-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathclassification_dataset_preprocessing.py
288 lines (221 loc) · 6.82 KB
/
classification_dataset_preprocessing.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
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
"""
Author: Niharika gauraha
Preprocess classification datasets
"""
import csv
from sklearn.datasets import load_breast_cancer, load_digits
import numpy as np
from sklearn.preprocessing import LabelEncoder
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
def load_breast_cancer_data():
bc = load_breast_cancer()
X = bc.data
y = bc.target
return X, y
def load_digit_data():
digit = load_digits()
X = digit.data
y = digit.target
return X, y
def load_spambase_data():
data = []
# Read the training data
file = open('data_classification/spambase.data')
reader = csv.reader(file)
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-1] for x in data]).astype(np.float)
y = np.array([x[-1] for x in data]).astype(np.int)
del data # free up the memory
return X, y
def load_Phishing_dataset():
data = []
# Read the training data
file = open('data_classification/phising.csv')
reader = csv.reader(file, delimiter = ',')
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-1] for x in data]).astype(np.float)
y = np.array([x[-1] for x in data]).astype(np.int)
y[y==-1] = 0
del data # free up the memory
return X, y
# generic function, can be used with any dataset file
def load_dataset(filename):
data = []
# Read the training data
file = open(filename)
reader = csv.reader(file, delimiter = ' ')
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-1] for x in data]).astype(np.float)
y = np.array([x[-1] for x in data]).astype(np.int)
del data # free up the memory
return X, y
def load_bank_dataset():
data = []
# Read the training data
file = open('data_classification/bank.csv')
reader = csv.reader(file, delimiter = ',')
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-1] for x in data])
y = np.array([x[-1] for x in data])
del data # free up the memory
le = LabelEncoder()
for i in range(X.shape[1]):
try:
X[:, i] = X[:, i].astype(np.float)
except:
le.fit(X[:, i])
X[:, i] = le.transform(X[:, i])
y[y == 'no'] = 0
y[y == 'yes'] = 1
y = y.astype(np.int)
return X, y
def load_australian_dataset():
data = []
# Read the training data
file = open('data_classification/australian.dat')
reader = csv.reader(file, delimiter = ' ')
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-1] for x in data])
y = np.array([x[-1] for x in data])
del data # free up the memory
le = LabelEncoder()
for i in range(X.shape[1]):
try:
X[:, i] = X[:, i].astype(np.float)
except:
le.fit(X[:, i])
X[:, i] = le.transform(X[:, i])
y = y.astype(np.int)
y[y == -1] = 0
return X, y
def load_adult_dataset():
data = []
# Read the training data
file = open('data_classification/adult.data')
reader = csv.reader(file, delimiter = ',')
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-1] for x in data])
y = np.array([x[-1] for x in data])
del data # free up the memory
le = LabelEncoder()
for i in range(X.shape[1]):
try:
X[:, i] = X[:, i].astype(np.float)
except:
le.fit(X[:, i])
X[:, i] = le.transform(X[:, i])
y = y.astype(np.int)
y[y == -1] = 0
return X, y
def load_tic_tac_toe_dataset():
data = []
# Read the training data
file = open('data_classification/tic-tac-toe.data')
reader = csv.reader(file, delimiter=',')
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-1] for x in data])
y = np.array([x[-1] for x in data])
del data # free up the memory
le = LabelEncoder()
for i in range(X.shape[1]):
try:
X[:, i] = X[:, i].astype(np.float)
except:
le.fit(X[:, i])
X[:, i] = le.transform(X[:, i])
y[y == 'negative'] = 0
y[y == 'positive'] = 1
y = y.astype(np.int)
return X, y
def load_covertype_dataset():
data = []
# Read the training data
file = open('data_classification/covtype.data')
reader = csv.reader(file, delimiter = ',')
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-1] for x in data]).astype(np.float)
y = np.array([x[-1] for x in data]).astype(np.int)
y = y-1
del data # free up the memory
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=1-(1875/len(X)), stratify=y)
# it is huge dataset, returning only slice of it
return x_train, y_train
def load_monks1_data():
data = []
# Read the training data
file = open('data_classification/monks-1.train')
reader = csv.reader(file, delimiter = ' ')
for row in reader:
data.append(row)
file.close()
#skip one '' string read from file
X1 = np.array([x[2:-1] for x in data]).astype(np.float)
y1 = np.array([x[1] for x in data]).astype(np.float)
del data # free up the memory
data = []
file = open('data_classification/monks-1.test')
reader = csv.reader(file, delimiter=' ')
for row in reader:
data.append(row)
file.close()
X2 = np.array([x[2:-1] for x in data]).astype(np.float)
y2 = np.array([x[1] for x in data]).astype(np.int)
X = np.row_stack((X1,X2))
y = np.concatenate((y1,y2))
y = y.astype(np.int)
return X, y
def load_monks2_data():
data = []
# Read the training data
file = open('data_classification/monks-2.train')
reader = csv.reader(file, delimiter = ' ')
for row in reader:
data.append(row)
file.close()
#skip one '' string read from file
X1 = np.array([x[2:-1] for x in data]).astype(np.float)
y1 = np.array([x[1] for x in data]).astype(np.float)
del data # free up the memory
data = []
file = open('data_classification/monks-2.test')
reader = csv.reader(file, delimiter=' ')
for row in reader:
data.append(row)
file.close()
X2 = np.array([x[2:-1] for x in data]).astype(np.float)
y2 = np.array([x[1] for x in data]).astype(np.int)
X = np.row_stack((X1,X2))
y = np.concatenate((y1,y2))
y = y.astype(np.int)
return X, y
if __name__ == '__main__':
x, y = load_spambase_data()
#x, y = load_breast_cancer_data()
#x, y = load_Phishing_dataset()
#x, y = load_covertype_dataset()
#x, y = load_adult_dataset()
#x, y = load_tic_tac_toe_dataset()
#x, y = load_australian_dataset()
#x, y = load_monks1_data()
#x, y = load_monks2_data()
#x, y = load_bank_dataset()
#x, y = load_digit_data()
print(len(y[y==0]))
print(len(y[y == 1]))