0 +3094,29,5,34,90717,4,0.40,2,0,0,0,0,0,1 +3095,50,23,19,90272,1,0.50,2,104,0,0,0,0,1 +3096,49,25,43,94109,1,1.60,2,0,0,0,0,1,1 +3097,43,18,179,94108,3,1.20,1,0,1,1,1,1,0 +3098,58,32,44,92182,3,2.20,3,0,0,0,0,0,0 +3099,41,16,21,92024,2,0.10,2,0,0,0,0,0,0 +3100,65,40,115,92647,1,2.50,1,174,0,0,0,0,1 +3101,52,27,81,90024,4,3.80,2,0,0,0,0,0,1 +3102,55,31,91,93555,2,2.80,1,0,0,0,0,0,0 +3103,49,25,30,90095,4,0.90,2,0,0,0,0,0,1 +3104,52,22,55,92129,3,1.40,3,0,0,0,0,1,0 +3105,56,31,48,91775,2,2.10,3,0,0,0,0,0,1 +3106,30,4,23,94122,4,0.30,2,121,0,0,0,0,0 +3107,36,10,21,92084,3,0.10,2,0,0,0,0,0,0 +3108,41,17,55,92374,2,1.70,1,0,0,0,0,0,0 +3109,42,15,21,95678,3,1.00,2,0,0,0,0,1,0 +3110,60,34,40,93940,3,2.20,3,0,0,1,0,1,0 +3111,44,20,30,95020,4,0.30,1,0,0,0,0,0,1 +3112,34,9,78,90095,3,0.60,2,0,0,0,0,1,0 +3113,56,32,65,92677,2,3.20,3,0,0,0,0,1,0 +3114,31,5,50,91330,4,2.10,3,209,0,0,0,1,0 +3115,29,4,55,90024,4,2.00,2,0,0,1,0,1,0 +3116,31,5,111,94305,2,0.20,1,0,0,0,0,0,0 +3117,36,10,21,92008,3,0.10,2,0,0,0,0,0,1 +3118,42,16,65,92614,3,0.50,3,256,0,0,0,1,0 +3119,64,39,114,90095,1,0.80,3,0,0,0,0,1,0 +3120,61,36,54,91320,3,0.90,3,179,0,0,0,1,0 +3121,35,11,75,94542,2,1.70,2,0,0,0,0,1,0 +3122,28,2,13,91791,4,0.40,1,0,0,0,0,0,1 +3123,38,14,54,90095,2,0.60,3,218,0,0,0,0,0 +3124,44,17,22,94546,3,1.00,2,126,0,0,0,1,1 +3125,45,20,198,95053,2,2.80,1,0,0,0,0,1,1 +3126,46,20,18,92521,1,0.20,1,0,0,0,0,1,1 +3127,57,32,74,92780,4,0.70,1,0,0,0,0,0,1 +3128,40,14,61,94539,4,0.20,3,0,0,0,0,1,0 +3129,38,12,64,94115,2,1.80,1,0,0,0,0,0,0 +3130,39,14,10,92705,2,0.30,2,0,0,1,0,0,1 +3131,23,-2,82,92152,2,1.80,2,0,0,1,0,0,1 +3132,47,22,61,94025,3,2.70,2,168,0,0,0,1,1 +3133,32,7,83,94302,2,2.50,1,148,0,1,0,1,0 +3134,30,5,73,93711,3,2.60,3,0,0,0,0,1,0 +3135,54,30,22,95060,2,0.40,1,89,0,0,0,1,0 +3136,25,0,91,95039,2,1.80,2,321,0,0,0,0,0 +3137,60,34,65,95354,3,2.20,3,94,0,1,1,0,1 +3138,61,36,13,91711,3,0.50,1,0,0,0,0,1,0 +3139,36,11,103,93555,1,4.60,1,255,0,0,0,1,0 +3140,52,26,95,92130,1,0.30,1,0,0,0,0,1,0 +3141,33,7,31,94303,4,1.00,1,0,0,0,0,1,1 +3142,57,31,131,90405,3,0.60,1,0,1,0,0,1,0 +3143,34,8,175,95051,4,1.10,3,0,1,1,1,1,1 +3144,50,24,38,91105,4,0.10,1,0,0,0,0,1,0 +3145,43,18,104,91711,3,1.00,1,0,0,0,0,1,0 +3146,34,10,114,94305,3,3.30,3,0,1,0,0,0,0 +3147,26,1,38,91910,4,1.70,2,0,0,0,0,1,0 +3148,26,0,30,94024,4,1.30,3,0,0,0,0,1,1 +3149,48,22,19,95616,2,0.10,3,106,0,0,0,0,0 +3150,49,25,25,95192,4,1.00,1,0,0,0,0,1,1 +3151,47,22,124,90027,4,5.00,3,0,1,0,0,0,0 +3152,43,19,20,94110,3,0.50,1,0,0,0,0,0,0 +3153,40,15,83,90275,1,1.00,3,0,0,0,0,0,0 +3154,31,5,18,94111,4,0.30,2,0,0,0,0,0,1 +3155,27,1,99,94305,1,3.00,3,149,1,0,0,0,1 +3156,55,29,62,92626,3,0.30,2,0,0,0,0,1,0 +3157,54,30,24,92647,1,0.10,2,0,0,0,0,0,0 +3158,23,-1,13,94720,4,1.00,1,84,0,0,0,1,0 +3159,54,28,64,90095,2,0.80,3,0,0,1,0,1,0 +3160,57,33,62,92831,3,2.67,1,240,0,0,0,0,0 +3161,41,15,158,94304,1,4.70,2,0,1,1,1,0,1 +3162,28,4,88,94024,1,5.40,1,0,0,0,0,1,0 +3163,33,7,28,94109,4,0.80,1,0,0,0,0,1,0 +3164,51,27,52,94132,2,1.00,3,0,0,0,0,0,0 +3165,28,4,82,95136,4,0.00,1,0,0,0,0,1,1 +3166,63,37,140,91711,2,6.90,1,97,0,0,0,0,1 +3167,29,4,80,90028,1,0.80,2,0,0,0,0,1,1 +3168,62,38,58,94720,4,1.20,2,228,0,0,0,0,1 +3169,51,25,180,94701,1,1.70,1,0,0,0,0,1,0 +3170,52,28,55,94608,1,1.60,2,227,0,0,0,0,0 +3171,43,16,65,94110,3,2.67,2,100,0,0,0,0,0 +3172,39,12,62,91910,3,2.33,2,0,0,0,0,0,0 +3173,35,9,23,95670,4,0.30,1,0,0,0,0,0,0 +3174,34,10,35,94309,1,1.70,1,0,0,0,0,1,0 +3175,49,24,35,94701,4,0.20,2,0,0,0,0,0,1 +3176,43,18,74,92009,4,0.40,1,0,0,0,0,0,0 +3177,48,24,14,91330,3,0.40,1,0,0,0,0,1,0 +3178,30,4,83,91007,2,1.50,3,199,0,0,0,0,1 +3179,46,21,71,95814,4,1.90,3,0,0,0,0,0,0 +3180,43,17,53,90245,2,0.70,1,130,0,1,0,1,0 +3181,27,3,103,92121,2,0.60,1,84,0,0,0,0,0 +3182,39,15,109,95827,1,1.70,1,0,0,0,0,1,0 +3183,58,33,60,94304,2,1.90,2,94,0,1,0,1,0 +3184,44,17,12,94542,3,0.67,2,0,0,0,0,1,0 +3185,39,15,141,92354,2,8.00,1,0,0,0,0,1,0 +3186,35,10,128,92843,1,3.80,1,0,0,0,0,1,0 +3187,41,16,98,95192,3,1.00,1,296,0,0,0,0,0 +3188,43,18,41,94035,1,0.50,3,0,0,0,0,0,0 +3189,55,25,90,90717,2,4.50,3,0,0,0,0,0,1 +3190,32,6,31,92675,1,0.30,1,0,0,0,0,0,0 +3191,56,26,74,91335,1,3.00,3,0,0,0,0,0,0 +3192,30,5,83,93101,4,1.80,3,0,0,0,0,0,1 +3193,65,39,35,94005,1,0.50,3,0,0,0,0,0,0 +3194,31,7,140,95616,1,4.00,1,0,0,0,0,0,1 +3195,41,15,65,90019,3,0.50,3,0,0,0,0,0,0 +3196,55,29,35,90007,3,1.40,1,0,0,0,0,0,0 +3197,37,7,73,94043,4,1.80,3,0,0,0,0,1,1 +3198,34,10,29,93555,1,1.50,2,0,0,0,0,1,0 +3199,34,9,55,92122,4,2.00,2,147,0,0,0,0,1 +3200,33,9,20,95521,4,0.70,2,0,0,0,0,1,0 +3201,48,23,70,92122,1,2.80,2,0,0,0,0,0,0 +3202,28,3,81,92121,4,0.20,1,0,0,0,0,0,0 +3203,30,4,25,92173,2,0.30,1,0,0,1,0,1,0 +3204,44,20,119,92677,2,7.50,1,239,0,0,0,1,0 +3205,61,35,49,90095,4,1.70,2,185,0,0,0,0,0 +3206,59,33,38,92407,1,1.40,1,0,0,0,0,1,1 +3207,33,7,80,91103,2,1.50,3,0,0,0,0,1,1 +3208,56,32,84,93407,1,4.30,1,0,0,0,0,1,1 +3209,53,29,61,95032,4,1.60,2,0,0,0,0,1,0 +3210,42,16,173,91355,2,1.50,2,373,1,0,1,1,1 +3211,43,19,60,94301,2,2.50,1,0,0,1,0,0,0 +3212,35,9,83,90277,2,4.50,3,0,0,0,0,1,0 +3213,61,35,59,92697,1,2.80,2,0,0,0,0,0,0 +3214,39,9,32,90212,3,2.00,3,116,0,0,0,1,0 +3215,61,37,33,91775,3,0.10,3,0,0,0,0,1,0 +3216,40,15,19,90630,4,0.20,3,0,0,0,0,1,0 +3217,34,8,14,95014,4,0.30,1,0,0,0,0,0,0 +3218,65,39,94,93022,4,4.10,1,120,1,0,1,1,1 +3219,40,16,154,94122,2,6.10,1,325,0,0,0,1,0 +3220,39,15,33,92346,1,2.00,2,0,0,0,0,0,0 +3221,61,35,28,93302,2,0.20,3,135,0,0,0,1,0 +3222,40,16,44,93407,1,1.80,1,0,0,1,0,1,0 +3223,49,23,81,93107,2,0.80,3,0,0,0,0,0,0 +3224,43,18,29,95126,1,0.50,3,0,0,0,0,1,0 +3225,45,21,58,94025,3,0.30,3,0,0,1,0,1,0 +3226,52,28,38,95064,4,0.90,2,0,0,0,0,0,1 +3227,32,8,82,93943,3,1.50,1,0,0,0,0,1,1 +3228,31,7,18,94720,1,0.40,3,0,0,0,0,1,0 +3229,27,2,45,94305,2,1.70,2,0,0,0,0,0,1 +3230,33,9,64,92507,4,3.40,1,0,0,0,0,0,0 +3231,65,40,48,94708,3,2.40,1,0,0,0,0,0,1 +3232,62,37,24,90717,1,0.30,3,0,0,1,0,1,0 +3233,55,25,65,92093,4,2.00,3,0,0,0,0,1,0 +3234,46,20,111,95037,1,0.00,1,329,0,0,0,0,0 +3235,37,12,114,91107,3,0.60,2,0,0,0,0,1,0 +3236,60,35,39,91711,2,1.60,3,0,0,0,0,1,0 +3237,44,14,19,94112,1,0.75,3,0,0,0,0,0,1 +3238,35,9,22,94085,3,0.10,2,0,0,0,1,1,1 +3239,52,28,49,94928,4,1.10,2,0,0,0,0,1,0 +3240,30,4,40,90095,1,0.30,1,0,0,0,0,1,0 +3241,62,36,63,93407,1,1.60,1,118,0,0,0,1,0 +3242,41,15,55,94305,1,2.80,1,0,0,0,0,0,0 +3243,38,14,33,92096,1,2.00,2,0,0,0,0,1,0 +3244,52,26,31,92054,4,1.50,3,0,0,0,0,1,0 +3245,48,24,24,92624,4,0.20,1,0,0,0,0,1,0 +3246,47,22,81,90009,4,3.60,3,0,0,0,0,1,1 +3247,41,17,81,95422,1,0.80,2,223,0,0,0,1,0 +3248,44,20,113,95032,2,3.30,1,0,0,0,0,1,1 +3249,31,6,92,92037,2,3.30,1,0,0,0,0,0,0 +3250,50,25,81,92806,1,1.20,1,0,0,0,0,0,0 +3251,36,11,101,90212,3,1.20,3,0,0,1,0,0,1 +3252,52,26,78,90720,3,3.00,2,0,0,0,0,0,1 +3253,62,38,78,92521,2,0.00,3,0,0,0,0,1,0 +3254,55,30,35,94025,1,1.50,2,118,0,0,0,0,1 +3255,61,37,9,93907,2,0.30,3,0,0,0,0,1,0 +3256,34,7,82,95741,4,2.00,2,0,0,0,0,1,1 +3257,34,9,41,94305,1,2.50,3,0,0,0,0,0,0 +3258,59,35,84,92407,1,1.80,3,0,0,0,0,1,0 +3259,41,17,42,91910,4,2.20,2,185,0,1,0,1,0 +3260,33,8,54,92251,3,2.30,1,0,0,0,0,0,1 +3261,55,30,84,95821,2,0.00,3,0,0,0,0,0,0 +3262,64,40,131,91103,1,3.80,1,0,0,0,0,0,0 +3263,44,19,85,90024,2,3.80,3,0,0,0,0,1,0 +3264,32,8,84,92093,4,3.40,1,0,0,0,0,1,0 +3265,67,41,114,95616,4,2.40,3,0,0,0,0,1,0 +3266,40,14,61,94612,3,0.50,3,0,0,0,0,1,0 +3267,57,31,39,92821,1,2.20,3,0,0,0,0,1,1 +3268,59,35,21,95818,2,1.00,1,120,0,0,0,1,0 +3269,43,17,111,91423,4,5.40,3,0,1,0,0,1,0 +3270,58,34,68,94305,2,2.80,1,113,0,0,0,0,0 +3271,50,23,179,94609,4,3.60,2,0,1,0,0,1,0 +3272,52,27,93,90291,4,4.10,2,0,1,0,0,0,1 +3273,35,9,85,92121,2,1.80,1,0,0,0,0,0,0 +3274,40,15,180,90095,1,4.10,1,0,0,0,0,0,0 +3275,31,5,110,92123,2,1.50,3,0,0,0,0,1,0 +3276,32,8,65,95134,1,1.20,1,268,0,0,0,1,0 +3277,55,31,159,92123,1,3.90,3,0,1,0,0,0,0 +3278,43,19,81,92121,2,3.20,1,0,0,0,0,1,0 +3279,31,6,132,94571,1,3.80,1,0,0,0,0,1,0 +3280,26,-1,44,94901,1,2.00,2,0,0,0,0,0,0 +3281,58,33,98,90277,1,2.60,1,0,0,0,0,0,0 +3282,51,25,62,95014,2,1.50,2,0,0,0,0,1,1 +3283,45,21,91,95054,1,4.70,1,0,0,0,0,1,0 +3284,56,30,29,92152,4,0.70,2,87,0,0,0,1,0 +3285,25,-1,101,95819,4,2.10,3,0,0,0,0,0,1 +3286,38,13,65,91706,3,0.70,2,0,0,0,0,1,0 +3287,62,36,58,95020,1,2.80,2,0,0,0,0,0,1 +3288,39,13,32,90747,2,0.80,3,0,0,0,0,1,0 +3289,56,30,140,94122,4,0.50,1,292,1,0,0,0,0 +3290,50,25,44,94303,1,0.30,1,187,0,0,0,1,1 +3291,52,27,113,92038,1,0.10,3,0,0,0,0,0,0 +3292,53,28,38,94998,1,1.30,2,0,0,0,0,1,0 +3293,25,-1,13,95616,4,0.40,1,0,0,1,0,0,0 +3294,44,20,62,94939,2,2.50,1,0,0,1,0,1,0 +3295,42,12,29,93611,3,2.00,3,0,0,0,0,0,0 +3296,42,16,141,94960,3,4.00,2,0,1,0,0,0,0 +3297,63,37,132,94080,1,4.40,2,0,1,0,0,1,0 +3298,57,32,23,93407,1,0.30,3,0,0,0,0,1,1 +3299,56,32,11,94110,2,0.30,1,89,0,0,0,0,0 +3300,60,34,90,92192,4,1.90,2,0,0,0,0,1,0 +3301,62,38,43,92354,1,1.90,2,0,0,0,0,1,0 +3302,48,22,59,90086,4,2.60,1,0,0,0,0,1,1 +3303,37,11,28,94501,2,0.80,3,0,0,0,0,0,0 +3304,55,29,28,94539,2,0.70,2,82,0,0,0,1,1 +3305,42,17,108,95120,3,1.00,1,383,0,0,0,1,0 +3306,39,13,78,95616,1,2.80,3,0,0,0,0,0,0 +3307,47,22,65,90840,1,2.40,1,0,0,0,0,1,0 +3308,34,10,25,92038,4,1.00,1,0,0,0,0,1,0 +3309,48,23,108,92120,2,3.80,3,0,0,0,0,0,1 +3310,52,27,43,94611,4,0.20,2,0,0,0,0,1,0 +3311,53,29,95,94720,4,1.00,2,0,0,0,0,1,1 +3312,49,25,24,95819,1,0.30,1,0,0,0,0,0,0 +3313,47,22,190,94550,2,8.80,1,0,0,0,0,0,0 +3314,48,24,24,91950,1,0.90,3,0,0,0,0,0,0 +3315,38,13,41,90073,4,1.70,1,0,0,0,0,1,0 +3316,48,22,80,94720,3,1.10,1,0,0,0,0,0,0 +3317,56,26,63,94501,3,2.00,3,0,0,0,0,1,0 +3318,65,41,79,90035,3,2.00,3,0,0,0,0,0,0 +3319,46,20,105,90089,4,3.20,1,0,1,0,0,0,0 +3320,60,35,153,95136,3,2.00,3,0,1,0,0,0,1 +3321,50,25,114,92104,1,0.60,1,0,0,0,0,0,1 +3322,41,15,120,94521,1,5.20,1,0,0,0,0,1,0 +3323,41,16,104,92008,1,4.00,3,0,0,0,1,1,1 +3324,60,35,20,92110,1,1.30,1,0,0,0,0,1,0 +3325,57,31,41,91401,1,1.40,1,0,0,1,0,1,0 +3326,48,23,35,93302,2,1.30,1,0,0,0,0,0,0 +3327,53,27,174,91006,1,2.90,2,0,1,0,0,1,0 +3328,42,18,164,93407,1,1.30,3,0,1,1,1,1,1 +3329,45,20,22,90230,1,0.10,1,0,0,0,0,0,0 +3330,35,10,132,94123,1,3.80,1,82,0,0,0,0,1 +3331,34,9,32,95054,4,1.10,3,0,0,0,0,1,0 +3332,67,42,21,94607,3,0.10,3,0,0,0,0,0,1 +3333,36,9,49,94402,2,1.67,2,0,0,0,0,0,1 +3334,37,13,79,91711,4,0.10,2,280,0,0,0,1,0 +3335,40,14,30,94720,2,0.80,3,86,0,0,0,0,0 +3336,35,10,118,92069,2,7.80,1,358,0,0,0,0,0 +3337,60,34,11,94305,4,0.70,3,0,0,0,0,1,0 +3338,59,29,61,92008,3,2.00,3,0,0,0,0,1,0 +3339,35,9,43,92037,4,1.20,2,0,0,1,0,1,0 +3340,27,1,141,95135,4,5.10,3,354,1,0,0,0,0 +3341,29,3,54,94104,4,1.80,3,0,0,0,0,0,0 +3342,35,9,33,91125,2,0.30,1,0,0,1,0,1,0 +3343,38,13,84,91330,3,1.20,3,121,0,0,0,1,1 +3344,62,37,125,94801,1,1.00,3,0,1,0,0,1,0 +3345,43,19,110,90639,1,3.40,1,0,0,0,0,0,1 +3346,35,11,14,94720,4,1.00,1,0,0,0,1,1,1 +3347,41,15,65,92037,2,2.80,1,0,0,0,0,1,1 +3348,65,41,78,92109,3,2.00,3,0,0,0,1,1,1 +3349,61,35,18,94303,3,0.30,3,0,0,0,0,0,0 +3350,55,25,95,92407,2,4.50,3,275,0,0,0,0,0 +3351,28,3,95,90245,2,1.80,2,0,0,0,0,0,0 +3352,52,26,191,92121,1,1.70,1,0,0,0,0,1,0 +3353,34,4,19,92521,1,0.67,3,83,0,0,0,1,0 +3354,49,23,19,94521,4,0.60,3,0,0,0,0,1,1 +3355,42,18,39,92703,1,0.30,3,0,0,0,0,1,0 +3356,49,23,93,90036,1,2.40,1,0,0,0,0,1,1 +3357,49,23,115,95051,3,4.60,3,0,1,0,0,0,0 +3358,32,6,112,94111,1,2.70,2,408,0,1,1,1,1 +3359,59,35,40,94536,4,0.40,1,0,0,0,0,0,0 +3360,43,19,45,91773,3,0.60,2,0,0,0,0,0,0 +3361,48,24,133,90740,1,5.00,1,0,0,0,0,0,0 +3362,31,5,85,94117,3,1.60,1,87,0,0,0,1,1 +3363,30,4,18,90277,2,0.30,2,0,0,0,0,1,0 +3364,58,34,54,93003,4,1.30,2,0,0,0,0,1,0 +3365,41,15,41,94143,2,2.40,2,105,0,0,0,0,0 +3366,38,8,21,95060,1,0.67,3,0,0,0,0,1,0 +3367,33,9,152,90024,1,6.00,1,0,0,0,0,1,1 +3368,51,27,53,92122,1,1.60,2,0,0,0,0,1,0 +3369,45,18,163,94720,3,5.33,2,0,1,0,1,0,1 +3370,34,10,84,95616,4,0.10,2,0,0,0,0,1,0 +3371,39,13,59,90033,3,0.90,3,199,0,1,0,1,0 +3372,44,18,33,95351,3,0.50,2,0,0,0,0,0,0 +3373,55,29,81,94928,4,4.90,1,209,0,0,0,1,0 +3374,28,2,182,92660,3,7.20,2,442,1,0,1,1,1 +3375,57,31,61,91360,1,2.20,3,0,0,0,0,0,0 +3376,43,18,88,90089,4,1.10,2,0,0,0,0,1,0 +3377,46,21,170,95136,2,2.80,1,0,0,0,0,0,0 +3378,35,10,83,95370,4,0.70,3,315,0,0,0,1,0 +3379,25,0,44,94536,4,0.60,2,0,0,0,0,0,1 +3380,65,41,83,94305,3,2.00,3,0,0,0,0,1,0 +3381,64,38,21,95422,1,0.80,2,76,0,0,0,0,1 +3382,39,15,143,91711,1,3.50,1,0,0,0,0,1,1 +3383,62,36,103,92182,2,2.80,1,0,0,1,1,1,0 +3384,46,22,135,95135,3,4.10,1,213,1,0,0,1,0 +3385,36,11,162,94583,1,8.60,1,153,0,1,0,1,0 +3386,42,17,73,90089,4,0.40,1,0,0,1,0,0,0 +3387,35,10,142,94061,4,0.80,3,0,1,0,0,0,0 +3388,63,37,25,94035,2,0.20,3,0,0,0,0,1,0 +3389,45,21,115,91320,2,3.30,1,85,0,0,0,1,0 +3390,27,3,88,92182,3,0.80,1,238,0,0,0,0,0 +3391,29,3,73,94720,3,0.30,3,0,0,0,0,0,0 +3392,55,29,94,94109,1,0.80,3,221,0,0,0,0,0 +3393,32,7,58,92612,1,1.00,1,0,0,0,0,1,0 +3394,37,11,81,95123,3,0.90,2,0,0,0,0,1,1 +3395,25,-1,113,90089,4,2.10,3,0,0,0,0,1,0 +3396,41,16,35,94061,2,1.40,2,135,0,0,0,0,0 +3397,52,28,65,93106,1,0.00,1,0,0,0,0,1,1 +3398,31,6,170,94010,2,6.70,1,137,0,0,0,1,0 +3399,40,14,62,92028,2,2.40,2,0,0,0,0,1,1 +3400,54,29,54,94720,2,2.10,3,97,0,0,0,0,0 +3401,48,22,39,94065,1,1.20,2,0,0,0,0,0,0 +3402,39,15,28,95818,1,1.40,3,118,0,0,0,1,1 +3403,64,40,95,90095,2,0.00,3,0,0,0,0,1,1 +3404,54,29,82,94709,3,3.70,2,0,1,0,0,1,0 +3405,39,14,21,94303,1,0.60,3,101,0,0,0,0,0 +3406,55,30,50,94061,2,2.10,3,0,0,0,0,1,0 +3407,42,12,34,92177,3,2.00,3,0,0,0,0,0,1 +3408,58,32,19,90405,4,0.70,3,0,0,0,0,0,0 +3409,45,21,71,90029,4,1.90,1,0,0,0,0,1,0 +3410,29,5,113,95351,2,2.00,2,84,0,0,0,1,1 +3411,36,11,9,90230,4,0.20,3,0,0,0,0,1,0 +3412,63,37,118,94010,1,2.00,1,427,0,0,0,0,0 +3413,55,29,79,90029,4,4.90,1,0,0,0,0,0,0 +3414,54,24,72,95123,3,1.40,3,0,0,0,0,0,1 +3415,61,36,18,95010,1,1.30,1,0,0,0,0,0,0 +3416,36,12,93,90720,2,2.20,1,0,0,0,0,1,1 +3417,61,37,62,94111,1,0.00,2,244,0,0,0,1,0 +3418,39,12,23,90024,3,1.00,2,0,0,0,0,1,1 +3419,57,31,40,91775,3,1.40,3,0,0,0,1,1,1 +3420,35,10,34,95503,4,1.70,1,87,0,0,0,1,1 +3421,66,41,114,94305,1,0.80,3,0,0,0,0,1,1 +3422,49,23,125,90245,1,2.40,1,0,0,0,0,0,1 +3423,48,23,41,92677,1,1.40,3,0,0,0,0,0,1 +3424,61,35,38,93009,2,1.00,3,0,0,0,0,0,0 +3425,44,19,45,94539,4,0.00,2,0,0,0,0,1,1 +3426,23,-1,12,91605,4,1.00,1,90,0,0,0,1,0 +3427,31,5,115,90025,2,1.50,3,189,0,0,0,1,0 +3428,39,15,175,94080,2,8.00,1,0,0,0,0,1,0 +3429,45,21,24,93106,1,0.90,3,0,0,0,0,0,0 +3430,39,14,28,91320,2,1.40,2,108,0,0,0,0,1 +3431,64,38,32,90291,2,0.30,1,0,0,0,0,1,1 +3432,64,38,63,94305,2,1.70,3,184,0,1,0,1,0 +3433,47,23,32,95370,1,1.00,1,0,0,0,0,0,1 +3434,34,9,60,94306,4,1.30,1,0,0,1,0,0,0 +3435,56,31,53,95521,2,1.60,3,78,0,0,0,0,0 +3436,33,8,58,92037,4,1.30,1,0,0,1,0,0,0 +3437,56,29,42,92104,4,2.50,2,0,0,0,0,0,0 +3438,57,31,39,94304,4,0.70,2,0,0,1,0,1,0 +3439,43,17,72,94806,1,2.80,1,271,0,0,0,1,0 +3440,43,17,80,95020,3,0.10,1,0,0,0,1,1,1 +3441,26,1,39,95133,4,0.60,2,0,0,0,0,0,1 +3442,64,40,18,94309,2,0.30,3,0,0,1,1,1,1 +3443,43,18,30,93940,1,0.50,3,0,0,0,0,1,0 +3444,44,18,54,90639,1,2.80,1,202,0,0,0,0,0 +3445,60,35,128,93101,1,0.90,1,0,0,0,0,1,0 +3446,37,13,38,94701,1,1.50,2,116,0,0,0,0,1 +3447,56,32,120,90232,1,7.40,1,186,0,0,0,1,0 +3448,54,29,25,90747,4,0.10,3,109,0,0,0,0,0 +3449,43,18,85,92606,4,1.90,3,110,0,0,0,1,1 +3450,57,32,135,90095,3,4.80,2,0,1,1,1,1,0 +3451,29,4,14,94590,4,0.50,3,0,0,0,0,0,1 +3452,54,30,70,92182,1,1.60,3,251,0,0,0,1,1 +3453,61,37,23,94720,3,0.40,2,0,0,0,0,0,0 +3454,29,3,31,94709,4,0.30,2,0,0,0,0,1,0 +3455,47,21,132,92120,1,0.30,1,0,0,0,0,1,0 +3456,43,19,28,93010,3,0.50,1,0,0,0,0,1,1 +3457,46,22,125,94536,2,4.70,3,0,1,0,0,1,0 +3458,55,31,91,94110,2,2.80,1,0,0,0,0,1,0 +3459,48,23,191,95053,2,2.80,1,231,0,0,0,0,1 +3460,26,1,88,94025,2,1.80,2,0,0,0,0,0,0 +3461,63,37,84,92691,4,2.40,3,0,0,0,0,1,1 +3462,57,27,64,92007,3,2.00,3,142,0,0,0,1,0 +3463,58,33,28,94608,2,0.50,2,146,0,1,0,1,0 +3464,28,3,149,92121,1,0.80,1,0,0,0,0,1,0 +3465,61,37,172,92612,4,4.25,1,0,1,0,1,1,1 +3466,65,41,42,95616,1,1.90,2,0,0,0,0,0,0 +3467,33,6,53,94122,2,1.00,2,96,0,0,0,0,1 +3468,63,37,149,90840,2,0.20,3,364,1,0,0,1,0 +3469,43,19,113,93933,2,1.80,2,0,0,0,0,0,1 +3470,26,2,79,95630,2,2.50,1,0,0,0,0,1,0 +3471,57,31,175,90503,2,0.50,1,429,0,0,0,1,1 +3472,50,25,38,95503,1,1.40,3,0,0,0,0,1,0 +3473,54,27,120,92672,4,3.00,2,431,1,0,0,1,0 +3474,59,34,52,92173,4,0.70,1,0,0,1,0,0,0 +3475,49,24,42,92121,2,0.70,2,0,0,0,0,1,0 +3476,54,30,13,92037,1,0.30,1,0,0,0,0,0,0 +3477,65,39,141,90280,2,6.90,1,0,0,1,0,1,0 +3478,34,10,131,94024,2,4.33,1,156,0,0,0,1,1 +3479,31,6,133,95747,1,1.50,3,0,1,0,0,0,0 +3480,31,6,64,94720,2,2.50,1,0,0,0,0,1,0 +3481,64,39,49,94591,2,1.50,1,0,0,1,0,1,0 +3482,52,26,34,93023,1,0.30,3,0,0,0,0,1,0 +3483,57,33,91,95133,1,4.30,1,81,0,1,0,0,0 +3484,60,36,195,90066,1,4.70,1,0,0,0,0,1,0 +3485,45,18,53,92104,3,2.50,2,112,0,0,0,0,0 +3486,39,13,39,92103,2,0.80,3,0,0,0,0,0,0 +3487,25,1,20,92806,4,1.00,1,0,0,0,0,0,1 +3488,29,4,104,91711,4,1.80,3,0,0,0,0,0,1 +3489,40,15,51,94117,2,1.10,2,131,0,0,0,1,0 +3490,36,12,154,91320,3,6.40,1,0,1,1,0,0,0 +3491,33,9,38,95814,1,1.33,1,115,0,0,0,0,0 +3492,51,27,12,92697,2,0.40,1,0,0,0,0,0,1 +3493,35,9,28,94546,1,0.60,3,0,0,0,0,0,1 +3494,54,28,33,94710,2,0.40,3,0,0,0,0,1,0 +3495,29,2,31,91330,4,1.50,2,0,0,0,0,0,0 +3496,32,8,44,91401,1,1.80,2,192,0,0,0,1,0 +3497,37,13,49,91711,4,2.00,3,192,0,0,0,0,0 +3498,55,31,134,92130,2,0.30,1,0,0,0,0,0,0 +3499,30,6,182,93561,4,0.80,3,94,1,0,0,1,0 +3500,49,23,114,94550,1,0.30,1,286,0,0,0,1,0 +3501,51,26,90,94110,1,2.80,2,0,0,0,0,1,1 +3502,65,39,105,91380,4,1.70,3,0,0,1,0,1,0 +3503,32,8,58,95616,3,2.00,1,90,0,0,0,1,0 +3504,29,3,53,95814,4,2.10,3,0,0,0,0,1,0 +3505,46,20,15,95370,4,0.60,3,0,0,1,0,1,0 +3506,64,39,103,90304,1,0.80,3,0,0,0,0,1,1 +3507,27,1,58,95827,4,1.80,2,154,0,0,1,1,1 +3508,50,23,83,91791,1,2.67,2,0,0,0,1,1,1 +3509,33,9,125,92182,1,4.30,3,0,1,0,0,1,0 +3510,38,12,61,91330,3,0.90,3,0,0,0,0,0,0 +3511,38,11,69,92124,3,2.33,2,0,0,0,0,0,0 +3512,37,11,89,94609,1,1.50,3,0,0,0,0,1,0 +3513,46,20,70,90405,4,2.90,1,0,0,0,0,0,1 +3514,31,4,39,94501,2,1.00,2,0,0,0,0,0,0 +3515,35,9,41,90024,4,1.20,2,0,0,0,0,1,0 +3516,50,26,148,94143,2,0.40,1,508,0,0,0,0,0 +3517,45,21,38,93943,3,0.60,2,148,0,0,0,1,0 +3518,30,6,95,94234,1,3.90,3,146,1,0,0,0,1 +3519,60,36,129,95039,2,6.00,1,0,0,0,0,0,0 +3520,31,5,84,94720,4,1.80,2,0,0,1,0,1,0 +3521,60,35,29,92126,3,1.30,2,0,0,0,0,0,0 +3522,36,10,30,91711,2,0.80,3,0,0,0,0,1,0 +3523,64,40,90,94028,2,0.00,3,134,0,0,0,0,0 +3524,29,4,150,91302,1,0.80,1,0,0,0,0,0,1 +3525,58,33,15,94583,4,0.90,2,0,0,0,0,0,0 +3526,59,34,13,96651,4,0.90,2,0,0,0,0,0,0 +3527,58,33,9,95008,2,0.20,3,0,0,0,0,1,0 +3528,35,10,24,95054,4,1.10,3,0,0,0,0,0,0 +3529,43,17,41,90210,3,2.20,2,0,0,0,0,1,0 +3530,33,7,25,94132,4,1.00,1,0,0,0,0,1,1 +3531,54,28,49,90073,4,2.80,2,0,0,1,0,0,0 +3532,38,12,58,94542,3,0.90,3,128,0,0,0,0,1 +3533,38,12,141,94022,2,0.00,1,0,0,0,0,1,1 +3534,57,32,50,94545,4,2.10,1,211,0,0,0,0,0 +3535,34,10,61,95006,3,2.00,1,0,0,0,0,0,1 +3536,52,27,65,92104,1,1.20,1,0,0,0,0,1,1 +3537,50,24,112,94005,1,0.30,1,229,0,0,0,0,0 +3538,60,34,19,92093,3,0.30,3,0,0,0,0,1,0 +3539,26,0,23,93561,1,0.10,2,0,0,0,0,0,0 +3540,56,30,60,91380,1,2.20,3,0,0,0,0,0,0 +3541,39,15,30,94305,4,0.30,1,0,0,1,0,0,1 +3542,45,20,144,92106,4,5.40,1,210,1,0,0,1,0 +3543,30,5,118,92182,4,3.00,3,0,1,0,0,1,0 +3544,37,11,194,94303,2,0.00,1,0,0,0,0,0,0 +3545,45,19,109,92037,3,1.10,1,0,0,0,0,0,0 +3546,48,22,174,95827,1,2.40,1,0,0,0,0,1,0 +3547,65,40,34,94720,1,1.10,3,119,0,0,0,1,1 +3548,46,20,84,92354,3,0.70,2,0,0,0,0,1,0 +3549,40,16,41,91107,1,2.00,2,0,0,0,0,0,1 +3550,33,7,92,90840,3,1.60,1,0,0,0,0,0,0 +3551,40,10,19,94609,1,0.75,3,116,0,0,0,0,0 +3552,60,35,55,92807,3,0.50,2,172,0,0,0,0,0 +3553,51,27,22,93106,4,0.50,2,0,0,0,0,1,1 +3554,41,16,155,95070,1,7.00,1,0,0,0,0,0,0 +3555,37,13,72,92407,4,2.00,3,0,0,1,0,0,0 +3556,35,9,81,91107,1,2.70,2,0,0,0,0,1,0 +3557,35,11,30,94303,1,1.70,1,0,0,1,0,0,1 +3558,46,20,54,90755,4,2.90,1,189,0,0,0,1,1 +3559,60,34,60,94065,3,2.50,1,0,0,0,0,1,0 +3560,51,25,68,94065,1,1.50,2,0,0,0,0,0,0 +3561,31,5,65,94591,4,2.20,2,126,0,0,0,1,0 +3562,30,6,31,94720,3,1.00,2,142,0,0,0,0,0 +3563,32,8,169,94596,1,6.50,3,272,1,1,1,1,0 +3564,53,27,139,94998,1,0.90,3,0,1,0,0,0,0 +3565,33,7,29,94720,1,0.60,3,0,0,0,0,0,0 +3566,40,15,43,92120,2,1.10,2,0,0,0,0,0,1 +3567,57,33,80,92064,2,2.80,1,0,0,0,0,1,1 +3568,51,26,43,91040,1,1.30,2,123,0,0,0,1,0 +3569,30,4,194,93407,2,4.50,1,0,0,0,0,0,1 +3570,41,15,24,92130,2,0.80,3,0,0,1,0,1,0 +3571,54,29,32,91107,2,0.60,3,0,0,0,0,1,1 +3572,42,18,153,93955,3,5.60,1,416,1,0,0,0,0 +3573,30,6,30,90245,1,0.40,3,0,0,0,0,1,1 +3574,60,36,165,90095,3,5.60,1,0,1,0,0,0,1 +3575,56,30,64,95123,3,0.30,2,0,0,0,0,0,1 +3576,63,38,15,94305,4,0.60,2,83,0,0,0,0,0 +3577,56,30,70,90245,3,0.30,2,0,0,0,0,0,0 +3578,39,9,32,91016,3,2.00,3,0,0,0,0,1,0 +3579,29,5,128,91302,2,4.10,2,209,1,0,0,1,0 +3580,28,2,84,94305,1,2.90,3,102,0,1,1,0,1 +3581,41,16,62,94553,2,2.20,3,0,0,0,0,1,1 +3582,28,4,33,91330,3,1.00,2,0,0,0,0,0,1 +3583,49,25,65,92354,1,0.00,1,0,0,0,0,1,0 +3584,30,3,33,95112,4,1.50,2,85,0,0,0,0,0 +3585,63,37,15,92121,1,0.80,2,115,0,0,0,1,0 +3586,45,18,45,92037,3,1.00,2,0,0,0,0,1,0 +3587,40,15,132,94131,2,3.90,1,0,0,0,0,1,0 +3588,28,4,29,94080,3,0.10,2,0,0,0,0,1,0 +3589,62,38,65,91768,1,0.00,2,0,0,0,0,1,0 +3590,38,12,52,92807,2,2.40,2,147,0,0,0,0,0 +3591,32,7,64,92630,2,0.10,1,0,0,0,0,1,1 +3592,58,32,73,94109,2,2.30,3,224,0,0,0,1,1 +3593,33,3,20,94704,1,0.67,3,0,0,0,0,0,0 +3594,60,34,44,90018,2,0.30,1,192,0,0,0,1,0 +3595,34,8,79,95616,1,2.50,1,0,0,0,0,1,0 +3596,38,14,104,90025,2,1.80,2,79,0,0,0,0,0 +3597,44,20,88,94720,1,4.70,1,0,0,0,0,0,0 +3598,56,26,51,92028,3,2.00,3,0,0,0,0,1,0 +3599,37,11,61,95120,3,0.90,2,0,0,0,0,0,0 +3600,45,19,23,93101,2,0.10,3,91,0,0,1,1,1 +3601,44,20,38,90018,2,2.10,3,95,0,0,0,1,0 +3602,37,13,75,94305,3,2.60,2,0,0,1,0,0,0 +3603,47,21,42,95841,4,0.10,1,0,0,0,0,1,1 +3604,51,25,45,92407,4,0.10,1,0,0,0,0,1,1 +3605,63,38,59,92612,3,0.50,2,0,0,0,0,1,0 +3606,61,31,130,92333,2,2.60,3,0,1,0,0,0,0 +3607,43,18,9,96145,2,0.00,3,96,0,0,0,1,1 +3608,41,15,62,90401,3,0.90,3,0,0,0,0,0,0 +3609,59,35,202,94025,1,4.70,1,553,0,0,0,0,0 +3610,29,5,162,94022,1,4.30,1,0,0,0,0,0,1 +3611,32,6,93,90029,3,1.60,1,79,0,0,0,1,0 +3612,64,39,145,92705,1,0.90,1,0,0,0,0,0,0 +3613,50,25,99,90245,1,4.60,1,368,1,1,1,0,1 +3614,35,11,148,92672,1,5.80,3,0,1,0,0,1,0 +3615,34,10,154,94583,3,5.40,2,0,1,0,0,1,0 +3616,58,34,149,95616,2,6.00,1,0,0,0,0,1,1 +3617,41,15,69,92507,1,1.50,3,78,0,0,0,1,0 +3618,37,11,30,94304,2,0.30,1,146,0,0,0,0,0 +3619,35,8,48,92697,2,1.00,2,0,0,0,0,1,0 +3620,45,20,42,94703,1,0.30,3,0,0,0,0,1,0 +3621,53,29,132,95020,2,0.30,1,403,0,0,0,0,0 +3622,53,27,81,91730,3,1.70,2,193,0,0,0,1,0 +3623,54,29,60,94901,4,3.80,2,0,0,0,0,1,1 +3624,28,3,45,91105,4,1.70,2,95,0,0,0,0,0 +3625,58,28,70,92028,1,1.40,3,0,0,0,0,0,0 +3626,47,21,71,92037,4,2.90,1,0,0,0,0,1,0 +3627,24,-3,28,90089,4,1.00,3,0,0,0,0,0,0 +3628,27,1,83,90034,2,0.20,1,0,0,0,0,0,1 +3629,42,18,131,94949,1,3.40,1,0,0,0,0,0,1 +3630,50,26,82,95051,1,0.00,1,0,0,0,0,1,1 +3631,41,16,79,95020,1,4.00,3,225,0,0,0,1,0 +3632,46,21,51,90089,4,1.90,3,0,0,0,0,0,0 +3633,46,20,111,95307,2,6.30,1,0,0,0,0,0,1 +3634,51,25,93,90048,1,0.30,1,0,0,0,0,1,0 +3635,59,35,73,90009,4,2.30,3,0,0,0,0,0,0 +3636,58,33,24,95616,2,0.50,2,0,0,0,0,1,0 +3637,37,11,64,96094,3,0.90,2,0,0,0,0,1,0 +3638,39,14,104,94608,3,1.00,1,242,0,0,0,1,0 +3639,47,22,38,92866,4,1.90,3,0,0,0,0,1,0 +3640,51,26,191,94063,1,8.10,1,0,0,1,0,1,0 +3641,64,34,53,95821,4,1.67,3,0,0,0,0,0,1 +3642,59,35,74,94402,4,2.30,3,0,0,0,0,0,0 +3643,55,29,21,92704,4,0.70,3,0,0,1,0,1,0 +3644,57,32,80,92606,3,1.60,3,144,0,0,0,1,1 +3645,59,33,41,91711,4,2.50,1,174,0,0,0,0,0 +3646,42,17,79,92103,1,3.70,3,0,0,1,0,0,1 +3647,34,9,141,92056,3,6.90,2,260,1,0,0,1,0 +3648,41,14,32,91605,3,1.00,2,0,0,0,0,0,1 +3649,43,13,38,95616,3,2.00,3,0,0,0,0,1,0 +3650,53,29,85,92691,3,1.80,2,0,0,0,0,1,0 +3651,47,21,93,91604,2,0.80,3,107,0,0,0,0,0 +3652,49,23,140,90504,1,1.90,3,0,1,0,0,0,1 +3653,35,9,69,94704,4,2.20,2,0,0,0,0,0,1 +3654,52,27,32,92521,2,2.00,2,0,0,0,0,0,1 +3655,53,28,61,94061,4,0.90,1,177,0,0,0,0,0 +3656,48,22,125,90086,1,2.40,1,0,0,0,0,1,0 +3657,35,8,30,95014,4,1.00,2,0,0,1,0,0,0 +3658,52,26,104,94025,2,2.40,2,0,0,0,0,1,1 +3659,60,35,24,92612,1,0.10,1,0,0,0,0,0,0 +3660,33,7,22,94002,1,0.40,2,0,0,0,0,0,0 +3661,38,12,59,93401,2,2.40,2,0,0,0,0,0,0 +3662,29,4,120,94553,1,4.10,2,0,1,1,1,0,1 +3663,35,9,164,94305,2,0.00,1,500,0,0,0,0,0 +3664,26,2,60,94111,4,1.60,1,0,0,0,1,1,1 +3665,48,24,43,91791,3,1.90,2,0,0,0,0,1,0 +3666,43,19,70,91711,3,2.33,1,0,0,1,0,0,0 +3667,60,35,51,94143,2,2.80,1,0,0,0,0,1,0 +3668,27,3,59,94590,4,1.60,1,0,0,0,0,1,0 +3669,38,13,129,92037,4,0.30,3,75,1,0,0,1,0 +3670,40,15,22,95616,2,1.40,2,0,0,0,0,1,1 +3671,38,14,29,94402,4,0.40,2,0,0,0,0,1,0 +3672,50,25,18,93106,1,0.40,3,0,0,0,0,1,0 +3673,38,13,65,91320,3,0.50,3,0,0,0,0,1,0 +3674,34,9,65,95134,4,1.30,1,0,0,0,0,0,1 +3675,42,16,38,93437,1,0.20,1,0,0,1,0,0,0 +3676,60,34,110,92126,2,2.00,1,0,0,0,0,1,0 +3677,62,37,22,95818,1,1.50,2,111,0,0,0,1,0 +3678,59,33,43,94234,2,0.30,1,0,0,0,0,0,1 +3679,49,25,30,92093,4,0.60,1,0,0,0,0,0,0 +3680,49,23,134,90095,2,6.30,1,0,0,0,0,1,0 +3681,36,11,32,90064,3,1.30,1,0,0,0,0,0,0 +3682,33,9,139,95054,1,4.30,1,0,0,0,0,0,0 +3683,43,17,45,95051,2,0.70,1,0,0,0,0,0,0 +3684,53,27,62,95070,3,3.00,2,0,0,1,0,0,0 +3685,57,31,51,92093,4,1.70,2,103,0,0,0,1,0 +3686,53,27,93,94588,1,0.80,3,313,0,0,0,0,0 +3687,60,35,122,92521,1,1.30,1,0,0,0,0,0,0 +3688,34,10,45,93943,1,1.33,1,0,0,0,0,0,0 +3689,51,26,179,90245,1,8.10,1,0,0,1,0,1,0 +3690,36,12,64,94708,3,2.80,1,205,0,0,0,0,1 +3691,63,39,41,95449,2,1.10,1,0,0,0,0,0,0 +3692,37,13,58,95211,2,0.60,3,0,0,0,0,0,1 +3693,57,33,64,94132,4,2.20,1,0,0,0,0,1,0 +3694,52,27,28,93117,3,1.70,2,0,0,0,0,0,0 +3695,38,8,21,92037,1,0.67,3,0,0,0,0,1,0 +3696,61,35,60,90272,1,2.80,2,0,0,0,0,1,0 +3697,31,5,78,94309,2,0.20,1,0,0,0,0,0,1 +3698,39,13,59,95616,3,0.50,3,0,0,0,0,0,0 +3699,38,12,59,96001,3,0.50,3,0,0,1,1,1,1 +3700,46,22,83,94501,4,1.40,2,0,0,0,0,1,1 +3701,48,22,128,94608,1,5.70,1,0,0,1,0,0,0 +3702,58,33,95,90503,1,2.60,1,0,0,0,0,1,0 +3703,50,25,160,93108,4,4.30,3,410,1,0,0,0,0 +3704,67,41,78,94301,4,2.40,3,0,0,1,0,0,0 +3705,36,11,184,91304,2,5.10,2,0,1,0,0,0,0 +3706,30,4,30,91770,3,1.00,1,0,0,0,0,1,0 +3707,58,33,51,94305,2,1.60,3,123,0,0,0,1,0 +3708,43,18,35,92647,1,0.60,3,0,0,0,0,0,0 +3709,31,1,74,92116,4,4.00,3,0,0,0,0,0,0 +3710,37,11,43,92521,4,1.20,2,0,0,1,0,0,0 +3711,49,22,23,90032,2,1.00,2,0,0,0,0,1,1 +3712,27,1,20,94720,4,0.40,1,99,0,0,0,1,0 +3713,50,25,112,92154,1,0.60,1,0,0,0,0,0,0 +3714,46,20,74,90064,3,0.70,2,0,0,0,0,1,1 +3715,49,23,65,94720,2,0.40,3,232,0,0,0,0,1 +3716,29,5,124,92037,2,0.20,1,0,0,0,0,0,1 +3717,55,29,65,91773,3,2.50,1,0,0,0,0,0,0 +3718,61,37,73,94550,3,2.00,3,285,0,0,0,0,0 +3719,45,19,8,92833,2,0.10,3,0,0,0,0,0,1 +3720,33,8,53,92126,3,2.30,1,76,0,0,0,1,0 +3721,63,39,131,92521,3,2.60,3,229,1,0,0,1,0 +3722,32,6,13,91040,4,0.30,1,0,0,1,1,1,1 +3723,42,17,60,93118,1,2.40,1,98,0,0,0,1,0 +3724,51,27,45,94022,1,1.60,2,82,0,0,0,1,0 +3725,44,20,39,93108,2,2.10,3,119,0,0,0,0,0 +3726,33,6,78,94305,4,2.00,2,0,0,0,0,0,0 +3727,39,13,43,94304,3,0.50,3,0,0,0,0,1,0 +3728,56,30,31,94117,2,0.30,1,109,0,1,1,1,1 +3729,28,3,118,91902,3,2.40,2,161,1,0,0,0,0 +3730,43,17,82,94040,3,0.10,1,0,0,0,0,1,0 +3731,30,6,112,92093,3,2.50,1,0,0,0,0,1,0 +3732,34,8,10,92867,1,0.40,2,0,0,0,0,1,0 +3733,26,1,18,92521,2,0.90,3,95,0,0,0,0,0 +3734,58,32,72,94105,3,0.30,2,0,0,0,0,1,0 +3735,43,19,72,95193,4,0.20,3,0,0,0,0,1,0 +3736,40,14,78,91103,1,5.20,1,0,0,0,0,1,0 +3737,54,30,78,96001,3,1.80,2,0,0,0,0,0,0 +3738,44,19,30,91423,1,0.50,3,0,0,0,0,1,0 +3739,54,28,45,95008,3,1.40,1,0,0,0,0,0,1 +3740,39,14,80,90502,2,0.40,1,0,0,0,0,0,0 +3741,59,35,174,92660,1,4.70,1,0,0,0,0,1,1 +3742,53,29,51,92152,2,3.20,3,0,0,0,0,1,0 +3743,32,8,181,94596,1,6.00,1,0,0,0,1,1,1 +3744,40,14,78,94720,4,1.40,2,194,0,0,0,1,1 +3745,54,29,79,90025,3,1.60,3,0,0,0,0,0,0 +3746,27,3,119,90640,1,5.40,1,118,0,0,0,1,0 +3747,63,39,49,93943,4,1.20,2,109,0,1,1,1,1 +3748,26,0,83,91360,3,3.90,2,0,1,0,0,1,0 +3749,33,7,100,94025,1,2.70,2,126,0,0,0,1,0 +3750,43,19,70,90095,3,2.33,1,0,0,0,0,1,0 +3751,57,32,52,90266,3,0.50,2,0,0,0,0,1,0 +3752,26,2,12,94591,4,1.00,1,0,0,0,0,1,0 +3753,55,30,82,93003,4,1.30,3,219,0,0,0,0,1 +3754,30,4,34,95351,2,0.30,2,0,0,0,0,1,1 +3755,63,37,112,93106,4,2.40,3,0,0,0,0,1,1 +3756,55,25,42,94115,3,1.00,3,0,0,0,0,1,0 +3757,35,11,83,92122,2,2.20,1,0,0,0,0,0,0 +3758,45,21,142,91101,1,1.40,2,0,1,0,0,1,0 +3759,47,23,199,94720,2,6.67,1,0,0,0,0,1,0 +3760,31,4,29,92093,4,1.50,2,121,0,0,0,1,1 +3761,56,26,70,91107,3,1.40,3,273,0,0,0,1,1 +3762,49,24,25,95831,2,0.70,3,0,0,0,0,1,0 +3763,53,27,84,95616,2,1.10,1,0,0,0,0,1,0 +3764,62,36,81,95051,3,4.40,1,0,0,0,0,0,1 +3765,63,37,15,94720,2,0.40,1,0,0,0,0,0,0 +3766,26,0,54,94706,3,0.30,3,0,0,0,0,1,0 +3767,59,35,108,90245,4,3.80,2,304,1,0,0,1,0 +3768,40,16,83,95819,4,2.67,1,0,0,0,0,1,1 +3769,42,16,62,94309,1,0.70,3,170,0,0,1,1,1 +3770,29,4,134,90095,2,3.30,1,204,0,0,0,0,0 +3771,40,16,75,94306,3,2.33,1,79,0,0,0,0,0 +3772,31,7,109,91711,2,2.00,2,341,0,0,0,0,1 +3773,35,10,152,94112,2,3.00,1,0,0,0,0,1,0 +3774,62,36,83,93940,4,2.40,3,0,0,1,0,0,0 +3775,51,26,52,92521,4,1.80,3,0,0,0,0,1,0 +3776,32,6,31,90275,2,2.00,3,0,0,0,0,1,1 +3777,27,3,135,93108,3,2.70,3,449,1,0,0,0,1 +3778,62,37,98,94706,1,0.90,1,151,0,0,0,1,0 +3779,66,41,14,95814,4,0.60,2,0,0,0,0,0,0 +3780,53,27,64,93407,4,2.60,1,0,0,0,0,1,1 +3781,49,25,109,92780,2,6.80,1,0,0,0,0,0,0 +3782,65,40,118,94104,1,1.30,1,333,0,0,1,1,1 +3783,30,5,80,91311,4,2.20,2,0,0,1,0,1,0 +3784,60,34,51,90028,3,1.40,3,0,0,0,0,0,0 +3785,30,6,115,94611,4,3.80,2,0,1,0,0,1,0 +3786,54,28,83,95841,1,2.40,1,0,0,0,0,1,0 +3787,54,28,90,91301,1,0.30,1,0,0,0,0,1,0 +3788,37,12,28,95616,4,1.70,1,0,0,1,1,1,0 +3789,32,7,82,95616,2,2.50,1,221,0,0,0,1,1 +3790,51,27,24,94301,3,0.40,1,0,0,0,0,1,1 +3791,46,22,71,92029,2,1.70,1,0,0,0,0,1,1 +3792,41,17,80,91330,1,0.30,1,0,0,0,0,0,0 +3793,62,36,109,92709,4,1.70,3,0,0,0,0,1,0 +3794,54,28,140,91711,1,2.90,1,0,0,0,0,1,0 +3795,52,27,39,92612,4,0.20,2,0,0,1,0,1,0 +3796,51,25,39,94010,1,1.20,2,98,0,0,0,1,0 +3797,24,-2,50,94920,3,2.40,2,0,0,1,0,0,0 +3798,61,35,31,92521,2,0.30,1,0,0,0,0,1,0 +3799,55,25,35,93943,3,1.00,3,144,0,0,0,1,1 +3800,37,11,44,93109,4,0.20,1,0,0,0,0,0,1 +3801,64,38,35,93955,1,0.50,3,0,0,0,0,1,0 +3802,34,8,20,95616,2,0.30,1,106,0,0,0,1,1 +3803,31,7,10,95616,4,0.70,2,0,0,0,0,1,0 +3804,42,18,83,96001,4,2.00,3,0,0,0,0,1,0 +3805,47,22,203,95842,2,8.80,1,0,0,0,0,1,0 +3806,29,5,84,93109,3,0.80,1,0,0,0,0,0,0 +3807,34,8,41,92096,4,0.80,1,0,0,0,0,0,0 +3808,36,11,164,95051,2,7.80,1,0,0,0,0,1,1 +3809,34,10,152,90089,2,6.50,1,0,0,0,0,0,0 +3810,26,2,62,94080,4,1.60,1,0,0,1,0,0,0 +3811,48,24,12,94707,4,1.00,1,89,0,0,0,0,0 +3812,47,23,28,94061,4,0.60,1,0,0,0,0,1,0 +3813,39,13,52,94720,1,2.00,1,0,0,0,0,0,1 +3814,62,37,19,91343,3,1.30,2,97,0,0,0,1,0 +3815,34,9,35,94304,3,1.30,1,0,0,0,0,0,0 +3816,43,19,28,95053,4,0.30,1,96,0,0,0,1,0 +3817,55,30,70,94904,3,2.00,2,0,0,0,0,1,1 +3818,65,40,140,92093,1,0.90,1,0,0,0,0,0,0 +3819,26,0,102,94305,4,2.30,3,0,0,0,0,0,0 +3820,57,27,50,93950,4,2.00,3,0,0,0,0,1,0 +3821,32,7,61,94102,3,2.30,1,205,0,0,0,1,1 +3822,35,9,188,92220,2,3.70,2,259,1,0,0,1,0 +3823,63,33,178,91768,4,9.00,3,0,1,0,0,0,0 +3824,49,25,44,94708,4,0.90,2,194,0,0,0,1,0 +3825,23,-1,12,95064,4,1.00,1,0,0,1,0,0,1 +3826,30,6,69,94305,4,3.40,1,188,0,0,0,0,1 +3827,43,19,132,90089,1,5.00,1,0,0,0,0,0,0 +3828,39,14,128,93943,2,3.90,1,196,0,0,0,1,0 +3829,31,6,44,95616,4,0.80,1,122,0,0,0,1,0 +3830,65,39,44,92038,1,0.50,3,0,0,0,0,1,1 +3831,34,8,34,92130,2,2.00,3,0,0,1,0,1,0 +3832,37,12,132,90089,2,3.90,1,0,0,0,0,0,0 +3833,62,38,158,90230,2,2.10,1,0,0,0,0,0,1 +3834,33,9,83,93943,1,0.10,1,0,0,0,0,1,0 +3835,48,22,28,94720,1,1.40,3,75,0,0,0,1,0 +3836,33,9,131,90065,3,2.20,3,0,1,1,0,0,0 +3837,45,19,31,95616,3,0.50,2,0,0,0,0,1,1 +3838,44,19,40,92350,4,0.00,2,0,0,0,0,1,0 +3839,37,11,71,94501,2,1.80,1,127,0,1,0,0,0 +3840,31,5,42,93010,2,2.00,3,0,0,0,0,1,0 +3841,56,31,35,95211,3,0.10,2,114,0,0,0,0,0 +3842,30,4,81,94305,2,0.20,1,0,0,0,0,1,0 +3843,61,35,91,95136,2,2.00,1,0,0,0,0,1,0 +3844,32,7,129,94720,4,5.20,2,0,1,0,0,0,1 +3845,51,27,75,95828,1,2.70,1,0,0,0,0,0,0 +3846,26,1,54,94061,4,0.60,2,230,0,0,0,0,0 +3847,31,5,43,94720,1,1.50,1,0,0,0,0,0,0 +3848,43,18,94,94110,4,1.10,2,0,0,0,0,0,0 +3849,57,32,84,93106,4,1.30,3,0,0,0,0,0,1 +3850,42,18,34,92653,1,2.00,2,0,0,1,0,0,0 +3851,48,23,15,94061,4,0.80,1,0,0,0,0,1,0 +3852,46,21,99,90277,2,3.80,3,194,0,0,0,1,0 +3853,33,7,15,92152,1,0.40,2,82,0,1,1,1,1 +3854,45,21,83,94105,4,2.00,3,0,0,0,0,1,0 +3855,31,6,83,94720,4,1.80,3,0,0,0,0,1,0 +3856,42,18,143,95630,1,1.70,1,0,0,1,0,1,0 +3857,56,30,81,90401,4,2.60,3,0,0,0,0,1,0 +3858,63,39,39,91711,1,1.90,2,0,0,0,0,0,0 +3859,42,18,158,92124,2,0.40,2,277,1,0,0,0,1 +3860,50,24,62,90245,1,1.40,3,0,0,0,0,0,0 +3861,31,6,64,92121,2,0.10,1,0,0,0,0,1,1 +3862,65,40,29,90025,1,1.50,2,0,0,0,0,0,0 +3863,60,34,64,94104,3,2.50,1,0,0,0,0,1,0 +3864,34,10,21,91770,4,0.70,2,0,0,0,0,1,0 +3865,62,32,142,95112,2,2.80,3,0,1,0,0,0,1 +3866,56,30,64,93105,3,2.50,1,0,0,0,0,0,0 +3867,51,25,40,91401,4,1.80,1,0,0,1,0,0,1 +3868,44,19,61,94080,3,2.70,2,0,0,0,0,0,0 +3869,41,16,44,92037,1,0.30,3,0,0,0,0,0,0 +3870,43,16,78,95670,3,2.67,2,161,0,0,0,1,1 +3871,25,0,25,94596,2,0.90,3,0,0,0,0,0,0 +3872,40,16,125,91304,2,1.90,1,0,0,0,0,0,1 +3873,53,29,63,94720,2,1.00,3,0,0,0,0,1,0 +3874,54,30,54,94550,1,1.60,3,185,0,0,0,1,0 +3875,36,12,92,94709,2,0.00,1,184,0,0,0,0,0 +3876,26,2,119,95351,2,0.60,1,381,0,0,0,1,1 +3877,35,11,40,91784,1,2.40,2,0,0,0,0,1,0 +3878,29,4,41,93105,1,1.00,1,0,0,0,0,0,0 +3879,35,11,81,92064,2,0.00,1,0,0,0,0,1,1 +3880,28,4,101,95136,3,2.50,1,270,0,0,0,0,0 +3881,48,24,25,90024,4,0.50,2,0,0,0,0,0,0 +3882,46,20,55,91016,1,1.50,2,0,0,1,0,0,0 +3883,31,7,43,92646,1,2.10,3,166,0,0,0,0,1 +3884,40,16,98,94534,2,1.80,2,98,0,0,0,1,0 +3885,27,1,112,91330,4,2.30,3,402,0,0,0,1,1 +3886,32,2,69,93943,4,4.00,3,102,0,0,0,1,0 +3887,67,43,79,95616,4,1.70,2,215,0,0,1,1,1 +3888,24,-2,118,92634,2,7.20,1,0,0,1,0,1,0 +3889,45,18,81,95133,3,2.67,2,251,0,0,0,1,1 +3890,26,0,19,93014,1,0.10,2,121,0,0,0,1,0 +3891,42,17,139,91101,2,2.90,3,0,1,0,0,1,0 +3892,65,40,63,94701,3,0.50,2,0,0,0,0,1,0 +3893,59,33,102,91763,2,1.40,1,0,0,0,0,1,0 +3894,30,5,40,92521,4,1.70,2,0,0,0,0,1,0 +3895,32,6,44,92886,1,0.30,1,81,0,0,0,1,1 +3896,36,12,59,94104,3,2.00,1,216,0,0,0,0,0 +3897,48,24,224,93940,2,6.67,1,0,0,0,1,1,1 +3898,56,31,64,90245,2,2.30,3,0,0,0,0,0,0 +3899,44,20,129,96001,2,3.30,1,0,0,0,0,1,0 +3900,60,34,43,92697,1,1.40,1,0,0,0,0,1,1 +3901,51,27,12,92834,3,0.40,1,0,0,1,1,1,1 +3902,34,10,53,94107,3,2.60,2,0,0,0,0,1,0 +3903,45,21,39,93305,2,2.10,3,0,0,0,0,0,1 +3904,47,23,65,93943,1,0.00,1,0,0,0,0,0,0 +3905,29,5,18,94122,1,0.40,3,94,0,0,0,1,1 +3906,52,28,55,94596,1,1.60,3,0,0,0,0,0,0 +3907,61,35,60,90245,1,2.50,3,0,0,0,0,1,0 +3908,40,14,42,91330,2,0.30,1,187,0,0,0,1,0 +3909,24,0,44,90638,3,0.10,2,0,0,0,0,0,0 +3910,33,7,111,90245,2,1.30,1,0,0,0,0,1,0 +3911,33,8,62,94596,1,1.00,1,0,0,0,0,1,0 +3912,52,26,44,94025,2,0.80,3,148,0,0,0,0,1 +3913,40,14,69,95348,1,1.50,3,0,0,0,0,0,0 +3914,45,20,62,92064,3,0.80,3,172,0,0,0,1,0 +3915,27,3,35,94080,1,1.80,2,0,0,0,0,0,0 +3916,38,13,91,92037,1,2.80,1,0,0,0,0,1,1 +3917,50,26,12,92121,1,0.20,1,96,0,0,0,0,0 +3918,41,15,89,94608,3,0.10,1,292,0,0,0,1,0 +3919,60,34,65,90024,4,1.70,2,0,0,1,0,1,0 +3920,64,34,179,90024,2,4.50,3,400,1,0,0,0,0 +3921,34,8,82,93106,2,1.50,3,0,0,1,1,1,1 +3922,30,6,48,95812,1,1.20,1,0,0,0,0,1,0 +3923,31,4,20,95616,4,1.50,2,0,0,0,0,1,0 +3924,41,15,91,90502,1,2.80,3,330,0,1,0,1,0 +3925,61,37,122,94609,2,6.00,1,0,0,0,0,1,0 +3926,42,18,22,90717,1,1.40,3,0,0,0,0,1,0 +3927,48,23,43,94301,2,1.30,1,0,0,0,0,1,0 +3928,59,34,38,90291,4,1.70,1,0,0,0,0,0,1 +3929,57,33,61,92115,3,2.67,1,0,0,0,0,1,0 +3930,37,13,33,91773,4,0.40,2,0,0,0,0,0,0 +3931,53,27,145,95605,1,2.90,1,345,0,0,0,0,0 +3932,53,27,170,95003,1,1.00,1,0,0,0,0,1,0 +3933,26,2,55,94305,3,0.70,2,0,0,0,0,1,0 +3934,39,14,40,91302,1,2.50,3,0,0,0,0,1,0 +3935,35,11,68,94923,2,0.00,1,126,0,0,0,0,1 +3936,59,33,53,90034,3,2.50,1,0,0,0,0,1,0 +3937,43,18,63,95616,3,0.80,3,0,0,1,0,0,0 +3938,39,15,123,91604,2,2.20,1,92,0,0,0,0,1 +3939,49,24,13,95929,2,0.00,1,0,0,0,0,1,0 +3940,47,23,12,92110,4,0.20,1,102,0,0,0,0,1 +3941,41,17,53,93727,2,2.50,1,102,0,0,0,1,0 +3942,57,33,79,94588,1,2.70,2,294,0,0,0,1,1 +3943,42,17,89,90095,1,0.10,2,170,0,0,0,1,0 +3944,61,36,188,91360,1,9.30,2,0,1,0,0,0,0 +3945,56,26,62,91320,3,1.40,3,0,0,0,0,1,0 +3946,29,3,123,92821,3,5.60,3,428,1,0,0,1,0 +3947,25,-1,40,93117,3,2.40,2,0,0,0,0,1,0 +3948,32,8,119,94710,4,5.00,3,0,1,0,0,1,0 +3949,37,12,123,94304,4,3.10,2,253,1,0,1,1,1 +3950,31,5,23,93407,1,0.40,2,0,0,0,0,1,1 +3951,38,14,62,94143,1,1.50,3,255,0,0,0,1,0 +3952,40,14,69,92870,3,2.10,1,106,0,0,0,1,0 +3953,61,36,124,94611,2,3.90,1,0,0,1,0,0,1 +3954,50,26,52,93555,4,0.10,3,0,0,0,0,0,0 +3955,32,7,134,93108,2,3.10,1,0,0,0,0,0,0 +3956,62,36,58,94501,1,0.80,2,0,0,0,0,0,0 +3957,62,37,45,90033,3,0.50,2,200,0,0,0,1,1 +3958,40,15,75,95449,4,1.10,2,0,0,0,0,1,0 +3959,59,34,23,90009,4,0.40,2,78,0,0,0,0,0 +3960,43,19,123,91107,3,1.30,1,0,1,0,0,1,0 +3961,62,37,48,92028,3,2.20,1,0,0,0,0,0,0 +3962,48,22,145,95482,1,0.30,1,140,0,0,0,1,0 +3963,29,5,31,93014,1,1.00,3,0,0,0,0,0,0 +3964,58,32,38,93106,3,2.20,3,0,0,0,0,1,0 +3965,43,18,78,94025,4,1.90,3,0,0,0,0,0,0 +3966,39,15,94,91941,2,1.90,1,0,0,0,0,1,0 +3967,33,7,84,95051,1,2.90,3,0,0,0,0,1,0 +3968,40,15,22,94306,1,0.60,3,0,0,0,0,1,0 +3969,28,3,78,93108,4,0.20,1,0,0,0,0,1,1 +3970,38,11,75,94305,3,2.33,2,0,0,0,0,1,0 +3971,65,40,71,95060,3,2.20,1,0,0,0,0,0,1 +3972,35,11,24,95616,1,0.50,3,0,0,0,0,1,1 +3973,29,5,112,94998,2,4.33,1,0,0,0,0,1,1 +3974,61,35,53,90064,1,2.80,2,167,0,0,0,1,0 +3975,46,21,41,94305,1,0.50,3,0,0,0,0,0,0 +3976,50,23,25,91330,1,0.50,2,0,0,0,0,1,0 +3977,60,33,42,90277,4,2.50,2,194,0,0,0,1,0 +3978,54,27,51,94309,3,1.00,2,113,0,1,1,1,1 +3979,43,18,19,92325,2,0.30,2,0,0,0,0,1,0 +3980,38,14,90,93010,2,0.00,1,258,0,1,1,1,1 +3981,46,22,89,92866,4,1.40,2,0,0,0,0,1,0 +3982,64,39,22,92691,3,0.50,1,0,0,1,1,1,1 +3983,24,0,119,94566,1,1.50,1,0,0,0,0,1,0 +3984,39,13,93,93555,4,3.60,3,0,1,0,0,1,0 +3985,34,8,18,95741,4,0.30,1,0,0,0,0,0,0 +3986,65,40,32,90095,1,1.10,3,120,0,0,0,1,0 +3987,38,14,182,92152,3,2.60,3,0,1,0,1,1,1 +3988,62,36,19,95833,2,0.20,3,0,0,0,0,1,1 +3989,59,35,85,91330,1,3.40,3,0,1,0,1,0,1 +3990,49,25,90,92709,4,1.40,2,0,0,1,0,1,0 +3991,57,32,59,95014,2,3.70,1,134,0,0,0,1,0 +3992,64,38,84,94571,1,2.00,1,0,0,0,0,0,0 +3993,47,22,95,93311,2,3.90,2,0,1,0,0,0,0 +3994,30,6,13,93555,3,0.90,3,0,0,0,0,1,0 +3995,42,18,88,92675,4,0.80,1,0,0,0,0,1,1 +3996,53,28,34,92697,2,0.60,3,0,0,0,0,1,1 +3997,50,24,11,94501,4,0.60,3,0,0,0,0,0,1 +3998,62,38,80,94545,4,1.70,2,0,0,0,0,0,0 +3999,34,10,41,94102,1,1.33,1,0,0,0,0,0,1 +4000,47,21,90,90245,2,0.80,3,0,0,0,0,0,0 +4001,62,37,93,93003,3,3.00,3,0,1,0,1,1,1 +4002,61,35,81,94709,4,1.90,2,0,0,0,0,0,0 +4003,59,34,60,94015,2,2.80,1,0,0,0,0,1,0 +4004,47,21,39,92612,3,0.60,2,0,0,0,0,1,1 +4005,65,39,22,92507,3,0.70,2,0,0,0,0,0,0 +4006,56,32,32,95827,2,0.80,1,79,0,1,0,1,0 +4007,56,32,28,92130,1,1.20,3,0,0,0,0,1,0 +4008,31,7,35,91745,2,1.00,2,0,0,0,0,0,1 +4009,61,31,154,94555,3,7.50,3,351,1,0,1,1,1 +4010,42,18,189,91605,2,7.60,1,0,0,0,0,1,0 +4011,44,19,40,94618,4,1.90,3,84,0,0,0,0,0 +4012,47,21,88,94304,2,1.70,2,0,0,0,0,1,0 +4013,30,6,124,91320,2,0.60,1,0,0,0,0,1,0 +4014,62,38,23,91304,2,0.30,3,0,0,0,0,0,0 +4015,56,32,23,94720,4,0.70,1,0,0,0,0,1,1 +4016,25,-1,139,93106,2,2.00,1,0,0,0,0,0,1 +4017,53,28,173,91614,4,2.70,1,427,1,0,0,1,0 +4018,26,0,42,92009,4,1.30,3,153,0,0,0,1,0 +4019,59,35,161,94301,1,2.90,1,160,0,0,0,0,1 +4020,62,36,28,95020,3,0.70,2,0,0,0,0,1,0 +4021,58,32,191,93943,4,5.20,3,194,1,0,0,0,1 +4022,40,14,42,90638,2,0.30,1,106,0,0,0,0,1 +4023,35,5,81,94234,4,4.00,3,0,0,0,0,1,0 +4024,51,25,175,90089,3,0.70,1,312,1,0,0,0,0 +4025,41,15,82,94720,3,0.10,1,0,0,0,0,1,0 +4026,51,27,53,94114,1,1.80,3,0,0,0,0,0,1 +4027,27,1,142,92038,3,5.50,1,0,1,0,0,0,0 +4028,46,21,42,93727,4,1.90,3,0,0,0,0,1,0 +4029,46,20,64,94117,4,2.90,1,189,0,0,0,0,0 +4030,31,5,90,94301,2,1.30,1,0,0,1,0,1,0 +4031,58,32,44,92354,1,0.80,2,0,0,0,0,0,0 +4032,42,18,29,91320,1,0.30,3,0,0,0,0,1,0 +4033,59,35,93,94301,2,1.60,1,0,0,0,0,0,1 +4034,54,24,69,93117,3,1.40,3,132,0,0,0,1,0 +4035,35,11,82,94022,2,1.70,2,0,0,0,0,1,1 +4036,34,9,180,93955,2,6.50,3,0,1,0,1,1,0 +4037,46,21,13,93117,2,0.70,3,0,0,0,0,1,0 +4038,52,28,72,91335,1,0.00,1,178,0,0,0,0,0 +4039,55,30,54,91367,3,1.70,1,0,0,0,0,1,0 +4040,34,9,104,92152,1,4.60,1,0,0,0,0,1,1 +4041,57,32,44,90266,2,1.90,2,157,0,0,0,0,0 +4042,45,19,40,95060,1,0.20,1,0,0,1,1,1,1 +4043,29,3,190,92612,2,4.50,1,246,0,0,0,1,1 +4044,49,23,64,94588,4,2.60,1,0,0,0,0,1,1 +4045,36,11,9,90266,2,0.30,2,99,0,1,0,0,0 +4046,57,31,38,94720,4,0.70,2,0,0,0,0,1,0 +4047,25,0,72,94303,3,2.60,3,0,0,0,0,1,0 +4048,43,17,82,94114,1,5.20,1,79,0,0,0,1,0 +4049,27,2,48,90049,2,1.60,3,119,0,1,0,1,0 +4050,54,28,82,94122,4,2.60,3,294,0,0,0,0,0 +4051,53,26,14,94590,2,1.00,2,83,0,0,0,0,0 +4052,55,29,162,93105,1,2.90,1,0,0,0,0,1,1 +4053,43,19,54,94608,2,1.70,1,0,0,0,0,1,0 +4054,35,11,90,94720,2,0.00,1,0,0,0,0,0,0 +4055,59,34,64,94116,4,1.70,1,0,0,0,0,0,0 +4056,42,18,65,93460,3,2.10,3,0,0,0,0,1,1 +4057,51,25,113,91320,2,6.30,1,0,0,0,0,0,0 +4058,57,32,38,90740,2,2.10,3,0,0,0,0,0,0 +4059,39,15,65,92037,1,1.50,3,0,0,0,0,0,0 +4060,53,27,39,91330,4,1.50,3,0,0,0,0,1,0 +4061,31,6,174,93023,2,6.70,1,0,0,0,0,1,1 +4062,33,3,59,91040,2,1.75,3,0,0,0,0,1,0 +4063,38,14,43,95053,2,1.70,1,0,0,0,0,1,0 +4064,47,21,24,94108,2,0.10,3,0,0,0,0,0,1 +4065,63,39,50,94402,1,0.00,2,166,0,0,0,0,0 +4066,44,19,68,94305,1,3.70,3,0,0,0,0,1,0 +4067,61,37,61,94122,3,2.00,3,0,0,0,0,1,0 +4068,52,28,21,94025,4,0.50,2,0,0,0,0,1,0 +4069,59,34,21,95035,2,0.50,2,0,0,0,0,1,0 +4070,56,32,31,94596,4,1.30,1,0,0,0,0,0,0 +4071,58,33,70,94720,4,0.70,1,0,0,1,0,0,0 +4072,30,6,25,94304,3,1.00,2,135,0,0,0,0,1 +4073,42,17,78,92521,1,1.00,3,0,0,0,0,1,0 +4074,51,27,19,92120,1,0.20,1,0,0,0,0,0,0 +4075,60,35,23,94608,1,0.30,3,0,0,0,0,1,0 +4076,30,4,40,90601,4,0.80,1,0,0,0,0,1,0 +4077,49,23,22,92220,1,0.30,3,0,0,0,0,0,0 +4078,26,0,71,92093,4,1.80,2,0,0,1,0,1,0 +4079,36,12,58,91320,1,3.60,2,0,0,0,0,0,0 +4080,65,40,75,90036,3,2.20,1,0,0,0,0,1,0 +4081,27,0,40,90068,1,2.00,2,110,0,0,0,0,1 +4082,60,35,155,92521,1,1.50,3,0,1,0,0,0,1 +4083,32,6,83,90036,4,2.20,2,0,0,0,0,0,0 +4084,46,20,99,94302,3,1.10,1,0,0,0,0,0,0 +4085,60,36,59,94124,1,0.00,2,0,0,1,0,0,0 +4086,28,2,53,94609,3,2.40,2,0,0,0,0,1,0 +4087,50,26,11,93106,4,0.20,1,0,0,1,0,0,0 +4088,52,28,179,94583,4,4.20,3,0,1,0,0,0,0 +4089,29,-1,71,94801,2,1.75,3,0,0,0,0,0,0 +4090,30,4,85,94234,4,2.10,3,0,0,0,0,1,0 +4091,42,18,49,92717,3,2.10,3,0,0,1,0,1,0 +4092,32,6,122,94025,2,1.30,1,0,0,0,0,1,1 +4093,40,15,171,94539,2,3.30,1,0,0,0,0,1,0 +4094,49,24,138,93111,2,2.20,2,0,1,0,0,1,0 +4095,53,23,8,95616,4,0.40,3,0,0,1,0,1,0 +4096,42,17,59,94105,4,0.40,1,0,0,0,0,1,0 +4097,38,14,49,90740,3,2.80,1,0,0,0,0,0,0 +4098,60,34,92,95670,2,2.00,1,0,0,0,0,0,0 +4099,27,3,75,90032,4,0.00,1,0,0,0,0,0,0 +4100,61,35,60,92831,1,2.80,2,0,0,0,0,1,1 +4101,27,2,41,90254,2,1.70,2,0,0,0,0,1,0 +4102,45,21,40,93460,3,0.60,2,0,0,0,0,1,1 +4103,41,16,81,94305,2,0.40,1,146,0,0,0,1,1 +4104,44,20,52,94143,1,0.80,3,196,0,0,0,0,1 +4105,38,14,25,95616,4,1.00,1,0,0,0,0,0,0 +4106,39,15,139,91801,1,3.40,1,353,0,0,0,1,0 +4107,48,22,54,93106,1,1.20,2,0,0,0,0,0,0 +4108,47,22,81,94123,1,2.90,1,0,0,0,0,0,1 +4109,64,39,73,94025,3,2.20,1,0,0,1,0,0,1 +4110,27,0,30,93107,4,1.00,3,0,0,0,0,1,1 +4111,66,41,59,95617,3,2.40,1,0,0,0,0,0,0 +4112,43,17,21,95351,3,1.50,1,0,0,0,0,0,0 +4113,34,9,65,95014,3,0.70,2,104,0,0,0,1,0 +4114,28,2,41,93118,3,1.10,2,161,0,0,0,1,0 +4115,52,28,52,92126,4,0.10,3,121,0,0,0,0,0 +4116,45,20,84,94131,4,1.10,2,180,0,0,0,1,0 +4117,24,-2,135,90065,2,7.20,1,0,0,0,0,1,0 +4118,39,14,18,92037,4,0.20,3,0,0,1,0,0,0 +4119,40,16,34,93561,1,0.70,1,0,0,0,0,1,1 +4120,30,5,85,92624,4,1.80,3,0,0,0,0,1,0 +4121,49,23,23,94080,1,1.40,3,0,0,0,0,0,0 +4122,53,27,65,91711,4,2.80,2,0,0,0,0,0,1 +4123,56,30,195,90089,1,2.90,1,0,0,0,0,0,0 +4124,50,24,40,93460,4,2.60,1,89,0,0,0,1,0 +4125,53,29,141,90064,2,0.20,3,0,1,0,0,0,0 +4126,60,34,95,94104,2,0.70,2,322,0,0,0,1,1 +4127,58,33,23,90095,3,1.30,2,131,0,0,0,0,0 +4128,43,19,82,95758,2,1.80,2,0,0,0,0,1,1 +4129,46,21,53,93555,4,1.90,3,0,0,0,0,0,0 +4130,29,3,10,91320,4,0.40,1,87,0,0,0,1,1 +4131,56,30,75,91910,1,1.90,2,125,0,0,0,1,0 +4132,48,23,23,94534,4,0.40,2,122,0,0,0,0,0 +4133,61,36,133,90266,1,2.60,1,0,0,0,0,1,0 +4134,41,17,129,94720,1,3.40,1,0,0,0,0,0,1 +4135,35,11,85,92154,4,0.10,2,131,0,0,0,0,0 +4136,48,23,168,95929,2,2.80,1,308,0,0,0,1,0 +4137,43,19,83,92691,4,2.00,3,0,0,0,0,1,0 +4138,37,12,52,93943,2,1.10,2,0,0,0,0,1,0 +4139,47,22,114,95819,1,0.60,1,0,0,1,1,1,1 +4140,29,3,81,95827,1,2.90,3,0,0,0,0,0,0 +4141,63,38,32,94015,1,1.50,2,0,0,0,0,0,0 +4142,43,19,63,94118,3,2.10,3,0,0,0,0,0,0 +4143,57,32,70,90024,3,1.60,3,0,0,0,0,0,0 +4144,55,31,20,94720,2,0.30,1,0,0,0,0,1,0 +4145,47,23,138,91367,2,3.30,1,0,0,0,0,1,1 +4146,58,34,63,94305,4,1.60,2,0,0,0,0,0,0 +4147,53,28,85,95814,1,1.30,3,118,0,0,0,1,0 +4148,59,35,180,96008,2,6.50,2,0,1,1,1,1,1 +4149,46,22,80,95747,4,2.00,3,0,0,0,0,1,0 +4150,41,15,53,93106,1,0.70,3,0,0,0,0,1,0 +4151,46,20,72,92009,2,1.70,2,75,0,0,0,1,0 +4152,44,18,123,95841,3,5.90,1,0,1,0,1,1,1 +4153,44,18,91,91361,2,0.80,3,0,0,0,0,1,0 +4154,50,26,148,94608,2,6.80,1,0,0,0,0,1,0 +4155,51,25,163,94305,2,1.30,3,0,1,0,0,1,0 +4156,55,30,28,90291,4,0.10,3,149,0,0,0,1,1 +4157,37,12,193,92780,1,8.60,1,0,0,0,0,0,0 +4158,34,10,22,94545,3,0.90,3,0,0,0,0,1,0 +4159,59,34,74,92780,4,0.70,1,0,0,0,0,1,1 +4160,45,20,70,94305,4,1.90,3,0,0,0,0,1,1 +4161,30,4,11,95054,1,0.10,2,0,0,0,0,1,1 +4162,32,8,61,94703,3,2.60,2,0,0,0,0,0,0 +4163,61,37,41,94704,1,0.80,1,0,0,0,0,1,1 +4164,54,28,108,94110,4,1.90,2,0,1,0,0,1,0 +4165,35,10,23,90058,4,1.10,3,0,0,0,0,0,1 +4166,63,38,135,91768,2,3.80,3,183,1,0,0,0,0 +4167,66,40,30,95133,2,0.70,3,86,0,0,0,0,0 +4168,48,24,144,94025,4,3.50,2,0,1,0,0,0,0 +4169,60,34,139,95020,4,0.40,1,0,1,0,0,1,0 +4170,41,17,143,90059,2,2.70,3,209,1,0,0,1,0 +4171,31,7,44,93561,1,1.20,1,0,0,0,0,1,1 +4172,58,31,49,94521,4,2.50,2,0,0,0,0,1,0 +4173,67,42,75,90041,4,0.10,2,182,0,0,0,1,0 +4174,35,9,43,93943,2,0.30,1,0,0,0,0,1,0 +4175,40,14,59,91335,3,0.50,3,0,0,0,0,1,0 +4176,42,17,154,93955,3,4.90,1,0,1,0,1,1,1 +4177,44,18,75,95131,1,0.70,3,0,0,0,0,0,1 +4178,47,23,75,93106,1,2.60,2,0,0,0,0,0,1 +4179,59,35,88,91311,2,1.60,1,278,0,0,0,0,0 +4180,29,3,91,94122,1,3.40,3,0,1,0,0,0,0 +4181,36,6,11,92008,1,0.67,3,0,0,1,1,1,1 +4182,47,22,22,90024,1,0.40,3,0,0,0,0,1,0 +4183,55,29,49,92691,2,0.80,3,220,0,0,0,0,1 +4184,41,17,140,94542,1,3.50,1,342,0,0,0,0,0 +4185,51,25,99,90277,2,2.40,2,0,0,0,0,0,0 +4186,26,2,82,91950,2,2.50,1,199,0,0,0,0,0 +4187,33,9,10,90005,4,1.00,1,81,0,0,0,0,1 +4188,30,5,109,94305,4,2.20,2,103,0,0,0,0,1 +4189,30,4,45,90041,4,1.30,3,0,0,0,0,0,0 +4190,45,19,93,91116,2,1.70,2,0,0,0,0,0,0 +4191,40,16,89,95814,3,3.90,2,216,1,1,1,1,0 +4192,42,15,39,91711,3,1.00,2,132,0,0,0,0,0 +4193,50,26,21,91768,1,0.20,1,89,0,0,0,1,0 +4194,62,37,31,95008,3,0.20,1,0,0,0,0,1,0 +4195,63,37,31,95819,1,0.50,3,0,0,0,0,1,0 +4196,43,19,52,95054,4,2.20,2,0,0,0,0,0,0 +4197,49,25,13,95814,1,0.90,3,0,0,0,0,1,0 +4198,51,25,21,90840,2,0.40,3,76,0,1,0,1,0 +4199,61,36,50,96003,4,1.70,1,189,0,0,0,1,0 +4200,43,19,81,90630,4,0.20,3,0,0,0,0,0,1 +4201,43,19,74,94035,4,1.90,1,0,0,0,0,0,1 +4202,61,36,89,93109,3,0.50,1,0,0,0,0,1,0 +4203,35,9,82,95064,3,0.90,2,0,0,0,0,1,0 +4204,59,33,88,93106,4,1.90,2,0,0,0,0,0,0 +4205,40,16,61,91711,3,2.10,3,0,0,0,0,0,0 +4206,61,36,139,95133,2,3.90,1,0,0,0,0,0,0 +4207,48,23,29,93711,1,1.30,2,0,0,0,0,0,0 +4208,37,11,51,93305,3,2.10,1,0,0,0,0,1,1 +4209,56,32,58,95064,1,1.80,3,241,0,0,0,1,0 +4210,35,9,21,91125,2,1.40,3,125,0,0,0,1,0 +4211,35,8,43,95819,2,1.67,2,0,0,0,0,0,0 +4212,40,16,104,94301,2,1.80,2,0,0,0,0,0,0 +4213,50,23,9,94109,1,0.50,2,98,0,0,0,1,0 +4214,49,25,39,91125,3,1.90,2,0,0,0,0,0,0 +4215,46,22,89,94303,1,2.70,1,0,0,1,1,1,1 +4216,64,40,21,94028,2,0.30,3,0,0,0,0,0,0 +4217,60,35,173,90059,3,3.10,3,0,1,0,0,1,0 +4218,45,21,29,95051,1,0.30,3,105,0,0,0,1,1 +4219,52,27,43,94005,4,0.20,2,0,0,0,0,0,1 +4220,58,34,30,90066,3,0.40,2,0,0,0,0,0,0 +4221,54,30,39,94806,4,0.10,3,0,0,1,0,1,0 +4222,48,22,83,90028,2,0.40,3,248,0,0,0,1,0 +4223,51,25,58,93106,3,0.70,2,223,0,0,0,0,0 +4224,53,26,8,94709,1,0.50,2,0,0,0,0,0,1 +4225,57,27,39,95929,3,1.00,3,0,0,1,0,0,1 +4226,43,18,204,91902,2,8.80,1,0,0,0,0,1,0 +4227,37,13,45,94591,1,1.80,1,0,0,0,0,0,0 +4228,32,7,111,90277,1,3.80,1,0,0,1,0,0,0 +4229,34,10,83,95060,2,2.00,2,148,0,0,0,0,0 +4230,54,24,83,94596,1,3.00,3,0,0,0,0,0,0 +4231,62,36,115,92093,2,2.80,1,202,0,0,0,1,1 +4232,56,32,60,93106,1,1.80,3,227,0,0,0,1,0 +4233,39,15,53,94116,1,1.80,1,0,0,0,0,0,0 +4234,32,7,134,95929,2,3.30,1,0,0,0,0,1,0 +4235,50,24,91,93555,1,0.80,3,0,0,0,0,1,0 +4236,27,1,91,92173,2,0.20,1,0,0,0,0,1,0 +4237,37,12,128,91342,2,3.90,1,0,0,0,0,1,1 +4238,60,34,78,90401,3,4.40,1,0,0,1,0,0,0 +4239,43,19,161,92093,2,7.60,1,464,0,0,0,1,0 +4240,62,36,60,92182,3,2.20,3,0,0,0,0,1,0 +4241,39,14,161,95064,1,4.10,1,509,0,1,0,0,0 +4242,34,9,40,95054,4,2.00,2,0,0,0,0,1,1 +4243,46,21,68,94720,1,0.20,2,0,0,0,0,1,0 +4244,46,22,74,94550,3,0.70,1,0,0,0,0,1,0 +4245,51,26,55,92121,3,2.00,2,93,0,0,0,1,0 +4246,44,20,145,90630,1,3.50,1,0,0,0,0,0,1 +4247,60,35,24,94920,1,1.50,2,0,0,0,0,0,0 +4248,65,39,10,90210,1,0.80,2,0,0,0,0,1,0 +4249,58,33,138,90720,2,3.90,1,0,0,1,0,1,0 +4250,37,12,63,91942,4,2.10,3,0,0,0,0,1,0 +4251,52,28,54,90041,4,0.10,3,0,0,0,0,0,1 +4252,42,16,62,95064,3,0.90,3,0,0,0,0,1,0 +4253,54,29,81,91107,1,0.10,3,0,0,0,0,0,0 +4254,54,28,61,90601,3,3.00,2,0,0,0,0,1,1 +4255,51,27,68,91711,1,1.60,3,0,0,0,0,1,0 +4256,59,35,78,90095,2,2.80,1,0,0,0,0,1,0 +4257,41,17,165,91311,2,7.60,1,157,0,0,0,0,0 +4258,43,17,48,95762,3,2.20,2,0,0,0,0,0,1 +4259,52,26,155,92660,3,7.20,2,0,1,0,0,1,0 +4260,52,26,158,94920,2,3.70,3,251,1,0,0,0,1 +4261,57,31,52,94105,1,1.40,1,0,0,0,0,1,0 +4262,53,28,18,92507,4,0.80,1,0,0,0,0,0,0 +4263,58,33,42,92093,4,1.70,1,0,0,0,0,0,0 +4264,59,33,18,94542,2,0.20,3,0,0,0,0,0,0 +4265,57,31,40,94304,2,0.30,1,0,0,1,1,1,1 +4266,27,2,44,93943,4,0.60,2,0,0,1,1,1,0 +4267,42,16,11,94015,1,0.20,1,87,0,0,0,0,1 +4268,52,26,194,91902,2,5.70,2,0,1,0,0,1,0 +4269,49,23,108,95616,2,2.40,2,0,0,0,0,1,0 +4270,47,23,12,92518,4,0.50,2,0,0,0,0,0,0 +4271,45,19,19,93117,3,1.50,1,94,0,0,0,1,1 +4272,25,1,150,92507,1,6.33,1,0,0,0,0,0,0 +4273,47,22,89,92647,4,1.90,3,0,0,0,0,1,0 +4274,44,19,83,95812,2,3.80,3,0,0,1,0,0,1 +4275,30,3,79,91380,4,2.00,2,0,0,0,0,1,0 +4276,63,38,102,95616,4,3.40,2,0,0,0,0,0,0 +4277,50,24,155,92717,1,7.30,1,0,0,0,0,1,1 +4278,40,16,138,92612,1,3.50,1,0,0,0,0,1,0 +4279,56,31,51,92028,3,1.70,1,0,0,0,0,1,1 +4280,39,15,80,94608,2,1.80,2,86,0,0,0,1,1 +4281,42,18,135,95136,2,3.30,1,0,0,1,1,1,1 +4282,28,1,34,94949,4,1.50,2,162,0,0,0,0,1 +4283,26,0,195,92093,3,6.33,3,0,1,1,1,1,0 +4284,58,32,62,91320,3,2.20,3,217,0,0,1,1,1 +4285,38,13,173,94305,2,3.30,1,243,0,0,0,0,0 +4286,23,-3,149,93555,2,7.20,1,0,0,0,0,1,0 +4287,53,29,20,93955,1,0.20,1,131,0,0,0,1,1 +4288,54,28,42,95207,4,2.50,1,0,0,0,0,1,1 +4289,42,17,28,94010,1,0.60,3,0,0,0,0,0,1 +4290,54,28,95,90254,1,1.90,2,0,0,0,0,1,0 +4291,66,42,95,94596,2,0.00,3,0,0,0,0,1,0 +4292,46,21,34,90034,1,0.10,1,124,0,0,0,1,0 +4293,63,37,191,94131,2,4.30,3,205,1,0,0,0,0 +4294,63,38,41,90034,2,1.50,1,173,0,0,0,1,1 +4295,58,34,150,92110,1,7.40,1,481,0,0,0,1,0 +4296,65,41,91,91360,2,0.00,3,146,0,0,0,0,0 +4297,35,9,84,94709,4,2.20,2,0,0,0,0,1,0 +4298,33,9,73,92110,4,3.40,1,140,0,0,0,1,0 +4299,43,19,122,93106,1,0.30,1,0,0,0,0,1,0 +4300,30,5,73,90065,1,2.60,2,133,0,0,0,1,0 +4301,61,37,20,95973,2,0.30,3,0,0,0,0,1,0 +4302,49,24,130,92677,4,1.10,1,281,1,0,1,1,0 +4303,52,27,85,92037,3,3.40,3,0,1,0,0,0,0 +4304,45,21,134,94550,2,3.30,1,0,0,0,0,1,1 +4305,64,39,98,95678,3,1.80,2,80,0,0,0,1,0 +4306,26,1,54,91709,2,1.60,3,0,0,1,0,0,0 +4307,35,11,41,92123,3,2.00,1,0,0,0,0,1,0 +4308,45,19,128,94928,4,6.00,3,0,1,0,0,1,0 +4309,44,20,132,94115,3,2.60,1,308,1,0,0,0,0 +4310,34,8,188,94025,1,2.90,3,0,1,0,0,1,0 +4311,65,41,170,94143,4,6.10,2,0,1,0,1,1,1 +4312,32,8,14,90034,3,0.90,3,111,0,0,0,0,0 +4313,41,15,93,95616,1,2.80,3,0,0,0,0,1,0 +4314,52,28,79,94596,1,2.70,2,0,0,0,0,1,1 +4315,35,9,79,94305,4,2.20,2,0,0,0,0,0,0 +4316,51,26,62,90024,4,1.80,3,119,0,0,0,1,0 +4317,30,6,95,91950,2,0.20,1,0,0,1,0,1,0 +4318,58,33,60,92672,4,1.30,3,0,0,0,0,1,0 +4319,49,23,75,92374,1,1.50,2,0,0,0,0,0,1 +4320,63,38,85,91320,4,0.10,2,0,0,0,0,0,1 +4321,40,15,143,94801,1,4.10,1,0,0,0,0,1,0 +4322,27,0,34,92717,1,2.00,2,112,0,0,0,0,1 +4323,38,14,44,91320,2,1.70,1,0,0,0,0,0,0 +4324,52,28,31,92008,4,0.90,2,151,0,1,0,1,0 +4325,49,24,13,94538,4,0.80,1,111,0,0,0,1,0 +4326,59,35,52,95616,4,1.50,1,0,0,0,0,1,1 +4327,32,8,42,95136,1,0.20,3,102,0,0,0,1,0 +4328,30,4,102,91775,4,2.10,3,139,0,0,0,0,1 +4329,64,38,143,95039,2,6.40,3,0,1,1,1,1,0 +4330,59,33,10,94063,4,0.70,3,0,0,0,0,1,0 +4331,62,37,44,90401,1,1.10,3,0,0,0,0,0,0 +4332,61,37,158,94720,2,6.00,1,306,0,1,1,1,1 +4333,53,26,12,92672,2,1.00,2,0,0,0,0,0,1 +4334,51,26,59,90095,1,1.20,1,139,0,0,0,1,0 +4335,55,29,92,92130,1,1.90,2,0,0,0,0,0,0 +4336,36,10,82,94542,2,2.80,1,0,0,0,0,0,1 +4337,44,19,44,90509,4,0.00,2,0,0,0,0,0,0 +4338,26,2,182,93010,2,3.20,2,0,1,0,0,0,0 +4339,54,30,121,92121,2,0.40,1,0,0,0,0,1,0 +4340,35,11,38,95518,1,1.70,1,0,0,0,0,0,1 +4341,34,10,92,90024,2,2.70,1,0,0,1,1,0,1 +4342,28,3,53,94305,2,1.60,3,0,0,0,0,0,0 +4343,32,7,45,93611,3,2.30,1,83,0,1,0,1,0 +4344,38,14,63,95422,1,3.60,2,0,0,1,0,1,0 +4345,53,28,181,95051,1,8.10,1,0,0,0,0,1,0 +4346,26,1,184,94608,2,4.20,3,577,1,0,1,1,1 +4347,45,21,33,94970,3,0.50,1,136,0,0,1,1,1 +4348,58,33,22,90024,3,0.20,1,0,0,0,0,1,0 +4349,59,33,99,92093,2,2.70,1,0,0,0,0,0,0 +4350,45,18,44,90089,3,1.00,2,193,0,0,0,0,0 +4351,64,39,101,95134,4,3.40,2,0,0,0,0,0,1 +4352,30,3,32,94132,1,2.00,2,0,0,0,0,1,1 +4353,40,16,59,94305,4,2.67,1,0,0,0,0,1,0 +4354,61,36,25,94015,2,0.50,2,0,0,0,0,1,1 +4355,40,16,140,93940,3,5.60,1,0,1,0,0,0,0 +4356,40,10,29,94720,1,0.75,3,0,0,0,0,1,0 +4357,43,19,35,90630,1,0.70,1,0,0,0,0,0,0 +4358,39,14,141,93302,4,6.30,1,0,1,1,1,1,1 +4359,35,11,75,92672,4,2.00,3,79,0,0,0,0,0 +4360,38,12,58,95054,2,2.80,1,0,0,0,0,1,0 +4361,67,43,41,90024,2,1.10,1,0,0,0,0,0,0 +4362,55,30,42,93940,2,2.00,2,196,0,0,0,0,1 +4363,28,2,55,93940,3,1.10,2,0,0,0,0,0,0 +4364,30,4,18,93711,4,0.30,2,84,0,0,0,1,0 +4365,59,35,75,92121,4,2.30,3,0,0,1,0,0,0 +4366,26,2,85,95020,2,2.50,1,0,0,0,0,0,0 +4367,52,28,43,90089,4,1.10,2,0,0,0,0,0,0 +4368,40,15,149,90250,2,3.90,1,319,0,0,0,1,1 +4369,31,7,25,93943,2,1.00,2,0,0,1,1,1,1 +4370,50,25,19,94005,4,0.40,2,103,0,0,0,1,1 +4371,27,3,18,93524,1,0.40,3,0,0,0,0,0,0 +4372,64,39,13,90024,4,0.60,2,0,0,0,0,1,0 +4373,34,10,41,91765,1,2.40,2,0,0,0,0,0,0 +4374,30,6,139,94501,1,4.30,1,0,0,0,0,1,0 +4375,39,15,62,93955,3,2.33,1,131,0,0,1,1,1 +4376,34,10,51,90032,3,2.00,1,130,0,0,0,0,0 +4377,40,15,71,93950,3,3.00,1,272,0,0,0,1,0 +4378,33,8,145,92507,1,2.70,3,0,1,0,0,1,0 +4379,38,12,45,91768,4,1.20,2,138,0,0,0,1,0 +4380,42,17,53,93023,4,1.90,3,0,0,0,0,1,0 +4381,37,13,64,94105,1,1.50,3,0,0,0,0,1,0 +4382,33,8,39,94542,4,0.80,1,0,0,0,0,1,0 +4383,60,34,38,92182,3,2.20,3,0,0,1,0,0,0 +4384,28,4,85,94709,3,2.50,1,0,0,0,0,1,0 +4385,45,20,61,92717,3,2.70,2,0,0,0,0,0,1 +4386,56,32,23,94610,1,1.20,3,127,0,0,0,1,1 +4387,53,27,122,94305,1,2.40,1,330,0,0,0,0,0 +4388,37,12,72,91380,4,0.70,3,0,0,0,0,0,0 +4389,47,21,123,90840,1,7.30,1,0,0,0,0,0,0 +4390,58,32,40,90057,1,1.60,1,0,0,1,1,1,1 +4391,52,26,62,95134,4,2.80,2,0,0,0,0,1,0 +4392,46,22,113,94105,2,3.30,1,0,0,0,0,0,1 +4393,52,27,81,92634,4,3.80,2,0,0,0,0,0,0 +4394,24,0,59,95521,4,1.60,1,0,0,0,0,0,0 +4395,57,31,25,94523,2,0.70,2,103,0,0,0,0,0 +4396,66,41,25,94720,4,0.60,2,0,0,0,0,1,1 +4397,30,5,14,95014,4,0.50,3,0,0,0,0,1,0 +4398,48,23,19,90058,1,0.10,1,0,0,0,0,1,0 +4399,63,37,61,91942,1,2.50,3,0,0,0,0,0,0 +4400,48,23,21,94904,1,0.10,1,0,0,0,0,0,0 +4401,34,10,44,94143,1,1.33,1,0,0,0,0,1,0 +4402,60,35,42,91902,3,1.50,1,0,0,0,0,0,1 +4403,55,25,52,90095,1,1.40,3,207,0,1,0,0,0 +4404,50,24,112,92064,1,0.00,1,0,0,0,0,0,0 +4405,29,5,34,94301,1,0.40,3,0,0,0,0,0,0 +4406,61,35,83,91320,2,1.70,3,245,0,0,0,1,0 +4407,50,25,24,95133,4,0.40,2,137,0,0,0,1,0 +4408,37,13,71,90755,2,1.70,2,0,0,0,0,1,1 +4409,64,40,181,93403,2,2.30,2,0,1,0,1,1,1 +4410,43,19,75,91765,4,0.20,3,102,0,0,0,1,0 +4411,39,14,153,91614,2,3.00,1,0,0,0,0,0,0 +4412,23,-2,75,90291,2,1.80,2,0,0,0,0,1,1 +4413,34,10,19,91711,4,0.40,2,0,0,0,0,0,0 +4414,29,2,31,91775,4,1.50,2,0,0,0,0,0,1 +4415,33,8,178,94720,3,8.50,1,0,1,1,1,1,0 +4416,60,35,65,90245,2,1.50,1,220,0,0,0,0,1 +4417,49,25,8,94720,1,0.30,1,97,0,0,0,0,0 +4418,54,28,92,92374,2,1.10,1,0,0,0,0,1,0 +4419,59,34,145,95125,4,1.80,1,198,1,0,0,1,0 +4420,42,17,85,93065,1,3.70,3,272,0,0,0,0,0 +4421,62,38,149,92130,1,4.70,1,0,0,0,0,1,0 +4422,63,38,9,94707,4,0.60,2,100,0,0,0,1,1 +4423,57,31,164,94607,2,3.80,3,422,1,0,1,1,1 +4424,61,36,40,95816,3,0.50,2,100,0,1,0,0,0 +4425,35,10,54,93943,1,2.50,3,0,0,0,0,0,1 +4426,26,0,164,95973,2,4.00,3,301,1,0,0,1,0 +4427,33,8,140,95814,1,4.60,1,0,0,0,0,1,0 +4428,31,7,18,91711,1,0.40,3,0,0,0,0,0,0 +4429,51,27,12,95818,4,1.00,1,0,0,1,0,1,0 +4430,55,29,140,94720,2,2.70,1,0,0,0,0,1,0 +4431,38,12,24,94588,2,0.80,3,0,0,0,0,1,1 +4432,38,12,60,92806,2,1.80,1,0,0,0,0,1,0 +4433,53,27,50,92660,2,0.80,3,0,0,0,0,1,0 +4434,62,38,44,92612,1,1.90,2,0,0,0,0,0,1 +4435,35,9,51,94596,4,2.20,2,110,0,0,0,1,0 +4436,46,21,34,90840,2,1.30,1,116,0,0,0,0,0 +4437,60,35,33,90095,2,0.50,2,0,0,0,0,1,0 +4438,63,38,63,92507,2,1.50,1,0,0,0,0,1,0 +4439,43,18,22,90025,2,0.00,3,0,0,0,0,0,0 +4440,33,7,104,94542,2,3.60,3,0,1,0,0,0,1 +4441,43,19,75,90041,3,0.30,3,0,0,0,0,0,0 +4442,62,36,75,92709,2,1.70,3,0,0,0,0,0,0 +4443,48,23,62,91367,4,3.60,3,83,0,0,0,0,1 +4444,38,14,48,90034,1,1.80,1,169,0,0,0,0,0 +4445,36,10,73,95035,2,2.80,1,0,0,0,0,1,1 +4446,49,25,135,90064,2,1.40,1,82,0,0,0,1,1 +4447,61,35,61,92177,3,2.20,3,117,0,0,0,1,1 +4448,49,22,78,95616,3,2.00,2,0,0,0,0,1,0 +4449,59,34,40,94102,3,0.90,3,0,0,0,0,1,0 +4450,30,6,44,95211,1,0.20,3,0,0,0,0,0,1 +4451,44,20,45,94111,2,2.50,1,0,0,0,0,1,0 +4452,67,41,18,92130,2,0.40,1,0,0,0,0,1,0 +4453,59,35,53,90035,4,2.30,3,174,0,0,0,1,0 +4454,37,11,11,94112,3,0.10,2,0,0,0,0,0,0 +4455,50,24,38,94143,3,0.60,2,0,0,0,0,1,0 +4456,56,31,28,94040,1,1.50,2,0,0,1,1,1,1 +4457,29,3,35,94040,2,0.30,1,88,0,0,1,1,1 +4458,55,29,81,92843,3,1.70,2,171,0,0,0,1,0 +4459,48,22,90,94590,2,0.80,3,205,0,0,0,0,0 +4460,32,8,115,90064,1,4.00,1,0,0,0,0,0,0 +4461,47,22,78,92093,1,0.20,2,0,0,0,0,1,0 +4462,46,21,30,94301,4,1.90,3,0,0,0,0,1,0 +4463,33,7,39,95630,4,0.80,1,0,0,0,0,1,1 +4464,39,13,69,94123,3,0.10,1,0,0,0,0,0,0 +4465,60,35,29,93943,3,0.20,1,79,0,0,0,1,1 +4466,39,15,54,94108,4,2.20,2,0,0,0,0,0,1 +4467,34,10,60,90071,3,2.80,1,0,0,0,1,1,1 +4468,55,30,99,91768,1,0.10,3,0,0,0,0,0,0 +4469,67,42,51,94117,3,2.20,1,0,0,0,0,1,1 +4470,40,14,53,94025,3,0.50,3,0,0,1,1,1,1 +4471,44,20,111,91911,2,5.30,2,0,1,0,0,1,0 +4472,56,30,79,94588,3,0.80,1,302,0,0,0,0,0 +4473,50,25,90,95616,1,2.80,2,0,0,0,0,1,0 +4474,31,5,18,92115,2,0.30,1,124,0,0,0,1,1 +4475,66,41,73,95817,3,2.40,1,0,0,0,0,0,0 +4476,43,18,59,95039,3,0.80,3,91,0,0,0,1,0 +4477,58,32,40,95833,2,0.30,1,0,0,0,0,0,0 +4478,33,9,41,92028,1,1.50,2,0,0,0,1,1,1 +4479,33,9,53,91380,1,2.10,3,0,0,0,0,0,0 +4480,32,8,128,93117,2,4.33,1,0,0,0,0,1,0 +4481,55,30,145,92037,2,6.00,3,0,1,0,0,1,0 +4482,25,-2,35,95045,4,1.00,3,0,0,0,0,1,0 +4483,40,14,28,90404,2,0.80,3,0,0,0,0,0,0 +4484,54,28,155,90095,1,1.00,1,256,0,0,0,1,1 +4485,36,11,195,95747,2,3.00,1,0,0,0,0,1,1 +4486,35,9,50,92182,4,2.20,2,0,0,0,0,0,0 +4487,44,19,48,92735,3,0.80,3,0,0,0,0,0,1 +4488,38,14,81,94583,1,3.60,2,0,0,0,0,1,1 +4489,30,4,50,91030,1,1.50,1,0,0,0,0,0,0 +4490,39,13,21,95518,3,0.20,2,0,0,0,0,1,0 +4491,35,9,142,90250,2,0.00,1,0,0,1,0,1,0 +4492,41,16,64,91604,4,0.40,1,0,0,0,0,1,0 +4493,56,26,91,94939,1,3.00,3,0,0,0,0,1,1 +4494,52,28,74,96064,1,2.60,2,0,0,0,0,1,1 +4495,29,4,182,95354,1,3.70,3,0,1,0,0,1,0 +4496,38,14,82,95616,4,2.67,1,0,0,0,0,0,0 +4497,51,25,45,95616,4,2.60,1,0,0,0,0,0,0 +4498,45,21,85,95136,2,3.20,1,0,0,1,0,1,0 +4499,51,26,133,90291,1,0.60,1,328,0,0,0,0,0 +4500,53,26,22,91304,1,0.50,2,0,0,0,0,1,1 +4501,50,26,24,94305,4,0.50,2,0,0,0,0,0,1 +4502,59,33,38,94132,3,2.20,3,178,0,1,1,1,1 +4503,57,32,80,92647,2,0.00,3,0,0,0,0,0,0 +4504,45,21,33,92374,3,0.50,1,108,0,0,0,1,0 +4505,27,1,41,93023,4,1.80,3,147,0,0,0,0,0 +4506,40,15,90,94063,4,1.10,2,0,0,1,0,1,0 +4507,39,13,89,92037,1,2.80,3,153,0,0,0,1,1 +4508,26,1,8,94550,2,0.90,3,0,0,0,0,0,1 +4509,27,2,85,94117,1,1.90,1,0,0,0,0,1,1 +4510,55,30,53,94550,3,1.70,1,0,0,0,0,1,0 +4511,64,39,20,93109,3,0.10,3,0,0,0,0,0,0 +4512,41,17,9,91911,1,1.00,1,0,0,0,0,1,1 +4513,46,22,25,95747,4,0.60,1,0,0,0,0,1,1 +4514,43,19,114,92325,1,1.70,1,0,0,0,0,1,0 +4515,24,-3,41,91768,4,1.00,3,0,0,0,0,1,0 +4516,29,3,49,94305,4,2.10,3,0,0,0,0,0,0 +4517,58,32,12,95929,4,0.70,3,0,0,0,0,1,0 +4518,45,18,50,91902,3,2.50,2,0,0,0,0,1,0 +4519,53,28,30,94609,4,0.20,2,0,0,0,0,1,0 +4520,45,21,32,92399,4,0.60,1,77,0,0,0,0,1 +4521,32,7,41,94706,4,2.00,2,0,0,0,0,0,0 +4522,56,31,25,95123,3,0.10,2,0,0,0,0,0,0 +4523,31,5,29,90630,1,0.30,1,0,0,0,0,0,0 +4524,29,4,50,94040,4,1.70,2,0,0,0,0,1,0 +4525,48,24,79,94542,3,0.70,1,0,0,0,0,1,1 +4526,36,11,110,94110,1,3.80,1,0,0,0,0,1,1 +4527,36,9,40,92518,2,1.67,2,129,0,1,0,1,0 +4528,41,16,18,90024,1,0.60,3,0,0,0,0,0,1 +4529,48,23,48,94086,1,0.30,1,0,0,0,0,0,0 +4530,27,0,40,92103,4,1.00,3,0,0,0,0,0,0 +4531,33,9,19,95370,2,1.00,2,92,0,0,0,1,0 +4532,31,7,35,94025,1,1.33,1,131,0,0,0,0,1 +4533,48,22,133,90073,2,3.10,2,0,1,0,0,1,0 +4534,59,34,19,95762,2,0.50,2,0,0,0,0,1,0 +4535,41,17,83,94025,4,2.67,1,0,0,0,0,1,0 +4536,42,18,39,96091,3,2.10,3,0,0,0,0,0,0 +4537,62,37,38,92354,3,0.50,2,0,0,0,0,0,0 +4538,62,36,63,95929,1,2.50,3,0,0,0,0,1,1 +4539,51,24,85,94305,3,2.00,2,0,0,0,0,0,0 +4540,48,24,14,94305,4,1.00,1,0,0,0,0,1,0 +4541,56,32,64,90210,4,1.50,1,0,0,0,0,1,0 +4542,62,38,124,95023,1,3.80,1,405,0,0,0,1,0 +4543,53,29,20,94131,1,0.20,1,0,0,1,1,1,1 +4544,62,38,33,95134,3,0.10,3,0,0,0,0,1,0 +4545,28,4,80,95819,3,2.50,1,0,0,0,0,1,0 +4546,61,35,35,90025,2,0.20,3,0,0,0,0,1,0 +4547,48,24,74,91109,3,0.70,1,0,0,1,0,1,0 +4548,50,25,32,94304,2,0.70,2,0,0,0,0,1,0 +4549,58,33,73,93109,4,0.70,1,241,0,0,0,0,0 +4550,53,29,41,94080,2,0.80,1,0,0,0,0,1,0 +4551,65,40,18,95621,1,1.50,2,0,0,0,0,1,0 +4552,27,0,28,91330,4,1.50,2,0,0,0,0,1,0 +4553,50,23,64,92037,1,2.67,2,0,0,0,0,0,0 +4554,50,25,44,92093,2,0.70,2,192,0,0,0,1,0 +4555,41,16,109,94801,3,1.00,1,0,0,1,0,1,0 +4556,43,19,71,95054,3,0.30,3,179,0,0,0,0,0 +4557,55,29,79,94608,2,1.10,1,0,0,1,0,1,0 +4558,33,9,30,95054,2,1.00,2,0,0,0,0,1,0 +4559,44,19,82,95521,2,0.40,1,0,0,0,0,1,1 +4560,47,20,101,91950,3,2.00,2,270,0,0,0,1,0 +4561,43,18,13,94709,2,0.10,2,0,0,0,1,1,1 +4562,59,33,59,91365,3,1.40,3,0,0,0,0,0,0 +4563,65,40,64,94928,2,1.50,1,0,0,0,0,0,1 +4564,28,2,188,92350,2,4.50,1,0,0,1,0,1,0 +4565,58,32,28,90095,2,0.30,1,148,0,0,0,0,0 +4566,33,8,120,92614,2,4.20,3,76,1,0,0,0,1 +4567,24,0,131,92831,1,5.40,1,0,0,0,0,1,0 +4568,46,20,19,94105,3,0.50,2,97,0,1,0,1,0 +4569,26,0,44,94305,4,1.30,3,0,0,1,0,0,0 +4570,47,21,49,92152,3,2.20,2,0,0,1,0,0,0 +4571,32,6,99,91902,2,4.50,3,249,0,0,0,1,0 +4572,58,28,95,94304,1,3.00,3,0,0,0,0,0,0 +4573,32,7,81,95112,4,1.80,3,0,0,0,0,1,0 +4574,46,20,73,95616,2,0.80,3,264,0,0,1,1,1 +4575,35,11,193,91765,2,6.50,1,0,0,0,0,0,1 +4576,53,27,115,90095,2,0.50,3,0,1,0,0,0,0 +4577,55,30,41,93003,2,0.60,3,0,0,0,0,1,1 +4578,63,37,80,90401,2,1.70,3,0,0,0,0,1,1 +4579,45,20,90,94143,4,1.10,2,0,0,0,0,1,1 +4580,58,32,41,94305,1,0.20,1,81,0,0,0,1,0 +4581,50,24,102,91103,2,6.30,1,0,0,0,0,1,0 +4582,37,13,59,94234,1,1.50,3,0,0,0,0,0,1 +4583,25,-1,69,92691,3,0.30,3,0,0,0,0,1,0 +4584,52,26,83,92521,1,3.10,1,0,1,0,0,1,0 +4585,26,0,49,90089,3,2.40,2,0,0,0,0,0,0 +4586,35,11,180,94010,1,3.60,3,571,1,0,1,1,1 +4587,58,32,61,91910,3,2.20,3,0,0,0,0,1,1 +4588,37,11,59,94720,4,0.20,3,0,0,0,0,0,0 +4589,35,10,85,95351,4,2.10,3,0,0,0,0,0,1 +4590,31,7,13,93727,1,0.50,3,0,0,0,0,1,0 +4591,58,34,151,94022,3,0.60,2,0,1,0,0,0,0 +4592,43,16,44,94577,3,1.00,2,0,0,0,0,1,0 +4593,43,18,53,92115,3,0.80,3,154,0,0,0,0,0 +4594,54,30,133,95747,1,5.00,2,0,1,0,0,0,1 +4595,53,27,31,91320,3,0.90,3,78,0,0,0,1,0 +4596,32,7,101,90232,4,2.20,2,0,0,0,0,1,0 +4597,37,13,61,95131,3,2.80,1,0,0,0,0,0,0 +4598,34,10,68,90095,3,2.60,2,0,0,0,0,0,0 +4599,51,26,21,94143,4,0.80,1,0,0,0,0,1,0 +4600,49,25,149,90024,2,0.40,1,0,0,0,0,1,0 +4601,54,24,75,93555,1,1.40,3,0,0,0,0,0,0 +4602,37,12,55,95630,1,2.50,3,0,0,0,0,1,0 +4603,57,32,81,94305,2,3.70,1,226,0,0,0,1,1 +4604,37,12,179,91768,1,8.60,1,0,0,0,0,1,0 +4605,32,7,81,90601,2,3.40,2,0,1,0,0,0,1 +4606,48,22,42,94611,1,1.20,2,0,0,0,0,0,0 +4607,44,20,199,94607,2,6.67,1,0,0,0,0,1,0 +4608,50,23,18,93117,1,0.50,2,0,0,0,0,1,1 +4609,44,19,28,91604,1,0.30,3,0,0,0,0,1,0 +4610,54,28,80,95006,4,2.60,3,143,0,0,0,0,0 +4611,37,13,79,91330,1,3.60,2,104,0,0,0,1,0 +4612,34,7,52,93940,2,1.00,2,0,0,0,0,1,0 +4613,32,6,18,92007,2,0.30,2,0,0,0,0,1,0 +4614,63,38,52,91361,4,1.70,1,218,0,0,0,1,1 +4615,56,30,15,92093,4,0.70,3,102,0,0,0,0,0 +4616,37,12,84,93943,4,0.70,3,0,0,0,0,1,0 +4617,66,41,114,92521,1,0.80,3,0,0,0,0,1,1 +4618,38,13,41,95521,3,0.50,3,0,0,0,0,0,1 +4619,35,9,29,95354,3,0.90,1,126,0,0,0,1,0 +4620,61,36,23,95521,1,0.10,1,96,0,0,0,0,0 +4621,52,26,84,94132,1,2.40,1,0,0,0,0,1,0 +4622,57,32,60,93407,3,1.70,1,0,0,1,1,1,1 +4623,47,20,13,94545,3,0.67,2,0,0,0,0,1,0 +4624,50,25,45,90813,2,0.60,3,0,0,0,0,0,0 +4625,36,11,83,90638,1,2.80,1,0,0,0,0,0,0 +4626,45,21,102,92037,4,4.70,2,81,1,0,0,0,0 +4627,58,34,58,90034,4,2.30,3,169,0,0,0,1,0 +4628,27,1,134,93106,1,1.70,2,307,1,0,0,1,0 +4629,27,1,130,94801,3,2.90,2,0,1,0,0,0,0 +4630,48,24,148,91311,2,3.30,1,0,0,0,1,1,1 +4631,46,21,92,92886,1,0.20,2,0,0,0,0,0,0 +4632,32,8,142,90095,4,6.20,2,120,1,0,1,1,1 +4633,54,29,62,94720,4,0.70,1,0,0,0,0,0,1 +4634,31,5,50,93106,1,1.50,1,0,0,0,0,1,0 +4635,42,17,29,94928,1,0.60,3,0,0,0,0,1,0 +4636,30,5,85,91910,2,2.50,1,293,0,1,1,1,1 +4637,41,16,78,95616,4,0.40,1,0,0,0,0,1,0 +4638,44,19,85,92054,4,1.90,3,0,0,0,0,1,1 +4639,37,13,89,91711,2,1.70,2,0,0,0,0,1,0 +4640,51,25,33,92866,3,0.90,3,0,0,0,0,1,1 +4641,30,6,42,90034,1,2.10,3,0,0,0,0,1,0 +4642,36,11,31,94022,4,1.70,1,124,0,0,0,1,1 +4643,65,40,143,95616,4,6.60,2,0,1,0,0,1,0 +4644,33,7,35,95616,4,0.80,1,0,0,0,0,1,0 +4645,58,34,22,94608,1,0.10,2,0,0,0,0,1,0 +4646,34,10,45,92038,1,1.70,1,84,0,0,0,0,0 +4647,38,13,119,94545,2,3.30,1,0,0,0,0,0,0 +4648,59,35,43,95616,4,1.30,1,0,0,0,0,1,0 +4649,37,11,75,94704,3,0.90,2,0,0,0,0,1,0 +4650,59,35,121,91423,1,4.30,1,0,0,0,0,1,0 +4651,47,23,63,95521,1,0.80,3,0,0,0,0,1,0 +4652,48,24,58,94005,2,1.70,1,0,0,0,0,0,0 +4653,38,12,184,91311,3,8.00,1,0,1,0,0,1,0 +4654,34,10,155,92780,2,6.50,1,0,0,0,0,1,1 +4655,44,17,69,90095,3,2.67,2,0,0,0,0,0,0 +4656,33,7,188,95054,2,7.00,2,581,1,0,0,0,0 +4657,47,21,38,91101,3,0.60,2,0,0,1,0,0,0 +4658,41,16,9,90089,2,0.30,2,0,0,0,0,0,1 +4659,36,11,69,95929,4,2.10,3,0,0,0,0,1,1 +4660,28,4,199,92121,1,6.33,1,0,0,0,0,0,0 +4661,59,35,38,92122,1,0.80,1,0,0,0,0,1,0 +4662,43,19,129,95039,1,5.00,1,0,0,1,0,1,0 +4663,56,31,59,94303,2,1.90,2,0,0,0,0,1,0 +4664,28,3,115,92407,1,1.90,1,200,0,0,0,1,0 +4665,62,37,83,93657,4,0.10,2,0,0,0,0,0,0 +4666,40,16,65,90095,2,3.20,1,0,0,0,0,1,0 +4667,34,9,72,94555,3,2.30,1,124,0,0,0,0,0 +4668,52,28,72,94720,1,1.60,3,0,0,0,0,1,0 +4669,40,14,63,94025,3,0.50,3,221,0,0,0,1,0 +4670,27,1,64,94501,4,1.80,2,0,0,0,0,1,1 +4671,52,26,194,94305,1,1.70,1,0,0,0,0,1,0 +4672,39,14,104,95035,1,4.00,3,0,0,0,1,1,1 +4673,52,26,180,95831,1,1.70,1,550,0,0,0,1,0 +4674,50,23,18,95503,2,1.00,2,88,0,0,0,1,1 +4675,40,14,93,93933,1,2.80,3,328,0,1,1,1,1 +4676,35,11,32,91360,1,1.33,1,137,0,0,0,1,1 +4677,39,13,68,91950,3,2.10,1,0,0,1,0,1,0 +4678,25,0,38,93407,2,1.60,3,0,0,0,0,0,0 +4679,33,7,115,93305,1,2.70,2,283,0,0,0,1,0 +4680,26,0,161,94551,2,7.20,1,0,0,0,0,0,0 +4681,46,21,154,90245,2,2.80,1,94,0,0,0,0,0 +4682,27,3,68,95503,4,0.00,1,0,0,0,0,0,1 +4683,55,25,44,92093,3,1.00,3,0,0,0,0,1,0 +4684,52,28,149,92121,2,0.40,1,0,0,0,0,0,0 +4685,59,34,103,91360,1,2.60,1,0,0,0,0,1,0 +4686,63,39,41,91355,4,1.30,2,0,0,0,0,1,0 +4687,61,35,113,91741,2,2.80,1,0,0,0,0,0,0 +4688,58,34,48,93460,4,1.30,2,0,0,0,0,1,1 +4689,29,3,69,92093,4,1.80,2,0,0,0,0,1,1 +4690,51,27,43,95053,4,1.10,2,164,0,0,0,1,1 +4691,59,34,19,92192,1,0.30,3,0,0,0,0,1,0 +4692,41,17,65,90024,3,2.10,3,0,0,0,0,1,0 +4693,59,35,32,92064,3,0.40,2,0,0,0,0,0,1 +4694,52,28,20,95616,1,0.30,1,0,0,0,0,0,0 +4695,39,13,25,94132,2,0.80,3,0,0,0,0,0,0 +4696,45,19,70,95605,1,2.80,1,0,0,0,0,0,1 +4697,59,35,70,92103,4,2.30,3,0,0,0,0,0,0 +4698,49,22,103,91330,3,2.00,2,167,0,0,0,0,0 +4699,48,22,162,94143,3,1.40,1,400,1,0,0,0,0 +4700,61,36,61,91320,2,2.80,1,153,0,0,0,0,1 +4701,31,7,170,95006,1,6.00,1,0,0,0,0,1,0 +4702,42,16,49,90034,1,2.80,1,0,0,0,0,0,0 +4703,35,5,108,90630,2,2.75,3,0,1,1,0,0,0 +4704,57,27,62,94025,3,2.00,3,0,0,0,0,1,0 +4705,54,28,102,91360,3,1.70,2,0,0,0,0,1,0 +4706,61,37,141,92677,3,0.70,1,0,1,0,1,1,1 +4707,60,36,8,92626,2,1.00,1,0,0,0,0,0,0 +4708,59,35,91,95008,2,1.60,1,0,0,1,0,0,1 +4709,62,37,10,92606,3,0.50,1,0,0,0,0,1,0 +4710,26,1,35,90089,2,1.70,2,119,0,0,0,0,1 +4711,41,17,71,92182,3,0.30,3,0,0,0,0,0,1 +4712,65,40,59,94022,3,2.40,1,0,0,0,0,0,0 +4713,25,0,14,94309,2,0.90,3,0,0,0,0,0,1 +4714,25,1,122,93022,2,0.20,1,0,0,0,0,1,0 +4715,27,3,81,90291,3,1.50,1,307,0,1,1,1,1 +4716,65,39,35,92009,1,0.50,3,150,0,0,0,1,0 +4717,60,34,83,95616,2,1.40,1,75,0,1,0,1,0 +4718,29,5,121,95449,1,1.50,1,0,0,0,0,1,0 +4719,32,6,35,91107,3,1.00,1,0,0,1,0,1,0 +4720,32,8,140,94102,4,6.60,3,0,1,0,1,0,1 +4721,41,15,88,90740,1,2.80,3,0,0,1,0,0,0 +4722,52,26,70,94117,2,1.10,1,0,0,1,0,1,0 +4723,40,16,63,92807,1,1.50,3,0,0,0,0,0,0 +4724,39,15,125,90250,1,3.50,1,0,0,0,0,1,1 +4725,34,8,21,94107,4,1.00,1,0,0,0,0,0,0 +4726,34,8,75,95814,2,1.80,1,0,0,0,0,0,0 +4727,34,10,38,95039,1,1.33,1,0,0,1,0,1,0 +4728,41,17,58,92009,4,2.67,1,0,0,0,0,1,1 +4729,59,35,31,90630,3,0.40,2,0,0,0,0,1,0 +4730,40,14,18,90049,4,1.50,3,0,0,0,0,0,0 +4731,52,27,29,94720,1,1.50,2,159,0,0,0,0,1 +4732,37,11,29,91711,2,1.40,3,0,0,0,0,1,1 +4733,39,13,69,92096,3,0.10,1,247,0,0,0,0,0 +4734,49,23,121,90032,1,4.90,1,0,0,0,0,1,0 +4735,63,39,64,95814,1,1.80,3,147,0,0,0,1,1 +4736,34,9,84,94707,4,2.20,2,323,0,0,0,1,0 +4737,51,25,65,94143,3,0.70,2,0,0,0,0,0,0 +4738,61,36,85,94998,3,1.80,2,0,0,0,0,0,0 +4739,56,32,44,94575,3,1.50,1,153,0,0,0,1,0 +4740,62,38,174,94305,1,4.70,1,0,0,0,0,1,1 +4741,56,30,178,93940,1,2.90,1,0,0,0,0,1,0 +4742,58,32,55,93106,4,2.50,1,0,0,0,0,1,0 +4743,58,33,25,92121,4,0.90,2,90,0,0,0,1,1 +4744,50,26,21,94305,1,0.20,1,0,0,0,0,1,0 +4745,44,20,72,95616,3,0.30,3,0,0,0,0,1,0 +4746,49,23,129,94085,1,0.30,1,0,0,0,0,1,1 +4747,31,7,18,95616,1,0.40,3,0,0,0,0,1,0 +4748,49,25,91,94704,4,1.40,2,0,0,0,0,1,0 +4749,43,18,38,94309,1,0.50,3,144,0,0,0,1,0 +4750,31,5,21,94115,3,1.00,1,0,0,0,0,1,0 +4751,66,41,38,95134,1,1.10,3,0,0,0,0,0,1 +4752,41,17,154,92697,1,1.70,1,0,0,0,0,0,1 +4753,39,14,178,92123,1,4.10,1,207,0,0,0,1,0 +4754,46,21,85,92867,1,0.20,2,0,0,1,1,1,1 +4755,57,33,93,94025,2,1.60,1,161,0,0,0,0,0 +4756,59,35,151,93106,2,6.00,1,0,0,0,0,1,0 +4757,30,4,78,92677,4,2.20,2,236,0,1,0,0,0 +4758,26,2,135,94588,1,1.50,1,0,0,0,0,0,0 +4759,46,21,40,90045,1,0.30,1,116,0,0,0,0,0 +4760,66,41,80,92093,4,0.10,2,0,0,0,0,1,0 +4761,50,25,18,95819,2,0.00,1,0,0,0,0,0,1 +4762,61,35,74,91320,2,0.70,2,0,0,0,0,1,1 +4763,37,7,94,91016,4,1.80,3,232,0,0,0,1,0 +4764,51,25,173,95051,1,0.50,2,0,1,0,0,1,0 +4765,56,32,88,95051,4,1.00,2,0,0,0,0,1,1 +4766,58,34,82,94025,1,4.30,1,263,0,0,0,0,0 +4767,41,15,54,91775,3,2.10,1,0,0,0,0,1,0 +4768,35,9,45,90639,3,0.90,1,101,0,1,0,0,0 +4769,38,14,39,93118,1,2.00,2,0,0,0,0,1,0 +4770,26,2,20,95064,4,1.00,1,116,0,0,0,0,0 +4771,35,5,93,90095,4,1.80,3,0,0,0,0,0,1 +4772,36,11,85,90502,3,1.20,3,0,0,0,0,1,0 +4773,26,2,95,92130,3,0.80,1,0,0,0,0,1,0 +4774,53,28,48,92029,2,1.90,2,0,0,0,0,1,0 +4775,56,32,22,91768,1,1.20,3,0,0,0,0,1,1 +4776,44,14,33,94063,1,0.75,3,171,0,0,0,0,0 +4777,47,23,40,95123,2,2.10,3,156,0,0,0,1,0 +4778,32,8,30,94534,4,0.40,2,78,0,0,0,1,0 +4779,52,27,22,90755,4,0.80,1,0,0,0,0,1,1 +4780,39,14,20,90747,1,0.60,3,0,0,0,0,1,0 +4781,47,20,49,92104,3,2.50,2,0,0,0,0,1,0 +4782,35,9,25,94526,3,0.10,2,0,0,1,0,1,0 +4783,26,0,150,91311,2,7.20,1,0,0,0,0,0,1 +4784,43,19,32,94720,4,0.30,1,0,0,0,0,0,0 +4785,52,28,9,90405,2,0.20,1,0,0,0,0,0,0 +4786,30,5,23,94304,2,0.90,3,0,0,1,0,1,0 +4787,36,12,18,95521,4,1.00,1,0,0,0,0,1,1 +4788,48,22,42,95054,3,0.60,2,121,0,0,0,1,0 +4789,36,10,39,92009,1,2.00,1,153,0,0,0,0,0 +4790,58,34,84,95120,4,1.60,2,0,0,0,0,1,0 +4791,35,11,101,94143,3,3.80,3,150,1,0,0,1,0 +4792,59,35,43,91791,4,0.40,1,0,0,0,0,0,1 +4793,36,10,28,90840,4,1.00,1,130,0,0,0,1,0 +4794,45,21,59,94703,2,2.50,1,155,0,0,0,1,0 +4795,56,30,29,94110,4,1.50,3,146,0,0,0,0,0 +4796,46,21,39,91710,2,1.30,1,101,0,0,0,1,0 +4797,26,0,42,95032,4,1.30,3,0,0,1,0,0,0 +4798,37,11,24,94115,4,1.00,1,0,0,0,0,0,0 +4799,44,20,62,91604,3,0.30,3,0,0,0,0,0,1 +4800,44,20,33,94306,4,0.30,1,142,0,0,0,0,1 +4801,33,7,73,94028,1,2.50,1,135,0,0,0,0,0 +4802,34,10,88,94404,2,0.00,1,121,0,0,0,1,0 +4803,35,11,58,91330,3,2.80,1,0,0,0,0,1,0 +4804,48,24,48,92064,2,2.10,3,0,0,0,0,1,0 +4805,58,32,40,94124,1,2.80,2,0,0,0,0,0,0 +4806,30,6,160,90630,1,4.30,1,249,0,0,0,1,0 +4807,62,37,39,93117,3,1.50,1,0,0,0,0,1,0 +4808,40,14,53,90064,1,2.00,1,0,0,0,0,1,1 +4809,42,16,32,90033,3,0.50,2,0,0,0,0,0,1 +4810,43,19,32,94501,3,0.60,2,0,0,0,0,0,0 +4811,58,34,11,92037,2,0.30,1,96,0,0,0,1,0 +4812,36,12,123,90502,2,3.00,3,0,1,0,0,0,0 +4813,29,4,184,92126,4,2.20,3,612,1,0,0,1,0 +4814,49,23,60,95023,3,0.70,2,142,0,0,0,1,1 +4815,60,34,41,90064,3,2.20,3,0,0,0,0,0,1 +4816,58,32,99,92697,2,1.40,1,0,0,0,0,0,1 +4817,50,24,83,92333,3,3.00,2,0,0,0,0,0,1 +4818,46,22,134,93305,2,3.30,1,0,0,0,0,0,0 +4819,45,19,85,94112,2,1.70,2,0,0,0,0,1,0 +4820,32,6,41,95833,3,0.90,1,179,0,0,0,0,0 +4821,42,17,44,94124,1,0.30,3,0,0,1,1,1,1 +4822,30,6,62,95831,1,0.10,1,0,0,0,0,1,1 +4823,60,36,149,92007,1,4.70,1,0,0,0,0,1,0 +4824,46,21,115,95616,2,4.20,3,0,1,1,1,1,1 +4825,32,6,25,96001,3,1.00,1,0,0,0,0,1,0 +4826,56,32,84,95014,2,1.60,1,0,0,0,0,1,0 +4827,56,31,81,93943,2,0.00,3,225,0,0,0,0,0 +4828,30,6,181,91203,1,4.30,1,230,0,0,0,1,0 +4829,52,28,62,90089,1,1.80,3,0,0,0,0,1,0 +4830,31,7,11,94304,1,0.50,3,80,0,0,0,1,1 +4831,37,12,60,95616,4,2.10,3,217,0,0,0,1,0 +4832,30,6,42,91711,1,2.10,3,144,0,0,0,0,1 +4833,29,4,83,91950,4,2.20,2,0,0,0,0,1,1 +4834,49,24,109,92647,1,0.60,1,0,0,0,0,0,0 +4835,49,23,70,94305,1,0.30,1,217,0,0,0,0,0 +4836,65,39,25,95370,2,0.40,1,113,0,0,0,1,0 +4837,54,24,72,93943,3,1.40,3,218,0,0,0,0,1 +4838,36,10,183,95348,2,0.00,1,0,0,0,0,0,0 +4839,56,30,44,91330,4,2.50,1,0,0,0,0,0,1 +4840,34,8,52,95060,4,0.20,1,0,0,0,0,1,0 +4841,33,9,18,91768,4,0.40,2,0,0,0,0,1,0 +4842,59,35,40,92870,4,0.40,1,135,0,0,0,1,0 +4843,49,23,174,95449,3,4.60,2,590,1,0,0,0,0 +4844,61,34,41,94123,4,2.50,2,0,0,0,0,1,0 +4845,31,6,81,90840,2,2.50,1,313,0,0,0,0,0 +4846,45,21,128,94305,1,4.70,1,0,0,0,0,0,0 +4847,35,10,135,94596,3,4.80,2,0,1,0,0,1,0 +4848,37,11,65,94143,2,2.40,2,260,0,0,0,1,0 +4849,58,32,145,94920,2,0.50,1,119,0,0,0,1,0 +4850,49,25,65,90007,2,1.00,3,0,0,0,0,1,1 +4851,63,39,119,91330,1,2.90,1,0,0,1,0,1,0 +4852,55,31,124,93407,2,0.30,1,0,0,0,0,1,0 +4853,38,12,33,94708,4,1.50,3,0,0,1,0,0,1 +4854,45,19,41,91109,1,0.20,1,0,0,0,0,1,0 +4855,44,20,105,91730,1,4.70,1,0,0,0,0,0,1 +4856,58,32,130,94720,2,2.70,1,0,0,0,0,1,0 +4857,56,31,80,92069,4,1.30,3,0,0,0,0,1,0 +4858,37,13,115,90025,1,0.80,2,0,0,0,0,1,1 +4859,50,24,62,94550,2,0.80,3,0,0,0,0,1,0 +4860,34,8,165,91107,1,7.00,3,541,1,0,0,0,0 +4861,51,25,34,93106,3,0.60,2,128,0,0,0,1,0 +4862,49,24,18,95616,1,0.40,3,121,0,0,0,1,0 +4863,33,7,44,95605,1,0.30,1,0,0,0,0,0,0 +4864,61,35,25,91768,1,0.80,2,142,0,0,0,1,0 +4865,41,16,52,91311,2,2.20,3,0,0,0,0,1,0 +4866,50,24,133,90025,4,1.40,2,342,1,0,0,0,1 +4867,41,17,71,94801,2,3.20,1,0,0,0,0,1,1 +4868,38,12,61,94598,4,0.20,3,0,0,0,0,1,0 +4869,51,27,62,94063,2,3.20,3,118,0,0,0,0,1 +4870,63,39,33,92121,3,0.10,3,0,0,0,0,0,1 +4871,55,30,28,94040,2,2.00,2,0,0,0,0,1,1 +4872,46,22,53,95616,4,1.90,1,187,0,0,0,0,0 +4873,27,3,69,94305,3,0.70,2,0,0,0,0,1,1 +4874,59,35,165,94309,2,6.00,1,0,0,0,0,1,0 +4875,26,0,75,94061,3,0.30,3,0,0,0,0,0,0 +4876,61,36,54,94539,3,1.50,1,0,0,0,0,1,0 +4877,44,19,142,95054,1,1.50,3,0,1,0,0,0,0 +4878,53,29,53,92648,4,0.10,3,0,0,0,0,0,0 +4879,34,9,41,92093,1,1.00,1,0,0,0,0,1,0 +4880,40,15,43,90095,4,1.70,1,98,0,0,0,0,0 +4881,56,32,79,92037,3,2.67,1,0,0,0,0,1,0 +4882,57,32,24,92346,2,0.20,3,140,0,0,0,1,0 +4883,43,19,73,94301,3,2.33,1,0,0,1,1,1,1 +4884,38,13,129,92646,3,4.10,3,0,1,0,1,1,1 +4885,60,34,50,95670,3,2.20,3,0,0,0,0,1,1 +4886,54,30,28,92103,2,0.80,1,0,0,0,0,1,0 +4887,51,26,64,94005,4,1.80,3,0,0,0,0,0,0 +4888,41,15,49,90245,3,0.90,3,0,0,0,1,1,1 +4889,25,1,121,93106,1,5.40,1,158,0,0,0,1,0 +4890,58,28,58,90073,3,2.00,3,0,0,0,0,1,0 +4891,61,35,51,93555,3,1.40,3,0,0,0,0,1,0 +4892,56,31,61,90024,4,0.90,1,0,0,1,1,1,1 +4893,43,19,35,94112,1,0.30,3,120,0,1,0,1,0 +4894,42,12,39,94704,3,2.00,3,0,0,1,1,1,1 +4895,48,22,74,93950,1,1.40,3,0,0,1,0,0,0 +4896,45,20,201,92120,2,2.80,1,0,0,0,0,1,1 +4897,40,15,81,94304,2,0.40,1,0,0,0,0,1,0 +4898,43,18,44,91345,1,2.40,1,0,0,0,0,0,0 +4899,52,26,19,94143,1,1.40,3,96,0,0,0,1,0 +4900,54,29,85,94928,4,1.30,3,299,0,0,0,1,0 +4901,26,1,74,90028,4,2.20,1,0,0,0,0,1,0 +4902,26,0,54,96094,3,1.10,2,0,0,0,0,1,0 +4903,33,8,58,90505,2,2.50,1,0,0,0,0,1,0 +4904,40,15,18,94534,2,0.10,2,119,0,0,0,1,1 +4905,64,40,88,94305,1,3.80,1,243,0,0,0,1,1 +4906,62,37,19,93109,3,0.50,1,89,0,0,0,0,0 +4907,54,28,49,94608,1,2.20,3,128,0,0,0,0,0 +4908,34,9,101,94080,3,0.60,2,0,0,0,0,0,0 +4909,40,16,138,92121,2,6.10,1,0,0,0,0,1,0 +4910,41,16,25,95014,2,0.10,2,0,0,0,0,0,1 +4911,48,22,120,90291,1,0.00,1,0,0,0,0,1,0 +4912,46,22,153,94539,2,7.50,1,0,0,0,0,0,0 +4913,51,26,28,94061,1,1.30,2,94,0,1,0,1,0 +4914,30,4,110,93943,1,2.90,3,0,0,0,0,1,0 +4915,65,39,94,92374,1,2.00,1,0,0,0,0,0,1 +4916,49,24,48,93117,1,1.30,2,0,0,0,0,0,1 +4917,29,5,123,90291,2,0.60,1,0,0,0,0,1,0 +4918,36,10,33,95616,4,1.20,2,82,0,1,0,1,0 +4919,50,25,42,90232,2,0.70,2,110,0,0,0,0,1 +4920,41,16,68,92122,3,3.00,1,0,0,0,0,1,1 +4921,42,16,28,94002,4,1.50,3,91,0,0,0,1,1 +4922,37,11,42,95814,3,0.50,3,0,0,0,0,1,1 +4923,31,5,28,90717,1,0.30,1,0,0,0,0,1,1 +4924,40,15,73,92029,3,3.00,1,0,0,0,0,1,1 +4925,36,12,89,91304,2,2.70,1,0,0,0,0,0,0 +4926,64,39,82,94025,4,3.40,2,0,0,0,0,1,0 +4927,37,13,83,92220,2,1.70,2,0,0,0,0,0,1 +4928,43,19,121,94720,1,0.70,2,0,1,0,1,1,1 +4929,57,33,28,90245,1,1.20,3,98,0,0,0,1,0 +4930,62,36,39,92028,2,0.30,1,0,0,0,0,1,0 +4931,63,38,110,90095,3,1.80,2,109,0,0,0,1,0 +4932,57,27,55,95616,1,1.40,3,0,0,0,0,1,0 +4933,59,35,111,91107,1,4.30,1,0,0,0,0,1,0 +4934,47,23,94,92029,1,4.70,1,0,0,0,0,1,1 +4935,26,0,85,93950,2,1.60,3,0,0,0,0,1,1 +4936,59,33,81,94022,2,1.40,1,0,0,0,0,1,0 +4937,45,20,94,92009,3,0.50,3,0,0,0,0,0,0 +4938,33,8,162,94960,1,8.60,1,0,0,0,1,1,1 +4939,61,35,80,95973,4,1.70,3,0,0,0,0,1,0 +4940,54,29,70,92093,3,2.00,2,116,0,0,0,1,1 +4941,46,22,19,92870,3,0.50,1,0,0,0,0,1,0 +4942,28,4,112,90049,2,1.60,2,0,1,0,0,1,0 +4943,52,26,109,94710,1,2.40,1,308,0,0,1,1,1 +4944,26,0,12,96003,1,0.10,2,0,0,0,0,1,0 +4945,49,24,33,92093,3,1.70,2,0,0,0,0,1,0 +4946,42,18,49,95351,2,1.70,1,106,0,0,0,0,1 +4947,51,26,42,93118,1,1.30,2,0,0,0,0,1,0 +4948,39,13,41,95064,2,0.30,1,108,0,0,0,1,1 +4949,44,20,43,95032,1,0.70,1,0,0,0,0,0,1 +4950,29,5,64,94114,4,0.00,1,249,0,0,0,0,1 +4951,47,23,19,90089,1,1.00,1,0,0,0,0,0,1 +4952,53,27,65,92124,1,2.20,3,0,0,0,0,1,1 +4953,29,3,53,94005,4,1.80,3,0,0,0,0,1,0 +4954,47,21,32,95051,3,1.50,1,75,0,0,0,1,0 +4955,45,19,22,94904,3,1.50,1,0,0,0,0,1,1 +4956,63,37,39,91207,2,0.70,3,0,0,0,0,1,1 +4957,39,13,59,94109,4,0.20,3,0,0,1,0,0,1 +4958,29,-1,50,95842,2,1.75,3,0,0,0,0,0,1 +4959,50,26,19,90095,1,0.90,3,0,0,0,0,0,0 +4960,51,27,55,93014,1,1.60,2,197,0,1,0,1,0 +4961,58,28,81,91604,1,3.00,3,0,0,0,0,1,0 +4962,39,14,108,91401,3,1.20,3,0,0,0,0,1,1 +4963,46,20,122,90065,3,3.00,3,0,1,0,1,1,1 +4964,32,6,98,95054,2,4.50,3,306,0,0,0,0,0 +4965,53,27,110,90245,1,4.90,1,0,0,0,0,1,0 +4966,29,5,33,94709,1,1.80,2,78,0,0,0,1,0 +4967,41,17,34,91361,1,0.70,1,143,0,0,0,0,0 +4968,41,16,69,92697,1,0.10,2,0,0,0,0,1,0 +4969,58,32,41,93022,4,2.50,1,0,0,0,0,1,1 +4970,45,19,60,94143,2,0.40,3,250,0,0,0,1,0 +4971,37,13,95,95821,2,1.70,2,0,0,0,0,0,1 +4972,58,28,73,90024,1,1.40,3,0,0,1,0,0,0 +4973,58,32,41,93401,3,2.20,3,148,0,0,0,1,1 +4974,31,1,68,95045,4,4.00,3,0,0,0,0,1,0 +4975,59,33,64,92867,4,1.70,2,0,0,0,0,0,1 +4976,38,11,29,95207,4,1.00,2,0,0,0,0,1,0 +4977,29,5,31,95039,1,1.80,2,0,0,0,0,1,1 +4978,40,15,54,90266,3,0.80,3,0,0,0,0,1,0 +4979,57,27,63,90210,4,2.00,3,0,0,0,0,1,0 +4980,50,26,92,90740,1,2.60,2,213,0,0,0,0,1 +4981,29,5,135,95762,3,5.30,1,0,1,0,1,1,1 +4982,34,9,195,90266,2,3.00,1,122,0,0,0,1,0 +4983,36,10,45,95126,4,0.20,1,0,0,0,0,0,1 +4984,51,26,72,95370,1,2.90,1,0,0,0,0,0,0 +4985,27,1,98,94043,4,2.30,3,0,0,0,0,0,1 +4986,48,23,30,94720,3,1.70,2,162,0,0,0,1,0 +4987,32,6,78,95825,1,2.90,3,0,0,0,0,0,0 +4988,48,23,43,93943,3,1.70,2,159,0,0,0,1,0 +4989,34,8,85,95134,1,2.50,1,136,0,0,0,0,1 +4990,24,0,38,93555,1,1.00,3,0,0,0,0,1,0 +4991,55,25,58,95023,4,2.00,3,219,0,0,0,0,1 +4992,51,25,92,91330,1,1.90,2,100,0,0,0,0,1 +4993,30,5,13,90037,4,0.50,3,0,0,0,0,0,0 +4994,45,21,218,91801,2,6.67,1,0,0,0,0,1,0 +4995,64,40,75,94588,3,2.00,3,0,0,0,0,1,0 +4996,29,3,40,92697,1,1.90,3,0,0,0,0,1,0 +4997,30,4,15,92037,4,0.40,1,85,0,0,0,1,0 +4998,63,39,24,93023,2,0.30,3,0,0,0,0,0,0 +4999,65,40,49,90034,3,0.50,2,0,0,0,0,1,0 +5000,28,4,83,92612,3,0.80,1,0,0,0,0,1,1 diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/Age Distribution.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Age Distribution.png new file mode 100644 index 00000000..5ea87572 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Age Distribution.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/Age.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Age.png new file mode 100644 index 00000000..59f20a67 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Age.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/Approved_Not_Approved.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Approved_Not_Approved.png new file mode 100644 index 00000000..b29f5dbc Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Approved_Not_Approved.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/Average CC Spending.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Average CC Spending.png new file mode 100644 index 00000000..3b4d03b9 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Average CC Spending.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/Box Plot of income.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Box Plot of income.png new file mode 100644 index 00000000..50de6357 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Box Plot of income.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/CCAvg Distribution by Personal Loan.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/CCAvg Distribution by Personal Loan.png new file mode 100644 index 00000000..b305f04c Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/CCAvg Distribution by Personal Loan.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/Distribution of Education.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Distribution of Education.png new file mode 100644 index 00000000..4f0b906b Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Distribution of Education.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/FNN_Accuracy.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/FNN_Accuracy.png new file mode 100644 index 00000000..575caf58 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/FNN_Accuracy.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/FNN_Loss.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/FNN_Loss.png new file mode 100644 index 00000000..a474b39d Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/FNN_Loss.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/Heatmap.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Heatmap.png new file mode 100644 index 00000000..22231ba0 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Heatmap.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/Mortgage Distribution by Personal Loan.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Mortgage Distribution by Personal Loan.png new file mode 100644 index 00000000..c756109b Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Mortgage Distribution by Personal Loan.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/Personal loans.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Personal loans.png new file mode 100644 index 00000000..05248596 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Personal loans.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/TabNet_Accuracy.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/TabNet_Accuracy.png new file mode 100644 index 00000000..8833e5ce Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/TabNet_Accuracy.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/TabNet_Loss.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/TabNet_Loss.png new file mode 100644 index 00000000..37b9a4c5 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/TabNet_Loss.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/Updated_Correlation_Matrix.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Updated_Correlation_Matrix.png new file mode 100644 index 00000000..a836d466 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/Updated_Correlation_Matrix.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/WDNN_Accuracy.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/WDNN_Accuracy.png new file mode 100644 index 00000000..8ccd361e Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/WDNN_Accuracy.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/WDNN_Loss.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/WDNN_Loss.png new file mode 100644 index 00000000..16f6d5a2 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/WDNN_Loss.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/bar graph.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/bar graph.png new file mode 100644 index 00000000..8bc39c89 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/bar graph.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/conf_matrix.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/conf_matrix.png new file mode 100644 index 00000000..e1882016 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/conf_matrix.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/confusion matrix.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/confusion matrix.png new file mode 100644 index 00000000..9225e45f Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/confusion matrix.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/histogram.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/histogram.png new file mode 100644 index 00000000..d6a51938 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/histogram.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/income.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/income.png new file mode 100644 index 00000000..f1d4c2ed Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/income.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/input visualisation.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/input visualisation.png new file mode 100644 index 00000000..59f3b957 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/input visualisation.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/modelloss.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/modelloss.png new file mode 100644 index 00000000..4870b192 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/modelloss.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/pie chart.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/pie chart.png new file mode 100644 index 00000000..0a9fc52a Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/pie chart.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Images/training loss.png b/Loan Status Prediction/Bank Loan Approval Prediction/Images/training loss.png new file mode 100644 index 00000000..6b5a5827 Binary files /dev/null and b/Loan Status Prediction/Bank Loan Approval Prediction/Images/training loss.png differ diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Model/FNN_TabNet_WDNN.ipynb b/Loan Status Prediction/Bank Loan Approval Prediction/Model/FNN_TabNet_WDNN.ipynb new file mode 100644 index 00000000..b96f77b5 --- /dev/null +++ b/Loan Status Prediction/Bank Loan Approval Prediction/Model/FNN_TabNet_WDNN.ipynb @@ -0,0 +1 @@ +{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":8469482,"sourceType":"datasetVersion","datasetId":5049987}],"dockerImageVersionId":30698,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false},"colab":{"provenance":[],"gpuType":"T4"},"accelerator":"GPU"},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# About this notebook\n\nThis notebook presents three different Deep Learning models for training Universal Bank dataset. These are the models which are taken:\n\n- Feedforward Neural Network with k-Fold validation\n- TabNet model with k-Fold validation\n- Wide & Deep neural network architecture\n\nAmongst this, TabNet model is selected which gives 0.985 validation accuracy.","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","id":"PiYW-FFi9jwv","execution":{"iopub.status.busy":"2024-05-22T12:18:08.633837Z","iopub.execute_input":"2024-05-22T12:18:08.634916Z","iopub.status.idle":"2024-05-22T12:18:09.199354Z","shell.execute_reply.started":"2024-05-22T12:18:08.634873Z","shell.execute_reply":"2024-05-22T12:18:09.198173Z"},"trusted":true},"execution_count":1,"outputs":[]},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings(\"ignore\")","metadata":{"id":"TfIruao4X8ho","execution":{"iopub.status.busy":"2024-05-22T12:18:09.201292Z","iopub.execute_input":"2024-05-22T12:18:09.201753Z","iopub.status.idle":"2024-05-22T12:18:09.206470Z","shell.execute_reply.started":"2024-05-22T12:18:09.201723Z","shell.execute_reply":"2024-05-22T12:18:09.205330Z"},"trusted":true},"execution_count":2,"outputs":[]},{"cell_type":"markdown","source":"# Loading the Dataset","metadata":{}},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/UniversalBank.csv')","metadata":{"id":"lkce0KVw95Y3","execution":{"iopub.status.busy":"2024-05-22T12:18:09.207871Z","iopub.execute_input":"2024-05-22T12:18:09.208222Z","iopub.status.idle":"2024-05-22T12:18:09.256617Z","shell.execute_reply.started":"2024-05-22T12:18:09.208194Z","shell.execute_reply":"2024-05-22T12:18:09.255506Z"},"trusted":true},"execution_count":3,"outputs":[]},{"cell_type":"markdown","source":"# Dataset Description\n\n#### Observations\n\n1. Minimum value of Experience is -3 which is not possible.\n2. ZIP Code is not a numeric data. It is to be considered as nominal data. Out of 5000 records, there are only 467 unique ZIP codes. Thus this represents that the dataset is restricted to a particular region.\n3. Education has 3 unique values {1: Bachelor, 2: Masters, 3: Advanced Degree}. So this is again not a numeric data. It is ordinal data.\n4. Personal Loan (Target Variable) is either 0 or 1. {0: Loan not approved, 1: Loan approved}. So this is binary data,\n5. Securities Account is binary data representing {0: doesn't have security account, 1: has security account}\n6. CD Account is binary data representing {0: doesn't have CD Account, 1: has CD Account}\n7. Online is binary data representing {0: doesn't use online banking, 1: uses online banking}\n8. Credit Card is binary data representing {0: doesn't have credit card, 1: has credit card}\n9. ID is the unique column representing IDs of records.\n\nRest are numeric data","metadata":{}},{"cell_type":"code","source":"train.describe()","metadata":{"id":"UENL5vRu9jwx","outputId":"1860a398-05d7-459d-c77d-07fc5cce2a1d","execution":{"iopub.status.busy":"2024-05-22T12:18:09.259813Z","iopub.execute_input":"2024-05-22T12:18:09.260277Z","iopub.status.idle":"2024-05-22T12:18:09.327621Z","shell.execute_reply.started":"2024-05-22T12:18:09.260236Z","shell.execute_reply":"2024-05-22T12:18:09.326203Z"},"trusted":true},"execution_count":4,"outputs":[{"execution_count":4,"output_type":"execute_result","data":{"text/plain":" ID Age Experience Income ZIP Code \\\ncount 5000.000000 5000.000000 5000.000000 5000.000000 5000.000000 \nmean 2500.500000 45.338400 20.104600 73.774200 93152.503000 \nstd 1443.520003 11.463166 11.467954 46.033729 2121.852197 \nmin 1.000000 23.000000 -3.000000 8.000000 9307.000000 \n25% 1250.750000 35.000000 10.000000 39.000000 91911.000000 \n50% 2500.500000 45.000000 20.000000 64.000000 93437.000000 \n75% 3750.250000 55.000000 30.000000 98.000000 94608.000000 \nmax 5000.000000 67.000000 43.000000 224.000000 96651.000000 \n\n Family CCAvg Education Mortgage Personal Loan \\\ncount 5000.000000 5000.000000 5000.000000 5000.000000 5000.000000 \nmean 2.396400 1.937938 1.881000 56.498800 0.096000 \nstd 1.147663 1.747659 0.839869 101.713802 0.294621 \nmin 1.000000 0.000000 1.000000 0.000000 0.000000 \n25% 1.000000 0.700000 1.000000 0.000000 0.000000 \n50% 2.000000 1.500000 2.000000 0.000000 0.000000 \n75% 3.000000 2.500000 3.000000 101.000000 0.000000 \nmax 4.000000 10.000000 3.000000 635.000000 1.000000 \n\n Securities Account CD Account Online CreditCard \ncount 5000.000000 5000.00000 5000.000000 5000.000000 \nmean 0.104400 0.06040 0.596800 0.294000 \nstd 0.305809 0.23825 0.490589 0.455637 \nmin 0.000000 0.00000 0.000000 0.000000 \n25% 0.000000 0.00000 0.000000 0.000000 \n50% 0.000000 0.00000 1.000000 0.000000 \n75% 0.000000 0.00000 1.000000 1.000000 \nmax 1.000000 1.00000 1.000000 1.000000 ","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
IDAgeExperienceIncomeZIP CodeFamilyCCAvgEducationMortgagePersonal LoanSecurities AccountCD AccountOnlineCreditCard
count5000.0000005000.0000005000.0000005000.0000005000.0000005000.0000005000.0000005000.0000005000.0000005000.0000005000.0000005000.000005000.0000005000.000000
mean2500.50000045.33840020.10460073.77420093152.5030002.3964001.9379381.88100056.4988000.0960000.1044000.060400.5968000.294000
std1443.52000311.46316611.46795446.0337292121.8521971.1476631.7476590.839869101.7138020.2946210.3058090.238250.4905890.455637
min1.00000023.000000-3.0000008.0000009307.0000001.0000000.0000001.0000000.0000000.0000000.0000000.000000.0000000.000000
25%1250.75000035.00000010.00000039.00000091911.0000001.0000000.7000001.0000000.0000000.0000000.0000000.000000.0000000.000000
50%2500.50000045.00000020.00000064.00000093437.0000002.0000001.5000002.0000000.0000000.0000000.0000000.000001.0000000.000000
75%3750.25000055.00000030.00000098.00000094608.0000003.0000002.5000003.000000101.0000000.0000000.0000000.000001.0000001.000000
max5000.00000067.00000043.000000224.00000096651.0000004.00000010.0000003.000000635.0000001.0000001.0000001.000001.0000001.000000
\n
"},"metadata":{}}]},{"cell_type":"code","source":"train.info()","metadata":{"id":"k282xrot9jwy","outputId":"2ab9f04f-ad0a-4f2f-a840-7fdbfba27412","execution":{"iopub.status.busy":"2024-05-22T12:18:09.329105Z","iopub.execute_input":"2024-05-22T12:18:09.329534Z","iopub.status.idle":"2024-05-22T12:18:09.356863Z","shell.execute_reply.started":"2024-05-22T12:18:09.329495Z","shell.execute_reply":"2024-05-22T12:18:09.355640Z"},"trusted":true},"execution_count":5,"outputs":[{"name":"stdout","text":"\nRangeIndex: 5000 entries, 0 to 4999\nData columns (total 14 columns):\n # Column Non-Null Count Dtype \n--- ------ -------------- ----- \n 0 ID 5000 non-null int64 \n 1 Age 5000 non-null int64 \n 2 Experience 5000 non-null int64 \n 3 Income 5000 non-null int64 \n 4 ZIP Code 5000 non-null int64 \n 5 Family 5000 non-null int64 \n 6 CCAvg 5000 non-null float64\n 7 Education 5000 non-null int64 \n 8 Mortgage 5000 non-null int64 \n 9 Personal Loan 5000 non-null int64 \n 10 Securities Account 5000 non-null int64 \n 11 CD Account 5000 non-null int64 \n 12 Online 5000 non-null int64 \n 13 CreditCard 5000 non-null int64 \ndtypes: float64(1), int64(13)\nmemory usage: 547.0 KB\n","output_type":"stream"}]},{"cell_type":"markdown","source":"# Checking for negative values if any\n\nIt can be seen that Experience field has 52 negative values. But this field should always be zero or positive.","metadata":{}},{"cell_type":"code","source":"(train < 0).sum()","metadata":{"id":"cMZ7mYX59jwy","outputId":"ece57ba4-57c2-4139-9df9-3ae716acabc2","execution":{"iopub.status.busy":"2024-05-22T12:18:09.360718Z","iopub.execute_input":"2024-05-22T12:18:09.361085Z","iopub.status.idle":"2024-05-22T12:18:09.372442Z","shell.execute_reply.started":"2024-05-22T12:18:09.361054Z","shell.execute_reply":"2024-05-22T12:18:09.371149Z"},"trusted":true},"execution_count":6,"outputs":[{"execution_count":6,"output_type":"execute_result","data":{"text/plain":"ID 0\nAge 0\nExperience 52\nIncome 0\nZIP Code 0\nFamily 0\nCCAvg 0\nEducation 0\nMortgage 0\nPersonal Loan 0\nSecurities Account 0\nCD Account 0\nOnline 0\nCreditCard 0\ndtype: int64"},"metadata":{}}]},{"cell_type":"markdown","source":"# Type Casting\n\n1. Numeric to Boolean\n2. Numeric to String","metadata":{}},{"cell_type":"code","source":"train['ZIP Code'].nunique() # Out of 5000 records, there are 467 unique values","metadata":{"id":"xti6FLFY9jwz","outputId":"25f7ada3-7ff9-4bcd-f133-bd51160462c9","execution":{"iopub.status.busy":"2024-05-22T12:18:09.374428Z","iopub.execute_input":"2024-05-22T12:18:09.374875Z","iopub.status.idle":"2024-05-22T12:18:09.387246Z","shell.execute_reply.started":"2024-05-22T12:18:09.374814Z","shell.execute_reply":"2024-05-22T12:18:09.386091Z"},"trusted":true},"execution_count":7,"outputs":[{"execution_count":7,"output_type":"execute_result","data":{"text/plain":"467"},"metadata":{}}]},{"cell_type":"code","source":"train['CD Account'] = train['CD Account'].astype(bool)\ntrain['Online'] = train['Online'].astype(bool)\ntrain['CreditCard'] = train['CreditCard'].astype(bool)\ntrain['Personal Loan'] = train['Personal Loan'].astype(bool)\ntrain['ZIP Code'] = train['ZIP Code'].astype(str)\ntrain['Education'] = train['Education'].astype(str)\ntrain['Securities Account'] = train['Securities Account'].astype(bool)","metadata":{"id":"QRjZsRVX9jwz","execution":{"iopub.status.busy":"2024-05-22T12:18:09.389036Z","iopub.execute_input":"2024-05-22T12:18:09.389498Z","iopub.status.idle":"2024-05-22T12:18:09.412351Z","shell.execute_reply.started":"2024-05-22T12:18:09.389428Z","shell.execute_reply":"2024-05-22T12:18:09.411116Z"},"trusted":true},"execution_count":8,"outputs":[]},{"cell_type":"markdown","source":"# Checking the data where Experience is less than 0\n\nIt can be observed that other fields have valid records. So we can't drop these records. Instead we will replace it with appropriate values.","metadata":{}},{"cell_type":"code","source":"train[train['Experience']<0]","metadata":{"id":"CV2qIofA9jw0","outputId":"a92ff6bb-4acb-4e83-acaf-e7d6fa11b591","execution":{"iopub.status.busy":"2024-05-22T12:18:09.414487Z","iopub.execute_input":"2024-05-22T12:18:09.415155Z","iopub.status.idle":"2024-05-22T12:18:09.468384Z","shell.execute_reply.started":"2024-05-22T12:18:09.415110Z","shell.execute_reply":"2024-05-22T12:18:09.467107Z"},"trusted":true},"execution_count":9,"outputs":[{"execution_count":9,"output_type":"execute_result","data":{"text/plain":" ID Age Experience Income ZIP Code Family CCAvg Education \\\n89 90 25 -1 113 94303 4 2.30 3 \n226 227 24 -1 39 94085 2 1.70 2 \n315 316 24 -2 51 90630 3 0.30 3 \n451 452 28 -2 48 94132 2 1.75 3 \n524 525 24 -1 75 93014 4 0.20 1 \n536 537 25 -1 43 92173 3 2.40 2 \n540 541 25 -1 109 94010 4 2.30 3 \n576 577 25 -1 48 92870 3 0.30 3 \n583 584 24 -1 38 95045 2 1.70 2 \n597 598 24 -2 125 92835 2 7.20 1 \n649 650 25 -1 82 92677 4 2.10 3 \n670 671 23 -1 61 92374 4 2.60 1 \n686 687 24 -1 38 92612 4 0.60 2 \n793 794 24 -2 150 94720 2 2.00 1 \n889 890 24 -2 82 91103 2 1.60 3 \n909 910 23 -1 149 91709 1 6.33 1 \n1173 1174 24 -1 35 94305 2 1.70 2 \n1428 1429 25 -1 21 94583 4 0.40 1 \n1522 1523 25 -1 101 94720 4 2.30 3 \n1905 1906 25 -1 112 92507 2 2.00 1 \n2102 2103 25 -1 81 92647 2 1.60 3 \n2430 2431 23 -1 73 92120 4 2.60 1 \n2466 2467 24 -2 80 94105 2 1.60 3 \n2545 2546 25 -1 39 94720 3 2.40 2 \n2618 2619 23 -3 55 92704 3 2.40 2 \n2717 2718 23 -2 45 95422 4 0.60 2 \n2848 2849 24 -1 78 94720 2 1.80 2 \n2876 2877 24 -2 80 91107 2 1.60 3 \n2962 2963 23 -2 81 91711 2 1.80 2 \n2980 2981 25 -1 53 94305 3 2.40 2 \n3076 3077 29 -1 62 92672 2 1.75 3 \n3130 3131 23 -2 82 92152 2 1.80 2 \n3157 3158 23 -1 13 94720 4 1.00 1 \n3279 3280 26 -1 44 94901 1 2.00 2 \n3284 3285 25 -1 101 95819 4 2.10 3 \n3292 3293 25 -1 13 95616 4 0.40 1 \n3394 3395 25 -1 113 90089 4 2.10 3 \n3425 3426 23 -1 12 91605 4 1.00 1 \n3626 3627 24 -3 28 90089 4 1.00 3 \n3796 3797 24 -2 50 94920 3 2.40 2 \n3824 3825 23 -1 12 95064 4 1.00 1 \n3887 3888 24 -2 118 92634 2 7.20 1 \n3946 3947 25 -1 40 93117 3 2.40 2 \n4015 4016 25 -1 139 93106 2 2.00 1 \n4088 4089 29 -1 71 94801 2 1.75 3 \n4116 4117 24 -2 135 90065 2 7.20 1 \n4285 4286 23 -3 149 93555 2 7.20 1 \n4411 4412 23 -2 75 90291 2 1.80 2 \n4481 4482 25 -2 35 95045 4 1.00 3 \n4514 4515 24 -3 41 91768 4 1.00 3 \n4582 4583 25 -1 69 92691 3 0.30 3 \n4957 4958 29 -1 50 95842 2 1.75 3 \n\n Mortgage Personal Loan Securities Account CD Account Online \\\n89 0 False False False False \n226 0 False False False False \n315 0 False False False True \n451 89 False False False True \n524 0 False False False True \n536 176 False False False True \n540 314 False False False True \n576 0 False False False False \n583 0 False False False True \n597 0 False True False False \n649 0 False False False True \n670 239 False False False True \n686 0 False False False True \n793 0 False False False True \n889 0 False False False True \n909 305 False False False False \n1173 0 False False False False \n1428 90 False False False True \n1522 256 False False False False \n1905 241 False False False True \n2102 0 False False False True \n2430 0 False False False True \n2466 0 False False False True \n2545 0 False False False True \n2618 145 False False False True \n2717 0 False False False True \n2848 0 False False False False \n2876 238 False False False False \n2962 0 False False False False \n2980 0 False False False False \n3076 0 False False False False \n3130 0 False True False False \n3157 84 False False False True \n3279 0 False False False False \n3284 0 False False False False \n3292 0 False True False False \n3394 0 False False False True \n3425 90 False False False True \n3626 0 False False False False \n3796 0 False True False False \n3824 0 False True False False \n3887 0 False True False True \n3946 0 False False False True \n4015 0 False False False False \n4088 0 False False False False \n4116 0 False False False True \n4285 0 False False False True \n4411 0 False False False True \n4481 0 False False False True \n4514 0 False False False True \n4582 0 False False False True \n4957 0 False False False False \n\n CreditCard \n89 True \n226 False \n315 False \n451 False \n524 False \n536 False \n540 False \n576 True \n583 False \n597 True \n649 False \n670 False \n686 False \n793 False \n889 True \n909 True \n1173 False \n1428 False \n1522 True \n1905 False \n2102 True \n2430 False \n2466 False \n2545 False \n2618 False \n2717 True \n2848 False \n2876 False \n2962 False \n2980 False \n3076 True \n3130 True \n3157 False \n3279 False \n3284 True \n3292 False \n3394 False \n3425 False \n3626 False \n3796 False \n3824 True \n3887 False \n3946 False \n4015 True \n4088 False \n4116 False \n4285 False \n4411 True \n4481 False \n4514 False \n4582 False \n4957 True ","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
IDAgeExperienceIncomeZIP CodeFamilyCCAvgEducationMortgagePersonal LoanSecurities AccountCD AccountOnlineCreditCard
899025-11139430342.3030FalseFalseFalseFalseTrue
22622724-1399408521.7020FalseFalseFalseFalseFalse
31531624-2519063030.3030FalseFalseFalseTrueFalse
45145228-2489413221.75389FalseFalseFalseTrueFalse
52452524-1759301440.2010FalseFalseFalseTrueFalse
53653725-1439217332.402176FalseFalseFalseTrueFalse
54054125-11099401042.303314FalseFalseFalseTrueFalse
57657725-1489287030.3030FalseFalseFalseFalseTrue
58358424-1389504521.7020FalseFalseFalseTrueFalse
59759824-21259283527.2010FalseTrueFalseFalseTrue
64965025-1829267742.1030FalseFalseFalseTrueFalse
67067123-1619237442.601239FalseFalseFalseTrueFalse
68668724-1389261240.6020FalseFalseFalseTrueFalse
79379424-21509472022.0010FalseFalseFalseTrueFalse
88989024-2829110321.6030FalseFalseFalseTrueTrue
90991023-11499170916.331305FalseFalseFalseFalseTrue
1173117424-1359430521.7020FalseFalseFalseFalseFalse
1428142925-1219458340.40190FalseFalseFalseTrueFalse
1522152325-11019472042.303256FalseFalseFalseFalseTrue
1905190625-11129250722.001241FalseFalseFalseTrueFalse
2102210325-1819264721.6030FalseFalseFalseTrueTrue
2430243123-1739212042.6010FalseFalseFalseTrueFalse
2466246724-2809410521.6030FalseFalseFalseTrueFalse
2545254625-1399472032.4020FalseFalseFalseTrueFalse
2618261923-3559270432.402145FalseFalseFalseTrueFalse
2717271823-2459542240.6020FalseFalseFalseTrueTrue
2848284924-1789472021.8020FalseFalseFalseFalseFalse
2876287724-2809110721.603238FalseFalseFalseFalseFalse
2962296323-2819171121.8020FalseFalseFalseFalseFalse
2980298125-1539430532.4020FalseFalseFalseFalseFalse
3076307729-1629267221.7530FalseFalseFalseFalseTrue
3130313123-2829215221.8020FalseTrueFalseFalseTrue
3157315823-1139472041.00184FalseFalseFalseTrueFalse
3279328026-1449490112.0020FalseFalseFalseFalseFalse
3284328525-11019581942.1030FalseFalseFalseFalseTrue
3292329325-1139561640.4010FalseTrueFalseFalseFalse
3394339525-11139008942.1030FalseFalseFalseTrueFalse
3425342623-1129160541.00190FalseFalseFalseTrueFalse
3626362724-3289008941.0030FalseFalseFalseFalseFalse
3796379724-2509492032.4020FalseTrueFalseFalseFalse
3824382523-1129506441.0010FalseTrueFalseFalseTrue
3887388824-21189263427.2010FalseTrueFalseTrueFalse
3946394725-1409311732.4020FalseFalseFalseTrueFalse
4015401625-11399310622.0010FalseFalseFalseFalseTrue
4088408929-1719480121.7530FalseFalseFalseFalseFalse
4116411724-21359006527.2010FalseFalseFalseTrueFalse
4285428623-31499355527.2010FalseFalseFalseTrueFalse
4411441223-2759029121.8020FalseFalseFalseTrueTrue
4481448225-2359504541.0030FalseFalseFalseTrueFalse
4514451524-3419176841.0030FalseFalseFalseTrueFalse
4582458325-1699269130.3030FalseFalseFalseTrueFalse
4957495829-1509584221.7530FalseFalseFalseFalseTrue
\n
"},"metadata":{}}]},{"cell_type":"markdown","source":"# Cheking the minimum difference between age and experience\n\nSo at age 23, people have no experience. So after 23, they can have n year experience.","metadata":{}},{"cell_type":"code","source":"n = 0\nwhile True:\n m = (train['Age'] - train['Experience'] <= n).sum()\n if m > 0:\n break\n n += 1\nprint(n)","metadata":{"id":"TSlPZHuz9jw0","outputId":"afbe85b6-044e-4595-926a-1eebe583c03e","execution":{"iopub.status.busy":"2024-05-22T12:18:09.472918Z","iopub.execute_input":"2024-05-22T12:18:09.473295Z","iopub.status.idle":"2024-05-22T12:18:09.490668Z","shell.execute_reply.started":"2024-05-22T12:18:09.473265Z","shell.execute_reply":"2024-05-22T12:18:09.489273Z"},"trusted":true},"execution_count":10,"outputs":[{"name":"stdout","text":"24\n","output_type":"stream"}]},{"cell_type":"code","source":"train.loc[train['Experience'] < 0, 'Experience'] = train.loc[train['Experience'] < 0, 'Age'] - 23","metadata":{"id":"QFNXs72J9jw1","execution":{"iopub.status.busy":"2024-05-22T12:18:09.546599Z","iopub.execute_input":"2024-05-22T12:18:09.546988Z","iopub.status.idle":"2024-05-22T12:18:09.562806Z","shell.execute_reply.started":"2024-05-22T12:18:09.546952Z","shell.execute_reply":"2024-05-22T12:18:09.561531Z"},"trusted":true},"execution_count":13,"outputs":[]},{"cell_type":"code","source":"train.describe() # checkong the minimum and maximum Experience value","metadata":{"id":"qpwCaO-H9jw1","outputId":"8cb33f4e-f982-43e7-c7ea-5a99b5233e79","execution":{"iopub.status.busy":"2024-05-22T12:18:09.564615Z","iopub.execute_input":"2024-05-22T12:18:09.565081Z","iopub.status.idle":"2024-05-22T12:18:09.601911Z","shell.execute_reply.started":"2024-05-22T12:18:09.565043Z","shell.execute_reply":"2024-05-22T12:18:09.600681Z"},"trusted":true},"execution_count":14,"outputs":[{"execution_count":14,"output_type":"execute_result","data":{"text/plain":" ID Age Experience Income Family \\\ncount 5000.000000 5000.000000 5000.000000 5000.000000 5000.000000 \nmean 2500.500000 45.338400 20.135400 73.774200 2.396400 \nstd 1443.520003 11.463166 11.414672 46.033729 1.147663 \nmin 1.000000 23.000000 0.000000 8.000000 1.000000 \n25% 1250.750000 35.000000 10.000000 39.000000 1.000000 \n50% 2500.500000 45.000000 20.000000 64.000000 2.000000 \n75% 3750.250000 55.000000 30.000000 98.000000 3.000000 \nmax 5000.000000 67.000000 43.000000 224.000000 4.000000 \n\n CCAvg Mortgage \ncount 5000.000000 5000.000000 \nmean 1.937938 56.498800 \nstd 1.747659 101.713802 \nmin 0.000000 0.000000 \n25% 0.700000 0.000000 \n50% 1.500000 0.000000 \n75% 2.500000 101.000000 \nmax 10.000000 635.000000 ","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
IDAgeExperienceIncomeFamilyCCAvgMortgage
count5000.0000005000.0000005000.0000005000.0000005000.0000005000.0000005000.000000
mean2500.50000045.33840020.13540073.7742002.3964001.93793856.498800
std1443.52000311.46316611.41467246.0337291.1476631.747659101.713802
min1.00000023.0000000.0000008.0000001.0000000.0000000.000000
25%1250.75000035.00000010.00000039.0000001.0000000.7000000.000000
50%2500.50000045.00000020.00000064.0000002.0000001.5000000.000000
75%3750.25000055.00000030.00000098.0000003.0000002.500000101.000000
max5000.00000067.00000043.000000224.0000004.00000010.000000635.000000
\n
"},"metadata":{}}]},{"cell_type":"markdown","source":"# Data-preprocessing\n\nThis code performs data preprocessing tasks, particularly encoding categorical variables and frequency encoding one of the features.\n\n#### Frequency Encoding for 'ZIP Code':\n\n- Calculates the frequency of each unique value in the 'ZIP Code' column by dividing the count of each value by the total number of samples in the DataFrame.\n- Maps these frequencies to the corresponding 'ZIP Code' values in the DataFrame, effectively encoding the 'ZIP Code' column with its frequency values.\n- Saves the frequency encoding dictionary (zip_code_freq) using the joblib.dump() function to a file named 'zip_code_freq_encoder.pkl'.\n\n#### Label Encoding for Categorical Columns:\n\n- Specifies a list of columns (columns_to_encode) that need to be label encoded: 'Education', 'Personal Loan', 'CD Account', 'Online', 'CreditCard', and 'Securities Account'.\n- Iterates over each column in columns_to_encode and applies label encoding using LabelEncoder() from scikit-learn.\n- Saves the trained label encoders for each column in a dictionary (label_encoders) where the column name is the key and the corresponding label encoder is the value.\n- Updates the DataFrame train by replacing the original categorical values with their encoded counterparts.\n\n#### Saving Label Encoders:\n\n- Saves the dictionary of label encoders (label_encoders) to a file named 'label_encoders.pkl' using the joblib.dump() function.","metadata":{}},{"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\nimport joblib\n\n# Displaying the DataFrame structure\nprint(\"Original DataFrame:\")\nprint(train.info())\n\n# Frequency encoding for 'ZIP Code'\nzip_code_freq = train['ZIP Code'].value_counts() / len(train)\ntrain['ZIP Code'] = train['ZIP Code'].map(zip_code_freq)\n\n# Saving the frequency encoding\njoblib.dump(zip_code_freq, 'zip_code_freq_encoder.pkl')\n\n# Columns to encode using LabelEncoder\ncolumns_to_encode = ['Education', 'Personal Loan', 'CD Account', 'Online', 'CreditCard', 'Securities Account']\n\n# Initialize a single label encoder dictionary to store the label encoders\nlabel_encoders = {}\n\n# Encoding the columns using a single LabelEncoder\nfor col in columns_to_encode:\n le = LabelEncoder()\n train[col] = le.fit_transform(train[col])\n label_encoders[col] = le\n\n# Saving the single label encoder dictionary\njoblib.dump(label_encoders, 'label_encoders.pkl')\n\n# Displaying info of the updated DataFrame\nprint(\"\\nUpdated DataFrame Info:\")\nprint(train.info())","metadata":{"id":"6Ly_zuCb9jw1","outputId":"92a96947-ac03-462f-a302-fcf4711f47b4","execution":{"iopub.status.busy":"2024-05-22T12:18:09.603244Z","iopub.execute_input":"2024-05-22T12:18:09.603574Z","iopub.status.idle":"2024-05-22T12:18:10.178636Z","shell.execute_reply.started":"2024-05-22T12:18:09.603546Z","shell.execute_reply":"2024-05-22T12:18:10.177235Z"},"trusted":true},"execution_count":15,"outputs":[{"name":"stdout","text":"Original DataFrame:\n\nRangeIndex: 5000 entries, 0 to 4999\nData columns (total 14 columns):\n # Column Non-Null Count Dtype \n--- ------ -------------- ----- \n 0 ID 5000 non-null int64 \n 1 Age 5000 non-null int64 \n 2 Experience 5000 non-null int64 \n 3 Income 5000 non-null int64 \n 4 ZIP Code 5000 non-null object \n 5 Family 5000 non-null int64 \n 6 CCAvg 5000 non-null float64\n 7 Education 5000 non-null object \n 8 Mortgage 5000 non-null int64 \n 9 Personal Loan 5000 non-null bool \n 10 Securities Account 5000 non-null bool \n 11 CD Account 5000 non-null bool \n 12 Online 5000 non-null bool \n 13 CreditCard 5000 non-null bool \ndtypes: bool(5), float64(1), int64(6), object(2)\nmemory usage: 376.1+ KB\nNone\n\nUpdated DataFrame Info:\n\nRangeIndex: 5000 entries, 0 to 4999\nData columns (total 14 columns):\n # Column Non-Null Count Dtype \n--- ------ -------------- ----- \n 0 ID 5000 non-null int64 \n 1 Age 5000 non-null int64 \n 2 Experience 5000 non-null int64 \n 3 Income 5000 non-null int64 \n 4 ZIP Code 5000 non-null float64\n 5 Family 5000 non-null int64 \n 6 CCAvg 5000 non-null float64\n 7 Education 5000 non-null int64 \n 8 Mortgage 5000 non-null int64 \n 9 Personal Loan 5000 non-null int64 \n 10 Securities Account 5000 non-null int64 \n 11 CD Account 5000 non-null int64 \n 12 Online 5000 non-null int64 \n 13 CreditCard 5000 non-null int64 \ndtypes: float64(2), int64(12)\nmemory usage: 547.0 KB\nNone\n","output_type":"stream"}]},{"cell_type":"markdown","source":"# Correlation Matrix","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\n\ncorrelation_matrix = train.corr()\n\n# Plotting the correlation matrix using seaborn\nplt.figure(figsize=(10, 8))\nsns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt=\".2f\", linewidths=0.5)\nplt.title('Correlation Matrix')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-05-22T13:41:20.611238Z","iopub.execute_input":"2024-05-22T13:41:20.611687Z","iopub.status.idle":"2024-05-22T13:41:21.686739Z","shell.execute_reply.started":"2024-05-22T13:41:20.611649Z","shell.execute_reply":"2024-05-22T13:41:21.685169Z"},"trusted":true},"execution_count":39,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]},{"cell_type":"markdown","source":"# Data Visualization\n\n#### Histogram of Age\n- This plot shows the distribution of ages in the dataset.\n- The histogram is stacked by the 'Personal Loan' variable, allowing us to see the distribution of ages for those who got and those who did not get personal loans.\n- It helps visualize if there are any differences in age distribution between those who got personal loans and those who did not.\n\n#### Boxplot of Income\n- This plot displays the distribution of income for each category of 'Personal Loan'.\n- The boxplot provides information about the median, quartiles, and potential outliers in income for each group.\n- It helps us to identify if there are significant differences in income between those who got personal loans and those who did not.\n\n#### Barplot of Education\n- This plot shows the count of individuals in each category of education, separated by the 'Personal Loan' variable.\n- It helps visualize the distribution of education levels among those who got personal loans and those who did not.\n- Differences in the proportions of education levels between the two groups can be observed.\n\n#### Violin Plot of CCAvg\n- This plot displays the distribution of average credit card spending (CCAvg) for each category of 'Personal Loan'.\n- It combines the features of a box plot and a kernel density plot, showing both summary statistics and the probability density of the data at different values.\n- It helps compare the distribution of CCAvg between individuals who got personal loans and those who did not.\n\n#### Boxen Plot of Mortgage\n- This plot shows the distribution of mortgage amounts for each category of 'Personal Loan'.\n- Similar to a box plot, it displays information about the median, quartiles, and potential outliers in mortgage amounts for each group.\n- It helps identify any differences in mortgage amounts between individuals who got personal loans and those who did not.\n\n#### Swarm Plot of Experience\n- This plot displays the distribution of work experience (in years) for each category of 'Personal Loan'.\n- It shows individual data points along the categorical axis, providing a clearer picture of the distribution compared to a traditional scatter plot.\n- It helps visualize if there are any patterns or differences in work experience between individuals who got personal loans and those who did not.\n\nThese plots collectively provide insights into how different variables relate to the likelihood of individuals accepting personal loans.","metadata":{}},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport seaborn as sns\n\n# Define the figure and axes\nfig, axs = plt.subplots(3, 2, figsize=(14, 18))\n\n# Plot 1: Histogram of Age\nsns.histplot(data=train, x='Age', hue='Personal Loan', multiple='stack', ax=axs[0, 0])\naxs[0, 0].set_title('Distribution of Age')\n\n# Plot 2: Boxplot of Income\nsns.boxplot(data=train, y='Income', x='Personal Loan', ax=axs[0, 1])\naxs[0, 1].set_title('Boxplot of Income')\n\n# Plot 3: Barplot of Education\nsns.countplot(data=train, x='Education', hue='Personal Loan', ax=axs[1, 0])\naxs[1, 0].set_title('Distribution of Education')\n\n# Plot 4: Violin Plot of CCAvg\nsns.violinplot(data=train, x='Personal Loan', y='CCAvg', ax=axs[1, 1])\naxs[1, 1].set_title('CCAvg Distribution by Personal Loan')\n\n# Plot 5: Boxen Plot of Mortgage\nsns.boxenplot(data=train, x='Personal Loan', y='Mortgage', ax=axs[2, 0])\naxs[2, 0].set_title('Mortgage Distribution by Personal Loan')\n\n# Plot 6: Swarm Plot of Experience\nsns.swarmplot(data=train, x='Personal Loan', y='Experience', ax=axs[2, 1])\naxs[2, 1].set_title('Experience Distribution by Personal Loan')\n\n# Adjust layout\nplt.tight_layout()\n\n# Show the plots\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-05-22T13:45:50.242161Z","iopub.execute_input":"2024-05-22T13:45:50.242579Z","iopub.status.idle":"2024-05-22T13:46:54.777627Z","shell.execute_reply.started":"2024-05-22T13:45:50.242547Z","shell.execute_reply":"2024-05-22T13:46:54.776311Z"},"trusted":true},"execution_count":42,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"X = train.drop(['ID', 'Personal Loan'], axis=1) # Features\ny = train['Personal Loan'] # Target","metadata":{"id":"k2K1KHWd9jw1","execution":{"iopub.status.busy":"2024-05-22T12:18:10.179991Z","iopub.execute_input":"2024-05-22T12:18:10.180353Z","iopub.status.idle":"2024-05-22T12:18:10.188571Z","shell.execute_reply.started":"2024-05-22T12:18:10.180316Z","shell.execute_reply":"2024-05-22T12:18:10.187218Z"},"trusted":true},"execution_count":16,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)","metadata":{"id":"9VNoR3Kx9jw2","execution":{"iopub.status.busy":"2024-05-22T12:18:10.190375Z","iopub.execute_input":"2024-05-22T12:18:10.190762Z","iopub.status.idle":"2024-05-22T12:18:10.294957Z","shell.execute_reply.started":"2024-05-22T12:18:10.190729Z","shell.execute_reply":"2024-05-22T12:18:10.293650Z"},"trusted":true},"execution_count":17,"outputs":[]},{"cell_type":"code","source":"# converting to numpy arrays\n\nX = X.to_numpy()\ny = y.to_numpy()","metadata":{"execution":{"iopub.status.busy":"2024-05-22T12:18:30.237376Z","iopub.execute_input":"2024-05-22T12:18:30.237867Z","iopub.status.idle":"2024-05-22T12:18:30.244769Z","shell.execute_reply.started":"2024-05-22T12:18:30.237836Z","shell.execute_reply":"2024-05-22T12:18:30.243713Z"},"trusted":true},"execution_count":20,"outputs":[]},{"cell_type":"code","source":"# import necessary modules\nfrom pytorch_tabnet.tab_model import TabNetClassifier\n \nimport os\nimport torch\n \nfrom sklearn.model_selection import KFold\nfrom sklearn.metrics import accuracy_score","metadata":{"execution":{"iopub.status.busy":"2024-05-22T12:18:26.987268Z","iopub.execute_input":"2024-05-22T12:18:26.987637Z","iopub.status.idle":"2024-05-22T12:18:30.235738Z","shell.execute_reply.started":"2024-05-22T12:18:26.987594Z","shell.execute_reply":"2024-05-22T12:18:30.234655Z"},"trusted":true},"execution_count":19,"outputs":[]},{"cell_type":"markdown","source":"# Feedforward Neural Network\n\nA Feedforward Neural Network (FNN) is a type of artificial neural network where connections between the nodes do not form a cycle. It is the simplest form of neural networks where the information moves in only one direction—forward—from the input nodes, through the hidden nodes (if any), and to the output nodes. There are no loops or cycles in the network.\n\n#### Key Components:\n- Input Layer: This layer receives the input data.\n- Hidden Layers: Intermediate layers where computations are performed. These layers apply transformations to the input data and pass it to the next layer.\n- Output Layer: Produces the final output of the network. For binary classification, a single neuron with a sigmoid activation function is typically used.\n- Activation Functions: Non-linear functions applied to each layer's output to introduce non-linearity into the network, allowing it to learn complex patterns.\n\nHere we implement a feedforward neural network for binary classification using TensorFlow and Keras. It uses K-Fold Cross-Validation to evaluate the model's performance, ensuring that the results are robust and generalize well to unseen data. Each fold involves training a new model and applying early stopping to prevent overfitting, with the best epoch's weights restored for evaluation.\n\n#### Layers:\n- The first dense layer has 64 neurons and uses the ReLU activation function.\n- The second dense layer has 32 neurons and also uses the ReLU activation function.\n- The output layer has 1 neuron and uses the sigmoid activation function to output a probability for binary classification.\n\n#### Compilation:\n- The loss function is binary_crossentropy, suitable for binary classification.\n- The optimizer is adam, an adaptive learning rate optimizer.\n- The metric is accuracy.\n\n#### K-Fold Cross-Validation:\n- The dataset is split into 5 parts (folds).\n\n

\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Accuracies over all folds
Fold 1Fold 2Fold 3Fold 4Fold 5
Best Epoch4745254745
Final Validation Loss0.12040.08330.10530.11130.0882
Final Validation Accuracy0.95490.96200.96600.96790.9710
\n\n\n\n
\nOverall Average Validation Loss: 0.10173177272081375
\nOverall Average Validation Accuracy: 0.9644000053405761","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.callbacks import EarlyStopping\n\n# Feedforward Neural Network model architecture\n\ndef create_model():\n model = tf.keras.Sequential([\n tf.keras.layers.Dense(64, activation='relu', input_shape=(X_train.shape[1],)),\n tf.keras.layers.Dense(32, activation='relu'),\n tf.keras.layers.Dense(1, activation='sigmoid') # binary classification\n ])\n model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n return model\n\n# K-Fold parameters\nn_splits = 5\nrandom_state = 42\n\n# KFold object\nkf = KFold(n_splits=n_splits, random_state=random_state, shuffle=True)\n\n# Lists to store results\nCV_loss_history = []\nCV_accuracy_history = []\n\nfor fold_index, (train_index, test_index) in enumerate(kf.split(X)):\n\n # Spliting data into training and validation sets\n X_train, X_valid = X[train_index], X[test_index]\n y_train, y_valid = y[train_index], y[test_index]\n\n # Creating a new FNN model for each fold\n model = create_model()\n\n # Early stopping callback to track best epoch for validation accuracy\n early_stopping = EarlyStopping(monitor='val_accuracy', patience=20, restore_best_weights=True)\n\n # Training the model with early stopping\n history = model.fit(X_train, y_train, epochs=50, validation_data=(X_valid, y_valid), callbacks=[early_stopping])\n\n # Getting final validation loss and accuracy\n val_loss = history.history['val_loss'][-1]\n val_acc = history.history['val_accuracy'][-1]\n\n # Printing results, including best epoch from EarlyStopping callback\n print(f\"Fold: {fold_index+1}\")\n print(f\"Best Epoch (Validation Accuracy): {early_stopping.best_epoch}\")\n print(f\"Final Validation Loss: {val_loss}\")\n print(f\"Final Validation Accuracy: {val_acc}\")\n\n # Storing results\n CV_loss_history.append(val_loss)\n CV_accuracy_history.append(val_acc)\n\n# Printing K-Fold evaluation results (average loss, accuracy)\nprint(f\"\\nOverall Average Validation Loss: {np.mean(CV_loss_history)}\")\nprint(f\"Overall Average Validation Accuracy: {np.mean(CV_accuracy_history)}\")","metadata":{"execution":{"iopub.status.busy":"2024-05-22T12:18:30.246026Z","iopub.execute_input":"2024-05-22T12:18:30.246341Z","iopub.status.idle":"2024-05-22T12:19:55.118220Z","shell.execute_reply.started":"2024-05-22T12:18:30.246314Z","shell.execute_reply":"2024-05-22T12:19:55.117046Z"},"trusted":true},"execution_count":21,"outputs":[{"name":"stderr","text":"2024-05-22 12:18:32.657193: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n2024-05-22 12:18:32.657356: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n2024-05-22 12:18:32.825289: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n","output_type":"stream"},{"name":"stdout","text":"Epoch 1/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 3ms/step - accuracy: 0.7604 - loss: 2.0709 - val_accuracy: 0.8840 - val_loss: 0.2505\nEpoch 2/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.8849 - loss: 0.2689 - val_accuracy: 0.8920 - val_loss: 0.2284\nEpoch 3/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9030 - loss: 0.2360 - val_accuracy: 0.8850 - val_loss: 0.2547\nEpoch 4/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9062 - loss: 0.2424 - val_accuracy: 0.9230 - val_loss: 0.1737\nEpoch 5/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9182 - loss: 0.2145 - val_accuracy: 0.8950 - val_loss: 0.2883\nEpoch 6/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9202 - loss: 0.2049 - val_accuracy: 0.9140 - val_loss: 0.1784\nEpoch 7/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9265 - loss: 0.2213 - val_accuracy: 0.8990 - val_loss: 0.2929\nEpoch 8/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9101 - loss: 0.2290 - val_accuracy: 0.9470 - val_loss: 0.1400\nEpoch 9/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9379 - loss: 0.1595 - val_accuracy: 0.9370 - val_loss: 0.1479\nEpoch 10/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9271 - loss: 0.1711 - val_accuracy: 0.9400 - val_loss: 0.2831\nEpoch 11/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9386 - loss: 0.2146 - val_accuracy: 0.9400 - val_loss: 0.1642\nEpoch 12/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9325 - loss: 0.1668 - val_accuracy: 0.9360 - val_loss: 0.1461\nEpoch 13/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9390 - loss: 0.1680 - val_accuracy: 0.9090 - val_loss: 0.2305\nEpoch 14/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9370 - loss: 0.1783 - val_accuracy: 0.9400 - val_loss: 0.1325\nEpoch 15/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9411 - loss: 0.1560 - val_accuracy: 0.9340 - val_loss: 0.1460\nEpoch 16/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9430 - loss: 0.1460 - val_accuracy: 0.9520 - val_loss: 0.1164\nEpoch 17/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9414 - loss: 0.1356 - val_accuracy: 0.9460 - val_loss: 0.1325\nEpoch 18/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9506 - loss: 0.1530 - val_accuracy: 0.9580 - val_loss: 0.1195\nEpoch 19/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9463 - loss: 0.1443 - val_accuracy: 0.9390 - val_loss: 0.1545\nEpoch 20/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9589 - loss: 0.1179 - val_accuracy: 0.9540 - val_loss: 0.1131\nEpoch 21/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9554 - loss: 0.1236 - val_accuracy: 0.9700 - val_loss: 0.0934\nEpoch 22/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9501 - loss: 0.1260 - val_accuracy: 0.9670 - val_loss: 0.0901\nEpoch 23/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9550 - loss: 0.1148 - val_accuracy: 0.9640 - val_loss: 0.0943\nEpoch 24/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9588 - loss: 0.1211 - val_accuracy: 0.9570 - val_loss: 0.1009\nEpoch 25/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9571 - loss: 0.1087 - val_accuracy: 0.9510 - val_loss: 0.1120\nEpoch 26/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9613 - loss: 0.1068 - val_accuracy: 0.9550 - val_loss: 0.1156\nEpoch 27/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9612 - loss: 0.1045 - val_accuracy: 0.9610 - val_loss: 0.0986\nEpoch 28/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9586 - loss: 0.1205 - val_accuracy: 0.9590 - val_loss: 0.1086\nEpoch 29/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9609 - loss: 0.1043 - val_accuracy: 0.9650 - val_loss: 0.0812\nEpoch 30/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9580 - loss: 0.1154 - val_accuracy: 0.9530 - val_loss: 0.1167\nEpoch 31/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9618 - loss: 0.0877 - val_accuracy: 0.9640 - val_loss: 0.0901\nEpoch 32/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9631 - loss: 0.0952 - val_accuracy: 0.9690 - val_loss: 0.0891\nEpoch 33/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9650 - loss: 0.0914 - val_accuracy: 0.9610 - val_loss: 0.1032\nEpoch 34/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9618 - loss: 0.1116 - val_accuracy: 0.9640 - val_loss: 0.1078\nEpoch 35/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9599 - loss: 0.1027 - val_accuracy: 0.9300 - val_loss: 0.2101\nEpoch 36/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9632 - loss: 0.1064 - val_accuracy: 0.9730 - val_loss: 0.0803\nEpoch 37/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9692 - loss: 0.0823 - val_accuracy: 0.9550 - val_loss: 0.1091\nEpoch 38/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9621 - loss: 0.0958 - val_accuracy: 0.9690 - val_loss: 0.0801\nEpoch 39/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9644 - loss: 0.0952 - val_accuracy: 0.9670 - val_loss: 0.0836\nEpoch 40/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9639 - loss: 0.1028 - val_accuracy: 0.9750 - val_loss: 0.0721\nEpoch 41/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9661 - loss: 0.0901 - val_accuracy: 0.9710 - val_loss: 0.0776\nEpoch 42/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9656 - loss: 0.0935 - val_accuracy: 0.9790 - val_loss: 0.0617\nEpoch 43/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9669 - loss: 0.0910 - val_accuracy: 0.9510 - val_loss: 0.1182\nEpoch 44/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9667 - loss: 0.0917 - val_accuracy: 0.9620 - val_loss: 0.1175\nEpoch 45/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9541 - loss: 0.1713 - val_accuracy: 0.9690 - val_loss: 0.0936\nEpoch 46/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9654 - loss: 0.1012 - val_accuracy: 0.9790 - val_loss: 0.0602\nEpoch 47/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9707 - loss: 0.0833 - val_accuracy: 0.9730 - val_loss: 0.0660\nEpoch 48/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9697 - loss: 0.0972 - val_accuracy: 0.9800 - val_loss: 0.0570\nEpoch 49/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9737 - loss: 0.0715 - val_accuracy: 0.9680 - val_loss: 0.0827\nEpoch 50/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9653 - loss: 0.0848 - val_accuracy: 0.9550 - val_loss: 0.1204\nFold: 1\nBest Epoch (Validation Accuracy): 47\nFinal Validation Loss: 0.12036914378404617\nFinal Validation Accuracy: 0.9549999833106995\nEpoch 1/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 3ms/step - accuracy: 0.6778 - loss: 3.7896 - val_accuracy: 0.9050 - val_loss: 0.4054\nEpoch 2/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.8911 - loss: 0.2998 - val_accuracy: 0.9120 - val_loss: 0.2791\nEpoch 3/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.8917 - loss: 0.2772 - val_accuracy: 0.8560 - val_loss: 0.3306\nEpoch 4/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9143 - loss: 0.2232 - val_accuracy: 0.8550 - val_loss: 0.2987\nEpoch 5/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9089 - loss: 0.2321 - val_accuracy: 0.9070 - val_loss: 0.1895\nEpoch 6/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9290 - loss: 0.1914 - val_accuracy: 0.9170 - val_loss: 0.1749\nEpoch 7/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9338 - loss: 0.1629 - val_accuracy: 0.9310 - val_loss: 0.1578\nEpoch 8/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9413 - loss: 0.1561 - val_accuracy: 0.9450 - val_loss: 0.1429\nEpoch 9/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9306 - loss: 0.1869 - val_accuracy: 0.9190 - val_loss: 0.2120\nEpoch 10/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9183 - loss: 0.2035 - val_accuracy: 0.9490 - val_loss: 0.1330\nEpoch 11/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9538 - loss: 0.1332 - val_accuracy: 0.9470 - val_loss: 0.1360\nEpoch 12/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9399 - loss: 0.1596 - val_accuracy: 0.9390 - val_loss: 0.1509\nEpoch 13/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9444 - loss: 0.1556 - val_accuracy: 0.9450 - val_loss: 0.1337\nEpoch 14/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9455 - loss: 0.1499 - val_accuracy: 0.9460 - val_loss: 0.1405\nEpoch 15/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9522 - loss: 0.1230 - val_accuracy: 0.9410 - val_loss: 0.1631\nEpoch 16/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9489 - loss: 0.1425 - val_accuracy: 0.9430 - val_loss: 0.1856\nEpoch 17/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9526 - loss: 0.1263 - val_accuracy: 0.9340 - val_loss: 0.1707\nEpoch 18/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9573 - loss: 0.1308 - val_accuracy: 0.9400 - val_loss: 0.1468\nEpoch 19/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9488 - loss: 0.1312 - val_accuracy: 0.9510 - val_loss: 0.1282\nEpoch 20/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9550 - loss: 0.1211 - val_accuracy: 0.9360 - val_loss: 0.1548\nEpoch 21/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9606 - loss: 0.1077 - val_accuracy: 0.9380 - val_loss: 0.1532\nEpoch 22/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9523 - loss: 0.1281 - val_accuracy: 0.9360 - val_loss: 0.1785\nEpoch 23/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9498 - loss: 0.1374 - val_accuracy: 0.9320 - val_loss: 0.1753\nEpoch 24/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9584 - loss: 0.1111 - val_accuracy: 0.9520 - val_loss: 0.1261\nEpoch 25/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9608 - loss: 0.1107 - val_accuracy: 0.9520 - val_loss: 0.1141\nEpoch 26/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9625 - loss: 0.1150 - val_accuracy: 0.9440 - val_loss: 0.1384\nEpoch 27/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9636 - loss: 0.1030 - val_accuracy: 0.9440 - val_loss: 0.1106\nEpoch 28/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9652 - loss: 0.0947 - val_accuracy: 0.9390 - val_loss: 0.1547\nEpoch 29/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9537 - loss: 0.1152 - val_accuracy: 0.9520 - val_loss: 0.1288\nEpoch 30/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9613 - loss: 0.1008 - val_accuracy: 0.9530 - val_loss: 0.1175\nEpoch 31/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9701 - loss: 0.0880 - val_accuracy: 0.9570 - val_loss: 0.1025\nEpoch 32/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9611 - loss: 0.0986 - val_accuracy: 0.9550 - val_loss: 0.1156\nEpoch 33/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9669 - loss: 0.0976 - val_accuracy: 0.9570 - val_loss: 0.1017\nEpoch 34/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9738 - loss: 0.0846 - val_accuracy: 0.9360 - val_loss: 0.1452\nEpoch 35/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9581 - loss: 0.1219 - val_accuracy: 0.9540 - val_loss: 0.1214\nEpoch 36/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9615 - loss: 0.1098 - val_accuracy: 0.9540 - val_loss: 0.1335\nEpoch 37/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9532 - loss: 0.1368 - val_accuracy: 0.9620 - val_loss: 0.0979\nEpoch 38/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9679 - loss: 0.0930 - val_accuracy: 0.9580 - val_loss: 0.0974\nEpoch 39/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9623 - loss: 0.0945 - val_accuracy: 0.9450 - val_loss: 0.1339\nEpoch 40/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9651 - loss: 0.0936 - val_accuracy: 0.9630 - val_loss: 0.0943\nEpoch 41/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9701 - loss: 0.0765 - val_accuracy: 0.9590 - val_loss: 0.1024\nEpoch 42/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9702 - loss: 0.0849 - val_accuracy: 0.9540 - val_loss: 0.0970\nEpoch 43/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9717 - loss: 0.0793 - val_accuracy: 0.9600 - val_loss: 0.1090\nEpoch 44/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9637 - loss: 0.0956 - val_accuracy: 0.9550 - val_loss: 0.1118\nEpoch 45/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9730 - loss: 0.0760 - val_accuracy: 0.9580 - val_loss: 0.0873\nEpoch 46/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9743 - loss: 0.0741 - val_accuracy: 0.9640 - val_loss: 0.0924\nEpoch 47/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9658 - loss: 0.1005 - val_accuracy: 0.9380 - val_loss: 0.1596\nEpoch 48/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9694 - loss: 0.0925 - val_accuracy: 0.9480 - val_loss: 0.1400\nEpoch 49/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9666 - loss: 0.1096 - val_accuracy: 0.9530 - val_loss: 0.1163\nEpoch 50/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9743 - loss: 0.0793 - val_accuracy: 0.9620 - val_loss: 0.0833\nFold: 2\nBest Epoch (Validation Accuracy): 45\nFinal Validation Loss: 0.08333558589220047\nFinal Validation Accuracy: 0.9620000123977661\nEpoch 1/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 3ms/step - accuracy: 0.8735 - loss: 1.7570 - val_accuracy: 0.9060 - val_loss: 0.2252\nEpoch 2/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9006 - loss: 0.3184 - val_accuracy: 0.9040 - val_loss: 0.2341\nEpoch 3/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9074 - loss: 0.2320 - val_accuracy: 0.9250 - val_loss: 0.1863\nEpoch 4/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9218 - loss: 0.2257 - val_accuracy: 0.9280 - val_loss: 0.1756\nEpoch 5/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9358 - loss: 0.1668 - val_accuracy: 0.9350 - val_loss: 0.1818\nEpoch 6/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9268 - loss: 0.1933 - val_accuracy: 0.9270 - val_loss: 0.1938\nEpoch 7/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9339 - loss: 0.1710 - val_accuracy: 0.9330 - val_loss: 0.2191\nEpoch 8/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9416 - loss: 0.1499 - val_accuracy: 0.9390 - val_loss: 0.1589\nEpoch 9/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9401 - loss: 0.1400 - val_accuracy: 0.9330 - val_loss: 0.2054\nEpoch 10/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9318 - loss: 0.1738 - val_accuracy: 0.9220 - val_loss: 0.2180\nEpoch 11/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9470 - loss: 0.1393 - val_accuracy: 0.9470 - val_loss: 0.1407\nEpoch 12/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9474 - loss: 0.1546 - val_accuracy: 0.9380 - val_loss: 0.1665\nEpoch 13/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9506 - loss: 0.1207 - val_accuracy: 0.9420 - val_loss: 0.1852\nEpoch 14/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9449 - loss: 0.1560 - val_accuracy: 0.9490 - val_loss: 0.1414\nEpoch 15/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9405 - loss: 0.1527 - val_accuracy: 0.9510 - val_loss: 0.1530\nEpoch 16/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9560 - loss: 0.1172 - val_accuracy: 0.9530 - val_loss: 0.1387\nEpoch 17/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9577 - loss: 0.1204 - val_accuracy: 0.9590 - val_loss: 0.1386\nEpoch 18/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9618 - loss: 0.1121 - val_accuracy: 0.9520 - val_loss: 0.1302\nEpoch 19/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9499 - loss: 0.1350 - val_accuracy: 0.9580 - val_loss: 0.1212\nEpoch 20/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9633 - loss: 0.1057 - val_accuracy: 0.9390 - val_loss: 0.1737\nEpoch 21/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9558 - loss: 0.1176 - val_accuracy: 0.9350 - val_loss: 0.2096\nEpoch 22/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9528 - loss: 0.1310 - val_accuracy: 0.9560 - val_loss: 0.1609\nEpoch 23/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9563 - loss: 0.1194 - val_accuracy: 0.9570 - val_loss: 0.1206\nEpoch 24/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9556 - loss: 0.1165 - val_accuracy: 0.9500 - val_loss: 0.1586\nEpoch 25/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9611 - loss: 0.1076 - val_accuracy: 0.9610 - val_loss: 0.1102\nEpoch 26/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9597 - loss: 0.1108 - val_accuracy: 0.9700 - val_loss: 0.1094\nEpoch 27/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9551 - loss: 0.1207 - val_accuracy: 0.9600 - val_loss: 0.1278\nEpoch 28/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9554 - loss: 0.1191 - val_accuracy: 0.9560 - val_loss: 0.1371\nEpoch 29/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9636 - loss: 0.0912 - val_accuracy: 0.9650 - val_loss: 0.1236\nEpoch 30/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9625 - loss: 0.1031 - val_accuracy: 0.9620 - val_loss: 0.1121\nEpoch 31/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9628 - loss: 0.1084 - val_accuracy: 0.9400 - val_loss: 0.1745\nEpoch 32/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9600 - loss: 0.1141 - val_accuracy: 0.9640 - val_loss: 0.1067\nEpoch 33/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9643 - loss: 0.1119 - val_accuracy: 0.9450 - val_loss: 0.1593\nEpoch 34/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9669 - loss: 0.0939 - val_accuracy: 0.9530 - val_loss: 0.1055\nEpoch 35/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9595 - loss: 0.1102 - val_accuracy: 0.9620 - val_loss: 0.1494\nEpoch 36/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9597 - loss: 0.1146 - val_accuracy: 0.9340 - val_loss: 0.3022\nEpoch 37/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9615 - loss: 0.1134 - val_accuracy: 0.9560 - val_loss: 0.1184\nEpoch 38/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9651 - loss: 0.0943 - val_accuracy: 0.9690 - val_loss: 0.1055\nEpoch 39/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9708 - loss: 0.0852 - val_accuracy: 0.9640 - val_loss: 0.1242\nEpoch 40/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9667 - loss: 0.0855 - val_accuracy: 0.9620 - val_loss: 0.1060\nEpoch 41/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9566 - loss: 0.1282 - val_accuracy: 0.9480 - val_loss: 0.1676\nEpoch 42/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9670 - loss: 0.0939 - val_accuracy: 0.9600 - val_loss: 0.1165\nEpoch 43/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9655 - loss: 0.0891 - val_accuracy: 0.9480 - val_loss: 0.1867\nEpoch 44/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9667 - loss: 0.0931 - val_accuracy: 0.9550 - val_loss: 0.1302\nEpoch 45/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9615 - loss: 0.1170 - val_accuracy: 0.9670 - val_loss: 0.1246\nEpoch 46/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9665 - loss: 0.0827 - val_accuracy: 0.9660 - val_loss: 0.1053\nFold: 3\nBest Epoch (Validation Accuracy): 25\nFinal Validation Loss: 0.10532169044017792\nFinal Validation Accuracy: 0.9660000205039978\nEpoch 1/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.6624 - loss: 5.6476 - val_accuracy: 0.8940 - val_loss: 0.3736\nEpoch 2/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.8885 - loss: 0.3064 - val_accuracy: 0.8990 - val_loss: 0.2515\nEpoch 3/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.8942 - loss: 0.2579 - val_accuracy: 0.9210 - val_loss: 0.3262\nEpoch 4/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9136 - loss: 0.2265 - val_accuracy: 0.9210 - val_loss: 0.2154\nEpoch 5/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9126 - loss: 0.2125 - val_accuracy: 0.9290 - val_loss: 0.1743\nEpoch 6/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9195 - loss: 0.2050 - val_accuracy: 0.9190 - val_loss: 0.1870\nEpoch 7/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9312 - loss: 0.1799 - val_accuracy: 0.9430 - val_loss: 0.1595\nEpoch 8/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9287 - loss: 0.1784 - val_accuracy: 0.9520 - val_loss: 0.1495\nEpoch 9/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9437 - loss: 0.1507 - val_accuracy: 0.9030 - val_loss: 0.2205\nEpoch 10/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9342 - loss: 0.1880 - val_accuracy: 0.9470 - val_loss: 0.1427\nEpoch 11/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9293 - loss: 0.2022 - val_accuracy: 0.9500 - val_loss: 0.1316\nEpoch 12/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9468 - loss: 0.1434 - val_accuracy: 0.9430 - val_loss: 0.1418\nEpoch 13/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9431 - loss: 0.1513 - val_accuracy: 0.9230 - val_loss: 0.1695\nEpoch 14/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9320 - loss: 0.1690 - val_accuracy: 0.9430 - val_loss: 0.1375\nEpoch 15/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9429 - loss: 0.1620 - val_accuracy: 0.9300 - val_loss: 0.1874\nEpoch 16/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9403 - loss: 0.1495 - val_accuracy: 0.8530 - val_loss: 0.5481\nEpoch 17/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9365 - loss: 0.2068 - val_accuracy: 0.9470 - val_loss: 0.1466\nEpoch 18/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9454 - loss: 0.1579 - val_accuracy: 0.9550 - val_loss: 0.1165\nEpoch 19/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9538 - loss: 0.1331 - val_accuracy: 0.9290 - val_loss: 0.1511\nEpoch 20/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9456 - loss: 0.1571 - val_accuracy: 0.9240 - val_loss: 0.2146\nEpoch 21/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9451 - loss: 0.1441 - val_accuracy: 0.9470 - val_loss: 0.1630\nEpoch 22/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9469 - loss: 0.1621 - val_accuracy: 0.9610 - val_loss: 0.1103\nEpoch 23/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9561 - loss: 0.1265 - val_accuracy: 0.9560 - val_loss: 0.1261\nEpoch 24/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9561 - loss: 0.1314 - val_accuracy: 0.9610 - val_loss: 0.0898\nEpoch 25/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9544 - loss: 0.1244 - val_accuracy: 0.9520 - val_loss: 0.1657\nEpoch 26/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9555 - loss: 0.1274 - val_accuracy: 0.9390 - val_loss: 0.1344\nEpoch 27/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9509 - loss: 0.1494 - val_accuracy: 0.9630 - val_loss: 0.0951\nEpoch 28/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9594 - loss: 0.1116 - val_accuracy: 0.9440 - val_loss: 0.1753\nEpoch 29/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9604 - loss: 0.1031 - val_accuracy: 0.9520 - val_loss: 0.1172\nEpoch 30/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9613 - loss: 0.1047 - val_accuracy: 0.9660 - val_loss: 0.0832\nEpoch 31/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9679 - loss: 0.0930 - val_accuracy: 0.9450 - val_loss: 0.1203\nEpoch 32/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9642 - loss: 0.1054 - val_accuracy: 0.9220 - val_loss: 0.1622\nEpoch 33/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9584 - loss: 0.1115 - val_accuracy: 0.9670 - val_loss: 0.0878\nEpoch 34/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9649 - loss: 0.0954 - val_accuracy: 0.9700 - val_loss: 0.0824\nEpoch 35/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9582 - loss: 0.1173 - val_accuracy: 0.9630 - val_loss: 0.0835\nEpoch 36/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9703 - loss: 0.0828 - val_accuracy: 0.9610 - val_loss: 0.0911\nEpoch 37/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9636 - loss: 0.1006 - val_accuracy: 0.9520 - val_loss: 0.1155\nEpoch 38/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9655 - loss: 0.1001 - val_accuracy: 0.9720 - val_loss: 0.0720\nEpoch 39/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9593 - loss: 0.1049 - val_accuracy: 0.9520 - val_loss: 0.1329\nEpoch 40/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9418 - loss: 0.1776 - val_accuracy: 0.9690 - val_loss: 0.0735\nEpoch 41/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9642 - loss: 0.0976 - val_accuracy: 0.9700 - val_loss: 0.0984\nEpoch 42/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9652 - loss: 0.0896 - val_accuracy: 0.9540 - val_loss: 0.1443\nEpoch 43/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9697 - loss: 0.1016 - val_accuracy: 0.9700 - val_loss: 0.0830\nEpoch 44/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9607 - loss: 0.1012 - val_accuracy: 0.9570 - val_loss: 0.1045\nEpoch 45/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9697 - loss: 0.0879 - val_accuracy: 0.9620 - val_loss: 0.0991\nEpoch 46/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9693 - loss: 0.0924 - val_accuracy: 0.9660 - val_loss: 0.0854\nEpoch 47/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9614 - loss: 0.1063 - val_accuracy: 0.9610 - val_loss: 0.1080\nEpoch 48/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9701 - loss: 0.1010 - val_accuracy: 0.9730 - val_loss: 0.0716\nEpoch 49/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9649 - loss: 0.0917 - val_accuracy: 0.9690 - val_loss: 0.0837\nEpoch 50/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9576 - loss: 0.1125 - val_accuracy: 0.9680 - val_loss: 0.1114\nFold: 4\nBest Epoch (Validation Accuracy): 47\nFinal Validation Loss: 0.11137939989566803\nFinal Validation Accuracy: 0.9679999947547913\nEpoch 1/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.8189 - loss: 0.9018 - val_accuracy: 0.9110 - val_loss: 0.2100\nEpoch 2/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.8866 - loss: 0.2767 - val_accuracy: 0.9090 - val_loss: 0.2921\nEpoch 3/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9030 - loss: 0.2494 - val_accuracy: 0.9300 - val_loss: 0.2141\nEpoch 4/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9086 - loss: 0.2271 - val_accuracy: 0.9090 - val_loss: 0.2797\nEpoch 5/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9281 - loss: 0.1890 - val_accuracy: 0.9270 - val_loss: 0.1811\nEpoch 6/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9303 - loss: 0.1790 - val_accuracy: 0.9440 - val_loss: 0.1567\nEpoch 7/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9343 - loss: 0.1729 - val_accuracy: 0.9480 - val_loss: 0.1415\nEpoch 8/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9329 - loss: 0.1731 - val_accuracy: 0.9450 - val_loss: 0.1441\nEpoch 9/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9365 - loss: 0.1669 - val_accuracy: 0.9490 - val_loss: 0.1597\nEpoch 10/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9343 - loss: 0.1755 - val_accuracy: 0.9460 - val_loss: 0.1384\nEpoch 11/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9324 - loss: 0.1802 - val_accuracy: 0.9330 - val_loss: 0.2057\nEpoch 12/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9304 - loss: 0.1635 - val_accuracy: 0.9600 - val_loss: 0.1184\nEpoch 13/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9471 - loss: 0.1295 - val_accuracy: 0.9480 - val_loss: 0.1442\nEpoch 14/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9451 - loss: 0.1394 - val_accuracy: 0.9520 - val_loss: 0.1241\nEpoch 15/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9530 - loss: 0.1247 - val_accuracy: 0.9670 - val_loss: 0.1176\nEpoch 16/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9443 - loss: 0.1415 - val_accuracy: 0.9460 - val_loss: 0.1500\nEpoch 17/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9530 - loss: 0.1196 - val_accuracy: 0.9510 - val_loss: 0.1344\nEpoch 18/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9508 - loss: 0.1264 - val_accuracy: 0.9620 - val_loss: 0.1057\nEpoch 19/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9536 - loss: 0.1173 - val_accuracy: 0.9690 - val_loss: 0.1046\nEpoch 20/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9516 - loss: 0.1254 - val_accuracy: 0.9600 - val_loss: 0.1248\nEpoch 21/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9510 - loss: 0.1355 - val_accuracy: 0.9430 - val_loss: 0.1629\nEpoch 22/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9487 - loss: 0.1421 - val_accuracy: 0.8690 - val_loss: 0.3047\nEpoch 23/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9523 - loss: 0.1316 - val_accuracy: 0.9500 - val_loss: 0.1270\nEpoch 24/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9576 - loss: 0.1123 - val_accuracy: 0.9610 - val_loss: 0.1247\nEpoch 25/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9547 - loss: 0.1232 - val_accuracy: 0.9660 - val_loss: 0.0986\nEpoch 26/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9605 - loss: 0.0999 - val_accuracy: 0.9600 - val_loss: 0.1083\nEpoch 27/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9590 - loss: 0.1056 - val_accuracy: 0.9650 - val_loss: 0.1034\nEpoch 28/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9632 - loss: 0.0934 - val_accuracy: 0.9660 - val_loss: 0.0985\nEpoch 29/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9528 - loss: 0.1142 - val_accuracy: 0.9720 - val_loss: 0.0884\nEpoch 30/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9599 - loss: 0.0980 - val_accuracy: 0.9720 - val_loss: 0.0877\nEpoch 31/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9652 - loss: 0.0982 - val_accuracy: 0.9640 - val_loss: 0.1016\nEpoch 32/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9643 - loss: 0.1049 - val_accuracy: 0.9660 - val_loss: 0.1027\nEpoch 33/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9607 - loss: 0.1029 - val_accuracy: 0.9620 - val_loss: 0.1115\nEpoch 34/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9723 - loss: 0.0815 - val_accuracy: 0.9340 - val_loss: 0.1601\nEpoch 35/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9590 - loss: 0.0930 - val_accuracy: 0.9660 - val_loss: 0.0955\nEpoch 36/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9704 - loss: 0.0815 - val_accuracy: 0.9680 - val_loss: 0.1022\nEpoch 37/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9743 - loss: 0.0685 - val_accuracy: 0.9770 - val_loss: 0.0782\nEpoch 38/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9722 - loss: 0.0738 - val_accuracy: 0.9680 - val_loss: 0.0887\nEpoch 39/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9657 - loss: 0.0990 - val_accuracy: 0.9670 - val_loss: 0.1161\nEpoch 40/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9673 - loss: 0.0952 - val_accuracy: 0.9540 - val_loss: 0.1181\nEpoch 41/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9667 - loss: 0.0920 - val_accuracy: 0.9690 - val_loss: 0.0895\nEpoch 42/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9712 - loss: 0.0790 - val_accuracy: 0.9740 - val_loss: 0.0827\nEpoch 43/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9722 - loss: 0.0791 - val_accuracy: 0.9500 - val_loss: 0.1326\nEpoch 44/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9637 - loss: 0.1023 - val_accuracy: 0.9720 - val_loss: 0.0882\nEpoch 45/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9664 - loss: 0.0857 - val_accuracy: 0.9750 - val_loss: 0.0863\nEpoch 46/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9657 - loss: 0.0802 - val_accuracy: 0.9790 - val_loss: 0.0799\nEpoch 47/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9771 - loss: 0.0722 - val_accuracy: 0.9710 - val_loss: 0.0958\nEpoch 48/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9593 - loss: 0.0954 - val_accuracy: 0.9670 - val_loss: 0.1057\nEpoch 49/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9693 - loss: 0.0811 - val_accuracy: 0.9700 - val_loss: 0.0889\nEpoch 50/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9650 - loss: 0.1138 - val_accuracy: 0.9710 - val_loss: 0.0883\nFold: 5\nBest Epoch (Validation Accuracy): 45\nFinal Validation Loss: 0.08825304359197617\nFinal Validation Accuracy: 0.9710000157356262\n\nOverall Average Validation Loss: 0.10173177272081375\nOverall Average Validation Accuracy: 0.9644000053405761\n","output_type":"stream"}]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n# Assuming history is accessible from tb_cls.fit output\nhistory = history.history # Replace with appropriate method to access history\n\n# Extract accuracy and loss for training and validation sets\ntrain_acc = history['accuracy'] # Replace with actual metric names\nval_acc = history['val_accuracy']\ntrain_loss = history['loss']\nval_loss = history['val_loss']\n\n# Plotting accuracy\nplt.figure(figsize=(10, 6))\nplt.plot(train_acc, label='Training Accuracy')\nplt.plot(val_acc, label='Validation Accuracy')\nplt.xlabel('Epoch')\nplt.ylabel('Accuracy')\nplt.title('Training vs. Validation Accuracy')\nplt.legend()\nplt.grid(True)\nplt.show()\n\n# Plotting accuracy\nplt.figure(figsize=(10, 6))\nplt.plot(train_loss, label='Training Logloss')\nplt.plot(val_loss, label='Validation Logloss')\nplt.xlabel('Epoch')\nplt.ylabel('Loss')\nplt.title('Training vs. Validation Logloss')\nplt.legend()\nplt.grid(True)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-05-22T12:19:55.119618Z","iopub.execute_input":"2024-05-22T12:19:55.120323Z","iopub.status.idle":"2024-05-22T12:19:55.794314Z","shell.execute_reply.started":"2024-05-22T12:19:55.120288Z","shell.execute_reply":"2024-05-22T12:19:55.793216Z"},"trusted":true},"execution_count":22,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]},{"cell_type":"markdown","source":"# TabNet Model\n\nTabNet (Tabular Neural Network) is a neural network architecture designed specifically for tabular data, commonly encountered in structured data sets. It was introduced in the paper \"TabNet: Attentive Interpretable Tabular Learning\" by Sercan O. Arik and Tomas Pfister. TabNet is an interpretable and efficient neural network architecture that combines elements of deep learning with attention mechanisms and feature selection techniques. It aims to achieve state-of-the-art performance on tabular data while providing insights into feature importance and model decisions.\n\n#### Architecture:\n\nThe architecture of TabNet consists of several key components:\n\n- Feature Embedding Layer: Converts categorical variables into dense representations suitable for neural networks. This layer often utilizes techniques like embedding layers or one-hot encoding followed by dense layers.\n- Feature Transformation Blocks: These blocks contain multiple sequential attention-based feature transformation steps. Each step performs feature selection and transformation using the features' interactions and dependencies.\n- Decision Steps: In each feature transformation block, decision steps apply feature-wise gating mechanisms to select relevant features and suppress irrelevant ones based on their importance.\n- Final Prediction Layer: The output of the feature transformation blocks is passed through a final prediction layer, typically consisting of fully connected layers followed by softmax or sigmoid activation functions for classification or regression tasks, respectively.\n\n#### Training Process:\n\nThe training process involves optimizing the model parameters to minimize a defined loss function (e.g., cross-entropy loss for classification tasks). TabNet employs optimization techniques such as the Adam optimizer and learning rate scheduling to efficiently update the model parameters during training.\n\n\n

\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Accuracies over all folds
Fold 1Fold 2Fold 3Fold 4Fold 5
Best Epoch3545464124
Final Validation LogLoss0.04380.06230.06260.04660.0651
Final Validation Accuracy0.9800.9850.9780.9720.982
","metadata":{}},{"cell_type":"code","source":"y = y.flatten()\n\nkf = KFold(n_splits=5, random_state=42, shuffle=True)\nCV_score_array = []\nfor train_index, test_index in kf.split(X):\n X_train, X_valid = X[train_index], X[test_index]\n y_train, y_valid = y[train_index], y[test_index]\n tb_cls = TabNetClassifier(optimizer_fn=torch.optim.Adam,\n optimizer_params=dict(lr=1e-3),\n scheduler_params={\"step_size\":10, \"gamma\":0.9},\n scheduler_fn=torch.optim.lr_scheduler.StepLR,\n mask_type='entmax'\n )\n history = tb_cls.fit(X_train, y_train,\n eval_set=[(X_train, y_train), (X_valid, y_valid)],\n eval_name=['train', 'valid'],\n eval_metric=['accuracy', 'logloss'],\n max_epochs=50, patience=25,\n batch_size=28, drop_last=False) \n CV_score_array.append(tb_cls.best_cost)\n\nprint(CV_score_array)","metadata":{"id":"-dP8x8KhBdDG","execution":{"iopub.status.busy":"2024-05-22T12:47:17.692097Z","iopub.execute_input":"2024-05-22T12:47:17.692499Z","iopub.status.idle":"2024-05-22T13:06:01.486815Z","shell.execute_reply.started":"2024-05-22T12:47:17.692470Z","shell.execute_reply":"2024-05-22T13:06:01.484461Z"},"trusted":true},"execution_count":31,"outputs":[{"name":"stdout","text":"epoch 0 | loss: 0.42207 | train_accuracy: 0.907 | train_logloss: 0.33201 | valid_accuracy: 0.896 | valid_logloss: 0.35855 | 0:00:04s\nepoch 1 | loss: 0.30114 | train_accuracy: 0.909 | train_logloss: 0.25234 | valid_accuracy: 0.904 | valid_logloss: 0.25999 | 0:00:08s\nepoch 2 | loss: 0.25561 | train_accuracy: 0.91925 | train_logloss: 0.21899 | valid_accuracy: 0.91 | valid_logloss: 0.21791 | 0:00:13s\nepoch 3 | loss: 0.22671 | train_accuracy: 0.9295 | train_logloss: 0.1824 | valid_accuracy: 0.918 | valid_logloss: 0.19067 | 0:00:17s\nepoch 4 | loss: 0.19331 | train_accuracy: 0.944 | train_logloss: 0.15418 | valid_accuracy: 0.941 | valid_logloss: 0.16627 | 0:00:21s\nepoch 5 | loss: 0.16893 | train_accuracy: 0.95225 | train_logloss: 0.1341 | valid_accuracy: 0.955 | valid_logloss: 0.13194 | 0:00:25s\nepoch 6 | loss: 0.14958 | train_accuracy: 0.957 | train_logloss: 0.1205 | valid_accuracy: 0.963 | valid_logloss: 0.11347 | 0:00:30s\nepoch 7 | loss: 0.14176 | train_accuracy: 0.95925 | train_logloss: 0.10867 | valid_accuracy: 0.963 | valid_logloss: 0.10337 | 0:00:34s\nepoch 8 | loss: 0.13032 | train_accuracy: 0.96475 | train_logloss: 0.10007 | valid_accuracy: 0.965 | valid_logloss: 0.09991 | 0:00:39s\nepoch 9 | loss: 0.13104 | train_accuracy: 0.96525 | train_logloss: 0.0923 | valid_accuracy: 0.969 | valid_logloss: 0.08984 | 0:00:43s\nepoch 10 | loss: 0.11881 | train_accuracy: 0.97 | train_logloss: 0.08569 | valid_accuracy: 0.973 | valid_logloss: 0.07166 | 0:00:48s\nepoch 11 | loss: 0.12288 | train_accuracy: 0.971 | train_logloss: 0.07971 | valid_accuracy: 0.977 | valid_logloss: 0.06722 | 0:00:52s\nepoch 12 | loss: 0.10859 | train_accuracy: 0.97275 | train_logloss: 0.07488 | valid_accuracy: 0.98 | valid_logloss: 0.06311 | 0:00:56s\nepoch 13 | loss: 0.09959 | train_accuracy: 0.97575 | train_logloss: 0.07077 | valid_accuracy: 0.981 | valid_logloss: 0.05703 | 0:01:01s\nepoch 14 | loss: 0.11044 | train_accuracy: 0.97675 | train_logloss: 0.06478 | valid_accuracy: 0.981 | valid_logloss: 0.05323 | 0:01:05s\nepoch 15 | loss: 0.09365 | train_accuracy: 0.97825 | train_logloss: 0.06351 | valid_accuracy: 0.983 | valid_logloss: 0.05273 | 0:01:10s\nepoch 16 | loss: 0.09568 | train_accuracy: 0.978 | train_logloss: 0.06496 | valid_accuracy: 0.985 | valid_logloss: 0.05218 | 0:01:14s\nepoch 17 | loss: 0.09254 | train_accuracy: 0.97825 | train_logloss: 0.06358 | valid_accuracy: 0.981 | valid_logloss: 0.0546 | 0:01:19s\nepoch 18 | loss: 0.09126 | train_accuracy: 0.97825 | train_logloss: 0.06093 | valid_accuracy: 0.986 | valid_logloss: 0.05267 | 0:01:23s\nepoch 19 | loss: 0.08991 | train_accuracy: 0.9795 | train_logloss: 0.05804 | valid_accuracy: 0.98 | valid_logloss: 0.05269 | 0:01:27s\nepoch 20 | loss: 0.08765 | train_accuracy: 0.97925 | train_logloss: 0.05804 | valid_accuracy: 0.98 | valid_logloss: 0.05537 | 0:01:32s\nepoch 21 | loss: 0.08851 | train_accuracy: 0.98125 | train_logloss: 0.05462 | valid_accuracy: 0.98 | valid_logloss: 0.05074 | 0:01:36s\nepoch 22 | loss: 0.07648 | train_accuracy: 0.982 | train_logloss: 0.05536 | valid_accuracy: 0.978 | valid_logloss: 0.05296 | 0:01:41s\nepoch 23 | loss: 0.07967 | train_accuracy: 0.98375 | train_logloss: 0.05075 | valid_accuracy: 0.983 | valid_logloss: 0.04974 | 0:01:45s\nepoch 24 | loss: 0.08996 | train_accuracy: 0.982 | train_logloss: 0.05352 | valid_accuracy: 0.982 | valid_logloss: 0.05144 | 0:01:50s\nepoch 25 | loss: 0.08011 | train_accuracy: 0.9825 | train_logloss: 0.05317 | valid_accuracy: 0.982 | valid_logloss: 0.04918 | 0:01:54s\nepoch 26 | loss: 0.08016 | train_accuracy: 0.983 | train_logloss: 0.05019 | valid_accuracy: 0.984 | valid_logloss: 0.04679 | 0:01:59s\nepoch 27 | loss: 0.08013 | train_accuracy: 0.983 | train_logloss: 0.0512 | valid_accuracy: 0.983 | valid_logloss: 0.04714 | 0:02:03s\nepoch 28 | loss: 0.07712 | train_accuracy: 0.984 | train_logloss: 0.04933 | valid_accuracy: 0.982 | valid_logloss: 0.04968 | 0:02:07s\nepoch 29 | loss: 0.07443 | train_accuracy: 0.9845 | train_logloss: 0.04763 | valid_accuracy: 0.983 | valid_logloss: 0.04586 | 0:02:12s\nepoch 30 | loss: 0.07709 | train_accuracy: 0.984 | train_logloss: 0.04749 | valid_accuracy: 0.983 | valid_logloss: 0.04686 | 0:02:16s\nepoch 31 | loss: 0.07983 | train_accuracy: 0.983 | train_logloss: 0.04984 | valid_accuracy: 0.983 | valid_logloss: 0.04849 | 0:02:21s\nepoch 32 | loss: 0.07573 | train_accuracy: 0.9825 | train_logloss: 0.05021 | valid_accuracy: 0.984 | valid_logloss: 0.04748 | 0:02:26s\nepoch 33 | loss: 0.0813 | train_accuracy: 0.98275 | train_logloss: 0.05036 | valid_accuracy: 0.982 | valid_logloss: 0.0467 | 0:02:30s\nepoch 34 | loss: 0.07579 | train_accuracy: 0.98325 | train_logloss: 0.05043 | valid_accuracy: 0.981 | valid_logloss: 0.048 | 0:02:34s\nepoch 35 | loss: 0.07136 | train_accuracy: 0.9835 | train_logloss: 0.04823 | valid_accuracy: 0.984 | valid_logloss: 0.04387 | 0:02:39s\nepoch 36 | loss: 0.07236 | train_accuracy: 0.985 | train_logloss: 0.046 | valid_accuracy: 0.982 | valid_logloss: 0.0458 | 0:02:43s\nepoch 37 | loss: 0.07784 | train_accuracy: 0.9825 | train_logloss: 0.04768 | valid_accuracy: 0.985 | valid_logloss: 0.04597 | 0:02:47s\nepoch 38 | loss: 0.07219 | train_accuracy: 0.98425 | train_logloss: 0.04593 | valid_accuracy: 0.986 | valid_logloss: 0.04468 | 0:02:52s\nepoch 39 | loss: 0.06311 | train_accuracy: 0.9845 | train_logloss: 0.04456 | valid_accuracy: 0.983 | valid_logloss: 0.04716 | 0:02:56s\nepoch 40 | loss: 0.06948 | train_accuracy: 0.98375 | train_logloss: 0.04345 | valid_accuracy: 0.984 | valid_logloss: 0.04546 | 0:03:01s\nepoch 41 | loss: 0.07713 | train_accuracy: 0.9835 | train_logloss: 0.04617 | valid_accuracy: 0.984 | valid_logloss: 0.04554 | 0:03:05s\nepoch 42 | loss: 0.07477 | train_accuracy: 0.98475 | train_logloss: 0.04493 | valid_accuracy: 0.984 | valid_logloss: 0.04435 | 0:03:09s\nepoch 43 | loss: 0.07505 | train_accuracy: 0.98375 | train_logloss: 0.04604 | valid_accuracy: 0.981 | valid_logloss: 0.04917 | 0:03:14s\nepoch 44 | loss: 0.0709 | train_accuracy: 0.98375 | train_logloss: 0.04504 | valid_accuracy: 0.982 | valid_logloss: 0.04658 | 0:03:18s\nepoch 45 | loss: 0.07225 | train_accuracy: 0.984 | train_logloss: 0.04359 | valid_accuracy: 0.985 | valid_logloss: 0.04426 | 0:03:23s\nepoch 46 | loss: 0.06808 | train_accuracy: 0.98425 | train_logloss: 0.04434 | valid_accuracy: 0.983 | valid_logloss: 0.05234 | 0:03:27s\nepoch 47 | loss: 0.07627 | train_accuracy: 0.9845 | train_logloss: 0.04397 | valid_accuracy: 0.984 | valid_logloss: 0.04693 | 0:03:31s\nepoch 48 | loss: 0.07598 | train_accuracy: 0.9855 | train_logloss: 0.04326 | valid_accuracy: 0.984 | valid_logloss: 0.04756 | 0:03:35s\nepoch 49 | loss: 0.0772 | train_accuracy: 0.98475 | train_logloss: 0.04365 | valid_accuracy: 0.982 | valid_logloss: 0.05281 | 0:03:40s\nStop training because you reached max_epochs = 50 with best_epoch = 35 and best_valid_logloss = 0.04387\nepoch 0 | loss: 0.44162 | train_accuracy: 0.907 | train_logloss: 0.34878 | valid_accuracy: 0.904 | valid_logloss: 0.33155 | 0:00:04s\nepoch 1 | loss: 0.29105 | train_accuracy: 0.9155 | train_logloss: 0.24177 | valid_accuracy: 0.911 | valid_logloss: 0.25004 | 0:00:08s\nepoch 2 | loss: 0.22514 | train_accuracy: 0.934 | train_logloss: 0.19869 | valid_accuracy: 0.918 | valid_logloss: 0.23364 | 0:00:13s\nepoch 3 | loss: 0.21107 | train_accuracy: 0.9405 | train_logloss: 0.17373 | valid_accuracy: 0.929 | valid_logloss: 0.21763 | 0:00:17s\nepoch 4 | loss: 0.18267 | train_accuracy: 0.9515 | train_logloss: 0.1425 | valid_accuracy: 0.936 | valid_logloss: 0.18631 | 0:00:21s\nepoch 5 | loss: 0.15541 | train_accuracy: 0.955 | train_logloss: 0.12093 | valid_accuracy: 0.936 | valid_logloss: 0.17068 | 0:00:26s\nepoch 6 | loss: 0.14804 | train_accuracy: 0.962 | train_logloss: 0.10803 | valid_accuracy: 0.944 | valid_logloss: 0.14117 | 0:00:30s\nepoch 7 | loss: 0.14028 | train_accuracy: 0.965 | train_logloss: 0.09945 | valid_accuracy: 0.949 | valid_logloss: 0.1378 | 0:00:34s\nepoch 8 | loss: 0.13006 | train_accuracy: 0.968 | train_logloss: 0.09474 | valid_accuracy: 0.954 | valid_logloss: 0.1259 | 0:00:39s\nepoch 9 | loss: 0.11872 | train_accuracy: 0.97175 | train_logloss: 0.08775 | valid_accuracy: 0.961 | valid_logloss: 0.1105 | 0:00:44s\nepoch 10 | loss: 0.11965 | train_accuracy: 0.97 | train_logloss: 0.08771 | valid_accuracy: 0.958 | valid_logloss: 0.1192 | 0:00:48s\nepoch 11 | loss: 0.11073 | train_accuracy: 0.9705 | train_logloss: 0.08109 | valid_accuracy: 0.954 | valid_logloss: 0.11311 | 0:00:53s\nepoch 12 | loss: 0.11456 | train_accuracy: 0.9715 | train_logloss: 0.07999 | valid_accuracy: 0.958 | valid_logloss: 0.09727 | 0:00:57s\nepoch 13 | loss: 0.10879 | train_accuracy: 0.9745 | train_logloss: 0.07587 | valid_accuracy: 0.964 | valid_logloss: 0.08607 | 0:01:01s\nepoch 14 | loss: 0.11226 | train_accuracy: 0.9755 | train_logloss: 0.07492 | valid_accuracy: 0.964 | valid_logloss: 0.08654 | 0:01:06s\nepoch 15 | loss: 0.1003 | train_accuracy: 0.97525 | train_logloss: 0.07016 | valid_accuracy: 0.959 | valid_logloss: 0.08956 | 0:01:10s\nepoch 16 | loss: 0.09475 | train_accuracy: 0.9755 | train_logloss: 0.06973 | valid_accuracy: 0.967 | valid_logloss: 0.07974 | 0:01:15s\nepoch 17 | loss: 0.10278 | train_accuracy: 0.977 | train_logloss: 0.06926 | valid_accuracy: 0.969 | valid_logloss: 0.08138 | 0:01:19s\nepoch 18 | loss: 0.09521 | train_accuracy: 0.9765 | train_logloss: 0.06699 | valid_accuracy: 0.967 | valid_logloss: 0.07849 | 0:01:24s\nepoch 19 | loss: 0.09255 | train_accuracy: 0.97875 | train_logloss: 0.06213 | valid_accuracy: 0.965 | valid_logloss: 0.07659 | 0:01:28s\nepoch 20 | loss: 0.09022 | train_accuracy: 0.97925 | train_logloss: 0.06492 | valid_accuracy: 0.97 | valid_logloss: 0.07641 | 0:01:33s\nepoch 21 | loss: 0.08926 | train_accuracy: 0.97825 | train_logloss: 0.06136 | valid_accuracy: 0.967 | valid_logloss: 0.07648 | 0:01:37s\nepoch 22 | loss: 0.09057 | train_accuracy: 0.97975 | train_logloss: 0.059 | valid_accuracy: 0.968 | valid_logloss: 0.0734 | 0:01:41s\nepoch 23 | loss: 0.07961 | train_accuracy: 0.977 | train_logloss: 0.06066 | valid_accuracy: 0.965 | valid_logloss: 0.07639 | 0:01:46s\nepoch 24 | loss: 0.08915 | train_accuracy: 0.98125 | train_logloss: 0.06006 | valid_accuracy: 0.971 | valid_logloss: 0.0749 | 0:01:51s\nepoch 25 | loss: 0.09187 | train_accuracy: 0.9795 | train_logloss: 0.05702 | valid_accuracy: 0.969 | valid_logloss: 0.0752 | 0:01:55s\nepoch 26 | loss: 0.08385 | train_accuracy: 0.981 | train_logloss: 0.05546 | valid_accuracy: 0.971 | valid_logloss: 0.07015 | 0:01:59s\nepoch 27 | loss: 0.09047 | train_accuracy: 0.98125 | train_logloss: 0.05502 | valid_accuracy: 0.97 | valid_logloss: 0.07018 | 0:02:04s\nepoch 28 | loss: 0.07843 | train_accuracy: 0.9815 | train_logloss: 0.05456 | valid_accuracy: 0.973 | valid_logloss: 0.06845 | 0:02:08s\nepoch 29 | loss: 0.07733 | train_accuracy: 0.981 | train_logloss: 0.05446 | valid_accuracy: 0.97 | valid_logloss: 0.07279 | 0:02:13s\nepoch 30 | loss: 0.08278 | train_accuracy: 0.9825 | train_logloss: 0.05136 | valid_accuracy: 0.974 | valid_logloss: 0.07053 | 0:02:18s\nepoch 31 | loss: 0.08567 | train_accuracy: 0.9815 | train_logloss: 0.05244 | valid_accuracy: 0.973 | valid_logloss: 0.06946 | 0:02:22s\nepoch 32 | loss: 0.06783 | train_accuracy: 0.982 | train_logloss: 0.04925 | valid_accuracy: 0.974 | valid_logloss: 0.06719 | 0:02:27s\nepoch 33 | loss: 0.07998 | train_accuracy: 0.98225 | train_logloss: 0.0484 | valid_accuracy: 0.972 | valid_logloss: 0.07016 | 0:02:31s\nepoch 34 | loss: 0.07416 | train_accuracy: 0.984 | train_logloss: 0.04737 | valid_accuracy: 0.972 | valid_logloss: 0.06746 | 0:02:36s\nepoch 35 | loss: 0.08626 | train_accuracy: 0.9835 | train_logloss: 0.04785 | valid_accuracy: 0.972 | valid_logloss: 0.06714 | 0:02:40s\nepoch 36 | loss: 0.08041 | train_accuracy: 0.984 | train_logloss: 0.04653 | valid_accuracy: 0.971 | valid_logloss: 0.06712 | 0:02:45s\nepoch 37 | loss: 0.07387 | train_accuracy: 0.98325 | train_logloss: 0.04694 | valid_accuracy: 0.971 | valid_logloss: 0.06607 | 0:02:50s\nepoch 38 | loss: 0.07533 | train_accuracy: 0.98275 | train_logloss: 0.04647 | valid_accuracy: 0.972 | valid_logloss: 0.06481 | 0:02:54s\nepoch 39 | loss: 0.07776 | train_accuracy: 0.98425 | train_logloss: 0.04621 | valid_accuracy: 0.971 | valid_logloss: 0.06531 | 0:02:58s\nepoch 40 | loss: 0.07213 | train_accuracy: 0.9855 | train_logloss: 0.04351 | valid_accuracy: 0.973 | valid_logloss: 0.06248 | 0:03:03s\nepoch 41 | loss: 0.08365 | train_accuracy: 0.9855 | train_logloss: 0.04594 | valid_accuracy: 0.972 | valid_logloss: 0.06532 | 0:03:07s\nepoch 42 | loss: 0.06911 | train_accuracy: 0.9855 | train_logloss: 0.04389 | valid_accuracy: 0.971 | valid_logloss: 0.06554 | 0:03:12s\nepoch 43 | loss: 0.06544 | train_accuracy: 0.985 | train_logloss: 0.04361 | valid_accuracy: 0.973 | valid_logloss: 0.06453 | 0:03:16s\nepoch 44 | loss: 0.06843 | train_accuracy: 0.985 | train_logloss: 0.04339 | valid_accuracy: 0.972 | valid_logloss: 0.06909 | 0:03:21s\nepoch 45 | loss: 0.07661 | train_accuracy: 0.985 | train_logloss: 0.0418 | valid_accuracy: 0.974 | valid_logloss: 0.06235 | 0:03:25s\nepoch 46 | loss: 0.06785 | train_accuracy: 0.9855 | train_logloss: 0.04336 | valid_accuracy: 0.97 | valid_logloss: 0.0625 | 0:03:29s\nepoch 47 | loss: 0.07299 | train_accuracy: 0.9855 | train_logloss: 0.0442 | valid_accuracy: 0.97 | valid_logloss: 0.06629 | 0:03:34s\nepoch 48 | loss: 0.07223 | train_accuracy: 0.98425 | train_logloss: 0.04478 | valid_accuracy: 0.969 | valid_logloss: 0.06743 | 0:03:38s\nepoch 49 | loss: 0.0698 | train_accuracy: 0.98575 | train_logloss: 0.04154 | valid_accuracy: 0.972 | valid_logloss: 0.06499 | 0:03:43s\nStop training because you reached max_epochs = 50 with best_epoch = 45 and best_valid_logloss = 0.06235\nepoch 0 | loss: 0.42437 | train_accuracy: 0.90725 | train_logloss: 0.3316 | valid_accuracy: 0.894 | valid_logloss: 0.3534 | 0:00:05s\nepoch 1 | loss: 0.27753 | train_accuracy: 0.91375 | train_logloss: 0.24663 | valid_accuracy: 0.905 | valid_logloss: 0.23881 | 0:00:09s\nepoch 2 | loss: 0.24037 | train_accuracy: 0.9215 | train_logloss: 0.21762 | valid_accuracy: 0.913 | valid_logloss: 0.22503 | 0:00:14s\nepoch 3 | loss: 0.21682 | train_accuracy: 0.931 | train_logloss: 0.21127 | valid_accuracy: 0.92 | valid_logloss: 0.22107 | 0:00:19s\nepoch 4 | loss: 0.19298 | train_accuracy: 0.937 | train_logloss: 0.17673 | valid_accuracy: 0.936 | valid_logloss: 0.17538 | 0:00:23s\nepoch 5 | loss: 0.19004 | train_accuracy: 0.943 | train_logloss: 0.16582 | valid_accuracy: 0.937 | valid_logloss: 0.16929 | 0:00:27s\nepoch 6 | loss: 0.16657 | train_accuracy: 0.94875 | train_logloss: 0.14952 | valid_accuracy: 0.944 | valid_logloss: 0.14036 | 0:00:32s\nepoch 7 | loss: 0.14627 | train_accuracy: 0.953 | train_logloss: 0.13535 | valid_accuracy: 0.95 | valid_logloss: 0.13525 | 0:00:37s\nepoch 8 | loss: 0.14664 | train_accuracy: 0.955 | train_logloss: 0.11642 | valid_accuracy: 0.952 | valid_logloss: 0.12078 | 0:00:42s\nepoch 9 | loss: 0.13628 | train_accuracy: 0.95675 | train_logloss: 0.11134 | valid_accuracy: 0.956 | valid_logloss: 0.12118 | 0:00:46s\nepoch 10 | loss: 0.12352 | train_accuracy: 0.966 | train_logloss: 0.09231 | valid_accuracy: 0.957 | valid_logloss: 0.10628 | 0:00:50s\nepoch 11 | loss: 0.11648 | train_accuracy: 0.9675 | train_logloss: 0.08539 | valid_accuracy: 0.961 | valid_logloss: 0.10423 | 0:00:55s\nepoch 12 | loss: 0.11134 | train_accuracy: 0.968 | train_logloss: 0.08447 | valid_accuracy: 0.96 | valid_logloss: 0.10725 | 0:01:00s\nepoch 13 | loss: 0.10862 | train_accuracy: 0.9715 | train_logloss: 0.07693 | valid_accuracy: 0.963 | valid_logloss: 0.09969 | 0:01:05s\nepoch 14 | loss: 0.09714 | train_accuracy: 0.9715 | train_logloss: 0.07525 | valid_accuracy: 0.967 | valid_logloss: 0.09323 | 0:01:09s\nepoch 15 | loss: 0.11006 | train_accuracy: 0.9755 | train_logloss: 0.06899 | valid_accuracy: 0.966 | valid_logloss: 0.09066 | 0:01:14s\nepoch 16 | loss: 0.09265 | train_accuracy: 0.978 | train_logloss: 0.06438 | valid_accuracy: 0.968 | valid_logloss: 0.08326 | 0:01:19s\nepoch 17 | loss: 0.09309 | train_accuracy: 0.978 | train_logloss: 0.0625 | valid_accuracy: 0.968 | valid_logloss: 0.0821 | 0:01:23s\nepoch 18 | loss: 0.09399 | train_accuracy: 0.979 | train_logloss: 0.05801 | valid_accuracy: 0.968 | valid_logloss: 0.08182 | 0:01:28s\nepoch 19 | loss: 0.09151 | train_accuracy: 0.978 | train_logloss: 0.05727 | valid_accuracy: 0.968 | valid_logloss: 0.08163 | 0:01:32s\nepoch 20 | loss: 0.08726 | train_accuracy: 0.97875 | train_logloss: 0.05679 | valid_accuracy: 0.968 | valid_logloss: 0.07612 | 0:01:37s\nepoch 21 | loss: 0.09841 | train_accuracy: 0.97725 | train_logloss: 0.05787 | valid_accuracy: 0.968 | valid_logloss: 0.08044 | 0:01:41s\nepoch 22 | loss: 0.08624 | train_accuracy: 0.979 | train_logloss: 0.05672 | valid_accuracy: 0.966 | valid_logloss: 0.07781 | 0:01:46s\nepoch 23 | loss: 0.09706 | train_accuracy: 0.97975 | train_logloss: 0.05578 | valid_accuracy: 0.968 | valid_logloss: 0.08015 | 0:01:50s\nepoch 24 | loss: 0.08781 | train_accuracy: 0.9805 | train_logloss: 0.05371 | valid_accuracy: 0.969 | valid_logloss: 0.07508 | 0:01:55s\nepoch 25 | loss: 0.08722 | train_accuracy: 0.98025 | train_logloss: 0.05421 | valid_accuracy: 0.971 | valid_logloss: 0.07676 | 0:02:00s\nepoch 26 | loss: 0.08846 | train_accuracy: 0.97925 | train_logloss: 0.05677 | valid_accuracy: 0.967 | valid_logloss: 0.08083 | 0:02:04s\nepoch 27 | loss: 0.08208 | train_accuracy: 0.9805 | train_logloss: 0.05216 | valid_accuracy: 0.966 | valid_logloss: 0.0746 | 0:02:09s\nepoch 28 | loss: 0.0802 | train_accuracy: 0.982 | train_logloss: 0.04959 | valid_accuracy: 0.972 | valid_logloss: 0.06991 | 0:02:13s\nepoch 29 | loss: 0.08122 | train_accuracy: 0.981 | train_logloss: 0.05118 | valid_accuracy: 0.974 | valid_logloss: 0.07266 | 0:02:18s\nepoch 30 | loss: 0.08246 | train_accuracy: 0.98175 | train_logloss: 0.04998 | valid_accuracy: 0.973 | valid_logloss: 0.07253 | 0:02:23s\nepoch 31 | loss: 0.08155 | train_accuracy: 0.98225 | train_logloss: 0.049 | valid_accuracy: 0.975 | valid_logloss: 0.07262 | 0:02:27s\nepoch 32 | loss: 0.06693 | train_accuracy: 0.9825 | train_logloss: 0.04727 | valid_accuracy: 0.976 | valid_logloss: 0.0712 | 0:02:32s\nepoch 33 | loss: 0.08107 | train_accuracy: 0.98225 | train_logloss: 0.04823 | valid_accuracy: 0.975 | valid_logloss: 0.07259 | 0:02:37s\nepoch 34 | loss: 0.0773 | train_accuracy: 0.9825 | train_logloss: 0.04848 | valid_accuracy: 0.973 | valid_logloss: 0.07483 | 0:02:41s\nepoch 35 | loss: 0.06749 | train_accuracy: 0.98275 | train_logloss: 0.04669 | valid_accuracy: 0.974 | valid_logloss: 0.07042 | 0:02:46s\nepoch 36 | loss: 0.06486 | train_accuracy: 0.9845 | train_logloss: 0.04203 | valid_accuracy: 0.974 | valid_logloss: 0.0672 | 0:02:51s\nepoch 37 | loss: 0.07212 | train_accuracy: 0.9835 | train_logloss: 0.04314 | valid_accuracy: 0.975 | valid_logloss: 0.06677 | 0:02:55s\nepoch 38 | loss: 0.08632 | train_accuracy: 0.98325 | train_logloss: 0.04319 | valid_accuracy: 0.975 | valid_logloss: 0.0657 | 0:02:59s\nepoch 39 | loss: 0.07931 | train_accuracy: 0.986 | train_logloss: 0.04155 | valid_accuracy: 0.975 | valid_logloss: 0.06679 | 0:03:04s\nepoch 40 | loss: 0.07521 | train_accuracy: 0.98525 | train_logloss: 0.04325 | valid_accuracy: 0.976 | valid_logloss: 0.06773 | 0:03:08s\nepoch 41 | loss: 0.06992 | train_accuracy: 0.9845 | train_logloss: 0.04208 | valid_accuracy: 0.977 | valid_logloss: 0.06638 | 0:03:13s\nepoch 42 | loss: 0.07875 | train_accuracy: 0.9855 | train_logloss: 0.04137 | valid_accuracy: 0.978 | valid_logloss: 0.06706 | 0:03:18s\nepoch 43 | loss: 0.06669 | train_accuracy: 0.98425 | train_logloss: 0.04238 | valid_accuracy: 0.977 | valid_logloss: 0.06838 | 0:03:22s\nepoch 44 | loss: 0.07082 | train_accuracy: 0.9845 | train_logloss: 0.041 | valid_accuracy: 0.98 | valid_logloss: 0.06493 | 0:03:27s\nepoch 45 | loss: 0.06728 | train_accuracy: 0.98625 | train_logloss: 0.04007 | valid_accuracy: 0.98 | valid_logloss: 0.06575 | 0:03:31s\nepoch 46 | loss: 0.06965 | train_accuracy: 0.9855 | train_logloss: 0.04029 | valid_accuracy: 0.978 | valid_logloss: 0.0626 | 0:03:36s\nepoch 47 | loss: 0.07059 | train_accuracy: 0.986 | train_logloss: 0.03907 | valid_accuracy: 0.977 | valid_logloss: 0.06416 | 0:03:40s\nepoch 48 | loss: 0.06808 | train_accuracy: 0.98575 | train_logloss: 0.03844 | valid_accuracy: 0.978 | valid_logloss: 0.06484 | 0:03:45s\nepoch 49 | loss: 0.06402 | train_accuracy: 0.9855 | train_logloss: 0.04075 | valid_accuracy: 0.978 | valid_logloss: 0.06853 | 0:03:49s\nStop training because you reached max_epochs = 50 with best_epoch = 46 and best_valid_logloss = 0.0626\nepoch 0 | loss: 0.43983 | train_accuracy: 0.9035 | train_logloss: 0.34161 | valid_accuracy: 0.922 | valid_logloss: 0.32513 | 0:00:04s\nepoch 1 | loss: 0.29305 | train_accuracy: 0.909 | train_logloss: 0.25167 | valid_accuracy: 0.926 | valid_logloss: 0.23462 | 0:00:08s\nepoch 2 | loss: 0.24797 | train_accuracy: 0.92225 | train_logloss: 0.2053 | valid_accuracy: 0.935 | valid_logloss: 0.19918 | 0:00:13s\nepoch 3 | loss: 0.2138 | train_accuracy: 0.93225 | train_logloss: 0.18106 | valid_accuracy: 0.938 | valid_logloss: 0.17341 | 0:00:17s\nepoch 4 | loss: 0.18299 | train_accuracy: 0.93675 | train_logloss: 0.16705 | valid_accuracy: 0.941 | valid_logloss: 0.15843 | 0:00:22s\nepoch 5 | loss: 0.17684 | train_accuracy: 0.94875 | train_logloss: 0.13862 | valid_accuracy: 0.951 | valid_logloss: 0.13583 | 0:00:26s\nepoch 6 | loss: 0.15728 | train_accuracy: 0.9505 | train_logloss: 0.13352 | valid_accuracy: 0.949 | valid_logloss: 0.12484 | 0:00:31s\nepoch 7 | loss: 0.14769 | train_accuracy: 0.958 | train_logloss: 0.12498 | valid_accuracy: 0.952 | valid_logloss: 0.11141 | 0:00:35s\nepoch 8 | loss: 0.1319 | train_accuracy: 0.95925 | train_logloss: 0.11133 | valid_accuracy: 0.957 | valid_logloss: 0.10125 | 0:00:40s\nepoch 9 | loss: 0.13235 | train_accuracy: 0.96425 | train_logloss: 0.09682 | valid_accuracy: 0.963 | valid_logloss: 0.09174 | 0:00:44s\nepoch 10 | loss: 0.1277 | train_accuracy: 0.96725 | train_logloss: 0.0985 | valid_accuracy: 0.964 | valid_logloss: 0.09822 | 0:00:49s\nepoch 11 | loss: 0.11582 | train_accuracy: 0.96525 | train_logloss: 0.09291 | valid_accuracy: 0.966 | valid_logloss: 0.09259 | 0:00:53s\nepoch 12 | loss: 0.11284 | train_accuracy: 0.968 | train_logloss: 0.08491 | valid_accuracy: 0.971 | valid_logloss: 0.08385 | 0:00:58s\nepoch 13 | loss: 0.11282 | train_accuracy: 0.97025 | train_logloss: 0.08422 | valid_accuracy: 0.973 | valid_logloss: 0.08642 | 0:01:03s\nepoch 14 | loss: 0.10793 | train_accuracy: 0.97225 | train_logloss: 0.07847 | valid_accuracy: 0.979 | valid_logloss: 0.07843 | 0:01:07s\nepoch 15 | loss: 0.11153 | train_accuracy: 0.9735 | train_logloss: 0.07542 | valid_accuracy: 0.98 | valid_logloss: 0.07064 | 0:01:11s\nepoch 16 | loss: 0.10154 | train_accuracy: 0.9745 | train_logloss: 0.07269 | valid_accuracy: 0.978 | valid_logloss: 0.07036 | 0:01:16s\nepoch 17 | loss: 0.09563 | train_accuracy: 0.974 | train_logloss: 0.07036 | valid_accuracy: 0.976 | valid_logloss: 0.06593 | 0:01:20s\nepoch 18 | loss: 0.0968 | train_accuracy: 0.974 | train_logloss: 0.07055 | valid_accuracy: 0.978 | valid_logloss: 0.06645 | 0:01:24s\nepoch 19 | loss: 0.09838 | train_accuracy: 0.9755 | train_logloss: 0.06668 | valid_accuracy: 0.976 | valid_logloss: 0.06526 | 0:01:29s\nepoch 20 | loss: 0.09587 | train_accuracy: 0.97275 | train_logloss: 0.06666 | valid_accuracy: 0.976 | valid_logloss: 0.06359 | 0:01:34s\nepoch 21 | loss: 0.0978 | train_accuracy: 0.97425 | train_logloss: 0.06717 | valid_accuracy: 0.974 | valid_logloss: 0.06344 | 0:01:38s\nepoch 22 | loss: 0.09172 | train_accuracy: 0.97675 | train_logloss: 0.06448 | valid_accuracy: 0.974 | valid_logloss: 0.0633 | 0:01:43s\nepoch 23 | loss: 0.0951 | train_accuracy: 0.977 | train_logloss: 0.06532 | valid_accuracy: 0.976 | valid_logloss: 0.06138 | 0:01:47s\nepoch 24 | loss: 0.09797 | train_accuracy: 0.977 | train_logloss: 0.06554 | valid_accuracy: 0.979 | valid_logloss: 0.06284 | 0:01:52s\nepoch 25 | loss: 0.09377 | train_accuracy: 0.9765 | train_logloss: 0.06315 | valid_accuracy: 0.978 | valid_logloss: 0.06134 | 0:01:56s\nepoch 26 | loss: 0.09182 | train_accuracy: 0.97925 | train_logloss: 0.06071 | valid_accuracy: 0.98 | valid_logloss: 0.05766 | 0:02:01s\nepoch 27 | loss: 0.09595 | train_accuracy: 0.9775 | train_logloss: 0.06301 | valid_accuracy: 0.978 | valid_logloss: 0.06026 | 0:02:05s\nepoch 28 | loss: 0.0983 | train_accuracy: 0.97775 | train_logloss: 0.0599 | valid_accuracy: 0.98 | valid_logloss: 0.05427 | 0:02:10s\nepoch 29 | loss: 0.08057 | train_accuracy: 0.98075 | train_logloss: 0.05603 | valid_accuracy: 0.982 | valid_logloss: 0.05379 | 0:02:14s\nepoch 30 | loss: 0.08707 | train_accuracy: 0.9795 | train_logloss: 0.05882 | valid_accuracy: 0.985 | valid_logloss: 0.05308 | 0:02:19s\nepoch 31 | loss: 0.09317 | train_accuracy: 0.9795 | train_logloss: 0.05766 | valid_accuracy: 0.981 | valid_logloss: 0.05484 | 0:02:23s\nepoch 32 | loss: 0.08158 | train_accuracy: 0.981 | train_logloss: 0.05691 | valid_accuracy: 0.984 | valid_logloss: 0.05239 | 0:02:28s\nepoch 33 | loss: 0.08554 | train_accuracy: 0.982 | train_logloss: 0.05619 | valid_accuracy: 0.983 | valid_logloss: 0.05108 | 0:02:32s\nepoch 34 | loss: 0.08017 | train_accuracy: 0.98325 | train_logloss: 0.0552 | valid_accuracy: 0.984 | valid_logloss: 0.04733 | 0:02:37s\nepoch 35 | loss: 0.08786 | train_accuracy: 0.983 | train_logloss: 0.05533 | valid_accuracy: 0.982 | valid_logloss: 0.05018 | 0:02:42s\nepoch 36 | loss: 0.07885 | train_accuracy: 0.982 | train_logloss: 0.054 | valid_accuracy: 0.981 | valid_logloss: 0.05224 | 0:02:46s\nepoch 37 | loss: 0.08603 | train_accuracy: 0.981 | train_logloss: 0.05438 | valid_accuracy: 0.983 | valid_logloss: 0.04862 | 0:02:50s\nepoch 38 | loss: 0.07875 | train_accuracy: 0.9825 | train_logloss: 0.05365 | valid_accuracy: 0.983 | valid_logloss: 0.04908 | 0:02:55s\nepoch 39 | loss: 0.08308 | train_accuracy: 0.98275 | train_logloss: 0.05268 | valid_accuracy: 0.984 | valid_logloss: 0.04948 | 0:02:59s\nepoch 40 | loss: 0.0704 | train_accuracy: 0.9835 | train_logloss: 0.05157 | valid_accuracy: 0.986 | valid_logloss: 0.0469 | 0:03:03s\nepoch 41 | loss: 0.07966 | train_accuracy: 0.9835 | train_logloss: 0.04967 | valid_accuracy: 0.985 | valid_logloss: 0.04664 | 0:03:08s\nepoch 42 | loss: 0.07787 | train_accuracy: 0.98275 | train_logloss: 0.05298 | valid_accuracy: 0.983 | valid_logloss: 0.05028 | 0:03:13s\nepoch 43 | loss: 0.08037 | train_accuracy: 0.983 | train_logloss: 0.05124 | valid_accuracy: 0.987 | valid_logloss: 0.04894 | 0:03:17s\nepoch 44 | loss: 0.08094 | train_accuracy: 0.984 | train_logloss: 0.05019 | valid_accuracy: 0.986 | valid_logloss: 0.04792 | 0:03:21s\nepoch 45 | loss: 0.07437 | train_accuracy: 0.9835 | train_logloss: 0.04985 | valid_accuracy: 0.985 | valid_logloss: 0.04904 | 0:03:26s\nepoch 46 | loss: 0.07631 | train_accuracy: 0.982 | train_logloss: 0.05042 | valid_accuracy: 0.984 | valid_logloss: 0.05085 | 0:03:30s\nepoch 47 | loss: 0.07983 | train_accuracy: 0.9835 | train_logloss: 0.04996 | valid_accuracy: 0.984 | valid_logloss: 0.05336 | 0:03:35s\nepoch 48 | loss: 0.07086 | train_accuracy: 0.98375 | train_logloss: 0.04742 | valid_accuracy: 0.982 | valid_logloss: 0.05139 | 0:03:39s\nepoch 49 | loss: 0.07612 | train_accuracy: 0.984 | train_logloss: 0.04716 | valid_accuracy: 0.985 | valid_logloss: 0.05371 | 0:03:43s\nStop training because you reached max_epochs = 50 with best_epoch = 41 and best_valid_logloss = 0.04664\nepoch 0 | loss: 0.44012 | train_accuracy: 0.904 | train_logloss: 0.338 | valid_accuracy: 0.913 | valid_logloss: 0.33881 | 0:00:04s\nepoch 1 | loss: 0.28962 | train_accuracy: 0.91125 | train_logloss: 0.24961 | valid_accuracy: 0.917 | valid_logloss: 0.25271 | 0:00:08s\nepoch 2 | loss: 0.24651 | train_accuracy: 0.915 | train_logloss: 0.21412 | valid_accuracy: 0.932 | valid_logloss: 0.19067 | 0:00:13s\nepoch 3 | loss: 0.22374 | train_accuracy: 0.923 | train_logloss: 0.19464 | valid_accuracy: 0.943 | valid_logloss: 0.17182 | 0:00:17s\nepoch 4 | loss: 0.20625 | train_accuracy: 0.93325 | train_logloss: 0.17387 | valid_accuracy: 0.956 | valid_logloss: 0.16291 | 0:00:21s\nepoch 5 | loss: 0.17737 | train_accuracy: 0.94375 | train_logloss: 0.15067 | valid_accuracy: 0.954 | valid_logloss: 0.13248 | 0:00:26s\nepoch 6 | loss: 0.16654 | train_accuracy: 0.94875 | train_logloss: 0.14014 | valid_accuracy: 0.96 | valid_logloss: 0.1401 | 0:00:31s\nepoch 7 | loss: 0.15215 | train_accuracy: 0.957 | train_logloss: 0.11921 | valid_accuracy: 0.961 | valid_logloss: 0.14243 | 0:00:35s\nepoch 8 | loss: 0.13483 | train_accuracy: 0.96525 | train_logloss: 0.10815 | valid_accuracy: 0.964 | valid_logloss: 0.1086 | 0:00:39s\nepoch 9 | loss: 0.12576 | train_accuracy: 0.96775 | train_logloss: 0.09007 | valid_accuracy: 0.97 | valid_logloss: 0.09043 | 0:00:44s\nepoch 10 | loss: 0.11438 | train_accuracy: 0.96975 | train_logloss: 0.08317 | valid_accuracy: 0.973 | valid_logloss: 0.08804 | 0:00:48s\nepoch 11 | loss: 0.11108 | train_accuracy: 0.9725 | train_logloss: 0.07812 | valid_accuracy: 0.97 | valid_logloss: 0.08863 | 0:00:53s\nepoch 12 | loss: 0.11124 | train_accuracy: 0.97375 | train_logloss: 0.07421 | valid_accuracy: 0.969 | valid_logloss: 0.08436 | 0:00:57s\nepoch 13 | loss: 0.10238 | train_accuracy: 0.9725 | train_logloss: 0.07255 | valid_accuracy: 0.972 | valid_logloss: 0.083 | 0:01:02s\nepoch 14 | loss: 0.09749 | train_accuracy: 0.9745 | train_logloss: 0.06854 | valid_accuracy: 0.975 | valid_logloss: 0.08209 | 0:01:06s\nepoch 15 | loss: 0.0881 | train_accuracy: 0.977 | train_logloss: 0.06347 | valid_accuracy: 0.974 | valid_logloss: 0.07769 | 0:01:11s\nepoch 16 | loss: 0.08479 | train_accuracy: 0.98175 | train_logloss: 0.05552 | valid_accuracy: 0.975 | valid_logloss: 0.07069 | 0:01:15s\nepoch 17 | loss: 0.08593 | train_accuracy: 0.9795 | train_logloss: 0.05531 | valid_accuracy: 0.976 | valid_logloss: 0.07577 | 0:01:19s\nepoch 18 | loss: 0.08929 | train_accuracy: 0.97925 | train_logloss: 0.0573 | valid_accuracy: 0.976 | valid_logloss: 0.0758 | 0:01:24s\nepoch 19 | loss: 0.08786 | train_accuracy: 0.97725 | train_logloss: 0.05973 | valid_accuracy: 0.973 | valid_logloss: 0.07705 | 0:01:28s\nepoch 20 | loss: 0.08803 | train_accuracy: 0.98025 | train_logloss: 0.05474 | valid_accuracy: 0.975 | valid_logloss: 0.07163 | 0:01:33s\nepoch 21 | loss: 0.08108 | train_accuracy: 0.98025 | train_logloss: 0.05286 | valid_accuracy: 0.976 | valid_logloss: 0.07074 | 0:01:37s\nepoch 22 | loss: 0.08473 | train_accuracy: 0.98025 | train_logloss: 0.0539 | valid_accuracy: 0.978 | valid_logloss: 0.07218 | 0:01:41s\nepoch 23 | loss: 0.08437 | train_accuracy: 0.97975 | train_logloss: 0.05322 | valid_accuracy: 0.977 | valid_logloss: 0.06907 | 0:01:45s\nepoch 24 | loss: 0.08656 | train_accuracy: 0.98 | train_logloss: 0.05175 | valid_accuracy: 0.98 | valid_logloss: 0.06512 | 0:01:50s\nepoch 25 | loss: 0.0797 | train_accuracy: 0.98 | train_logloss: 0.05298 | valid_accuracy: 0.976 | valid_logloss: 0.07155 | 0:01:54s\nepoch 26 | loss: 0.08064 | train_accuracy: 0.98225 | train_logloss: 0.04712 | valid_accuracy: 0.978 | valid_logloss: 0.06808 | 0:01:58s\nepoch 27 | loss: 0.07343 | train_accuracy: 0.9845 | train_logloss: 0.04434 | valid_accuracy: 0.979 | valid_logloss: 0.06781 | 0:02:03s\nepoch 28 | loss: 0.0784 | train_accuracy: 0.9825 | train_logloss: 0.04726 | valid_accuracy: 0.978 | valid_logloss: 0.0711 | 0:02:07s\nepoch 29 | loss: 0.07789 | train_accuracy: 0.9835 | train_logloss: 0.04476 | valid_accuracy: 0.978 | valid_logloss: 0.06917 | 0:02:12s\nepoch 30 | loss: 0.06916 | train_accuracy: 0.98325 | train_logloss: 0.04429 | valid_accuracy: 0.979 | valid_logloss: 0.06651 | 0:02:16s\nepoch 31 | loss: 0.07809 | train_accuracy: 0.984 | train_logloss: 0.0462 | valid_accuracy: 0.976 | valid_logloss: 0.07049 | 0:02:20s\nepoch 32 | loss: 0.07897 | train_accuracy: 0.98525 | train_logloss: 0.04287 | valid_accuracy: 0.978 | valid_logloss: 0.06972 | 0:02:25s\nepoch 33 | loss: 0.07303 | train_accuracy: 0.9845 | train_logloss: 0.04104 | valid_accuracy: 0.976 | valid_logloss: 0.06694 | 0:02:29s\nepoch 34 | loss: 0.08032 | train_accuracy: 0.98475 | train_logloss: 0.04435 | valid_accuracy: 0.975 | valid_logloss: 0.06805 | 0:02:34s\nepoch 35 | loss: 0.0653 | train_accuracy: 0.98375 | train_logloss: 0.04362 | valid_accuracy: 0.977 | valid_logloss: 0.06721 | 0:02:38s\nepoch 36 | loss: 0.0806 | train_accuracy: 0.98325 | train_logloss: 0.04249 | valid_accuracy: 0.976 | valid_logloss: 0.06749 | 0:02:42s\nepoch 37 | loss: 0.0635 | train_accuracy: 0.9835 | train_logloss: 0.0439 | valid_accuracy: 0.973 | valid_logloss: 0.06919 | 0:02:47s\nepoch 38 | loss: 0.07094 | train_accuracy: 0.9845 | train_logloss: 0.04206 | valid_accuracy: 0.975 | valid_logloss: 0.07153 | 0:02:51s\nepoch 39 | loss: 0.06411 | train_accuracy: 0.9855 | train_logloss: 0.03874 | valid_accuracy: 0.979 | valid_logloss: 0.06744 | 0:02:55s\nepoch 40 | loss: 0.08585 | train_accuracy: 0.9865 | train_logloss: 0.03897 | valid_accuracy: 0.975 | valid_logloss: 0.06951 | 0:03:00s\nepoch 41 | loss: 0.07474 | train_accuracy: 0.98475 | train_logloss: 0.04078 | valid_accuracy: 0.977 | valid_logloss: 0.06912 | 0:03:04s\nepoch 42 | loss: 0.0615 | train_accuracy: 0.9865 | train_logloss: 0.03818 | valid_accuracy: 0.979 | valid_logloss: 0.06766 | 0:03:09s\nepoch 43 | loss: 0.07032 | train_accuracy: 0.98625 | train_logloss: 0.03913 | valid_accuracy: 0.98 | valid_logloss: 0.06813 | 0:03:13s\nepoch 44 | loss: 0.0589 | train_accuracy: 0.98575 | train_logloss: 0.04025 | valid_accuracy: 0.976 | valid_logloss: 0.07139 | 0:03:17s\nepoch 45 | loss: 0.06452 | train_accuracy: 0.98775 | train_logloss: 0.03583 | valid_accuracy: 0.981 | valid_logloss: 0.06973 | 0:03:22s\nepoch 46 | loss: 0.05851 | train_accuracy: 0.98575 | train_logloss: 0.03958 | valid_accuracy: 0.975 | valid_logloss: 0.07459 | 0:03:26s\nepoch 47 | loss: 0.07004 | train_accuracy: 0.98625 | train_logloss: 0.03794 | valid_accuracy: 0.976 | valid_logloss: 0.07326 | 0:03:31s\nepoch 48 | loss: 0.05869 | train_accuracy: 0.98775 | train_logloss: 0.03746 | valid_accuracy: 0.979 | valid_logloss: 0.07279 | 0:03:35s\nepoch 49 | loss: 0.06429 | train_accuracy: 0.988 | train_logloss: 0.03648 | valid_accuracy: 0.977 | valid_logloss: 0.0706 | 0:03:40s\n\nEarly stopping occurred at epoch 49 with best_epoch = 24 and best_valid_logloss = 0.06512\n[0.043866922779519965, 0.06235424959751099, 0.06259904950568762, 0.04663541300107883, 0.06512253974846269]\n","output_type":"stream"}]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n# history accessible from tb_cls.fit output\nhistory = tb_cls.history \n\n# Extract accuracy and loss for training and validation sets\ntrain_acc = history['train_accuracy']\nval_acc = history['valid_accuracy']\ntrain_loss = history['train_logloss']\nval_loss = history['valid_logloss']\n\n# Plotting accuracy\nplt.figure(figsize=(10, 6))\nplt.plot(train_acc, label='Training Accuracy')\nplt.plot(val_acc, label='Validation Accuracy')\nplt.xlabel('Epoch')\nplt.ylabel('Accuracy')\nplt.title('Training vs. Validation Accuracy')\nplt.legend()\nplt.grid(True)\nplt.show()\n\n# Plotting accuracy\nplt.figure(figsize=(10, 6))\nplt.plot(train_loss, label='Training Logloss')\nplt.plot(val_loss, label='Validation Logloss')\nplt.xlabel('Epoch')\nplt.ylabel('Loss')\nplt.title('Training vs. Validation Logloss')\nplt.legend()\nplt.grid(True)\nplt.show()","metadata":{"id":"FG_I_RqcBdAr","execution":{"iopub.status.busy":"2024-05-22T13:12:46.370002Z","iopub.execute_input":"2024-05-22T13:12:46.370490Z","iopub.status.idle":"2024-05-22T13:12:46.960388Z","shell.execute_reply.started":"2024-05-22T13:12:46.370454Z","shell.execute_reply":"2024-05-22T13:12:46.959121Z"},"trusted":true},"execution_count":32,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"# saving model\ntb_cls.save_model('/kaggle/working/best_model')","metadata":{"execution":{"iopub.status.busy":"2024-05-22T13:12:52.907272Z","iopub.execute_input":"2024-05-22T13:12:52.907670Z","iopub.status.idle":"2024-05-22T13:12:52.934212Z","shell.execute_reply.started":"2024-05-22T13:12:52.907640Z","shell.execute_reply":"2024-05-22T13:12:52.932957Z"},"trusted":true},"execution_count":33,"outputs":[{"name":"stdout","text":"Successfully saved model at /kaggle/working/best_model.zip\n","output_type":"stream"},{"execution_count":33,"output_type":"execute_result","data":{"text/plain":"'/kaggle/working/best_model.zip'"},"metadata":{}}]},{"cell_type":"markdown","source":"# Wide & Deep neural network architecture\n\nThis implements a Wide & Deep neural network architecture using TensorFlow's Keras API for binary classification tasks.\n\n### Components of the Model:\n\n#### Normalization of Data:\n\n- The input data is normalized using mean and standard deviation calculated from the training data. This step helps in stabilizing the training process and improving convergence.\n\n#### Wide Component:\n\n- The wide component is a linear model that directly connects the input features to the output layer without any non-linear transformations. It is represented by a single Dense layer.\n\n#### Deep Component:\n\n- The deep component is a neural network consisting of multiple layers. Each layer is followed by Batch Normalization, LeakyReLU activation, and Dropout for regularization.\n- It comprises three Dense layers with 128, 64, and 32 units, respectively.\n\n#### Combining Wide and Deep Components:\n\n- The outputs from the wide and deep components are concatenated using the Concatenate layer.\n- This allows the model to learn both low-level and high-level feature representations simultaneously.\n\n#### Final Output Layer:\n\n- The concatenated output is passed through a final Dense layer with a sigmoid activation function, which outputs the predicted probability of the positive class (binary classification).\n\n# Metrics\n\n- Training Accuracy: 0.9715\n- Training Loss: 0.0752\n- val_accuracy: 0.9760\n- val_loss: 0.0531 \n- learning_rate: 1.0000e-05","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport tensorflow as tf\nfrom tensorflow.keras.layers import Dense, Input, Concatenate, Dropout, BatchNormalization, LeakyReLU\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau\n\n# Normalize the data\nX_train = np.array(X_train).astype('float32')\nX_test = np.array(X_test).astype('float32')\n\nmean = X_train.mean(axis=0)\nstd = X_train.std(axis=0)\n\nX_train -= mean\nX_train /= std\nX_test -= mean\nX_test /= std\n\n# Define input layers\ninputs = Input(shape=(12,))\n\n# Wide component (linear model)\nwide_output = Dense(1)(inputs)\n\n# Deep component (neural network)\ndeep_layer1 = Dense(128)(inputs)\ndeep_layer1 = BatchNormalization()(deep_layer1)\ndeep_layer1 = LeakyReLU()(deep_layer1)\ndeep_layer1 = Dropout(0.3)(deep_layer1)\n\ndeep_layer2 = Dense(64)(deep_layer1)\ndeep_layer2 = BatchNormalization()(deep_layer2)\ndeep_layer2 = LeakyReLU()(deep_layer2)\ndeep_layer2 = Dropout(0.3)(deep_layer2)\n\ndeep_layer3 = Dense(32)(deep_layer2)\ndeep_layer3 = BatchNormalization()(deep_layer3)\ndeep_layer3 = LeakyReLU()(deep_layer3)\ndeep_layer3 = Dropout(0.3)(deep_layer3)\n\ndeep_output = Dense(1)(deep_layer3)\n\n# Combine wide and deep components\ncombined = Concatenate()([wide_output, deep_output])\n\n# Final output layer\nfinal_output = Dense(1, activation='sigmoid')(combined)\n\n# Define model\nmodel_wd = Model(inputs=inputs, outputs=final_output)\n\n# Compile model with a lower learning rate and class weighting\noptimizer = tf.keras.optimizers.Adam(learning_rate=0.001)\nmodel_wd.compile(optimizer=optimizer, loss='binary_crossentropy', metrics=['accuracy'])\n\n# Callbacks\nearly_stopping = EarlyStopping(monitor='val_loss', patience=10, restore_best_weights=True)\nreduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=5, min_lr=0.00001)\n\n# Train model\nhistory = model_wd.fit(\n X_train, y_train,\n epochs=50,\n batch_size=32,\n validation_data=(X_test, y_test),\n callbacks=[early_stopping, reduce_lr]\n)\n\n# Plotting the training history\nimport matplotlib.pyplot as plt\n\n# Extract the history dictionary\nhistory_dict = history.history\n\n# Extract accuracy and loss for training and validation sets\ntrain_acc = history_dict['accuracy']\nval_acc = history_dict['val_accuracy']\ntrain_loss = history_dict['loss']\nval_loss = history_dict['val_loss']\n\n# Plotting accuracy\nplt.figure(figsize=(10, 6))\nplt.plot(train_acc, label='Training Accuracy')\nplt.plot(val_acc, label='Validation Accuracy')\nplt.xlabel('Epoch')\nplt.ylabel('Accuracy')\nplt.title('Training vs. Validation Accuracy')\nplt.legend()\nplt.grid(True)\nplt.show()\n\n# Plotting loss\nplt.figure(figsize=(10, 6))\nplt.plot(train_loss, label='Training Loss')\nplt.plot(val_loss, label='Validation Loss')\nplt.xlabel('Epoch')\nplt.ylabel('Loss')\nplt.title('Training vs. Validation Loss')\nplt.legend()\nplt.grid(True)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-05-22T12:38:08.000159Z","iopub.execute_input":"2024-05-22T12:38:08.000603Z","iopub.status.idle":"2024-05-22T12:38:33.303819Z","shell.execute_reply.started":"2024-05-22T12:38:08.000562Z","shell.execute_reply":"2024-05-22T12:38:33.302541Z"},"trusted":true},"execution_count":26,"outputs":[{"name":"stdout","text":"Epoch 1/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 6ms/step - accuracy: 0.7249 - loss: 0.5691 - val_accuracy: 0.9360 - val_loss: 0.3547 - learning_rate: 0.0010\nEpoch 2/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9137 - loss: 0.2822 - val_accuracy: 0.9670 - val_loss: 0.1513 - learning_rate: 0.0010\nEpoch 3/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9409 - loss: 0.1778 - val_accuracy: 0.9670 - val_loss: 0.1021 - learning_rate: 0.0010\nEpoch 4/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9478 - loss: 0.1414 - val_accuracy: 0.9720 - val_loss: 0.0841 - learning_rate: 0.0010\nEpoch 5/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9511 - loss: 0.1274 - val_accuracy: 0.9710 - val_loss: 0.0867 - learning_rate: 0.0010\nEpoch 6/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9462 - loss: 0.1290 - val_accuracy: 0.9690 - val_loss: 0.0793 - learning_rate: 0.0010\nEpoch 7/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9552 - loss: 0.1181 - val_accuracy: 0.9720 - val_loss: 0.0761 - learning_rate: 0.0010\nEpoch 8/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9555 - loss: 0.1201 - val_accuracy: 0.9710 - val_loss: 0.0752 - learning_rate: 0.0010\nEpoch 9/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9596 - loss: 0.1096 - val_accuracy: 0.9710 - val_loss: 0.0673 - learning_rate: 0.0010\nEpoch 10/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9657 - loss: 0.1043 - val_accuracy: 0.9740 - val_loss: 0.0661 - learning_rate: 0.0010\nEpoch 11/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9609 - loss: 0.1009 - val_accuracy: 0.9770 - val_loss: 0.0659 - learning_rate: 0.0010\nEpoch 12/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9610 - loss: 0.1045 - val_accuracy: 0.9720 - val_loss: 0.0635 - learning_rate: 0.0010\nEpoch 13/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9604 - loss: 0.0993 - val_accuracy: 0.9710 - val_loss: 0.0648 - learning_rate: 0.0010\nEpoch 14/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9676 - loss: 0.0999 - val_accuracy: 0.9710 - val_loss: 0.0618 - learning_rate: 0.0010\nEpoch 15/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9633 - loss: 0.1089 - val_accuracy: 0.9720 - val_loss: 0.0613 - learning_rate: 0.0010\nEpoch 16/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9640 - loss: 0.0956 - val_accuracy: 0.9800 - val_loss: 0.0575 - learning_rate: 0.0010\nEpoch 17/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9679 - loss: 0.0873 - val_accuracy: 0.9730 - val_loss: 0.0626 - learning_rate: 0.0010\nEpoch 18/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9648 - loss: 0.0899 - val_accuracy: 0.9740 - val_loss: 0.0624 - learning_rate: 0.0010\nEpoch 19/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9675 - loss: 0.0975 - val_accuracy: 0.9780 - val_loss: 0.0553 - learning_rate: 0.0010\nEpoch 20/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9698 - loss: 0.0864 - val_accuracy: 0.9740 - val_loss: 0.0583 - learning_rate: 0.0010\nEpoch 21/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9685 - loss: 0.0949 - val_accuracy: 0.9730 - val_loss: 0.0613 - learning_rate: 0.0010\nEpoch 22/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9707 - loss: 0.0921 - val_accuracy: 0.9760 - val_loss: 0.0568 - learning_rate: 0.0010\nEpoch 23/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9645 - loss: 0.0910 - val_accuracy: 0.9760 - val_loss: 0.0563 - learning_rate: 0.0010\nEpoch 24/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9739 - loss: 0.0896 - val_accuracy: 0.9770 - val_loss: 0.0559 - learning_rate: 0.0010\nEpoch 25/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9696 - loss: 0.0836 - val_accuracy: 0.9760 - val_loss: 0.0552 - learning_rate: 2.0000e-04\nEpoch 26/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9770 - loss: 0.0802 - val_accuracy: 0.9780 - val_loss: 0.0538 - learning_rate: 2.0000e-04\nEpoch 27/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9632 - loss: 0.0912 - val_accuracy: 0.9780 - val_loss: 0.0547 - learning_rate: 2.0000e-04\nEpoch 28/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9734 - loss: 0.0827 - val_accuracy: 0.9770 - val_loss: 0.0548 - learning_rate: 2.0000e-04\nEpoch 29/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9718 - loss: 0.0775 - val_accuracy: 0.9760 - val_loss: 0.0548 - learning_rate: 2.0000e-04\nEpoch 30/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9729 - loss: 0.0781 - val_accuracy: 0.9760 - val_loss: 0.0550 - learning_rate: 2.0000e-04\nEpoch 31/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9726 - loss: 0.0843 - val_accuracy: 0.9760 - val_loss: 0.0549 - learning_rate: 2.0000e-04\nEpoch 32/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9744 - loss: 0.0800 - val_accuracy: 0.9770 - val_loss: 0.0533 - learning_rate: 4.0000e-05\nEpoch 33/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9708 - loss: 0.0835 - val_accuracy: 0.9760 - val_loss: 0.0534 - learning_rate: 4.0000e-05\nEpoch 34/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9724 - loss: 0.0856 - val_accuracy: 0.9760 - val_loss: 0.0530 - learning_rate: 4.0000e-05\nEpoch 35/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9635 - loss: 0.1027 - val_accuracy: 0.9770 - val_loss: 0.0530 - learning_rate: 4.0000e-05\nEpoch 36/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9723 - loss: 0.0834 - val_accuracy: 0.9760 - val_loss: 0.0540 - learning_rate: 4.0000e-05\nEpoch 37/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9765 - loss: 0.0675 - val_accuracy: 0.9760 - val_loss: 0.0540 - learning_rate: 4.0000e-05\nEpoch 38/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9756 - loss: 0.0809 - val_accuracy: 0.9760 - val_loss: 0.0544 - learning_rate: 4.0000e-05\nEpoch 39/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9723 - loss: 0.0763 - val_accuracy: 0.9760 - val_loss: 0.0535 - learning_rate: 4.0000e-05\nEpoch 40/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9749 - loss: 0.0772 - val_accuracy: 0.9760 - val_loss: 0.0539 - learning_rate: 1.0000e-05\nEpoch 41/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9720 - loss: 0.0810 - val_accuracy: 0.9760 - val_loss: 0.0534 - learning_rate: 1.0000e-05\nEpoch 42/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9674 - loss: 0.0870 - val_accuracy: 0.9760 - val_loss: 0.0531 - learning_rate: 1.0000e-05\nEpoch 43/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9651 - loss: 0.0818 - val_accuracy: 0.9750 - val_loss: 0.0533 - learning_rate: 1.0000e-05\nEpoch 44/50\n\u001b[1m125/125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9715 - loss: 0.0752 - val_accuracy: 0.9760 - val_loss: 0.0531 - learning_rate: 1.0000e-05\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]},{"cell_type":"markdown","source":"# How prediction can be made using trained TabNet model","metadata":{}},{"cell_type":"code","source":"import joblib\nimport pandas as pd\nfrom sklearn.preprocessing import LabelEncoder\nfrom pytorch_tabnet.tab_model import TabNetClassifier\n\n# Load the frequency encoding for 'ZIP Code'\nzip_code_freq = joblib.load('/kaggle/working/zip_code_freq_encoder.pkl')\n\n# Load the label encoders\nlabel_encoders = joblib.load('/kaggle/working/label_encoders.pkl')\n\ntb_cls = TabNetClassifier()\ntb_cls.load_model('/kaggle/working/best_model.zip')\n\nnew_data = {\n 'Age': [25],\n 'Experience': [1],\n 'Income': [49],\n 'ZIP Code': ['91107'],\n 'Family': [4],\n 'CCAvg': [1.60],\n 'Education': ['1'],\n 'Mortgage': [0],\n 'Securities Account': [False],\n 'CD Account': [False],\n 'Online': [True],\n 'CreditCard': [False]\n}\n\n# Convert new_data to DataFrame\nnew_data = pd.DataFrame(new_data)\n\n# Display the structure of new_data\nprint(\"New DataFrame:\")\nprint(new_data.info())\n\n# Apply the same frequency encoding to 'ZIP Code'\nnew_data['ZIP Code'] = new_data['ZIP Code'].map(zip_code_freq)\n\n# Apply the same label encoding to other columns\ncolumns_to_encode = ['Education', 'CD Account', 'Online', 'CreditCard', 'Securities Account']\nfor col in columns_to_encode:\n le = label_encoders[col]\n new_data[col] = le.transform(new_data[col])\n\n# Convert the DataFrame to numpy array if necessary\nnew_data_np = new_data.to_numpy()\n\n# Make predictions using the loaded model\npredictions = tb_cls.predict(new_data_np)\n\n# If you need probabilities instead of class labels\nprobabilities = tb_cls.predict_proba(new_data_np)\n\nprint(\"Predictions:\")\nprint(predictions)\n\nprint(\"Probabilities:\")\nprint(probabilities)","metadata":{"execution":{"iopub.status.busy":"2024-05-22T13:16:12.939289Z","iopub.execute_input":"2024-05-22T13:16:12.939746Z","iopub.status.idle":"2024-05-22T13:16:13.029696Z","shell.execute_reply.started":"2024-05-22T13:16:12.939712Z","shell.execute_reply":"2024-05-22T13:16:13.028572Z"},"trusted":true},"execution_count":38,"outputs":[{"name":"stdout","text":"New DataFrame:\n\nRangeIndex: 1 entries, 0 to 0\nData columns (total 12 columns):\n # Column Non-Null Count Dtype \n--- ------ -------------- ----- \n 0 Age 1 non-null int64 \n 1 Experience 1 non-null int64 \n 2 Income 1 non-null int64 \n 3 ZIP Code 1 non-null object \n 4 Family 1 non-null int64 \n 5 CCAvg 1 non-null float64\n 6 Education 1 non-null object \n 7 Mortgage 1 non-null int64 \n 8 Securities Account 1 non-null bool \n 9 CD Account 1 non-null bool \n 10 Online 1 non-null bool \n 11 CreditCard 1 non-null bool \ndtypes: bool(4), float64(1), int64(5), object(2)\nmemory usage: 196.0+ bytes\nNone\nPredictions:\n[0]\nProbabilities:\n[[0.99735236 0.00264766]]\n","output_type":"stream"}]}]} \ No newline at end of file diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Model/README.md b/Loan Status Prediction/Bank Loan Approval Prediction/Model/README.md new file mode 100644 index 00000000..0fdac088 --- /dev/null +++ b/Loan Status Prediction/Bank Loan Approval Prediction/Model/README.md @@ -0,0 +1,149 @@ +## **BANK LOAN APPROVAL PREDICTION** + +### 🎯 **Goal** + + The main goal of this project is to come up with Deep Learning multi-layer neural network model for predicting approval for personal bank loans on the basis of customer's information which includes their age, experience, income, geographical information and many more. + +### 🧵 **Dataset** + +The Universal Bank dataset is taken from [Kaggle](https://www.kaggle.com/datasets/vinod00725/svm-classification?select=UniversalBank.csv) and can be found [here](https://github.com/abhisheks008/DL-Simplified/tree/main/Bank%20Loan%20Approval%20Prediction/Dataset). The dataset for this project consists of labeled data. The target column is called 'Personal Loan' which is used to predict whether a customer gets approved for loan or not. + +### 🧾 **Description** + +For training the model, different Deep Learning approches are considered. These are the deep learning algorithms which are considered. + +* Feedforward Neural-Network +* Feedforward Neural Network with k-Fold validation +* TabNet model with k-Fold validation +* Wide & Deep neural network architecture + +### 🧾 Data Preprocessing + +These are the observations which are made on dataset. + +* The minimum value of Experience is -3 and it also contains numeric values which are less than 0 which is not possible. It is observed that this field has 52 negative values. Further it was observed that minimum age and experience diffrence is 23. So wherever the experience was less than 0, it was replaced with their age minus 23. +* ZIP Code was initially represented as a numeric data. But it is a nominal data. Out of 5000 records, there are only 467 unique ZIP codes. Thus this represents that the dataset is restricted to a particular region. So this was converted to appropriate nominal data format. +* Education was also initially represented as a numeric data having 3 unique values {1: Bachelor, 2: Masters, 3: Advanced Degree}. So this is again not a numeric data. It is ordinal data and was converted to appropriate data format. +* Personal Loan (Target Variable) is either 0 or 1. {0: Loan not approved, 1: Loan approved}. So this is binary data, +* Securities Account is binary data representing {0: doesn't have security account, 1: has security account} +* CD Account is binary data representing {0: doesn't have CD Account, 1: has CD Account} +* Online is binary data representing {0: doesn't use online banking, 1: uses online banking} +* Credit Card is binary data representing {0: doesn't have credit card, 1: has credit card} + +All these binary data were initally numeric data, so these were changed to boolean data format. Rest are numeric data. + +### 🚀 **Models Implemented** + +Three deep learning algorithms are implemented which give more than 90% validation accuracy. These models are described as follows: + +#### Feedforward Neural Network with k-Fold validation + +Here we implement a feedforward neural network for binary classification using TensorFlow and Keras. It uses K-Fold Cross-Validation to evaluate the model's performance, ensuring that the results are reliable and generalize well to unseen data. Each fold involves training a new model and applying early stopping to prevent overfitting, with the best epoch's weights restored for evaluation. + +Layers: +* The first dense layer has 64 neurons and uses the ReLU activation function. +* The second dense layer has 32 neurons and also uses the ReLU activation function. +* The output layer has 1 neuron and uses the sigmoid activation function to output a probability for binary classification. + +Compilation: +* The loss function is binary_crossentropy, suitable for binary classification. +* The optimizer is adam, an adaptive learning rate optimizer. +* The metric is accuracy. + +K-Fold Cross-Validation: +* The dataset is split into 5 parts (folds). + +Accuracies over all folds + +| Fold | Fold 1 | Fold 2 | Fold 3 | Fold 4 | Fold 5 | +|----------------------|--------|--------|--------|--------|--------| +| **Best Epoch** | 47 | 45 | 25 | 47 | 45 | +| **Final Validation Loss** | 0.1204 | 0.0833 | 0.1053 | 0.1113 | 0.0882 | +| **Final Validation Accuracy** | 0.9549 | 0.9620 | 0.9660 | 0.9679 | 0.9710 | + +* Overall Average Validation Loss: 0.1017 +* Overall Average Validation Accuracy: 0.964 + +| ![image](https://github.com/theiturhs/DL-Simplified/assets/96874023/9352f641-2a02-4d11-b177-18a9c6b2a2f4) | ![image](https://github.com/theiturhs/DL-Simplified/assets/96874023/92325127-5511-41cb-8237-ec2da884e6f5) | +| ---- | ---- | +| Training vs Validation Accuracy : FNN Model | Training vs Validation Loss : FNN Model | + + +#### TabNet Model + +In this code, we implement a TabNet-based classifier for binary classification using PyTorch. The model's performance is evaluated using K-Fold Cross-Validation, ensuring that the results are reliable and generalize well to unseen data. Each fold involves training a new model and applying early stopping to prevent overfitting, with the best epoch's weights restored for evaluation. + +Components: + +* Model Architecture: TabNet is a deep learning model specifically designed for tabular data, with capabilities for feature selection and interpretability. +* Optimizer: Adam, an adaptive learning rate optimizer. +* Learning Rate Scheduler: Reduces the learning rate by a factor of 0.9 every 10 epochs. +* Evaluation Metrics: Accuracy and logloss are used to evaluate the model's performance. +* K-Fold Cross-Validation: The dataset is split into 5 folds to ensure robust evaluation. Each fold involves training a new model and storing the best validation loss. + +Accuracies over all folds + +| Fold | Fold 1 | Fold 2 | Fold 3 | Fold 4 | Fold 5 | +|------------------------------|--------|--------|--------|--------|--------| +| **Best Epoch** | 35 | 45 | 46 | 41 | 24 | +| **Final Validation LogLoss** | 0.0438 | 0.0623 | 0.0626 | 0.0466 | 0.0651 | +| **Final Validation Accuracy**| 0.980 | 0.985 | 0.978 | 0.972 | 0.982 | + +The parameters that yield better accuracy are selected. + +| ![image](https://github.com/theiturhs/DL-Simplified/assets/96874023/3da4eb3c-07b8-4d6b-85a9-192f8d58d397) | ![image](https://github.com/theiturhs/DL-Simplified/assets/96874023/2957e428-68d7-4208-b435-a68ed23dea38) | +| ---- | ----| +| Training vs Validation Accuracy : TabNet Model | Training vs Validation Loss : TabNet Model | + +#### Wide & Deep neural network architecture + +This implements a Wide & Deep neural network architecture using TensorFlow's Keras API for binary classification tasks. + +Components of the Model: +* Normalization of Data: The input data is normalized using mean and standard deviation calculated from the training data. This step helps in stabilizing the training process and improving convergence. +* Wide Component: The wide component is a linear model that directly connects the input features to the output layer without any non-linear transformations. It is represented by a single Dense layer. +* Deep Component: The deep component is a neural network consisting of multiple layers. Each layer is followed by Batch Normalization, LeakyReLU activation, and Dropout for regularization. It comprises three Dense layers with 128, 64, and 32 units, respectively. +* Combining Wide and Deep Components: The outputs from the wide and deep components are concatenated using the Concatenate layer. This allows the model to learn both low-level and high-level feature representations simultaneously. +* Final Output Layer: The concatenated output is passed through a final Dense layer with a sigmoid activation function, which outputs the predicted probability of the positive class (binary classification). + +Metrics +* Training Accuracy: 0.9715 +* Training Loss: 0.0752 +* val_accuracy: 0.9760 +* val_loss: 0.0531 + +| ![image](https://github.com/theiturhs/DL-Simplified/assets/96874023/39126a2b-c038-4678-a346-936604bc8f1e) | ![image](https://github.com/theiturhs/DL-Simplified/assets/96874023/0d4d3df9-5e95-41f9-9058-0f8f92e77146) | +| ---- | ---- | +| Training vs Validation Accuracy : WDNN Model | Training vs Validation Loss : WDNN Model | + +### 📚 **Libraries Needed** + +* pandas +* numpy +* matplotlib +* seaborn +* tensorflow +* joblib +* pytorch_tabnet +* sklearn + +### 📊 **Exploratory Data Analysis Results** + +| ![Age Distribution](https://github.com/theiturhs/DL-Simplified/assets/96874023/17709677-b86a-4d5a-8595-ac9a419de225) | ![Box Plot of income](https://github.com/theiturhs/DL-Simplified/assets/96874023/64ecfa44-e3be-4f35-9105-9aaed87bd940) | +| --- | --- | +| Distribution of Age | Box Plot of Income | +| ![CCAvg Distribution by Personal Loan](https://github.com/theiturhs/DL-Simplified/assets/96874023/0be9aab1-de5e-4170-a042-8e9620c6db15) | ![Distribution of Education](https://github.com/theiturhs/DL-Simplified/assets/96874023/36bb6796-132f-4c8c-9f1d-52c157222ff3) | +| CCAvg Distribution by Personal Loan | Distribution of Education | + +### 📈 **Performance of the Models based on the Accuracy Scores** + +Summary of model and their accuracy scores + +| Models | ANN | FNN | TabNet Model | WDNN Model | +| --- | --- | --- | --- | --- | +| Accuracy | 0.9820 | 0.9710 | 0.985 | 0.9760 | + +### 📢 **Conclusion** + +Concluding, this project aimed to classifies Bank Loan Approval using Deep Learning models. Among the models developed, the TabNet model achieved the highest validation score of 0.985. Using K-Fold Cross-Validation, it ensured that the results are reliable and generalize well to unseen data. + diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/Model/bank-loan-approval-using-AI.ipynb b/Loan Status Prediction/Bank Loan Approval Prediction/Model/bank-loan-approval-using-AI.ipynb new file mode 100644 index 00000000..2fc9e80b --- /dev/null +++ b/Loan Status Prediction/Bank Loan Approval Prediction/Model/bank-loan-approval-using-AI.ipynb @@ -0,0 +1,1864 @@ +{ + "cells": [ + { + "attachments": {}, + "cell_type": "markdown", + "id": "cathedral-nightlife", + "metadata": {}, + "source": [ + "# Bank Loan Approval Prediction using Artificial Neural Network" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "maritime-marketing", + "metadata": {}, + "source": [ + "In this project, we will build and train a deep neural network model to predict the likelyhood of a liability customer buying personal loans based on customer features." + ] + }, + { + "cell_type": "code", + "execution_count": 340, + "id": "olive-lease", + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "import numpy as np\n", + "import seaborn as sns\n", + "\n", + "import tensorflow as tf\n", + "from tensorflow import keras\n", + "from tensorflow.keras.layers import Dense, Activation, Dropout\n", + "from tensorflow.keras.optimizers import Adam\n", + "from tensorflow.keras.metrics import Accuracy\n", + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 341, + "id": "recreational-direction", + "metadata": {}, + "outputs": [], + "source": [ + "bank_df = pd.read_csv(\"UniversalBank.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": 342, + "id": "unable-sphere", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
IDAgeExperienceIncomeZIP CodeFamilyCCAvgEducationMortgagePersonal LoanSecurities AccountCD AccountOnlineCreditCard
01251499110741.61001000
124519349008931.51001000
233915119472011.01000000
343591009411212.72000000
45358459133041.02000001
\n", + "
" + ], + "text/plain": [ + " ID Age Experience Income ZIP Code Family CCAvg Education Mortgage \\\n", + "0 1 25 1 49 91107 4 1.6 1 0 \n", + "1 2 45 19 34 90089 3 1.5 1 0 \n", + "2 3 39 15 11 94720 1 1.0 1 0 \n", + "3 4 35 9 100 94112 1 2.7 2 0 \n", + "4 5 35 8 45 91330 4 1.0 2 0 \n", + "\n", + " Personal Loan Securities Account CD Account Online CreditCard \n", + "0 0 1 0 0 0 \n", + "1 0 1 0 0 0 \n", + "2 0 0 0 0 0 \n", + "3 0 0 0 0 0 \n", + "4 0 0 0 0 1 " + ] + }, + "execution_count": 342, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bank_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 343, + "id": "quiet-pittsburgh", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(5000, 14)" + ] + }, + "execution_count": 343, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bank_df.shape" + ] + }, + { + "cell_type": "markdown", + "id": "framed-strain", + "metadata": {}, + "source": [ + "- ID: Customer ID\n", + "- Age: Customer Age\n", + "- Experience: Amount of work experience in years\n", + "- Income: Amount of annual income (in thousands)\n", + "- Zipcode: Zipcode of where customer lives\n", + "- Family: Number of family members\n", + "- CCAvg: Average monthly credit card spendings\n", + "- Education: Education level (1: Bachelor, 2: Master, 3: Advanced Degree)\n", + "- Mortgage: Mortgage of house (in thousands)\n", + "- Securities Account: Boolean of whether customer has a securities account\n", + "- CD Account: Boolean of whether customer has Certificate of Deposit account\n", + "- Online: Boolean of whether customer uses online banking\n", + "- CreditCard: Does the customer use credit card issued by the bank?\n", + "- Personal Loan: This is the target variable (Binary Classification Problem)" + ] + }, + { + "cell_type": "markdown", + "id": "opening-shock", + "metadata": {}, + "source": [ + "## Exploratory Data Analysis" + ] + }, + { + "cell_type": "code", + "execution_count": 344, + "id": "separated-arthur", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "RangeIndex: 5000 entries, 0 to 4999\n", + "Data columns (total 14 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 ID 5000 non-null int64 \n", + " 1 Age 5000 non-null int64 \n", + " 2 Experience 5000 non-null int64 \n", + " 3 Income 5000 non-null int64 \n", + " 4 ZIP Code 5000 non-null int64 \n", + " 5 Family 5000 non-null int64 \n", + " 6 CCAvg 5000 non-null float64\n", + " 7 Education 5000 non-null int64 \n", + " 8 Mortgage 5000 non-null int64 \n", + " 9 Personal Loan 5000 non-null int64 \n", + " 10 Securities Account 5000 non-null int64 \n", + " 11 CD Account 5000 non-null int64 \n", + " 12 Online 5000 non-null int64 \n", + " 13 CreditCard 5000 non-null int64 \n", + "dtypes: float64(1), int64(13)\n", + "memory usage: 547.0 KB\n" + ] + } + ], + "source": [ + "bank_df.info()" + ] + }, + { + "cell_type": "code", + "execution_count": 345, + "id": "religious-seeking", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countmeanstdmin25%50%75%max
ID5000.02500.5000001443.5200031.01250.752500.53750.255000.0
Age5000.045.33840011.46316623.035.0045.055.0067.0
Experience5000.020.10460011.467954-3.010.0020.030.0043.0
Income5000.073.77420046.0337298.039.0064.098.00224.0
ZIP Code5000.093152.5030002121.8521979307.091911.0093437.094608.0096651.0
Family5000.02.3964001.1476631.01.002.03.004.0
CCAvg5000.01.9379381.7476590.00.701.52.5010.0
Education5000.01.8810000.8398691.01.002.03.003.0
Mortgage5000.056.498800101.7138020.00.000.0101.00635.0
Personal Loan5000.00.0960000.2946210.00.000.00.001.0
Securities Account5000.00.1044000.3058090.00.000.00.001.0
CD Account5000.00.0604000.2382500.00.000.00.001.0
Online5000.00.5968000.4905890.00.001.01.001.0
CreditCard5000.00.2940000.4556370.00.000.01.001.0
\n", + "
" + ], + "text/plain": [ + " count mean std min 25% \\\n", + "ID 5000.0 2500.500000 1443.520003 1.0 1250.75 \n", + "Age 5000.0 45.338400 11.463166 23.0 35.00 \n", + "Experience 5000.0 20.104600 11.467954 -3.0 10.00 \n", + "Income 5000.0 73.774200 46.033729 8.0 39.00 \n", + "ZIP Code 5000.0 93152.503000 2121.852197 9307.0 91911.00 \n", + "Family 5000.0 2.396400 1.147663 1.0 1.00 \n", + "CCAvg 5000.0 1.937938 1.747659 0.0 0.70 \n", + "Education 5000.0 1.881000 0.839869 1.0 1.00 \n", + "Mortgage 5000.0 56.498800 101.713802 0.0 0.00 \n", + "Personal Loan 5000.0 0.096000 0.294621 0.0 0.00 \n", + "Securities Account 5000.0 0.104400 0.305809 0.0 0.00 \n", + "CD Account 5000.0 0.060400 0.238250 0.0 0.00 \n", + "Online 5000.0 0.596800 0.490589 0.0 0.00 \n", + "CreditCard 5000.0 0.294000 0.455637 0.0 0.00 \n", + "\n", + " 50% 75% max \n", + "ID 2500.5 3750.25 5000.0 \n", + "Age 45.0 55.00 67.0 \n", + "Experience 20.0 30.00 43.0 \n", + "Income 64.0 98.00 224.0 \n", + "ZIP Code 93437.0 94608.00 96651.0 \n", + "Family 2.0 3.00 4.0 \n", + "CCAvg 1.5 2.50 10.0 \n", + "Education 2.0 3.00 3.0 \n", + "Mortgage 0.0 101.00 635.0 \n", + "Personal Loan 0.0 0.00 1.0 \n", + "Securities Account 0.0 0.00 1.0 \n", + "CD Account 0.0 0.00 1.0 \n", + "Online 1.0 1.00 1.0 \n", + "CreditCard 0.0 1.00 1.0 " + ] + }, + "execution_count": 345, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bank_df.describe().transpose()" + ] + }, + { + "cell_type": "code", + "execution_count": 346, + "id": "applied-dayton", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "ID 0\n", + "Age 0\n", + "Experience 0\n", + "Income 0\n", + "ZIP Code 0\n", + "Family 0\n", + "CCAvg 0\n", + "Education 0\n", + "Mortgage 0\n", + "Personal Loan 0\n", + "Securities Account 0\n", + "CD Account 0\n", + "Online 0\n", + "CreditCard 0\n", + "dtype: int64" + ] + }, + "execution_count": 346, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bank_df.isnull().sum()" + ] + }, + { + "cell_type": "markdown", + "id": "injured-bumper", + "metadata": {}, + "source": [ + "Great, we have no missing values!" + ] + }, + { + "cell_type": "code", + "execution_count": 347, + "id": "adopted-olympus", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "The average age of this dataset is 45.3.\n" + ] + } + ], + "source": [ + "avg_age = bank_df[\"Age\"].mean()\n", + "print (\"The average age of this dataset is {:.1f}.\".format(avg_age))" + ] + }, + { + "cell_type": "code", + "execution_count": 348, + "id": "adjusted-birmingham", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "The percentage of customers that own the bank's credit card is 29.40%.\n" + ] + } + ], + "source": [ + "percent_cc = sum(bank_df[\"CreditCard\"] == 1)/len(bank_df)\n", + "print (\"The percentage of customers that own the bank's credit card is {:.2%}.\".format(percent_cc))" + ] + }, + { + "cell_type": "code", + "execution_count": 349, + "id": "fiscal-ghana", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "The percentage of customers that took out a personal loan is 9.60%.\n" + ] + } + ], + "source": [ + "percent_loan = sum(bank_df[\"Personal Loan\"] == 1)/len(bank_df)\n", + "print (\"The percentage of customers that took out a personal loan is {:.2%}.\".format(percent_loan))" + ] + }, + { + "cell_type": "markdown", + "id": "distinct-filename", + "metadata": {}, + "source": [ + "## Data Visualization" + ] + }, + { + "cell_type": "code", + "execution_count": 350, + "id": "proprietary-liverpool", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "sns.countplot(x=bank_df[\"Personal Loan\"])\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 351, + "id": "33e3fe5f", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEGCAYAAACUzrmNAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAAAUyUlEQVR4nO3df5Bd5X3f8ffHGOzUhgBhQ2QJIuKRmcGOI0CDmVA81DQgmNpgT+LATEC2aQQTyJgmbYrTTiF4mHHrYE+wUzxyUECpDYFgipKQOjKlUKfmxworQvwy4leRRkZr4wKOHTrC3/6xz9aXZVfnSt57r6R9v2bu7Lnf85yzX7yDP5znnHufVBWSJO3MG0bdgCRpz2dYSJI6GRaSpE6GhSSpk2EhSer0xlE3MCiHHXZYLV68eNRtSNJeY/369d+pqrGZ9u2zYbF48WLGx8dH3YYk7TWSPDvbPqehJEmdDAtJUifDQpLUybCQJHUyLCRJnQwLSVInw0KS1MmwkCR1MiwkSZ322U9w74rj/82aUbewz1v/6fNH3YKkn4BXFpKkToaFJKmTYSFJ6mRYSJI6GRaSpE4DC4skRyS5K8kjSR5O8vFWPzTJuiRPtJ+HtHqSXJNkc5KNSY7rOdeKNv6JJCsG1bMkaWaDvLLYAfxuVR0DnAhcnOQY4DLgzqpaAtzZ3gOcASxpr5XAtTAZLsDlwHuAE4DLpwJGkjQcAwuLqtpWVQ+27ZeBR4GFwFnADW3YDcDZbfssYE1Nuhc4OMkC4HRgXVW9UFXfA9YBywfVtyTp9YZyzyLJYuBY4D7g8Kra1nZ9Gzi8bS8Enus5bEurzVaf6fesTDKeZHxiYmLu/gEkaZ4beFgkeStwK3BpVb3Uu6+qCqi5+l1VtaqqllXVsrGxGdcclyTthoGGRZL9mQyKL1XVV1r5+Ta9RPu5vdW3Akf0HL6o1WarS5KGZJBPQwW4Dni0qj7Ts2stMPVE0wrg9p76+e2pqBOBF9t01VeB05Ic0m5sn9ZqkqQhGeQXCZ4EnAc8lGRDq/0+8Cng5iQXAM8CH2777gDOBDYDPwA+ClBVLyT5JPBAG3dlVb0wwL4lSdMMLCyq6utAZtl96gzjC7h4lnOtBlbPXXeSpF3hJ7glSZ0MC0lSJ8NCktTJsJAkdTIsJEmdDAtJUifDQpLUybCQJHUyLCRJnQwLSVInw0KS1MmwkCR1MiwkSZ0MC0lSJ8NCktTJsJAkdRrksqqrk2xPsqmn9udJNrTXM1Mr6CVZnOSHPfu+0HPM8UkeSrI5yTVtuVZJ0hANclnV64HPA2umClX161PbSa4GXuwZ/2RVLZ3hPNcCvwncx+TSq8uBv5n7diVJsxnYlUVV3QPMuFZ2uzr4MHDjzs6RZAFwUFXd25ZdXQOcPcetSpI6jOqexcnA81X1RE/tqCTfTHJ3kpNbbSGwpWfMllabUZKVScaTjE9MTMx915I0T40qLM7ltVcV24Ajq+pY4HeALyc5aFdPWlWrqmpZVS0bGxubo1YlSYO8ZzGjJG8EPgQcP1WrqleAV9r2+iRPAu8AtgKLeg5f1GqSpCEaxZXFPwceq6r/P72UZCzJfm37F4AlwFNVtQ14KcmJ7T7H+cDtI+hZkua1QT46eyPwDeDoJFuSXNB2ncPrb2y/F9jYHqX9C+Ciqpq6Of5bwJ8Am4En8UkoSRq6gU1DVdW5s9Q/MkPtVuDWWcaPA++a0+YkSbvET3BLkjoZFpKkToaFJKmTYSFJ6mRYSJI6GRaSpE6GhSSpk2EhSepkWEiSOhkWkqROhoUkqZNhIUnqZFhIkjoZFpKkToaFJKnTIBc/Wp1ke5JNPbUrkmxNsqG9zuzZ94kkm5M8nuT0nvryVtuc5LJB9StJmt0gryyuB5bPUP9sVS1trzsAkhzD5Ap672zH/Ock+7WlVv8YOAM4Bji3jZUkDdEgV8q7J8niPoefBdxUVa8ATyfZDJzQ9m2uqqcAktzUxj4y1/1KkmY3insWlyTZ2KapDmm1hcBzPWO2tNpsdUnSEA3symIW1wKfBKr9vBr42FydPMlKYCXAkUceOVenlTQgJ33upFG3sM/7u9/+uzk5z1CvLKrq+ap6tap+BHyRH081bQWO6Bm6qNVmq892/lVVtayqlo2Njc1t85I0jw01LJIs6Hn7QWDqSam1wDlJ3pTkKGAJcD/wALAkyVFJDmDyJvjaYfYsSRrgNFSSG4FTgMOSbAEuB05JspTJaahngAsBqurhJDczeeN6B3BxVb3aznMJ8FVgP2B1VT08qJ4lSTMb5NNQ585Qvm4n468Crpqhfgdwxxy2JknaRX6CW5LUybCQJHUyLCRJnQwLSVKnYX8oT5pT//vKXxx1C/PCkf/hoVG3oBHzykKS1MmwkCR1MiwkSZ0MC0lSJ8NCktTJsJAkdTIsJEmdDAtJUifDQpLUybCQJHUyLCRJnQYWFklWJ9meZFNP7dNJHkuyMcltSQ5u9cVJfphkQ3t9oeeY45M8lGRzkmuSZFA9S5JmNsgri+uB5dNq64B3VdW7gW8Bn+jZ92RVLW2vi3rq1wK/yeS63EtmOKckacAGFhZVdQ/wwrTa31bVjvb2XmDRzs6RZAFwUFXdW1UFrAHOHkC7kqSdGOU9i48Bf9Pz/qgk30xyd5KTW20hsKVnzJZWm1GSlUnGk4xPTEzMfceSNE+NJCyS/DtgB/ClVtoGHFlVxwK/A3w5yUG7et6qWlVVy6pq2djY2Nw1LEnz3NAXP0ryEeBfAKe2qSWq6hXglba9PsmTwDuArbx2qmpRq0mShmioVxZJlgO/B3ygqn7QUx9Lsl/b/gUmb2Q/VVXbgJeSnNiegjofuH2YPUuS+gyLJHf2U5u2/0bgG8DRSbYkuQD4PHAgsG7aI7LvBTYm2QD8BXBRVU3dHP8t4E+AzcCTvPY+hyRpCHY6DZXkzcA/AQ5Lcggw9RmHg9jJjWaAqjp3hvJ1s4y9Fbh1ln3jwLt29rskSYPVdc/iQuBS4G3Aen4cFi8xeZUgSZoHdhoWVfVHwB8l+e2q+tyQepIk7WH6ehqqqj6X5JeBxb3HVNWaAfUlSdqD9BUWSf4MeDuwAXi1lac+US1J2sf1+zmLZcAxU5+LkCTNL/1+zmIT8HODbESStOfq98riMOCRJPfTPmkNUFUfGEhXkqQ9Sr9hccUgm5Ak7dn6fRrq7kE3Iknac/X7NNTLTD79BHAAsD/wD1W1y98MK0na+/R7ZXHg1Hb7Qr+zgBMH1ZQkac+yy986W5P+K3D63LcjSdoT9TsN9aGet29g8nMX/ziQjiRJe5x+n4Z6f8/2DuAZJqeiJEnzQL/3LD466EYkSXuufhc/WpTktiTb2+vWJIu6j5Qk7Qv6vcH9p8BaJte1eBvwl622U0lWt3DZ1FM7NMm6JE+0n4e0epJck2Rzko1Jjus5ZkUb/0SSFbvyDyhJ+sn1GxZjVfWnVbWjva4Hxvo47npg+bTaZcCdVbUEuLO9BziDybW3lwArgWthMlyAy4H3ACcAl08FjCRpOPoNi+8m+Y0k+7XXbwDf7Tqoqu4BXphWPgu4oW3fAJzdU1/THs29Fzg4yQImH9FdV1UvVNX3gHW8PoAkSQPUb1h8DPgw8G1gG/CrwEd283ceXlXb2va3gcPb9kLguZ5xW1pttvrrJFmZZDzJ+MTExG62J0mart+wuBJYUVVjVfWzTIbHH/ykv7ytjzFna2RU1aqqWlZVy8bG+pklkyT1o9+weHebAgKgql4Ajt3N3/l8m16i/dze6luBI3rGLWq12eqSpCHpNyze0HtTud107vcDfdOtBaaeaFoB3N5TP789FXUi8GKbrvoqcFqSQ1oPp7WaJGlI+v0//KuBbyS5pb3/NeCqroOS3AicAhyWZAuTTzV9Crg5yQXAs0zeCwG4AzgT2Az8APgoTF7FJPkk8EAbd2W7spEkDUm/n+Bek2QceF8rfaiqHunjuHNn2XXqDGMLuHiW86wGVvfTqyRp7vU9ldTCoTMgJEn7nl3+inJJ0vxjWEiSOhkWkqROhoUkqZNhIUnqZFhIkjoZFpKkToaFJKmTYSFJ6mRYSJI6GRaSpE6GhSSpk2EhSepkWEiSOhkWkqROQw+LJEcn2dDzeinJpUmuSLK1p35mzzGfSLI5yeNJTh92z5I03+3uOtq7raoeB5YCJNkP2ArcxuQyqp+tqj/sHZ/kGOAc4J3A24CvJXlHVb06zL4laT4b9TTUqcCTVfXsTsacBdxUVa9U1dNMrtF9wlC6kyQBow+Lc4Abe95fkmRjktVJDmm1hcBzPWO2tNrrJFmZZDzJ+MTExGA6lqR5aGRhkeQA4APALa10LfB2JqeotgFX7+o5q2pVVS2rqmVjY2Nz1aokzXujvLI4A3iwqp4HqKrnq+rVqvoR8EV+PNW0FTii57hFrSZJGpJRhsW59ExBJVnQs++DwKa2vRY4J8mbkhwFLAHuH1qXkqThPw0FkOQtwK8AF/aU/1OSpUABz0ztq6qHk9wMPALsAC72SShJGq6RhEVV/QPwM9Nq5+1k/FXAVYPuS5I0s1E/DSVJ2gsYFpKkToaFJKmTYSFJ6mRYSJI6GRaSpE6GhSSpk2EhSepkWEiSOhkWkqROhoUkqZNhIUnqZFhIkjoZFpKkToaFJKnTKNfgfibJQ0k2JBlvtUOTrEvyRPt5SKsnyTVJNifZmOS4UfUtSfPRqK8s/llVLa2qZe39ZcCdVbUEuLO9h8n1upe010rg2qF3Kknz2KjDYrqzgBva9g3A2T31NTXpXuDgaWt2S5IGaJRhUcDfJlmfZGWrHV5V29r2t4HD2/ZC4LmeY7e02mskWZlkPMn4xMTEoPqWpHlnJGtwN/+0qrYm+VlgXZLHendWVSWpXTlhVa0CVgEsW7Zsl46VJM1uZFcWVbW1/dwO3AacADw/Nb3Ufm5vw7cCR/QcvqjVJElDMJKwSPKWJAdObQOnAZuAtcCKNmwFcHvbXguc356KOhF4sWe6SpI0YKOahjocuC3JVA9frqr/luQB4OYkFwDPAh9u4+8AzgQ2Az8APjr8liVp/hpJWFTVU8AvzVD/LnDqDPUCLh5Ca5KkGexpj85KkvZAhoUkqZNhIUnqZFhIkjoZFpKkToaFJKmTYSFJ6mRYSJI6GRaSpE6GhSSpk2EhSepkWEiSOhkWkqROhoUkqZNhIUnqZFhIkjoNPSySHJHkriSPJHk4ycdb/YokW5NsaK8ze475RJLNSR5Pcvqwe5ak+W4UK+XtAH63qh5s63CvT7Ku7ftsVf1h7+AkxwDnAO8E3gZ8Lck7qurVoXYtSfPY0K8sqmpbVT3Ytl8GHgUW7uSQs4CbquqVqnqayXW4Txh8p5KkKSO9Z5FkMXAscF8rXZJkY5LVSQ5ptYXAcz2HbWGWcEmyMsl4kvGJiYlBtS1J887IwiLJW4FbgUur6iXgWuDtwFJgG3D1rp6zqlZV1bKqWjY2NjaX7UrSvDaSsEiyP5NB8aWq+gpAVT1fVa9W1Y+AL/LjqaatwBE9hy9qNUnSkIziaagA1wGPVtVneuoLeoZ9ENjUttcC5yR5U5KjgCXA/cPqV5I0mqehTgLOAx5KsqHVfh84N8lSoIBngAsBqurhJDcDjzD5JNXFPgklScM19LCoqq8DmWHXHTs55irgqoE1JUnaKT/BLUnqZFhIkjoZFpKkToaFJKmTYSFJ6mRYSJI6GRaSpE6GhSSpk2EhSepkWEiSOhkWkqROhoUkqZNhIUnqZFhIkjoZFpKkToaFJKnTXhMWSZYneTzJ5iSXjbofSZpP9oqwSLIf8MfAGcAxTC7Besxou5Kk+WOvCAvgBGBzVT1VVf8XuAk4a8Q9SdK8kaoadQ+dkvwqsLyq/mV7fx7wnqq6ZNq4lcDK9vZo4PGhNjo8hwHfGXUT2m3+/fZu+/Lf7+eramymHW8cdieDVFWrgFWj7mPQkoxX1bJR96Hd499v7zZf/357yzTUVuCInveLWk2SNAR7S1g8ACxJclSSA4BzgLUj7kmS5o29YhqqqnYkuQT4KrAfsLqqHh5xW6O0z0+17eP8++3d5uXfb6+4wS1JGq29ZRpKkjRChoUkqZNhsRdJsjrJ9iSbRt2Ldl2SI5LcleSRJA8n+fioe1J/krw5yf1J/r797f5g1D0Nm/cs9iJJ3gt8H1hTVe8adT/aNUkWAAuq6sEkBwLrgbOr6pERt6YOSQK8paq+n2R/4OvAx6vq3hG3NjReWexFquoe4IVR96HdU1XbqurBtv0y8CiwcLRdqR816fvt7f7tNa/+S9uwkEYgyWLgWOC+EbeiPiXZL8kGYDuwrqrm1d/OsJCGLMlbgVuBS6vqpVH3o/5U1atVtZTJb5A4Icm8mgo2LKQhavPdtwJfqqqvjLof7bqq+j/AXcDyEbcyVIaFNCTtJul1wKNV9ZlR96P+JRlLcnDb/ingV4DHRtrUkBkWe5EkNwLfAI5OsiXJBaPuSbvkJOA84H1JNrTXmaNuSn1ZANyVZCOT31W3rqr+asQ9DZWPzkqSOnllIUnqZFhIkjoZFpKkToaFJKmTYSFJ6mRYSNMkebXn0dYNSS6bYcwpSeb00cl2zl/ueX9RkvPn8ndIu2uvWFZVGrIftq91GLZTmPxW4f8FUFVfGEEP0oy8spD6lGR5kseSPAh8qKd+RZJ/3fN+U/uiQJKcn2RjWwfhz1rt/UnuS/LNJF9LcngbfxHwr9rVzMm9502yNMm97Vy3JTmk1f9Hkv/Y1lr4VpKTh/Y/iOYVw0J6vZ+aNg3160neDHwReD9wPPBzXSdJ8k7g3wPvq6pfAqYWO/o6cGJVHQvcBPxeVT0DfAH4bFUtrar/Oe10a4B/W1XvBh4CLu/Z98aqOgG4dFpdmjNOQ0mv97ppqCRLgaer6on2/r8AKzvO8z7glqr6DkBVTa1Fsgj487YY0gHA0zs7SZKfBg6uqrtb6Qbglp4hU19IuB5Y3NGTtFu8spB+cjt47b9Lb+4Y/zng81X1i8CFfYzv8kr7+Sr+B6AGxLCQ+vMYsDjJ29v7c3v2PQMcB5DkOOCoVv/vwK8l+Zm279BW/2lga9te0XOel4EDp//iqnoR+F7P/YjzgLunj5MGybCQXm/6PYtPVdU/Mjnt9NftBvf2nvG3AocmeRi4BPgWQFU9DFwF3J3k74GpryW/ArglyXrgOz3n+Uvgg1M3uKf1tAL4dPvW06XAlXP4zyt18ltnJUmdvLKQJHUyLCRJnQwLSVInw0KS1MmwkCR1MiwkSZ0MC0lSp/8HvXXM+uASmlIAAAAASUVORK5CYII=", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "sns.countplot(x=bank_df[\"Education\"])\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 352, + "id": "eaf499c5", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "sns.countplot(x=bank_df[\"CreditCard\"])\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 353, + "id": "5bf41e48", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plt.figure(figsize=(20,10))\n", + "sns.countplot(x=bank_df[\"Age\"])\n", + "plt.savefig('Age.png', facecolor='w', bbox_inches='tight')\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 354, + "id": "bright-temperature", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\gaura\\AppData\\Local\\Temp\\ipykernel_21132\\2679948862.py:3: UserWarning: \n", + "\n", + "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n", + "\n", + "Please adapt your code to use either `displot` (a figure-level function with\n", + "similar flexibility) or `histplot` (an axes-level function for histograms).\n", + "\n", + "For a guide to updating your code to use the new functions, please see\n", + "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n", + "\n", + " sns.distplot(bank_df[\"Income\"])\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "# lets look at the distribution of the income\n", + "plt.figure(figsize=(15,8))\n", + "sns.distplot(bank_df[\"Income\"])\n", + "plt.savefig('Income.png', facecolor='w', bbox_inches='tight')\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 355, + "id": "annoying-transport", + "metadata": {}, + "outputs": [], + "source": [ + "# lets create 2 dataframes: one with personal loans and one without personal loans\n", + "personal_loans = bank_df[bank_df['Personal Loan'] == 1].copy()\n", + "no_personal_loans = bank_df[bank_df['Personal Loan'] == 0].copy()" + ] + }, + { + "cell_type": "code", + "execution_count": 356, + "id": "heard-layer", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countmeanstdmin25%50%75%max
ID480.02390.6500001394.39367410.01166.502342.03566.00004981.0
Age480.045.06666711.59096426.035.0045.055.000065.0
Experience480.019.84375011.5824430.09.0020.030.000041.0
Income480.0144.74583331.58442960.0122.00142.5172.0000203.0
ZIP Code480.093153.2020831759.22375390016.091908.7593407.094705.500096008.0
Family480.02.6125001.1153931.02.003.04.00004.0
CCAvg480.03.9053542.0976810.02.603.85.347510.0
Education480.02.2333330.7533731.02.002.03.00003.0
Mortgage480.0100.845833160.8478620.00.000.0192.5000617.0
Personal Loan480.01.0000000.0000001.01.001.01.00001.0
Securities Account480.00.1250000.3310640.00.000.00.00001.0
CD Account480.00.2916670.4550040.00.000.01.00001.0
Online480.00.6062500.4890900.00.001.01.00001.0
CreditCard480.00.2979170.4578200.00.000.01.00001.0
\n", + "
" + ], + "text/plain": [ + " count mean std min 25% \\\n", + "ID 480.0 2390.650000 1394.393674 10.0 1166.50 \n", + "Age 480.0 45.066667 11.590964 26.0 35.00 \n", + "Experience 480.0 19.843750 11.582443 0.0 9.00 \n", + "Income 480.0 144.745833 31.584429 60.0 122.00 \n", + "ZIP Code 480.0 93153.202083 1759.223753 90016.0 91908.75 \n", + "Family 480.0 2.612500 1.115393 1.0 2.00 \n", + "CCAvg 480.0 3.905354 2.097681 0.0 2.60 \n", + "Education 480.0 2.233333 0.753373 1.0 2.00 \n", + "Mortgage 480.0 100.845833 160.847862 0.0 0.00 \n", + "Personal Loan 480.0 1.000000 0.000000 1.0 1.00 \n", + "Securities Account 480.0 0.125000 0.331064 0.0 0.00 \n", + "CD Account 480.0 0.291667 0.455004 0.0 0.00 \n", + "Online 480.0 0.606250 0.489090 0.0 0.00 \n", + "CreditCard 480.0 0.297917 0.457820 0.0 0.00 \n", + "\n", + " 50% 75% max \n", + "ID 2342.0 3566.0000 4981.0 \n", + "Age 45.0 55.0000 65.0 \n", + "Experience 20.0 30.0000 41.0 \n", + "Income 142.5 172.0000 203.0 \n", + "ZIP Code 93407.0 94705.5000 96008.0 \n", + "Family 3.0 4.0000 4.0 \n", + "CCAvg 3.8 5.3475 10.0 \n", + "Education 2.0 3.0000 3.0 \n", + "Mortgage 0.0 192.5000 617.0 \n", + "Personal Loan 1.0 1.0000 1.0 \n", + "Securities Account 0.0 0.0000 1.0 \n", + "CD Account 0.0 1.0000 1.0 \n", + "Online 1.0 1.0000 1.0 \n", + "CreditCard 0.0 1.0000 1.0 " + ] + }, + "execution_count": 356, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "personal_loans.describe().T" + ] + }, + { + "cell_type": "code", + "execution_count": 357, + "id": "beneficial-tribute", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countmeanstdmin25%50%75%max
ID4520.02512.1654871448.2993311.01259.752518.53768.255000.0
Age4520.045.36725711.45042723.035.0045.055.0067.0
Experience4520.020.13230111.456672-3.010.0020.030.0043.0
Income4520.066.23738940.5785348.035.0059.084.00224.0
ZIP Code4520.093152.4287612156.9496549307.091911.0093437.094608.0096651.0
Family4520.02.3734511.1487711.01.002.03.004.0
CCAvg4520.01.7290091.5676470.00.601.42.308.8
Education4520.01.8435840.8399751.01.002.03.003.0
Mortgage4520.051.78938192.0389310.00.000.098.00635.0
Personal Loan4520.00.0000000.0000000.00.000.00.000.0
Securities Account4520.00.1022120.3029610.00.000.00.001.0
CD Account4520.00.0358410.1859130.00.000.00.001.0
Online4520.00.5957960.4907920.00.001.01.001.0
CreditCard4520.00.2935840.4554540.00.000.01.001.0
\n", + "
" + ], + "text/plain": [ + " count mean std min 25% \\\n", + "ID 4520.0 2512.165487 1448.299331 1.0 1259.75 \n", + "Age 4520.0 45.367257 11.450427 23.0 35.00 \n", + "Experience 4520.0 20.132301 11.456672 -3.0 10.00 \n", + "Income 4520.0 66.237389 40.578534 8.0 35.00 \n", + "ZIP Code 4520.0 93152.428761 2156.949654 9307.0 91911.00 \n", + "Family 4520.0 2.373451 1.148771 1.0 1.00 \n", + "CCAvg 4520.0 1.729009 1.567647 0.0 0.60 \n", + "Education 4520.0 1.843584 0.839975 1.0 1.00 \n", + "Mortgage 4520.0 51.789381 92.038931 0.0 0.00 \n", + "Personal Loan 4520.0 0.000000 0.000000 0.0 0.00 \n", + "Securities Account 4520.0 0.102212 0.302961 0.0 0.00 \n", + "CD Account 4520.0 0.035841 0.185913 0.0 0.00 \n", + "Online 4520.0 0.595796 0.490792 0.0 0.00 \n", + "CreditCard 4520.0 0.293584 0.455454 0.0 0.00 \n", + "\n", + " 50% 75% max \n", + "ID 2518.5 3768.25 5000.0 \n", + "Age 45.0 55.00 67.0 \n", + "Experience 20.0 30.00 43.0 \n", + "Income 59.0 84.00 224.0 \n", + "ZIP Code 93437.0 94608.00 96651.0 \n", + "Family 2.0 3.00 4.0 \n", + "CCAvg 1.4 2.30 8.8 \n", + "Education 2.0 3.00 3.0 \n", + "Mortgage 0.0 98.00 635.0 \n", + "Personal Loan 0.0 0.00 0.0 \n", + "Securities Account 0.0 0.00 1.0 \n", + "CD Account 0.0 0.00 1.0 \n", + "Online 1.0 1.00 1.0 \n", + "CreditCard 0.0 1.00 1.0 " + ] + }, + "execution_count": 357, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "no_personal_loans.describe().T" + ] + }, + { + "cell_type": "code", + "execution_count": 358, + "id": "shared-abortion", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\gaura\\AppData\\Local\\Temp\\ipykernel_21132\\3634644339.py:2: UserWarning: \n", + "\n", + "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n", + "\n", + "Please adapt your code to use either `displot` (a figure-level function with\n", + "similar flexibility) or `histplot` (an axes-level function for histograms).\n", + "\n", + "For a guide to updating your code to use the new functions, please see\n", + "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n", + "\n", + " sns.distplot(personal_loans[\"Income\"], label='Approved')\n", + "C:\\Users\\gaura\\AppData\\Local\\Temp\\ipykernel_21132\\3634644339.py:3: UserWarning: \n", + "\n", + "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n", + "\n", + "Please adapt your code to use either `displot` (a figure-level function with\n", + "similar flexibility) or `histplot` (an axes-level function for histograms).\n", + "\n", + "For a guide to updating your code to use the new functions, please see\n", + "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n", + "\n", + " sns.distplot(no_personal_loans[\"Income\"], label='Not Approved')\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plt.figure(figsize=(15,8))\n", + "sns.distplot(personal_loans[\"Income\"], label='Approved')\n", + "sns.distplot(no_personal_loans[\"Income\"], label='Not Approved')\n", + "plt.legend()\n", + "plt.savefig('Approved_Not_Approved.png', facecolor='w', bbox_inches='tight')\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 359, + "id": "compressed-brazilian", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "cm = bank_df.corr()\n", + "plt.figure(figsize=(20,20))\n", + "sns.heatmap(cm, annot=True)\n", + "plt.savefig('Heatmap.png', facecolor='w', bbox_inches='tight')\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 360, + "id": "final-buddy", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\gaura\\AppData\\Local\\Temp\\ipykernel_21132\\1815586844.py:3: UserWarning: \n", + "\n", + "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n", + "\n", + "Please adapt your code to use either `displot` (a figure-level function with\n", + "similar flexibility) or `histplot` (an axes-level function for histograms).\n", + "\n", + "For a guide to updating your code to use the new functions, please see\n", + "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n", + "\n", + " sns.distplot(bank_df[\"CCAvg\"])\n" + ] + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA3gAAAHgCAYAAAD3xM9JAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAABLNklEQVR4nO3dd3icZ4Hu//uZqt6rJdmW5SbbiePEiZM4pFcCCUvbEOrCwtLOwrK7v0PZw3JYtsFZdjks9SwsNUASCASSkOIUIMVxixN3S24qVrekGZUZzczz+2NkIceyLdsavZp3vp/r0jVFU25nnEh3nmastQIAAAAApD+P0wEAAAAAADODggcAAAAALkHBAwAAAACXoOABAAAAgEtQ8AAAAADAJSh4AAAAAOASPqcDnK2ysjK7cOFCp2MAAAAAgCO2bNnSY60tn+p7aVfwFi5cqM2bNzsdAwAAAAAcYYw5fKrvMUUTAAAAAFyCggcAAAAALkHBAwAAAACXoOABAAAAgEtQ8AAAAADAJSh4AAAAAOASFDwAAAAAcAkKHgAAAAC4BAUPAAAAAFyCggcAAAAALkHBAwAAAACXoOABAAAAgEtQ8AAAAADAJSh4AAAAAOASFDwAAAAAcAkKHgAAAAC4BAUPAAAAAFyCggcAAAAALkHBAwAAAACX8DkdAOnrno1Hzvo5d6+bn4IkAAAAACRG8AAAAADANSh4AAAAAOASFDwAAAAAcAkKHgAAAAC4BAUPAAAAAFyCggcAAAAALkHBAwAAAACXoOABAAAAgEtQ8AAAAADAJSh4AAAAAOASFDwAAAAAcAkKHgAAAAC4BAUPAAAAAFyCggcAAAAALkHBAwAAAACXoOABAAAAgEtQ8AAAAADAJSh4AAAAAOASFDwAAAAAcAkKHgAAAAC4BAUPAAAAAFyCggcAAAAALkHBAwAAAACXoOABAAAAgEtQ8AAAAADAJSh4AAAAAOASFDwAAAAAcAkKHgAAAAC4BAUPAAAAAFyCggcAAAAALkHBAwAAAACXoOABAAAAgEtQ8AAAAADAJSh4AAAAAOASFDwAAAAAcAkKHgAAAAC4BAUPAAAAAFyCggcAAAAALkHBAwAAAACXoOABAAAAgEtQ8AAAAADAJSh4AAAAAOASFDwAAAAAcAkKHgAAAAC4BAUPAAAAAFyCggcAAAAALkHBAwAAAACXoOABAAAAgEtQ8AAAAADAJSh4AAAAAOASFDwAAAAAcAkKHgAAAAC4BAUPAAAAAFyCggcAAAAALkHBAwAAAACXoOABAAAAgEtQ8AAAAADAJSh4AAAAAOASFDwAAAAAcImUFjxjzK3GmL3GmCZjzCdP87g3GWOsMWZtKvMAAAAAgJv5UvXCxhivpK9JuklSq6RNxpgHrbW7XvW4fEkfk7QxVVkwd9yz8cg5Pe/udfNnOAkAAADgPqkcwbtMUpO19oC1Nirpp5LunOJx/yDpXyWNpjALAAAAALheKgtejaSWSbdbx++bYIy5WFKdtfahFOYAAAAAgIzg2CYrxhiPpC9L+utpPPYDxpjNxpjN3d3dqQ8HAAAAAGkolQWvTVLdpNu14/cdly9plaSnjTGHJF0u6cGpNlqx1n7bWrvWWru2vLw8hZEBAAAAIH2lsuBtkrTEGFNvjAlIukvSg8e/aa0dsNaWWWsXWmsXSnpB0h3W2s0pzAQAAAAArpWygmetjUn6qKRHJe2WdK+1dqcx5vPGmDtS9b4AAAAAkKlSdkyCJFlrH5b08Kvu++wpHnttKrMAAAAAgNs5tskKAAAAAGBmUfAAAAAAwCUoeAAAAADgEhQ8AAAAAHAJCh4AAAAAuAQFDwAAAABcgoIHAAAAAC5BwQMAAAAAl6DgAQAAAIBLUPAAAAAAwCUoeAAAAADgEhQ8AAAAAHAJCh4AAAAAuAQFDwAAAABcgoIHAAAAAC5BwQMAAAAAl6DgAQAAAIBLUPAAAAAAwCUoeAAAAADgEhQ8AAAAAHAJCh4AAAAAuAQFDwAAAABcgoIHAAAAAC7hczoAkCr3bDxy1s+5e938FCQBAAAAZgcjeAAAAADgEhQ8AAAAAHAJCh4AAAAAuAQFDwAAAABcgoIHAAAAAC5BwQMAAAAAl6DgAQAAAIBLUPAAAAAAwCUoeAAAAADgEhQ8AAAAAHAJCh4AAAAAuAQFDwAAAABcgoIHAAAAAC5BwQMAAAAAl6DgAQAAAIBLUPAAAAAAwCUoeAAAAADgEhQ8AAAAAHAJCh4AAAAAuAQFDwAAAABcgoIHAAAAAC5BwQMAAAAAl6DgAQAAAIBLUPAAAAAAwCUoeAAAAADgEhQ8AAAAAHAJCh4AAAAAuAQFDwAAAABcgoIHAAAAAC5BwQMAAAAAl6DgAQAAAIBL+JwOAJyL0bG49naEtKdjUE1dYa2qKdTNK6qUHfA6HQ0AAABwDAUPaaU3HNHHf/aSnm3qUcIm7/N5jGIJq/ygT69bXa03X1KnSxYUOxsUAAAAcAAFD2njQHdYf/a9TeoYGNUHr2nQhbWFaqwuUG1xjl482Kf7trTol9va9ZMXW/T2dfO1rCpfPg+zkAEAAJA5KHhIC5sO9en9P9gsjzH6yQcu18XzTxyhu6KhVFc0lOrzd8b01Sf361vPHNDC0hzdvW6B8oL8NQcAAEBmYHgDc96u9kG9/b82qiQnoAc+fOVJ5W6yvKBPn7qtUV+56yK19Y/oa081qa1/ZBbTAgAAAM6h4GFOC0di+vnWVi2vytfPP3SlFpTmTut5d15Uow9c3SBJ+vbvmnW4dyiVMQEAAIA5gYKHOe2xnR2KxOL6t7esVnFu4KyeW1OUrQ9f26CCLL9++MJh9YQiKUoJAAAAzA0sTsKcdaRvWJsPH9NVi8u0pDL/nF4jP8uv91y5UN98pln//dxBffCaBuVn+U/5+Hs2Hjmn97l73fxzet5sOZc/11z/MwEAAOBkjOBhTkpYqwe3t6kgy6cbllec12uV5gX1risWKhyJ6QfPH1Y0lpihlAAAAMDcQsHDnLTpUJ/a+0d126pqBf3nf3h5XUmO7rp0vtr7R/TTTUeUsHYGUgIAAABzCwUPc85QJKbHdnaqvixXF9YWztjrNlYX6PYLq7WnI6Q/7O+ZsdcFAAAA5goKHuac3+3vViQW1x2r58kYM6OvfcWiUq2cV6DHdnWopW94Rl8bAAAAcBoFD3NKLJHQ1sPH1FhdoMqCrBl/fWOM3rimVgXZfv100xGNROMz/h4AAACAUyh4mFN2Hw1pKBrX2gUlKXuP7IBXd62t08DImB54qU2W9XgAAABwCQoe5pTNh/pUmO3Xksq8lL7P/NJc3dRYqR1tA9p06FhK3wsAAACYLRQ8zBnHhqNq6grrkgXF8szw2rupvGZpuRaX5+mhV9rVNxRN+fsBAAAAqUbBw5yx5XByJO2S+cWz8n4eY/TGi2vkMUY/39rK0QkAAABIexQ8zAkJa7Xl8DEtrshTcW5g1t63KCeg2y+o1sGeIW080Dtr7wsAAACkAgUPc0JTV1gDI2NauzB1m6ucyiULirW0Mk+/3dmh3nBk1t8fAAAAmCkUPMwJmw71KSfgVWN1/qy/tzFGf7KmdnyqZhtTNQEAAJC2KHhwXDgS0+6jg7p4frF8Hmf+ShZm+3X7BdU61DukF5iqCQAAgDRFwYPjdrQNKGGTUyWddHyq5mM7O3WMXTUBAACQhih4cNy+zpBKcgOqyA86msMYozdcVCMZcQA6AAAA0hIFD44aiyfU3B3W0sp8mVk4++5MinICunVllZq6wtp6pN/pOAAAAMBZSWnBM8bcaozZa4xpMsZ8corvf9AY84ox5iVjzB+MMStSmQdzz6GeIY3FrZZV5jkdZcJl9SVaWJqjh15p1+DomNNxAAAAgGlLWcEzxnglfU3SbZJWSHrbFAXuHmvtBdbaiyR9UdKXU5UHc9PezpB8HqP6srlT8DzG6I1rahWLW/16e7vTcQAAAIBpS+UI3mWSmqy1B6y1UUk/lXTn5AdYawcn3cyVxKKnDLOvM6RF5bkK+ObWbOGy/KBuaKzUzvZBvdI24HQcAAAAYFpS+Vt1jaSWSbdbx+87gTHmI8aYZiVH8P5yqhcyxnzAGLPZGLO5u7s7JWEx+3rDEfWEo1paOftn303HVYvLNK8oSw9ub9dwNOZ0HAAAAOCMHB82sdZ+zVrbIOl/Svq7Uzzm29batdbateXl5bMbECmzrzMkSVo2Rwue12P0potrNRKN6aGXjzodBwAAADijVBa8Nkl1k27Xjt93Kj+V9IYU5sEcs7czpNLcgErznD0e4XSqC7N1zdJybWvpnyikAAAAwFyVyoK3SdISY0y9MSYg6S5JD05+gDFmyaSbt0van8I8mEPG4gkd6B7S0qq5OXo32XXLKlSeH9Qvt7UpMhZ3Og4AAABwSikreNbamKSPSnpU0m5J91prdxpjPm+MuWP8YR81xuw0xrwk6ROS3p2qPJhbDvYMKZawc3Z65mQ+r0dvWlOjgZExPbqrw+k4AAAAwCn5Uvni1tqHJT38qvs+O+n6x1L5/pi79naE5Pca1ZflOh1lWuaX5uqKhlI919yrlfMK1VA+d451AAAAAI5zfJMVZKZ9nSEtKsuT35s+fwVvXlGlsryA7t/SqpEoUzUBAAAw96TPb9dwjd5wRL1DUS2tTK9RsIDPo7eurVNodEy/2t4mazm2EQAAAHMLBQ+z7nDvsCSpPg2nOdYW5+iGxkq93Dqgl1r6nY4DAAAAnICCh1l3uG9YWX6PKvLn7vEIp3PN0nItKM3Rg9vbdWwo6nQcAAAAYAIFD7PuSN+Q5pfkyGOM01HOiccYvfWS5BGP925pUTzBVE0AAADMDRQ8zKqRaFxdgxHNL0mP3TNPpTg3oDsvqtHh3mE9suOo03EAAAAASRQ8zLKWY8OykhaU5jgd5bxdVFek9eNHJ9y3ucXpOAAAAAAFD7PrcO+QPEaqLc52OsqMuHVVtRrKc/WZB3Zo25FjTscBAABAhqPgYVYd7htWVWGWgj6v01FmhNdj9LZL56uyMKi/+OEWdQ6OOh0JAAAAGYyCh1kTT1i19o2k/fq7V8sJ+vTtd65VaDSm9/9gswZHx5yOBAAAgAzlczoAMkfH4Kii8YQWlKT/+rtXa6wu0FfftkYf/NEWves7L+oH77tMBVl+p2Odl3s2Hjnr59y9bn4KkgAAAGC6GMHDrDnSOyTJHRusTOXGFZX6+tsv1s72Ab3zOy9qYISRPAAAAMwuCh5mzeG+YRVk+VSYnd4jW6dz88oqff3tl2hX+4De9Z2NlDwAAADMKqZoYtYc6R3WgtJcmTQ94Hy6blpRqW++4xJ96Edb9cavP6uv3LVGq2oKU/6+Y/GEDvUMaW9nSId7h2Wtlc/rkc9jtKt9UAvLclWaG3D9P38AAIBMRsHDrBgYGVP/yJjWu3D93VRuaKzU9997mT7+s236k68/q7+5eZne/5pF8nhmrlzFE1YvtfTryT2denpvt/Z1hjQWt6d9TlG2Xw0VeWqsKtDy6nx5KHsAAACuQsHDrDjs8vV3U7mioVS//djV+vQDr+ifH9mjZ/Z16x/esEoN5Xnn/Jqh0TH9YX+Pntjdpaf3dql3KCqvx2jtgmL9+WsWaWllnpZW5quhPE8eYxRLJDQWt/res4d0oCespq6wdrUPasvhY6opytatq6rOK4+T2AQGAADgZBQ8zIojfcPye42qC91xwPl0FecG9PW3X6z7Nrfqc7/eqRv+7RldtbhM77xigW5YXiGf9/TLYGPxhHYdHdTGA3363f5uvXCgV2Nxq8Jsv65dVq4bGit1zZJyFeZMva4xML7Mtjw/qPL8oNbVlyphrV460q/Hd3fqO384qKWVebptVbUqC7Jm/M8PAACA2UXBw6w43Dus2uIceWdwimK6MMborZfW6brlFbp3c4t+/MJh/cUPt6iyIKjVtUVaUJqj+aW5qswPqn9kTD3hiHpCUR3oCWvzoWMKR2KSpEXlufqz9fW6YXmFLllQfMZyeCoeY3TxgmJdUFuo55t79fS+Ln396Sa95ZK6WVkrCAAAgNSh4CHlxuIJHR0Y0WuWlDsdxVHl+UF95LrF+ourF+nJPV36xdY2NXeH9cy+bkViiRMemxvwqqY4W3dcNE/r6ku0rr5UVYUzO8Lm93p09dJyrZlfpB+9cFj3vHhENzZW6rpl5WzEAgAAkKYoeEi5zsFRJaw0ryizpmeeis/r0c0rq3TzyipJUiJh1RWKqCs0quKcgMrygsoOeGctT36WX3/+mkV6YFubntjdqa7QqN50ca385zhCCAAAAOdQ8JBy7f2jkqQaCt6UPB6jqsKsGR+hOxt+r0dvuaRWlflBPbarU8ORuN515QL5PJQ8AACAdELBQ8q1D4woy+9R8Sk2ApmOc9kxEWfHGKNrllUoP8uv+7e26v4trXrr2jqOUgAAAEgjFDyk3NH+EVUXZrOuawbMRtG9eEGxwpGYfruzQ/lBn157QTWfHQAAQJqY1vwrY8wvjDG3G2OYr4WzEk9YHR0Y1TwHpx/i7L1mSZnWN5Tq2eZe/X5/j9NxAAAAME3TLWxfl3S3pP3GmH8xxixLYSa4SE84oljCssFKmjHG6LYLqnVhbaF+u7NDL7f2Ox0JAAAA0zCtgmetfcJa+3ZJF0s6JOkJY8xzxpg/M8ac+8IquF57/4gkdtBMRx5j9OZLajW/JEe/2Nam3nDE6UgAAAA4g2lPuTTGlEp6j6Q/l7RN0leULHyPpyQZXKG9f0Q+j1FZXtDpKDgHPo9Hd11aJ68x+smmI4rFE2d+EgAAABwzrU1WjDEPSFom6YeSXm+tPTr+rZ8ZYzanKhzSX/vAqKoKs+T1sEnHq6XLzqBFOQG9+ZJa/fCFw3pkZ4def+E8pyMBAADgFKa7i+b/s9Y+PPkOY0zQWhux1q5NQS64gLVWRwdGdGFtkdNRcJ4aqwt0ZUOpnmvuVUNZrlbMK3Q6EgAAAKYw3SmaX5jivudnMgjc59jwmEbHEppXyPo7N7h1ZZVqirJ1/9ZWDYyMOR0HAAAAUzhtwTPGVBljLpGUbYxZY4y5ePzrWkk5sxEQ6euPG6xwRIIb+LzJ9XjxhNWvXmqTtdbpSAAAAHiVM03RvEXJjVVqJX150v0hSZ9OUSa4RHv/iDxGqiyg4LlFaV5QNzVW6uEdHXq5bUCrmX4LAAAwp5y24Flrvy/p+8aYN1lrfz5LmeAS7QMjqsjPkt877c1akQauXFyml9sG9Jvt7VpSnqec4HSX8gIAACDVzjRF8x3jVxcaYz7x6q9ZyIc0drR/VNWFjN65jccY/cmaGo2MxfXQK0fP/AQAAADMmjMNreSOX+ZJyp/iC5jS4OiYQpEYB5y7VHVhtq5ZWq5tLf3a1xlyOg4AAADGnWmK5rfGL//37MSBWxyd2GCFgudW1y2r0I62Qf1yW5s+fuNSBXxMxQUAAHDatH4jM8Z80RhTYIzxG2M2GGO6J03fBE7SPjAqSUzRdDGf16M3rKlR/8iYnt7X5XQcAAAAaPrn4N1srR2U9DpJhyQtlvS3qQqF9NfeP6LS3ICy/F6noyCF6stydVFdkX6/v0e94YjTcQAAADLedAve8amct0u6z1o7kKI8cImjA2ywkiluXVklr8ew4QoAAMAcMN2C9xtjzB5Jl0jaYIwplzSaulhIZ9FYQseGoqqk4GWEgmy/rl9WoT0dIT21l6maAAAATppWwbPWflLSlZLWWmvHJA1JujOVwZC+ukKjspIq8yl4meLKxaUqywvoH369S9FYwuk4AAAAGetstr1bLulPjTHvkvRmSTenJhLSXddgci1WVQEFL1P4PB697sJ5OtAzpO8+e9DpOAAAABlrurto/lDS/5F0laRLx7/WpjAX0ljn4Kh8HqOSvIDTUTCLllbm68bGSn11w351h9hwBQAAwAnTHcFbK2m9tfbD1tr/Mf71l6kMhvTVGRpVeX5QHmOcjoJZ9unXLlckltBXNuxzOgoAAEBGmm7B2yGpKpVB4B6dgxFVMj0zIy0qz9Pb183XT15sUVNX2Ok4AAAAGWe6Ba9M0i5jzKPGmAePf6UyGNLTSDSugZExCl4G+8sblijH79W/PLLH6SgAAAAZx3fmh0iSPpfKEHCPrlDy9IzKgqDDSeCU0rygPnRdg77427164UCvLl9U6nQkAACAjDHdYxKekXRIkn/8+iZJW1OYC2mqY/B4wWMEL5O9d3295hVm6Z8e3q1EwjodBwAAIGNMdxfN90u6X9K3xu+qkfTLFGVCGuscjCjg86go2+90FDgoy+/V39yyTC+3DujXL7c7HQcAACBjTHcN3kckrZc0KEnW2v2SKlIVCumrc3BUlflBGXbQzHhvuKhGK+cV6Iu/3avRsbjTcQAAADLCdAtexFobPX7DGOOTxLwrnMBamyx4TM+EJI/H6DOvbVRb/4i+/9whp+MAAABkhOkWvGeMMZ+WlG2MuUnSfZJ+nbpYSEfhSEzD0TgFDxOuXFym65dX6D+fatKxoeiZnwAAAIDzMt2C90lJ3ZJekfQXkh6W9HepCoX01DkYkcQGKzjRp25brqFITP/3yf1ORwEAAHC9aR2TYK1NGGN+KemX1tru1EZCuuoc5IgEnGxJZb7+9NL5+uHzh/WuKxaqvizX6UgAAACuddoRPJP0OWNMj6S9kvYaY7qNMZ+dnXhIJ52Do8oJeJUXnO7xisgUf3XTEgV8Hn3xtxx+DgAAkEpnmqL5V0runnmptbbEWlsiaZ2k9caYv0p5OqSV4xussIMmXq0iP0t/cXWDHtnRoS2H+5yOAwAA4FpnKnjvlPQ2a+3B43dYaw9Ieoekd6UyGNKLtVZdoQjr73BK77+6XhX5Qf3jQ7tlLZvwAgAApMKZCp7fWtvz6jvH1+FxkjUmDIyMKRJLsP4Op5QT8OkTNy3V1iP9emRHh9NxAAAAXOlMBe90+5qz5zkmHN9gpYoRPJzGW9bWaVllvv71t3sUjSWcjgMAAOA6Zyp4q40xg1N8hSRdMBsBkR6OH5FQkU/Bw6l5PUaffO1yHe4d1o83HnY6DgAAgOuctuBZa73W2oIpvvKttUzRxITOwVEVZPmUHfA6HQVz3LVLy7V+can+74b9GhgZczoOAACAq0z3oHPgtLpCEUbvMC3GGH3qtkb1j4zpG083Ox0HAADAVSh4OG/WWnWHIyrPZ4MVTM+qmkL9yUU1+u6zB9XWP+J0HAAAANeg4OG8DY7GFI0lKHg4K399yzJJ0v95dK/DSQAAANzD53QApL+uUHIHTQoe7tl45Kwef3l9qR7Y1qb3XVWvVTWFKUoFAACQORjBw3nrDh3fQZOCh7Nz7bJy5QS8+qeHOfwcAABgJlDwcN66QxFl+T3KCzIgjLOT5ffq+uUVeq65V0/v7XY6DgAAQNqj4OG8dYciKs8LyhjjdBSkocvqS7SwNEf//MhuxeIcfg4AAHA+KHg4b92hiMo5IgHnyOfx6H/eulz7OsO6f0ur03EAAADSGgUP52UkGlcoEmP9Hc7LrauqdMmCYn358X0ajsacjgMAAJC2KHg4L93h5AYr7KCJ82GM0adfu1xdoYj+3+8OOh0HAAAgbVHwcF6O76BJwcP5umRBiW5bVaVv/a554ugNAAAAnB0KHs5Ld2hUXo9RcU7A6Shwgf/v1uWKxhL698f3Ox0FAAAgLVHwcF66QhGV5gbk9bCDJs5ffVmu3nH5Av1s0xHt7ww5HQcAACDtUPBwXrpDETZYwYz6yxuWKDfg0788ssfpKAAAAGmHgodzFosn1DcUZf0dZlRJbkAfvm6xNuzp0vPNvU7HAQAASCsUPJyz3qGorMQZeJhxf7Z+oeYVZumfHt6tRMI6HQcAACBtUPBwzrrYQRMpkuX36m9uWaZX2gb04PZ2p+MAAACkjZQWPGPMrcaYvcaYJmPMJ6f4/ieMMbuMMS8bYzYYYxakMg9m1sQRCXkUPMy8N1xUo1U1BfrSo3s1OhZ3Og4AAEBaSFnBM8Z4JX1N0m2SVkh6mzFmxasetk3SWmvthZLul/TFVOXBzOsOjaoo26+Aj4FgzDyPx+jTr21UW/+I/vvZQ07HAQAASAup/M38MklN1toD1tqopJ9KunPyA6y1T1lrh8dvviCpNoV5MMO6wxGmZyKlrmwo042NFfr6U03qDUecjgMAADDnpbLg1UhqmXS7dfy+U3mfpEdSmAczKJGwHJGAWfHJ25ZreCyur2zg8HMAAIAzmRNz64wx75C0VtKXTvH9DxhjNhtjNnd3d89uOEypfWBEY3GrMgoeUmxxRb7edlmdfrzxiJq7w07HAQAAmNNSWfDaJNVNul07ft8JjDE3SvqMpDustVPOwbLWfttau9Zau7a8vDwlYXF2mruHJEkVHJGAWfDxG5cq2+/l8HMAAIAzSGXB2yRpiTGm3hgTkHSXpAcnP8AYs0bSt5Qsd10pzIIZ1tSVHElhDR5mQ1leUB+6tkGP7+rUCwc4/BwAAOBUUlbwrLUxSR+V9Kik3ZLutdbuNMZ83hhzx/jDviQpT9J9xpiXjDEPnuLlMMc0d4eV7fcqN+B1OgoyxPuuqld1YZb+8SEOPwcAADgVXypf3Fr7sKSHX3XfZyddvzGV74/UaeoKqzw/KGOM01GQIbL8Xv3tLcv0iXu3c/g5AADAKcyJTVaQfg50h9lBE7Nu8uHnY/GE03EAAADmHAoezlr/cFQ94Sjr7zDrJh9+/lwza/EAAABejYKHs8YGK3DS8cPPn97bpXAk5nQcAACAOYWCh7N2/CwyjkiAUz55W6PG4gk9uafT6SgAAABzCgUPZ62pK6yAz6OiHL/TUZChFlfkae3CEr14sE+94SmPzwQAAMhIFDyctebuIS0qy5WHHTThoOuXV8jrMXp8N6N4AAAAx1HwcNaausJqqMhzOgYyXEGWX+sbyvRy64Da+kecjgMAADAnUPBwVkbH4mo5NqzF5RQ8OO/qpeXK9nv12M4Op6MAAADMCRQ8nJWDPUOyVozgYU7I8nt13bJy7e8KT+zuCgAAkMkoeDgrx3fQZAQPc8W6RaUqzPbr0Z0dstY6HQcAAMBRFDyclaausIyRFpXnOh0FkCT5vR7d2Fiptv4R7WgfdDoOAACAoyh4OCtNXWHVFmcry+91OgowYc38IlXkB/XE7k4lGMUDAAAZjIKHs9LcPcT0TMw5HmN0Q2OlukMRbW/pdzoOAACAYyh4mLZ4wupAd1gNFDzMQSvnFai6MEsb9nQpnmAUDwAAZCYKHqatvX9EkVhCi9lBE3OQxxjd2FipvqGoth055nQcAAAAR1DwMG3Ht6HniATMVcur8lVbnK0n93QpFk84HQcAAGDWUfAwbRyRgLnOGKObGivVPzKmzYcZxQMAAJmHgodpa+oKqyQ3oOLcgNNRgFNaXJGnhaU5empvl8YYxQMAABmGgodpa+4OM3qHOc8YoxtXVCo0GtOLB/ucjgMAADCrKHiYtqauMOvvkBYWleWpvixXv9/fzVo8AACQUSh4mJbecETHhsfUUJ7rdBRgWq5bVqHB0Zi2sKMmAADIIBQ8TEtz95AkcUQC0kZDea7qirP1zL5uzsUDAAAZg4KHaZk4IoE1eEgTxhhdv7xC/cNjeqmFUTwAAJAZKHiYlubusLL8HtUUZTsdBZi2pZX5mleUpaf3MooHAAAyAwUP09LUFdaisjx5PMbpKMC0GWN03bIK9Q5F9Upbv9NxAAAAUo6Ch2lp7g6z/g5pqbG6QJUFQT21t1sJRvEAAIDLUfBwRiPRuNr6Ryh4SEseY3Ttsgp1hyJ6bFen03EAAABSioKHM2ruDstaNlhB+lo1r1AluQF985lmWcsoHgAAcC8KHs6ouTu5gyYjeEhXXo/RVYvL9FJLv1482Od0HAAAgJTxOR0Ac19zV1geIy0sy3E6Clzqno1HUv4elywo1rNNPfrW7w5o3aLSlL8fAACAExjBwxk1dw9pfkmOgj6v01GAc+b3evTuKxfqyT1d2tsRcjoOAABASjCChzNq6gqz/g6ukBPwyu81+uTPX9Zb1tZN6zl3r5uf4lQAAAAzhxE8nFY8YXWwZ4j1d3CFnIBPly4s0fbWfvUPR52OAwAAMOMoeDitlr5hReMJRvDgGlctLpMkPdvU43ASAACAmUfBw2kd30GzgRE8uERRTkCra4u06dAxjUTjTscBAACYURQ8nFZT1/gRCYzgwUXWLy5TNJ7Q5sMcmQAAANyFgofTauoKqywvqMIcv9NRgBkzryhb9WW5er65V/EEB58DAAD3oODhtJq7w1pcket0DGDGrW8oU//ImHYdHXQ6CgAAwIyh4OGUrLUckQDXWl6dr5LcAJutAAAAV6Hg4ZR6wlENjsY4IgGu5DFGVzaU6kjfsFr6hp2OAwAAMCMoeDil4xusMIIHt7pkfrGCPo+ebWYUDwAAuAMFD6d0/IgERvDgVkG/V5cuLNGOtgENjIw5HQcAAOC8UfBwSk1dYeUEvKouzHI6CpAyVywqlbXSCwd6nY4CAABw3ih4OKXm7uQGK8YYp6MAKVOcG9CKeQV68WCforGE03EAAADOi8/pAJi7mrvCWreo1OkYaeGejUecjoDzsL6hTDvbB7Wt5ZjW1fN3HgAApC9G8DCloUhM7QOjaijnDDy434LSHNUUZevZpl4lLAefAwCA9EXBw5SO76C5uCLf4SRA6hljtH5xqXrCEe3vDDsdBwAA4JxR8DClfZ0hSdLSSnbQRGZYVVOogiwfRyYAAIC0RsHDlPZ3hRXweTS/JMfpKMCs8Hk8unxRqZq6wuocHHU6DgAAwDmh4GFK+zpDWlSWK5+XvyLIHJctLJHPY/RsE6N4AAAgPfHbO6a0vzOspZWsv0NmyQn6tGZ+sV5q6Vc4EnM6DgAAwFmj4OEk4UhMbf0jrL9DRrqyoVSxhNWLB/ucjgIAAHDWKHg4yf7xDVaWMIKHDFRZkKUlFXnaeKBXsQQHnwMAgPRCwcNJ9o8fkcAUTWSq9YvLFIrE9ErrgNNRAAAAzgoFDyfZ3xlSkB00kcGWVOSpPD+oZ5t7ZDn4HAAApBEKHk6yrzOshvI8eT3G6SiAI4wxurKhVO39o9p06JjTcQAAAKaNgoeT7O8MscEKMt6aumJl+7367h8OOh0FAABg2ih4OEFodEztA6NssIKMF/B5dFl9iR7b1aGWvmGn4wAAAEwLBQ8nYIMV4I8uX1QqjzH63nOHnI4CAAAwLRQ8nOD4EQlM0QSkwmy/br+wWj/b1KLQ6JjTcQAAAM6IgocT7OsMK8vvUV0xO2gCkvTe9fUKR2K6b3Or01EAAADOiIKHE+zrDGlxRZ487KAJSJJW1xVp7YJife+5Q4onODIBAADMbRQ8nGB/Z1hLK1h/B0z23qvqdaRvWBt2dzodBQAA4LQoeJgwMDKmjkF20ARe7eYVlaopytZ3ODIBAADMcRQ8TGjqYoMVYCo+r0fvuXKhNh7s0462AafjAAAAnBIFDxP2dSaPSFjCFE3gJG+9tE45Aa/++9lDTkcBAAA4JQoeJuzrDCnb71VtcbbTUYA5pzDbr7eurdOvt7erKzTqdBwAAIApUfAwYX9nmB00gdN4z5ULNZZI6EcvHHE6CgAAwJQoeJiwrzOkJay/A05pYVmublheqR+/cFijY3Gn4wAAAJyEggdJUt9QVF2hiBqrCpyOAsxp77uqXr1DUf1ia5vTUQAAAE5CwYMkaffRQUlSYzUFDzidyxeVaHVtob71u2YOPgcAAHMOBQ+SJhc8dtAETscYow9d26DDvcN6ZMdRp+MAAACcgIIHSdKu9kFV5AdVmhd0Ogow5928okqLynP1jaebZS2jeAAAYO6g4EGStOvoINMzgWnyeIw+eHWDdrYP6vf7e5yOAwAAMIGCB0VjCTV3hyl4wFm4c808VRVk6RtPNzsdBQAAYAIFD2rqCmssbrViHgUPmK6gz6s/f029nj/Qq21HjjkdBwAAQBIFD/rjBisr2GAFOCt3XTZfhdl+ffMZRvEAAMDcQMGDdh8dVNDn0cLSXKejAGklL+jTu69YoEd3dmpPx6DTcQAAACh4kHZ3DGpZVb58Xv46AGfrvVfVKy/o01ee2O90FAAAgNQWPGPMrcaYvcaYJmPMJ6f4/tXGmK3GmJgx5s2pzIKpWWu1q31QjVWsvwPORVFOQO+9ql6P7OjQzvYBp+MAAIAMl7KCZ4zxSvqapNskrZD0NmPMilc97Iik90i6J1U5cHqdgxEdGx7jgHPgPLzvqnoVZPn0748zigcAAJyVyhG8yyQ1WWsPWGujkn4q6c7JD7DWHrLWviwpkcIcOI3jG6xwRAJw7gqz/Xr/axbpid2derm13+k4AAAgg6Wy4NVIapl0u3X8vrNmjPmAMWazMWZzd3f3jIRD0q7xgrecggecl/esX6iiHL/+/fF9TkcBAAAZLC121bDWfttau9Zau7a8vNzpOK6y++igaouzVZjtdzoKkNbys/z6wNWL9NTebm3lXDwAAOCQVBa8Nkl1k27Xjt+HOWT30UGmZwIz5N1XLFRpbkBffoxRPAAA4IxUFrxNkpYYY+qNMQFJd0l6MIXvh7M0Eo3rYM8QBQ+YIblBnz583WL9oalHT+3tcjoOAADIQCkreNbamKSPSnpU0m5J91prdxpjPm+MuUOSjDGXGmNaJb1F0reMMTtTlQcn29sZUsJKK9hBE5gx77x8gerLcvWF3+zSWJz9owAAwOxK6Ro8a+3D1tql1toGa+0/jt/3WWvtg+PXN1lra621udbaUmvtylTmwYnYQROYeQGfR59+baOau4f04xcOOx0HAABkmLTYZAWpsfvooHIDXtUV5zgdBXCVGxsrtH5xqf5jw371D0edjgMAADIIBS+D7Wof1PLqAnk8xukogKsYY/R3t6/Q4MiYvrKBw88BAMDsoeBlqFg8oR3tA7qwttDpKIArNVYX6E8vna8fPn9YTV1hp+MAAIAMQcHLUPs6wxodS+iiuiKnowCu9dc3L1WW36v//eudstY6HQcAAGQACl6G2t7aL0laXVvkaA7AzcrygvrbW5bp9/t79POtHAMKAABSj4KXoba39Ksw268FpWywAqTSOy9foEsXFuvzv96prsFRp+MAAACXo+BlqO2tyfV3xrDBCpBKHo/Rv77pQkViCX3mlzuYqgkAAFKKgpeBhqMx7esMsf4OmCWLyvP0iZuW6vFdnfrNy0edjgMAAFyMgpeBdrYPKp6wrL8DZtH7rqrX6tpCfe7BneoNR5yOAwAAXIqCl4G2t/RLki6s44gEYLb4vB598c2rNTg6pv/585eVSDBVEwAAzDwKXgba3jqgmqJsVeRnOR0FyCjLqvL1mdc26ondXfrGM81OxwEAAC5EwctA21v6OeAccMi7r1yoO1bP0789tld/2N/jdBwAAOAyFLwM0zcU1ZG+Ya1mgxXAEcYY/fMbL1BDeZ7+8qfb1N4/4nQkAADgIhS8DPMyB5wDjssN+vTNd16iaCyhD/14qyKxuNORAACAS1DwMsz2lgEZI13AFE3AUQ3lefrSmy/U9pZ+feJn2xVn0xUAADADKHgZZntrvxaX5ykv6HM6CpDxbrugWp95baMeeuWoPsnOmgAAYAbwW34GsdZqe0u/rlte4XQUAOPef/UihSIx/d8N+5Ub9OnvX79CxhinYwEAgDRFwcsgbf0j6h2KssEKMMf81Y1LFB6N6bvPHlR+lk9/ffMypyMBAIA0RcHLINtbBiRJF7HBCjCnGGP0v17XqKFITF99skmh0Zj+7vZG+bzMogcAAGeHgpdBXmo5poDPo2VV+U5HAfAqxhj90xsvUH6WT//1h4M61Dukr75tjfKz/E5HAwAAaYSCl0FePNini2qLFPAxKgBM1z0bj5zT8+5eN/+sn+P1GP3d61aovjxXn/3VTr35G8/rO+9Zq9rinHPKAAAAMg+/6WeI0OiYXmkb0OWLSpyOAuAM3r5ugb7/Z5epfWBEd/zns3r4laNORwIAAGmCgpchNh8+poSV1i0qdToKgGm4akmZHvjwetUUZevDP96qj9yzVb3hiNOxAADAHMcUzQzxwoFe+b1GF88vdjoKgGlaXJGnX3z4Sn37dwf0H0/s0wvNvfrs61fo9RfOk8dzfkcpnMvU03OZdgoAAGYXBS9DbDzQp9W1RcoOeJ2OAmSEmSpQfq9HH7lusW5srNTf3r9dH/vpS/rG083665uX6cbGCs7MAwAAJ2CKZgYIR2J6pW1A61h/B6StZVX5euDD6/WVuy7S6Fhc7//BZr3ha8/qsZ0disUTTscDAABzBCN4GWDL4WOKJ6wuZ/0dkNa8HqM7L6rR7RdU6xdb2/SVDfv1gR9uUVVBlt56aZ3uurRO84qynY4JAAAcRMHLAC8c6JXPY3TJAtbfAW7g83r01kvr9MaLa7RhT5fu2XhEX31yv/7zyf1aV1+qW1dV6eaVlaoupOwBAJBpKHgZYOOBXl1YW6icAB834CY+r0e3rKzSLSur1NI3rPs2t+iRHR36+wd36u8f3KnVdUW6ekmZrmgo1cXzi5XlZw0uAABux2/8Ljccjenl1gG9/+pFTkcBkEJ1JTn6xM3L9Imbl6mpK6xHd3bo8V2d+tpTTfrqk00K+Dy6eH6RrmxIFr5YIiGfh2XYAAC4DQXP5bYcPqYY6++AjLK4Ik+LKxbrI9ctVmh0TJsO9em5pl49f6BX//7EPn35ccnvNVpQmqv6slzVl+aqtjhbPi+FDwCAdEfBc7kXDvTKy/o7IGPlZ/l1/fJKXb+8UpLUPxzVCwf69L3nDulgT1iP7+qUJPk8RvNLcpKFryxXdSU58lP4AABIOxQ8l9t4oE8X1BQqL8hHDUAqygno1lVV6huKSpKGIjEd6h3SwZ7k15N7umSV3LGzrjh7vPDlaX5JjrPBAQDAtPBbv4uNROPa3tqv915V73QUAHNUbtCnlfMKtXJeoaTkfzcOHy98vUN6Zl+3ntrbLa8xemTHUV2zrFxXLynXiuoCeTwcsg4AwFxDwXOxrUeOaSxudXk96+8ATE92wKvl1QVaXl0gSYqMxXW4b1gHusPqCUf1xd/u1Rd/u1dleUFdvaRM1ywr11WLy1SaF3Q4OQAAkCh4rvbMvm75vUZrF7L+DsC5Cfq9WlqZr6WV+bp73Xx1hUb1+3094yN7XfrFtjYZI11YU6jrl1fqhsYKrZxXIGMY3QMAwAkUPBd7YnenLl9Uqvwsv9NRAEzDPRuPnPVz7l43PwVJpjY53+WLSnVZfYna+0e0rzOkvR0h/ccT+/TvT+xTYbZfy6vytbyqQJ967XLO3wMAYBZR8FyquTusA91DevcVC52OAiCFzqUUzhSPMaotzlFtcY6uX16p0OiY9naEtKcjpK1HjmnjwT7dt6VFr1lSphsaK3X98gqVMZUTAICUouC51Ibdya3Pb2iscDgJgEyRn+XX2oUlWruwRGPxhA50hxVLWG3Y3aVHd3bKGGlNXZFuaKzUjY2VWlqZx1ROAABmGAXPpZ7Y1aXG6gLVFrO1OYDZ5/d6tKyqQHevm68vvMFqZ/ugntjdqQ27u/SlR/fqS4/uVV1Jtm5Ynix76xaVcO4eAAAzgILnQseGotp8uE8fvW6x01EAQMYYraop1KqaQn38xqXqHBzVht1d2rC7Uz958Yi+99whFWT5dP3yCt2yskpXLy1XLmd3AgBwTvgJ6kJP7e1Swko3rqh0OgqADHe6NYI3NFbqNUvK1dQV1u6jg3psV6d++VK7fB6ja5aW6+aVydE9jmAAAGD6KHgu9MTuTlUWBLVq/OBiAJirAj6PVswr0Ip5BYonrA73DWl3+6D2dIS0YU+XPOYVrV1QoptXVurmFVWaX8q0cwAAToeC5zKRWFzP7O3WHRfVyONh8wIA6cPrMVpUlqdFZXmy1urowKh2HR3U7qOD+sJDu/WFh3arqiBLK+YV6IKaQlUWZJ3w/Nk8MgIAgLmKgucyLxzo01A0rptWsHsmgPRljNG8omzNK8rWjY2V6huKatfRQe1qH9BTe7r05J4uVRYEdcH42r6K/KwzvygAABmAgucyG3Z3Ktvv1ZUNZU5HAYAZU5Ib0FWLy3TV4jKFRse0o31Qr7QOaMPuLj2xu0tVBVnqDUd0+4XVWlSe53RcAAAcQ8FzEWutntjVqdcsKVOW3+t0HABIifwsv65YVKorFpVqcGRMO9oH9ErbgP7t8X36t8f3aVVNgf5kTa1ev7qakT0AQMah4LnIjrZBtQ+M6uM3LnU6CgDMioJsv65sKNOVDWUaGBnTjrYBvdTSr3/4zS7940O7tLgiTxfVFWtFdYECvpPP2WPdHgDAbSh4LnLflhYFfB7dsrLK6SgAMOsKs/1av7hM6xeXqWtwVC+19Oulln7duzn538aV1QW6aH6RGsrz5DHntwnV6Y5/OBXKJABgNlDwXGJ0LK5fbmvTrSurVJjjdzoOADiqoiBLN6+s0o0rKnW4d1jbjhzTjvYBbWvpV36WT6tri7RmfpGstTLnWfYAAJhLKHgu8ejODg2OxvSnl9Y5HQUA5gyPMaovy1V9Wa5ev3qe9nSE9FJLv55v7tUfmnr02M5OvfHiGr1hTc1Jxy4AAJCOKHguce/mFtWVZOuKRaVORwGAOcnv9eiCmkJdUFOo4UhML7cNqPXYsP75kT3619/u0frFZXrjxTW6ZWWVcgL8eAQApCd+grlAS9+wnm3q1SduWsrh5gAwDTlBny5fVKq7163RwZ4hPbC1Vb/Y1qa/+tl25QZ26NZV1XrTxTW6fFEp/10FAKQVCp4L3Le5RcZIb76k1ukoAJB26sty9Ymbl+njNy7VpkN9emBbmx56+ah+vrVV8wqzdOeaGr3p4hotrsh3OioAAGdEwUtz8YTVfVta9Zol5ZpXlO10HABIWx6P0bpFpVq3qFSfu2OlHt/VqV9sbdW3f3dA33i6WRfUFOrOi+bp9gurnY4KAMApUfDS3B+aenR0YFR/d/sKp6MAgGtk+b16/ep5ev3qeeoORfTg9nY9sK1VX3hot77w0G4tKMnRhbWFWlVTqPwsdi4GAMwdFLw0d++mFhXn+HXjigqnowCAK5XnB/W+q+r1vqvqdbBnSL/Z3q4fbTysX798VL95+ajqy3J1QW2hVs4rVF4wfX+scrYfALhD+v4kgjoGRvXYrg694/IFCvq8TscBgLRzLqWmNC+oj92wVJ2Do3qlbUAvtw7oVy+168GX2jW/NEfLqwq0vCpfFflBztgDAMw6Cl4a+/rTTbJWeu/6eqejAEDGqSzIUmVBlm5YXqGOwVHtaBvU3o5BPbqzQ4/u7FBxjl/LxsveorJcp+NmpHMp8OeK0UwAcwUFL0219Y/opy+26K2X1qmuJMfpOACQsYwxqi7MVnVhtm5aUamBkTHt7QhpT8egthzu0wsHehXwevTMvm5d0VCqKxpK1VhVwPELAICUoOClqa891SRJ+sh1ix1OAgCYrDDbr8vqS3RZfYnG4gkd6A5rT0dIB3qGtGFPlySpKMevS+YX6+IFxVpTV6TVdUXKTcP1e+FITN2hyMRX71BEodGYhiIxhY9/jcY0FE1ejo4l1DcUVdxaJRJWCWsVT9jkbSsZScZIRkYekyzPxy8Lsn0K+rwK+jzK8p98mR3wKj/oU17Qp7ys5OWOtgEF/R5l+bzKCXiVE/Ap6PfIw9RZAC6Wfj9NoJa+Yd27qUV3r5uvGo5GAIA5y+/1aFlVgZZVFejudfN1dGBEzzf36vnmXm09cmyi8HmMtLAsV43VBVpRXaDG6nzVl+Wptjhbfq9nVjPHE3aimIUiY+OXMYVGxxQajU3cDo/G9OkHXpnyNXweM1Gyjn8V5QSU7fcq4PPI60kWN48x49eTtyUpIclaK2ulhP3j9fmlOYrE4oqMJTQ6fjk4OjZxeyQaV2g0pkgscdo/n8dI2f5k2csJJi9zA38sgDkBr3In5c7L8s36ZwAA54OCl4b+88kmeTxGH76W0TsASBeT14OtmV+sNfOLNRKNq+XYsFr6hnV0YFTPNfXooZePTjzO5zGqLc7W/NJcVRUEJ9b9leUFlJ/lV0GWXwXZPmX5vfJ5jHxej/xeo4SVYvGEYgmrsXhCodGYBkbGNDgyNukypsHRMR0bjqo7FNH+zrBCo2MajsZlp8if7fcqL8un/KBPtcXZyg/6dPXScpXnBye+SnODys/yKejznHKDmXNdFzfdNW7RWGJiBPHezS0nFMChaFzD0ZiGo3ENR5KXx4aiajuWvB5LTPUnl4I+z0Thy500Qjj562DPkMryAsoL+qa9uQ47lwJIBQpemjncO6T7t7bqXVcsUFVhltNxAADnITvg1dLKfC2tzJ+4b3Qsrs7BUfWEo6oqDOpQz7Bajg1rb8egukMRnaKDnJPcgFdFOQGV5wdVnBvQ/JKcZInL8ik/6Fd+1h/LzFSjWLNZNs6lDFUXTn+Wi7VW0XhCw9H4H6eYjk6aajr+1ROO6FDvkEZeVYS//fsDkpJlsCwvqLL8oMpyA+PXxy/zgirNC6h8/HrC2jk9XZQCCqQnCl6a+coT++X3Gn3o2ganowAAUiDL79WC0lwtKM096ZflWDyh3qGoesLJtW6h0ZgGR8Y0GosrFk+O1o3FrbweyedJjub5vB7lZ/lUmJ0c8SvM9qsgO1neJpe22dxxci4yxoyv8fOqOCdwxsfHE3ZibeFQJKYLagvVE46oJxxVTyii7nBERweSR2n0DkUVn6KZe4zGR2GTn0tR9qTrOcnLV48IpnoEFED6o+Clkd/t69YvtrXpg9c0qCKf0TsAyDQ+r2dimiac5fWYZDnL8kuS3nhx7Skfm0hY9Y+MJQtgKKKeoWQJfGZf98S02fb+Ee0+OnjSNFG/16gkN6CS3KBKcwPj1wMqzQ2oKCcgL7uxAngVCl6a6B+O6m/v367FFXn6+I1LnI4DAACmyeMxE8Vs8nTcLL/3hMdZazUcjWtgvPT1D0fVNxRV71BUveGI9neGTiiAHpPctbU0N6iS3IDK8gIqyw+qPC855XYuT/8EkDoUvDTxv361U73hqL7z7ktP+oEAAMBkmT7dMl0ZY5Q7vpHLvCl2yU5Yq9BoTH1DUfUNRdQ7FB2/HtUrbQMaGYtPPNbrMSrNTa6vLMsLKujzaFF5rhaV56kw2z+bfywAs4yClwZ+9VKbfr29XX9z81Ktqil0Og4AAJIokrPNY4wKx9fo1ZflnvT94UhM3eGIesLjZxOGo+ocjGj30UE9s6974nFleUE1jJe9hvJcNZTnqaE8TzXF2Uz5BFyAgjfHHR0Y0f/65Q6tmV+kD17DxioAAGBqOUGfFgR9WlB6YvmLJ6yuXFyqA91Dau4O60B3WM3dQ3pkx1H1D49NPC7g86i+NFeLxktf5+CoyvKSR2AwewhIHxS8OSwciekjP96qsbjVv7/1Ivk4aBUAAJwlr8dMjNLdpMoTvtc3FB0vfOHxAjikvR0hPbar84SdP/OzfKrID6o8P0sV+cHx68GzOvcPwOyg4M1Rw9GY3vu9TdreOqCv3b1GC6eYigEAAOaGuT5ddTr5jh/Pcf3yCsUSCfUNRdUTiqo7HFF3aFRdoYi2HTmmSCwx8Zxsv1fl44WvIj+o6qIsLanI07zCbHmY7gk4goI3B42OxfXn39+szYf69B93rdGtq6qdjgQAADKIz+NRRX7WSccyWWs1OBpTV2hU3aGIugYj6gol1/ltPhzXwzs6JCWLX0NFrpZU5GtxRXL0cHFFnhaU5pxw/iKAmUfBm2NGx+J6/w826/kDvfq3t6zWHavnOR0JAOCQuT4qhMxjJm30sqQi/4TvDUViWl1XpKausJq6wtrfFdLGA716YFvbxGP8XqO64hzVluSorjhbdSU5qi3OVl1xjupKclSc40/plM9z+XeKQ+KRbih4c0hzd1if+NlL2t46oC++6cLTHpoKAAAwl+QGfbqsvkSX1ZeccH84ElPzeOlr6g7rcO+QWvpG9HJr/wmbvEhSbsCryoKs5Hl+42f6ledP+ho/468kJ6DsABu/AFOh4M0B1lr9aOMR/eNDu5Tl9+qb77iYaZkAAMAV8oI+ra4r0uq6opO+FxodU+uxEbX0Davl2Ihajw2rK5Q85mF3+6B+F4ooFIlN+bp+r1FOwKfcgFc5QZ9yAl7lBnzKCSYvc191X07AK5+H6aFwPwqeww72DOkffrNLT+7p0tVLy/WlN1+oyoKsMz8RAAAgzeVn+dVY7VdjdcEpHzMSjasnnFzr1xOO6NhQVH3DUT3X1KvhaExDkbiGo8kD4IejMY2OJU75WkGf58TiF/BO3M4L+pLTT3P8KsoOKOCjDCI9UfAcsr2lX998plm/3dmhgNej/33HSr3rigVsNQwAADBJdsCrupLkGr3JirIDUz4+lkhoJBrXUDSu4UgseRmNaej49UhMw9G4QpExdQ6Oaiga01jcnvQ62X6vinL82rC7U/OKslVdlKWaomxVF2ZrXlGWKguy2DAGc1JKC54x5lZJX5HklfRf1tp/edX3g5J+IOkSSb2S/tRaeyiVmZzU0jesp/Z26TcvH9WLB/uUn+XTh65p0HvWLzxplyoAAACcPZ/Ho/wsj/Kz/NN+TjSWUDgS08DImAZGouofHhu/Pqa2/hFtPnxMAyMnrhc0RirPC6q6KFvVBVmqLspSdWGWqguzk5dF2arID1ICMetSVvCMMV5JX5N0k6RWSZuMMQ9aa3dNetj7JB2z1i42xtwl6V8l/WmqMs2maCyhAz1h7T46qJ1tg/r9/h7t7QxJkurLcvWZ1zbqrsvqzuo/PgAAAHPZue786vROlQGfRyW+gEpyA5JOPHv4eLahSExHB0bU3j86cdkxMKr2gRE1dYf1+/3dGorGT3iux0jl+UFVFmSpJDf5+qW5AZXmBSeul+QGVJDtV17Qp7zx6aKzMaOLHUXdy1h78pD0jLywMVdI+py19pbx25+SJGvtP096zKPjj3neGOOT1CGp3J4m1Nq1a+3mzZtTkvlcPbWnS1uPHNPRgeS/6EcHRnSkb3hiuD/g9WjtwmJdv7xC1y+v0KLyPIcTzwy27wYAAPij0bH4xMjf8qp8tQ+MqmNgRJ2DEfUNRZOHx4cjJxwW/2rGSHnjm8TkBpNrAwM+j/ze5FfA51HA65HfaxTweeT1GElm4rlm0utIkpn0veOslfaNDzxIkn3VFTvpO5N/K28oz5Od9F2vx8jrMfJ5PPIYI5/3+O3Jl54/3vaeeL/XoxO/P+n1Tn788ftP8xxv8nbyn8OJ/0yMMeOXcsWSKGPMFmvt2qm+l8opmjWSWibdbpW07lSPsdbGjDEDkkol9aQw14x7ZMdR3b+lVRX5WaoqzNLSynzdtKJKjdX5aqwuUH1ZLsPzAAAALpfl9yrLnzzqIWGlqoIsVRWcfFh8NJ7QUCQ+vi4wuTFMJBbXiuoCDUViCkWSawbDkeQmMmPxhKKxhIYiMUXjVtFYXGNxq7F4QrHE5BJmx99j8q3kex6/fbzaHC+ZE1VnvPRMFET98crx663HRiYeaq2UsFbxhFUskbw8/hVLJJRIzRjSjJqy/I3/gY/fvqiuSD/9wBUOJz07abHJijHmA5I+MH4zbIzZ62SeUznodIDZV6Y0K+OYUXz+mY3PP3Px2Wc2Pv/MlnGf/15JP/sLp1NMacGpvpHKgtcmqW7S7drx+6Z6TOv4FM1CJTdbOYG19tuSvp2inDhHxpjNpxoahvvx+Wc2Pv/MxWef2fj8Mxuff3pI5bzBTZKWGGPqjTEBSXdJevBVj3lQ0rvHr79Z0pOnW38HAAAAADi1lI3gja+p+6ikR5U8JuG71tqdxpjPS9psrX1Q0nck/dAY0ySpT8kSCAAAAAA4Byldg2etfVjSw6+677OTro9KeksqMyClmDab2fj8Mxuff+bis89sfP6Zjc8/DaTsmAQAAAAAwOxi734AAAAAcAkKHs6JMeZWY8xeY0yTMeaTTufB7DDG1BljnjLG7DLG7DTGfMzpTJh9xhivMWabMeY3TmfB7DLGFBlj7jfG7DHG7DbGpNfhUDgvxpi/Gv9v/w5jzE+MMVlnfhbSlTHmu8aYLmPMjkn3lRhjHjfG7B+/LHYyI6ZGwcNZM8Z4JX1N0m2SVkh6mzFmhbOpMEtikv7aWrtC0uWSPsJnn5E+Jmm30yHgiK9I+q21drmk1eLvQcYwxtRI+ktJa621q5TcQI/N8dzte5JufdV9n5S0wVq7RNKG8duYYyh4OBeXSWqy1h6w1kYl/VTSnQ5nwiyw1h611m4dvx5S8pe7GmdTYTYZY2ol3S7pv5zOgtlljCmUdLWSO2DLWhu11vY7GgqzzScpe/zs4hxJ7Q7nQQpZa3+n5C73k90p6fvj178v6Q2zmQnTQ8HDuaiR1DLpdqv4JT/jGGMWSlojaaPDUTC7/kPS/ycp4XAOzL56Sd2S/nt8iu5/GWNynQ6F2WGtbZP0fyQdkXRU0oC19jFnU8EBldbao+PXOyRVOhkGU6PgAThrxpg8ST+X9HFr7aDTeTA7jDGvk9Rlrd3idBY4wifpYknfsNaukTQkpmdljPG1VncqWfTnSco1xrzD2VRwkk1uxc92/HMQBQ/nok1S3aTbteP3IQMYY/xKlrsfW2t/4XQezKr1ku4wxhxScmr29caYHzkbCbOoVVKrtfb4qP39ShY+ZIYbJR201nZba8ck/ULSlQ5nwuzrNMZUS9L4ZZfDeTAFCh7OxSZJS4wx9caYgJKLrB90OBNmgTHGKLn+Zre19stO58HsstZ+ylpba61dqOS/909aa/k/+BnCWtshqcUYs2z8rhsk7XIwEmbXEUmXG2Nyxn8W3CA22clED0p69/j1d0v6lYNZcAo+pwMg/VhrY8aYj0p6VMldtL5rrd3pcCzMjvWS3inpFWPMS+P3fdpa+7BzkQDMov8h6cfj/3PvgKQ/czgPZom1dqMx5n5JW5XcUXmbpG87mwqpZIz5iaRrJZUZY1ol/b2kf5F0rzHmfZIOS3qrcwlxKiY5fRYAAAAAkO6YogkAAAAALkHBAwAAAACXoOABAAAAgEtQ8AAAAADAJSh4AAAAAOASFDwAQEYyxlQZY35qjGk2xmwxxjxsjFk6/vWwMWa/MWarMeZeY0zlpOf9hzGmzRjDz1AAwJzDDycAQMYZP6j5AUlPW2sbrLWXSPqUpEpJD0n6hrV2ibX2Yklfl1Q+/jyPpD+R1CLpGkfCAwBwGhQ8AEAmuk7SmLX2m8fvsNZul7RE0vPW2l9Puv9pa+2O8ZvXStop6RuS3iZJxph/McZ85PjjjTGfM8b8jTHGY4z5ujFmjzHm8fFRwTen/o8GAMhkFDwAQCZaJWnLWdx/3Nsk/UTJ0b/bjTF+ST+T9NZJj3nr+H1vlLRQ0gpJ75R0xXmnBgDgDCh4AABMgzEmIOm1kn5prR2UtFHSLdbabZIqjDHzjDGrJR2z1rZIukrSfdbahLW2Q9JTjoUHAGQMn9MBAABwwE5JU02X3KlTr627RVKRpFeSS/iUI2lE0m8k3Tf+elVKjt4BAOAIRvAAAJnoSUlBY8wHjt9hjLlQ0j5JVxpjbp90/9XGmFVKTs/8c2vtQmvtQkn1km4yxuQoWeruUrLk3Tf+1GclvWl8LV6lkuv3AABIKQoeACDjWGutkrth3jh+TMJOSf8sqUPS6yT9j/FjEnZJ+rCkkKRbldxh8/hrDEn6g6TXW2t3SsqX1GatPTr+kJ9LapW0S9KPJG2VNDAbfz4AQOYyyZ9xAABgphlj8qy1YWNMqaQXJa0fX48HAEBKsAYPAIDU+Y0xpkhSQNI/UO4AAKnGCB4AAAAAuARr8AAAAADAJSh4AAAAAOASFDwAAAAAcAkKHgAAAAC4BAUPAAAAAFyCggcAAAAALvH/A157BuRMegPcAAAAAElFTkSuQmCC", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "# lets look at the distribution of average credit card spending\n", + "plt.figure(figsize=(15,8))\n", + "sns.distplot(bank_df[\"CCAvg\"])\n", + "plt.savefig('Average CC Spending.png', facecolor='w', bbox_inches='tight')\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 361, + "id": "crude-yemen", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\gaura\\AppData\\Local\\Temp\\ipykernel_21132\\2192030919.py:2: UserWarning: \n", + "\n", + "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n", + "\n", + "Please adapt your code to use either `displot` (a figure-level function with\n", + "similar flexibility) or `histplot` (an axes-level function for histograms).\n", + "\n", + "For a guide to updating your code to use the new functions, please see\n", + "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n", + "\n", + " sns.distplot(personal_loans[\"CCAvg\"])\n", + "C:\\Users\\gaura\\AppData\\Local\\Temp\\ipykernel_21132\\2192030919.py:3: UserWarning: \n", + "\n", + "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n", + "\n", + "Please adapt your code to use either `displot` (a figure-level function with\n", + "similar flexibility) or `histplot` (an axes-level function for histograms).\n", + "\n", + "For a guide to updating your code to use the new functions, please see\n", + "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n", + "\n", + " sns.distplot(no_personal_loans[\"CCAvg\"])\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plt.figure(figsize=(15,8))\n", + "sns.distplot(personal_loans[\"CCAvg\"])\n", + "sns.distplot(no_personal_loans[\"CCAvg\"])\n", + "plt.savefig('Personal loans.png', facecolor='w', bbox_inches='tight')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "shaped-gospel", + "metadata": {}, + "source": [ + "## Data Preparation" + ] + }, + { + "cell_type": "code", + "execution_count": 362, + "id": "sunrise-mapping", + "metadata": {}, + "outputs": [], + "source": [ + "from tensorflow.keras.utils import to_categorical\n", + "\n", + "X = bank_df.drop(columns=[\"Personal Loan\"])\n", + "y = bank_df[\"Personal Loan\"]\n", + "\n", + "y = to_categorical(y)" + ] + }, + { + "cell_type": "code", + "execution_count": 363, + "id": "floral-saint", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "((4500, 13), (500, 13), (4500, 2), (500, 2))" + ] + }, + "execution_count": 363, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn.preprocessing import StandardScaler, MinMaxScaler\n", + "from sklearn.model_selection import train_test_split\n", + "\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1)\n", + "\n", + "sc = StandardScaler()\n", + "X_train = sc.fit_transform(X_train)\n", + "X_test = sc.transform(X_test)\n", + "\n", + "X_train.shape, X_test.shape, y_train.shape, y_test.shape" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "diagnostic-walnut", + "metadata": {}, + "source": [ + "## Building a multi-layer neural network model" + ] + }, + { + "cell_type": "code", + "execution_count": 364, + "id": "official-concern", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Model: \"sequential_9\"\n", + "_________________________________________________________________\n", + " Layer (type) Output Shape Param # \n", + "=================================================================\n", + " dense_54 (Dense) (None, 250) 3500 \n", + " \n", + " dropout_45 (Dropout) (None, 250) 0 \n", + " \n", + " dense_55 (Dense) (None, 500) 125500 \n", + " \n", + " dropout_46 (Dropout) (None, 500) 0 \n", + " \n", + " dense_56 (Dense) (None, 500) 250500 \n", + " \n", + " dropout_47 (Dropout) (None, 500) 0 \n", + " \n", + " dense_57 (Dense) (None, 500) 250500 \n", + " \n", + " dropout_48 (Dropout) (None, 500) 0 \n", + " \n", + " dense_58 (Dense) (None, 250) 125250 \n", + " \n", + " dropout_49 (Dropout) (None, 250) 0 \n", + " \n", + " dense_59 (Dense) (None, 2) 502 \n", + " \n", + "=================================================================\n", + "Total params: 755,752\n", + "Trainable params: 755,752\n", + "Non-trainable params: 0\n", + "_________________________________________________________________\n" + ] + } + ], + "source": [ + "# sequential model\n", + "ann_model = keras.Sequential()\n", + "\n", + "# adding dense layer\n", + "ann_model.add(Dense(250, input_dim=13, kernel_initializer='normal', activation='relu'))\n", + "ann_model.add(Dropout(0.3))\n", + "ann_model.add(Dense(500, activation='relu'))\n", + "ann_model.add(Dropout(0.3))\n", + "ann_model.add(Dense(500, activation='relu'))\n", + "ann_model.add(Dropout(0.3))\n", + "ann_model.add(Dense(500, activation='relu'))\n", + "ann_model.add(Dropout(0.4))\n", + "ann_model.add(Dense(250, activation='linear'))\n", + "ann_model.add(Dropout(0.4))\n", + "\n", + "# adding dense layer with softmax activation/output layer\n", + "ann_model.add(Dense(2, activation='softmax'))\n", + "ann_model.summary()" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "failing-hawaii", + "metadata": {}, + "source": [ + "## Compilation and training of deep learning model" + ] + }, + { + "cell_type": "code", + "execution_count": 365, + "id": "optional-scotland", + "metadata": {}, + "outputs": [], + "source": [ + "# custom functions for f1, precision and recall\n", + "\n", + "from keras import backend as K\n", + "\n", + "def recall_m(y_true, y_pred):\n", + " true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))\n", + " possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))\n", + " recall = true_positives / (possible_positives + K.epsilon())\n", + " return recall\n", + "\n", + "def precision_m(y_true, y_pred):\n", + " true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))\n", + " predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))\n", + " precision = true_positives / (predicted_positives + K.epsilon())\n", + " return precision\n", + "\n", + "def f1_m(y_true, y_pred):\n", + " precision = precision_m(y_true, y_pred)\n", + " recall = recall_m(y_true, y_pred)\n", + " return 2*((precision*recall)/(precision+recall+K.epsilon()))" + ] + }, + { + "cell_type": "code", + "execution_count": 366, + "id": "accredited-spending", + "metadata": {}, + "outputs": [], + "source": [ + "ann_model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=[f1_m]) # metrics=['accuracy']" + ] + }, + { + "cell_type": "code", + "execution_count": 367, + "id": "rolled-inquiry", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/20\n", + "113/113 [==============================] - 2s 9ms/step - loss: 0.1776 - f1_m: 0.9394 - val_loss: 0.1069 - val_f1_m: 0.9677\n", + "Epoch 2/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0999 - f1_m: 0.9676 - val_loss: 0.0757 - val_f1_m: 0.9655\n", + "Epoch 3/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0916 - f1_m: 0.9682 - val_loss: 0.0792 - val_f1_m: 0.9688\n", + "Epoch 4/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0773 - f1_m: 0.9715 - val_loss: 0.0696 - val_f1_m: 0.9752\n", + "Epoch 5/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0745 - f1_m: 0.9765 - val_loss: 0.0701 - val_f1_m: 0.9698\n", + "Epoch 6/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0662 - f1_m: 0.9776 - val_loss: 0.0666 - val_f1_m: 0.9752\n", + "Epoch 7/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0619 - f1_m: 0.9787 - val_loss: 0.0691 - val_f1_m: 0.9720\n", + "Epoch 8/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0612 - f1_m: 0.9795 - val_loss: 0.0791 - val_f1_m: 0.9720\n", + "Epoch 9/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0484 - f1_m: 0.9823 - val_loss: 0.0539 - val_f1_m: 0.9784\n", + "Epoch 10/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0513 - f1_m: 0.9815 - val_loss: 0.0762 - val_f1_m: 0.9752\n", + "Epoch 11/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0566 - f1_m: 0.9829 - val_loss: 0.0640 - val_f1_m: 0.9763\n", + "Epoch 12/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0367 - f1_m: 0.9870 - val_loss: 0.0568 - val_f1_m: 0.9784\n", + "Epoch 13/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0520 - f1_m: 0.9831 - val_loss: 0.0574 - val_f1_m: 0.9752\n", + "Epoch 14/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0431 - f1_m: 0.9876 - val_loss: 0.0606 - val_f1_m: 0.9795\n", + "Epoch 15/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0399 - f1_m: 0.9848 - val_loss: 0.0610 - val_f1_m: 0.9774\n", + "Epoch 16/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0355 - f1_m: 0.9881 - val_loss: 0.0570 - val_f1_m: 0.9763\n", + "Epoch 17/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0401 - f1_m: 0.9862 - val_loss: 0.0791 - val_f1_m: 0.9763\n", + "Epoch 18/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0331 - f1_m: 0.9870 - val_loss: 0.0802 - val_f1_m: 0.9688\n", + "Epoch 19/20\n", + "113/113 [==============================] - 1s 7ms/step - loss: 0.0347 - f1_m: 0.9842 - val_loss: 0.0625 - val_f1_m: 0.9720\n", + "Epoch 20/20\n", + "113/113 [==============================] - 1s 8ms/step - loss: 0.0359 - f1_m: 0.9856 - val_loss: 0.0680 - val_f1_m: 0.9774\n" + ] + } + ], + "source": [ + "history = ann_model.fit(X_train, y_train, epochs=20, validation_split=0.2, verbose=1)" + ] + }, + { + "cell_type": "code", + "execution_count": 368, + "id": "incorporate-fleet", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "# Plot the model performance across epochs\n", + "plt.figure(figsize=(15,8))\n", + "plt.plot(history.history['loss'])\n", + "plt.plot(history.history['val_loss'])\n", + "plt.title('model Loss')\n", + "plt.ylabel('loss')\n", + "plt.legend(['train_loss','val_loss'], loc = 'upper right')\n", + "plt.savefig('modelloss.png', facecolor='w', bbox_inches='tight')\n", + "plt.show()" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "adapted-royalty", + "metadata": {}, + "source": [ + "## Evaluating model performance" + ] + }, + { + "cell_type": "code", + "execution_count": 369, + "id": "operational-degree", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "16/16 [==============================] - 0s 2ms/step\n" + ] + } + ], + "source": [ + "predictions = ann_model.predict(X_test)\n", + "predict = []\n", + "\n", + "for i in predictions:\n", + " predict.append(np.argmax(i))" + ] + }, + { + "cell_type": "code", + "execution_count": 370, + "id": "injured-central", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "F1 Score: 0.9217.\n", + "Precision: 0.9636.\n", + "Recall: 0.8833.\n", + "Accuracy: 0.9820.\n" + ] + } + ], + "source": [ + "from sklearn import metrics\n", + "y_test = np.argmax(y_test, axis=1)\n", + "\n", + "f1_test = metrics.f1_score(y_test, predict)\n", + "prec = metrics.precision_score(y_test, predict)\n", + "rec = metrics.recall_score(y_test, predict)\n", + "acc = metrics.accuracy_score(y_test, predict)\n", + "\n", + "print (\"F1 Score: {:.4f}.\".format(f1_test))\n", + "print (\"Precision: {:.4f}.\".format(prec))\n", + "print (\"Recall: {:.4f}.\".format(rec))\n", + "print (\"Accuracy: {:.4f}.\".format(acc)) # note this is not a good measure of performance for this project as dataset is unbalanced." + ] + }, + { + "cell_type": "code", + "execution_count": 371, + "id": "incident-pulse", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "conf_mat = metrics.confusion_matrix(y_test, predict)\n", + "plt.figure(figsize=(10,8))\n", + "sns.heatmap(conf_mat, annot=True, cbar=False)\n", + "plt.savefig('conf_matrix.png', facecolor='w', bbox_inches='tight')\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 372, + "id": "mature-trademark", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " precision recall f1-score support\n", + "\n", + " 0 0.98 1.00 0.99 440\n", + " 1 0.96 0.88 0.92 60\n", + "\n", + " accuracy 0.98 500\n", + " macro avg 0.97 0.94 0.96 500\n", + "weighted avg 0.98 0.98 0.98 500\n", + "\n" + ] + } + ], + "source": [ + "print(metrics.classification_report(y_test, predict))" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.3" + }, + "vscode": { + "interpreter": { + "hash": "45899fa507a1304a3c6b832619928507c52e1988c6511a7c9c5f49ebe874162e" + } + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/README.md b/Loan Status Prediction/Bank Loan Approval Prediction/README.md new file mode 100644 index 00000000..a5fdf095 --- /dev/null +++ b/Loan Status Prediction/Bank Loan Approval Prediction/README.md @@ -0,0 +1,16 @@ +## Web Application for Bank Loan Approval Prediction using Flask + +### Goal 🎯 +The main goal is to develop a user-friendly web application that predicts whether the customer's bank loan will be approved or rejected using deep learning models. This application will allow users to enter necessary details and receive predictions. + +The backend of this web application utilizes Tabular Neural Network for Bank Loan Approval prediction. It has been trained on [Universal Bank Dataset](https://www.kaggle.com/datasets/jangedoo/utkface-new) that contains around 5000 data. + +Deep Learning models which are considered for training: + +* Feedforward Neural Network +* Feedforward Neural Network with k-Fold validation +* TabNet model with k-Fold validation +* Wide & Deep neural network architecture + +Amongst this, **TabNet model** is selected which gives 0.985 validation accuracy. + diff --git a/Loan Status Prediction/Bank Loan Approval Prediction/requirements.txt b/Loan Status Prediction/Bank Loan Approval Prediction/requirements.txt new file mode 100644 index 00000000..a60825e6 --- /dev/null +++ b/Loan Status Prediction/Bank Loan Approval Prediction/requirements.txt @@ -0,0 +1,10 @@ +python == 3.9.0 +numpy == 1.22.4 +pandas == 1.4.2 +seaborn == 0.11.2 +matplotlib == 3.5.1 +sklearn==0.2 +tensorflow == 2.8.2 +keras == 2.8.2 +pytorch_tabnet == 4.1.0 +joblib == 1.3.1 \ No newline at end of file