/
c.py
294 lines (213 loc) · 12.4 KB
/
c.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
287
288
289
290
291
292
293
294
from common import *
from library import *
from ae import *
from dae import *
datasets = ['page-blocks-1-3_vs_4', 'yeast-2_vs_8', 'kddcup-land_vs_portsweep']
version = 'ae_230'
result = pd.DataFrame()
for idx, dataset in enumerate(datasets):
svm = []; knn = []; c45 = []; cart = []
svm_ae_smote = []; knn_ae_smote = []; c45_ae_smote = []; cart_ae_smote = []
svm_smote_ae = []; knn_smote_ae = []; c45_smote_ae = []; cart_smote_ae = []
for times in range(1,6):
training = "{}-5-{}{}.dat".format(dataset, times, 'tra')
testing = "{}-5-{}{}.dat".format(dataset, times, 'tst')
df_train = pd.read_csv('../dataset/' + dataset + '-5-fold' + '/' + training, delimiter=',')
df_test = pd.read_csv('../dataset/' + dataset + '-5-fold' + '/' + testing, delimiter=',')
x_train, x_test, y_train, y_test = data_preprocess(df_train, df_test)
# ae
x_train_encoded, x_test_encoded = train_ae_230(x_train, x_test)
auc1 = run_svc(x_train_encoded, x_test_encoded, y_train, y_test)
auc2 = run_knn(x_train_encoded, x_test_encoded, y_train, y_test)
auc3 = run_c45(x_train_encoded, x_test_encoded, y_train, y_test)
auc4 = run_cart(x_train_encoded, x_test_encoded, y_train, y_test)
svm.append(auc1); knn.append(auc2); c45.append(auc3); cart.append(auc4)
# ae+smote
x_train_ae_smote, y_train_ae_smote = SMOTE(random_state=42).fit_resample(x_train_encoded, y_train)
auc5 = run_svc(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
auc6 = run_knn(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
auc7 = run_c45(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
auc8 = run_cart(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
svm_ae_smote.append(auc5); knn_ae_smote.append(auc6); c45_ae_smote.append(auc7); cart_ae_smote.append(auc8)
# smote+ae
x_train_smote, y_train_smote = SMOTE(random_state=42).fit_resample(x_train, y_train)
x_train_smote_encoded, x_test_smote_encoded = train_ae_230(x_train_smote, x_test)
auc9 = run_svc(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
auc10 = run_knn(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
auc11 = run_c45(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
auc12 = run_cart(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
svm_smote_ae.append(auc9); knn_smote_ae.append(auc10); c45_smote_ae.append(auc11); cart_smote_ae.append(auc12)
new=pd.DataFrame({'dataset':dataset,
'svm': np.mean(svm),
'svm_ae_smote': np.mean(svm_ae_smote),
'svm_smote_ae': np.mean(svm_smote_ae),
'knn': np.mean(knn),
'knn_ae_smote': np.mean(knn_ae_smote),
'knn_smote_ae': np.mean(knn_smote_ae),
'c45': np.mean(c45),
'c45_ae_smote': np.mean(c45_ae_smote),
'c45_smote_ae': np.mean(c45_smote_ae),
'cart': np.mean(cart),
'cart_ae_smote': np.mean(cart_ae_smote),
'cart_smote_ae': np.mean(cart_smote_ae),
}, index=[idx])
print(version)
print(new)
result = pd.concat([result, new], ignore_index=True)
result.to_csv('result/(ans)'+ version + '_' + dataset + '.csv',index=False,encoding='utf-8')
version = 'ae_240'
result = pd.DataFrame()
for idx, dataset in enumerate(datasets):
svm = []; knn = []; c45 = []; cart = []
svm_ae_smote = []; knn_ae_smote = []; c45_ae_smote = []; cart_ae_smote = []
svm_smote_ae = []; knn_smote_ae = []; c45_smote_ae = []; cart_smote_ae = []
for times in range(1,6):
training = "{}-5-{}{}.dat".format(dataset, times, 'tra')
testing = "{}-5-{}{}.dat".format(dataset, times, 'tst')
df_train = pd.read_csv('../dataset/' + dataset + '-5-fold' + '/' + training, delimiter=',')
df_test = pd.read_csv('../dataset/' + dataset + '-5-fold' + '/' + testing, delimiter=',')
x_train, x_test, y_train, y_test = data_preprocess(df_train, df_test)
# ae
x_train_encoded, x_test_encoded = train_ae_240(x_train, x_test)
auc1 = run_svc(x_train_encoded, x_test_encoded, y_train, y_test)
auc2 = run_knn(x_train_encoded, x_test_encoded, y_train, y_test)
auc3 = run_c45(x_train_encoded, x_test_encoded, y_train, y_test)
auc4 = run_cart(x_train_encoded, x_test_encoded, y_train, y_test)
svm.append(auc1); knn.append(auc2); c45.append(auc3); cart.append(auc4)
# ae+smote
x_train_ae_smote, y_train_ae_smote = SMOTE(random_state=42).fit_resample(x_train_encoded, y_train)
auc5 = run_svc(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
auc6 = run_knn(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
auc7 = run_c45(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
auc8 = run_cart(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
svm_ae_smote.append(auc5); knn_ae_smote.append(auc6); c45_ae_smote.append(auc7); cart_ae_smote.append(auc8)
# smote+ae
x_train_smote, y_train_smote = SMOTE(random_state=42).fit_resample(x_train, y_train)
x_train_smote_encoded, x_test_smote_encoded = train_ae_240(x_train_smote, x_test)
auc9 = run_svc(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
auc10 = run_knn(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
auc11 = run_c45(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
auc12 = run_cart(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
svm_smote_ae.append(auc9); knn_smote_ae.append(auc10); c45_smote_ae.append(auc11); cart_smote_ae.append(auc12)
new=pd.DataFrame({'dataset':dataset,
'svm': np.mean(svm),
'svm_ae_smote': np.mean(svm_ae_smote),
'svm_smote_ae': np.mean(svm_smote_ae),
'knn': np.mean(knn),
'knn_ae_smote': np.mean(knn_ae_smote),
'knn_smote_ae': np.mean(knn_smote_ae),
'c45': np.mean(c45),
'c45_ae_smote': np.mean(c45_ae_smote),
'c45_smote_ae': np.mean(c45_smote_ae),
'cart': np.mean(cart),
'cart_ae_smote': np.mean(cart_ae_smote),
'cart_smote_ae': np.mean(cart_smote_ae),
}, index=[idx])
print(version)
print(new)
result = pd.concat([result, new], ignore_index=True)
result.to_csv('result/(ans)'+ version + '_' + dataset + '.csv',index=False,encoding='utf-8')
version = 'dae_230'
result = pd.DataFrame()
for idx, dataset in enumerate(datasets):
svm = []; knn = []; c45 = []; cart = []
svm_ae_smote = []; knn_ae_smote = []; c45_ae_smote = []; cart_ae_smote = []
svm_smote_ae = []; knn_smote_ae = []; c45_smote_ae = []; cart_smote_ae = []
for times in range(1,6):
training = "{}-5-{}{}.dat".format(dataset, times, 'tra')
testing = "{}-5-{}{}.dat".format(dataset, times, 'tst')
df_train = pd.read_csv('../dataset/' + dataset + '-5-fold' + '/' + training, delimiter=',')
df_test = pd.read_csv('../dataset/' + dataset + '-5-fold' + '/' + testing, delimiter=',')
x_train, x_test, y_train, y_test = data_preprocess(df_train, df_test)
# ae
x_train_encoded, x_test_encoded = train_dae_230(x_train, x_test)
auc1 = run_svc(x_train_encoded, x_test_encoded, y_train, y_test)
auc2 = run_knn(x_train_encoded, x_test_encoded, y_train, y_test)
auc3 = run_c45(x_train_encoded, x_test_encoded, y_train, y_test)
auc4 = run_cart(x_train_encoded, x_test_encoded, y_train, y_test)
svm.append(auc1); knn.append(auc2); c45.append(auc3); cart.append(auc4)
# ae+smote
x_train_ae_smote, y_train_ae_smote = SMOTE(random_state=42).fit_resample(x_train_encoded, y_train)
auc5 = run_svc(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
auc6 = run_knn(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
auc7 = run_c45(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
auc8 = run_cart(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
svm_ae_smote.append(auc5); knn_ae_smote.append(auc6); c45_ae_smote.append(auc7); cart_ae_smote.append(auc8)
# smote+ae
x_train_smote, y_train_smote = SMOTE(random_state=42).fit_resample(x_train, y_train)
x_train_smote_encoded, x_test_smote_encoded = train_dae_230(x_train_smote, x_test)
auc9 = run_svc(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
auc10 = run_knn(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
auc11 = run_c45(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
auc12 = run_cart(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
svm_smote_ae.append(auc9); knn_smote_ae.append(auc10); c45_smote_ae.append(auc11); cart_smote_ae.append(auc12)
new=pd.DataFrame({'dataset':dataset,
'svm': np.mean(svm),
'svm_ae_smote': np.mean(svm_ae_smote),
'svm_smote_ae': np.mean(svm_smote_ae),
'knn': np.mean(knn),
'knn_ae_smote': np.mean(knn_ae_smote),
'knn_smote_ae': np.mean(knn_smote_ae),
'c45': np.mean(c45),
'c45_ae_smote': np.mean(c45_ae_smote),
'c45_smote_ae': np.mean(c45_smote_ae),
'cart': np.mean(cart),
'cart_ae_smote': np.mean(cart_ae_smote),
'cart_smote_ae': np.mean(cart_smote_ae),
}, index=[idx])
print(version)
print(new)
result = pd.concat([result, new], ignore_index=True)
result.to_csv('result/(ans)'+ version + '_' + dataset + '.csv',index=False,encoding='utf-8')
version = 'dae_240'
result = pd.DataFrame()
for idx, dataset in enumerate(datasets):
svm = []; knn = []; c45 = []; cart = []
svm_ae_smote = []; knn_ae_smote = []; c45_ae_smote = []; cart_ae_smote = []
svm_smote_ae = []; knn_smote_ae = []; c45_smote_ae = []; cart_smote_ae = []
for times in range(1,6):
training = "{}-5-{}{}.dat".format(dataset, times, 'tra')
testing = "{}-5-{}{}.dat".format(dataset, times, 'tst')
df_train = pd.read_csv('../dataset/' + dataset + '-5-fold' + '/' + training, delimiter=',')
df_test = pd.read_csv('../dataset/' + dataset + '-5-fold' + '/' + testing, delimiter=',')
x_train, x_test, y_train, y_test = data_preprocess(df_train, df_test)
# ae
x_train_encoded, x_test_encoded = train_dae_240(x_train, x_test)
auc1 = run_svc(x_train_encoded, x_test_encoded, y_train, y_test)
auc2 = run_knn(x_train_encoded, x_test_encoded, y_train, y_test)
auc3 = run_c45(x_train_encoded, x_test_encoded, y_train, y_test)
auc4 = run_cart(x_train_encoded, x_test_encoded, y_train, y_test)
svm.append(auc1); knn.append(auc2); c45.append(auc3); cart.append(auc4)
# ae+smote
x_train_ae_smote, y_train_ae_smote = SMOTE(random_state=42).fit_resample(x_train_encoded, y_train)
auc5 = run_svc(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
auc6 = run_knn(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
auc7 = run_c45(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
auc8 = run_cart(x_train_ae_smote, x_test_encoded, y_train_ae_smote, y_test)
svm_ae_smote.append(auc5); knn_ae_smote.append(auc6); c45_ae_smote.append(auc7); cart_ae_smote.append(auc8)
# smote+ae
x_train_smote, y_train_smote = SMOTE(random_state=42).fit_resample(x_train, y_train)
x_train_smote_encoded, x_test_smote_encoded = train_dae_240(x_train_smote, x_test)
auc9 = run_svc(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
auc10 = run_knn(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
auc11 = run_c45(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
auc12 = run_cart(x_train_smote_encoded, x_test_smote_encoded, y_train_smote, y_test)
svm_smote_ae.append(auc9); knn_smote_ae.append(auc10); c45_smote_ae.append(auc11); cart_smote_ae.append(auc12)
new=pd.DataFrame({'dataset':dataset,
'svm': np.mean(svm),
'svm_ae_smote': np.mean(svm_ae_smote),
'svm_smote_ae': np.mean(svm_smote_ae),
'knn': np.mean(knn),
'knn_ae_smote': np.mean(knn_ae_smote),
'knn_smote_ae': np.mean(knn_smote_ae),
'c45': np.mean(c45),
'c45_ae_smote': np.mean(c45_ae_smote),
'c45_smote_ae': np.mean(c45_smote_ae),
'cart': np.mean(cart),
'cart_ae_smote': np.mean(cart_ae_smote),
'cart_smote_ae': np.mean(cart_smote_ae),
}, index=[idx])
print(version)
print(new)
result = pd.concat([result, new], ignore_index=True)
result.to_csv('result/(ans)'+ version + '_' + dataset + '.csv',index=False,encoding='utf-8')