-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path00.0.divide_dataset_A.py
181 lines (165 loc) · 5.46 KB
/
00.0.divide_dataset_A.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
from sklearn.externals import joblib
import numpy
from MachineSpecificSettings import Settings
import scipy.io
from DataSetLoaderLib import DataSetLoader
from sklearn.metrics import accuracy_score
import time
y=numpy.array(joblib.load('DatasetA_ValidationClasses.joblib.pkl'))
x = DataSetLoader();
x = x.LoadDataSet("A");
train_p=0
train_n=0
test_p=0
test_n=0
total=0
x_test=[]
y_test=[]
x_train=[]
y_train=[]
for i in range(0,len(y)):
if y[i]==1:
if train_p<26:
x_train.append(x[i])
y_train.append(y[i])
train_p+=1
if test_p<28:
x_test.append(x[i])
y_test.append(y[i])
test_p+=1
else:
if train_n<44:
x_train.append(x[i])
y_train.append(y[i])
train_n+=1
if test_n<60:
x_test.append(x[i])
y_test.append(y[i])
test_n+=1
#=====================
from sklearn.neural_network import MLPClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn import tree
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn import svm
x_test_orig=x_test
x_train_orig=x_train
sizes=['10','50','100','150','200','250']
methods=['MRMR','JMI','JMIM']
for method in methods:
for size in sizes:
x_test=x_test_orig
x_train=x_train_orig
indices= joblib.load(method+' PICKLES/selected_indices_'+method+'.joblib.pkl')
x_test=numpy.array(x_test)[:,indices]
x_train=numpy.array(x_train)[:,indices]
indices= joblib.load(method+' PICKLES/'+size+'-'+method+'.joblib.pkl')
x_test=x_test[:,indices]
x_train=x_train[:,indices]
f=open('divided_results/'+method+'-'+size+'.txt','w')
print size
print method
print "MLP logistic sgd"
f.write("MLP logistic sgd\n")
clf = MLPClassifier(activation='logistic',solver='sgd')
start_time=time.time()
print "Time it took to train: "
f.write("Time it took to train:\n")
clf.fit(x_train,y_train)
end_time=time.time()-start_time
print end_time
f.write(str(end_time))
y_pred=clf.predict(x_test)
joblib.dump(clf,'divided_results/'+'MLP_logistic_sgd_'+method+'-'+size+'.joblib.pkl')
print "Accuracy scores: "
f.write("\nAccuracy scores:\n")
print accuracy_score(y_test, y_pred)
f.write(str(accuracy_score(y_test, y_pred)))
f.write('\n=======================\n')
print "AdaBoostClassifier"
f.write("\nAdaBoostClassifier")
clf = AdaBoostClassifier()
start_time=time.time()
print "Time it took to train: "
f.write("Time it took to train:\n")
clf.fit(x_train,y_train)
end_time=time.time()-start_time
print end_time
f.write(str(end_time))
y_pred=clf.predict(x_test)
joblib.dump(clf,'divided_results/'+'AdaBoostClassifier_'+method+'-'+size+'.joblib.pkl')
print "Accuracy scores: "
f.write("\nAccuracy scores:\n")
print accuracy_score(y_test, y_pred)
f.write(str(accuracy_score(y_test, y_pred)))
f.write('\n=======================\n')
print "DT classifier"
f.write("\nDT classifier")
clf = tree.DecisionTreeClassifier()
start_time=time.time()
print "Time it took to train: "
f.write("Time it took to train:\n")
clf.fit(x_train,y_train)
end_time=time.time()-start_time
print end_time
f.write(str(end_time))
y_pred=clf.predict(x_test)
joblib.dump(clf,'divided_results/'+'DT_classifier_'+method+'-'+size+'.joblib.pkl')
print "\nAccuracy scores: "
f.write("Accuracy scores:\n")
print accuracy_score(y_test, y_pred)
f.write(str(accuracy_score(y_test, y_pred)))
f.write('\n=======================\n')
f.write("\nExtra tree classifier")
print "Extra tree classifier"
clf = ExtraTreesClassifier()
start_time=time.time()
print "Time it took to train: "
f.write("Time it took to train:\n")
clf.fit(x_train,y_train)
end_time=time.time()-start_time
print end_time
f.write(str(end_time))
y_pred=clf.predict(x_test)
joblib.dump(clf,'divided_results/'+'Extra_tree_classifier_'+method+'-'+size+'.joblib.pkl')
print "\nAccuracy scores: "
f.write("Accuracy scores:\n")
print accuracy_score(y_test, y_pred)
f.write(str(accuracy_score(y_test, y_pred)))
f.write('\n=======================\n')
f.write("\nRandom Forest")
print "Random Forest"
clf = RandomForestClassifier()
start_time=time.time()
print "Time it took to train: "
f.write("Time it took to train:\n")
clf.fit(x_train,y_train)
end_time=time.time()-start_time
print end_time
f.write(str(end_time))
y_pred=clf.predict(x_test)
joblib.dump(clf,'divided_results/'+'Random_Forest_'+method+'-'+size+'.joblib.pkl')
print "Accuracy scores: "
f.write("\nAccuracy scores:\n")
print accuracy_score(y_test, y_pred)
f.write(str(accuracy_score(y_test, y_pred)))
f.write('\n=======================\n')
f.write("\nSVM SVC")
print "SVM SVC"
clf = svm.SVC()
start_time=time.time()
print "Time it took to train: "
f.write("Time it took to train:\n")
clf.fit(x_train,y_train)
end_time=time.time()-start_time
print end_time
f.write(str(end_time))
y_pred=clf.predict(x_test)
joblib.dump(clf,'divided_results/'+'SVM_SVC_'+method+'-'+size+'.joblib.pkl')
print "Accuracy scores: "
f.write("\nAccuracy scores:\n")
print accuracy_score(y_test, y_pred)
f.write(str(accuracy_score(y_test, y_pred)))
f.write('\n=======================\n')
f.close()