pip install a-pandas-ex-enumerate_groups from a_pandas_ex_enumerate_groups import pd_add_enumerate_group
pd_add_enumerate_group()
import pandas as pd
df = pd.read_csv(
"https://raw.githubusercontent.com/pandas-dev/pandas/main/doc/data/titanic.csv"
)
dfi = df.ds_enumerate_groups(
enumerated_column="Age_enu", column_to_enumerate="Age"
)
print(dfi[:20].to_string())
dfi = df.ds_enumerate_groups( enumerated_column="Cabin_en", column_to_enumerate="Cabin"
)
print(dfi[:20].to_string())
dfi = df.ds_enumerate_groups( enumerated_column="Fare_en", column_to_enumerate="Fare"
)
print(dfi[:20].to_string())
PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked Age_enu
803 804 1 3 Thomas, Master. Assad Alexander male 0.42 0 1 2625 8.5167 NaN C 0
755 756 1 2 Hamalainen, Master. Viljo male 0.67 1 1 250649 14.5000 NaN S 1
644 645 1 3 Baclini, Miss. Eugenie female 0.75 2 1 2666 19.2583 NaN C 2
469 470 1 3 Baclini, Miss. Helene Barbara female 0.75 2 1 2666 19.2583 NaN C 2
78 79 1 2 Caldwell, Master. Alden Gates male 0.83 0 2 248738 29.0000 NaN S 3
831 832 1 2 Richards, Master. George Sibley male 0.83 1 1 29106 18.7500 NaN S 3
305 306 1 1 Allison, Master. Hudson Trevor male 0.92 1 2 113781 151.5500 C22 C26 S 4
827 828 1 2 Mallet, Master. Andre male 1.00 0 2 S.C./PARIS 2079 37.0042 NaN C 5
381 382 1 3 Nakid, Miss. Maria ("Mary") female 1.00 0 2 2653 15.7417 NaN C 5
164 165 0 3 Panula, Master. Eino Viljami male 1.00 4 1 3101295 39.6875 NaN S 5
183 184 1 2 Becker, Master. Richard F male 1.00 2 1 230136 39.0000 F4 S 5
386 387 0 3 Goodwin, Master. Sidney Leonard male 1.00 5 2 CA 2144 46.9000 NaN S 5
172 173 1 3 Johnson, Miss. Eleanor Ileen female 1.00 1 1 347742 11.1333 NaN S 5
788 789 1 3 Dean, Master. Bertram Vere male 1.00 1 2 C.A. 2315 20.5750 NaN S 5
642 643 0 3 Skoog, Miss. Margit Elizabeth female 2.00 3 2 347088 27.9000 NaN S 6
7 8 0 3 Palsson, Master. Gosta Leonard male 2.00 3 1 349909 21.0750 NaN S 6
530 531 1 2 Quick, Miss. Phyllis May female 2.00 1 1 26360 26.0000 NaN S 6
297 298 0 1 Allison, Miss. Helen Loraine female 2.00 1 2 113781 151.5500 C22 C26 S 6
824 825 0 3 Panula, Master. Urho Abraham male 2.00 4 1 3101295 39.6875 NaN S 6
205 206 0 3 Strom, Miss. Telma Matilda female 2.00 0 1 347054 10.4625 G6 S 6
PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked Cabin_en
583 584 0 1 Ross, Mr. John Hugo male 36.0 0 0 13049 40.1250 A10 C 0
475 476 0 1 Clifford, Mr. George Quincy male NaN 0 0 110465 52.0000 A14 S 1
556 557 1 1 Duff Gordon, Lady. (Lucille Christiana Sutherland) ("Mrs Morgan") female 48.0 1 0 11755 39.6000 A16 C 2
284 285 0 1 Smith, Mr. Richard William male NaN 0 0 113056 26.0000 A19 S 3
599 600 1 1 Duff Gordon, Sir. Cosmo Edmund ("Mr Morgan") male 49.0 1 0 PC 17485 56.9292 A20 C 4
630 631 1 1 Barkworth, Mr. Algernon Henry Wilson male 80.0 0 0 27042 30.0000 A23 S 5
867 868 0 1 Roebling, Mr. Washington Augustus II male 31.0 0 0 PC 17590 50.4958 A24 S 6
647 648 1 1 Simonius-Blumer, Col. Oberst Alfons male 56.0 0 0 13213 35.5000 A26 C 7
209 210 1 1 Blank, Mr. Henry male 40.0 0 0 112277 31.0000 A31 C 8
185 186 0 1 Rood, Mr. Hugh Roscoe male NaN 0 0 113767 50.0000 A32 S 9
445 446 1 1 Dodge, Master. Washington male 4.0 0 2 33638 81.8583 A34 S 10
806 807 0 1 Andrews, Mr. Thomas Jr male 39.0 0 0 112050 0.0000 A36 S 11
96 97 0 1 Goldschmidt, Mr. George B male 71.0 0 0 PC 17754 34.6542 A5 C 12
23 24 1 1 Sloper, Mr. William Thompson male 28.0 0 0 113788 35.5000 A6 S 13
174 175 0 1 Smith, Mr. James Clinch male 56.0 0 0 17764 30.6958 A7 C 14
737 738 1 1 Lesurer, Mr. Gustave J male 35.0 0 0 PC 17755 512.3292 B101 C 15
815 816 0 1 Fry, Mr. Richard male NaN 0 0 112058 0.0000 B102 S 16
523 524 1 1 Hippach, Mrs. Louis Albert (Ida Sophia Fischer) female 44.0 0 1 111361 57.9792 B18 C 17
329 330 1 1 Hippach, Miss. Jean Gertrude female 16.0 0 1 111361 57.9792 B18 C 17
170 171 0 1 Van der hoef, Mr. Wyckoff male 61.0 0 0 111240 33.5000 B19 S 18
PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked Fare_en
271 272 1 3 Tornquist, Mr. William Henry male 25.0 0 0 LINE 0.0000 NaN S 0
597 598 0 3 Johnson, Mr. Alfred male 49.0 0 0 LINE 0.0000 NaN S 0
302 303 0 3 Johnson, Mr. William Cahoone Jr male 19.0 0 0 LINE 0.0000 NaN S 0
633 634 0 1 Parr, Mr. William Henry Marsh male NaN 0 0 112052 0.0000 NaN S 0
277 278 0 2 Parkes, Mr. Francis "Frank" male NaN 0 0 239853 0.0000 NaN S 0
413 414 0 2 Cunningham, Mr. Alfred Fleming male NaN 0 0 239853 0.0000 NaN S 0
674 675 0 2 Watson, Mr. Ennis Hastings male NaN 0 0 239856 0.0000 NaN S 0
263 264 0 1 Harrison, Mr. William male 40.0 0 0 112059 0.0000 B94 S 0
466 467 0 2 Campbell, Mr. William male NaN 0 0 239853 0.0000 NaN S 0
732 733 0 2 Knight, Mr. Robert J male NaN 0 0 239855 0.0000 NaN S 0
179 180 0 3 Leonard, Mr. Lionel male 36.0 0 0 LINE 0.0000 NaN S 0
806 807 0 1 Andrews, Mr. Thomas Jr male 39.0 0 0 112050 0.0000 A36 S 0
481 482 0 2 Frost, Mr. Anthony Wood "Archie" male NaN 0 0 239854 0.0000 NaN S 0
822 823 0 1 Reuchlin, Jonkheer. John George male 38.0 0 0 19972 0.0000 NaN S 0
815 816 0 1 Fry, Mr. Richard male NaN 0 0 112058 0.0000 B102 S 0
378 379 0 3 Betros, Mr. Tannous male 20.0 0 0 2648 4.0125 NaN C 1
872 873 0 1 Carlsson, Mr. Frans Olof male 33.0 0 0 695 5.0000 B51 B53 B55 S 2
326 327 0 3 Nysveen, Mr. Johan Hansen male 61.0 0 0 345364 6.2375 NaN S 3
843 844 0 3 Lemberopolous, Mr. Peter L male 34.5 0 0 2683 6.4375 NaN C 4
818 819 0 3 Holm, Mr. John Fredrik Alexander male 43.0 0 0 C 7075 6.4500 NaN S 5
df.d_enumerate_all_groups_in_all_columns(prefix="group_")
Out[4]:
PassengerId Survived Pclass ... group_Fare group_Cabin group_Embarked
0 1 0 3 ... 18 NaN 2.0
1 2 1 1 ... 207 81.0 0.0
2 3 1 3 ... 41 NaN 2.0
3 4 1 1 ... 189 55.0 2.0
4 5 0 3 ... 43 NaN 2.0
.. ... ... ... ... ... ... ...
886 887 0 2 ... 85 NaN 2.0
887 888 1 1 ... 153 30.0 2.0
888 889 0 3 ... 131 NaN 2.0
889 890 1 1 ... 153 60.0 0.0
890 891 0 3 ... 30 NaN 1.0
[891 rows x 24 columns]
df.d_enumerate_groups_in_multiple_columns(columns=[['Pclass','Survived']], prefix="group_", name_sep="_")
Out[7]:
PassengerId Survived Pclass ... Cabin Embarked group_Pclass_Survived
0 1 0 3 ... <NA> S 4
1 2 1 1 ... C85 C 1
2 3 1 3 ... <NA> S 5
3 4 1 1 ... C123 S 1
4 5 0 3 ... <NA> S 4
.. ... ... ... ... ... ... ...
886 887 0 2 ... <NA> S 2
887 888 1 1 ... B42 S 1
888 889 0 3 ... <NA> S 4
889 890 1 1 ... C148 C 1
890 891 0 3 ... <NA> Q 4
[891 rows x 13 columns]