-
Notifications
You must be signed in to change notification settings - Fork 0
/
read_data.py
135 lines (89 loc) · 4.53 KB
/
read_data.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
import pandas as pd
import linear_perceptron
import numpy as np
import datetime
def read_training_data_all():
features_dataframe = pd.read_table('Data/datatraining.txt', sep=",",header=None, usecols=[1,2,3,4,5,6], skiprows=[0])
features_dataframe.columns = ["Date/Time", "Temperatures", "Humidity", "Light", "CO2", "HumidityRatio"]
features_matrix = features_dataframe.values
labels_dataframe = pd.read_table('Data/datatraining.txt', sep=",", header=None, usecols=[7], skiprows=[0])
labels_dataframe.columns = ["occupancy"]
labels_matrix = labels_dataframe.values
#Converting the date time feature from a string into an integer
index = 0
for date_time in features_matrix:
splitted = date_time[0].split()
[hours, minutes, seconds] = [int(x) for x in splitted[1].split(':')]
x = datetime.timedelta(hours=hours, minutes=minutes, seconds=seconds)
date_time = x.seconds
features_matrix[index][0] = date_time
index+=1
fx,fy = features_matrix.shape
labels_matrix[labels_matrix == 0] = -1
return features_matrix, labels_matrix
def read_training_data_no_time():
features_dataframe = pd.read_table('Data/datatraining.txt', sep=",",header=None, usecols=[2,3,4,5,6], skiprows=[0])
features_dataframe.columns = ["Temperatures", "Humidity", "Light", "CO2", "HumidityRatio"]
features_matrix = features_dataframe.values
labels_dataframe = pd.read_table('Data/datatraining.txt', sep=",", header=None, usecols=[7], skiprows=[0])
labels_dataframe.columns = ["occupancy"]
labels_matrix = labels_dataframe.values
fx,fy = features_matrix.shape
labels_matrix[labels_matrix == 0] = -1
return features_matrix, labels_matrix
def read_testing_data2_all():
features_dataframe = pd.read_table('Data/datatest2.txt', sep=",",header=None, usecols=[1,2,3,4,5,6], skiprows=[0])
features_dataframe.columns = ["Date/Time","Temperatures", "Humidity", "Light", "CO2", "HumidityRatio"]
features_matrix = features_dataframe.values
labels_dataframe = pd.read_table('Data/datatest2.txt', sep=",", header=None, usecols=[7], skiprows=[0])
labels_dataframe.columns = ["occupancy"]
labels_matrix = labels_dataframe.values
index = 0
for date_time in features_matrix:
splitted = date_time[0].split()
[hours, minutes, seconds] = [int(x) for x in splitted[1].split(':')]
x = datetime.timedelta(hours=hours, minutes=minutes, seconds=seconds)
date_time = x.seconds
features_matrix[index][0] = date_time
index+=1
fx,fy = features_matrix.shape
labels_matrix[labels_matrix == 0] = -1
return features_matrix, labels_matrix
def read_testing_data2_no_time():
features_dataframe = pd.read_table('Data/datatest2.txt', sep=",",header=None, usecols=[2,3,4,5,6], skiprows=[0])
features_dataframe.columns = ["Temperatures", "Humidity", "Light", "CO2", "HumidityRatio"]
features_matrix = features_dataframe.values
labels_dataframe = pd.read_table('Data/datatest2.txt', sep=",", header=None, usecols=[7], skiprows=[0])
labels_dataframe.columns = ["occupancy"]
labels_matrix = labels_dataframe.values
fx,fy = features_matrix.shape
labels_matrix[labels_matrix == 0] = -1
return features_matrix, labels_matrix
def read_testing_data1_all():
features_dataframe = pd.read_table('Data/datatest.txt', sep=",",header=None, usecols=[1,2,3,4,5,6], skiprows=[0])
features_dataframe.columns = ["Date/Time","Temperatures", "Humidity", "Light", "CO2", "HumidityRatio"]
features_matrix = features_dataframe.values
labels_dataframe = pd.read_table('Data/datatest.txt', sep=",", header=None, usecols=[7], skiprows=[0])
labels_dataframe.columns = ["occupancy"]
labels_matrix = labels_dataframe.values
index = 0
for date_time in features_matrix:
splitted = date_time[0].split()
[hours, minutes, seconds] = [int(x) for x in splitted[1].split(':')]
x = datetime.timedelta(hours=hours, minutes=minutes, seconds=seconds)
date_time = x.seconds
features_matrix[index][0] = date_time
index+=1
fx,fy = features_matrix.shape
labels_matrix[labels_matrix == 0] = -1
return features_matrix, labels_matrix
def read_testing_data1_no_time():
features_dataframe = pd.read_table('Data/datatest.txt', sep=",",header=None, usecols=[2,3,4,5,6], skiprows=[0])
features_dataframe.columns = ["Temperatures", "Humidity", "Light", "CO2", "HumidityRatio"]
features_matrix = features_dataframe.values
labels_dataframe = pd.read_table('Data/datatest.txt', sep=",", header=None, usecols=[7], skiprows=[0])
labels_dataframe.columns = ["occupancy"]
labels_matrix = labels_dataframe.values
fx,fy = features_matrix.shape
labels_matrix[labels_matrix == 0] = -1
return features_matrix, labels_matrix