forked from AkaiTsuki/machine-learning-feature-analysis
-
Notifications
You must be signed in to change notification settings - Fork 0
/
main_naive_bayes.py
96 lines (70 loc) · 3.34 KB
/
main_naive_bayes.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
__author__ = 'jiachiliu'
import numpy as np
from nulearn.bayes import GaussianNaiveBayes
import timeit
from nulearn.validation import *
from nulearn.ranking import *
from nulearn.dataset import load_polluted_spambase
from sklearn.decomposition import PCA
from sklearn.lda import LDA
def naive_bayes_no_pca():
train, train_target, test, test_target = load_polluted_spambase()
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
start = timeit.default_timer()
cf = GaussianNaiveBayes()
cf.fit(train, train_target)
raw_predicts = cf.predict(test)
predict_class = cf.predict_class(raw_predicts)
cm = confusion_matrix(test_target, predict_class)
print "confusion matrix: TN: %s, FP: %s, FN: %s, TP: %s" % (cm[0, 0], cm[0, 1], cm[1, 0], cm[1, 1])
er, acc, fpr, tpr = confusion_matrix_analysis(cm)
print 'Error rate: %f, accuracy: %f, FPR: %f, TPR: %f' % (er, acc, fpr, tpr)
stop = timeit.default_timer()
print "Total Run Time: %s secs" % (stop - start)
def naive_bayes_with_pca():
train, train_target, test, test_target = load_polluted_spambase()
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
start = timeit.default_timer()
pca = PCA(n_components=100)
train = pca.fit_transform(train)
test = pca.transform(test)
print pca
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
cf = GaussianNaiveBayes()
cf.fit(train, train_target)
raw_predicts = cf.predict(test)
predict_class = cf.predict_class(raw_predicts)
cm = confusion_matrix(test_target, predict_class)
print "confusion matrix: TN: %s, FP: %s, FN: %s, TP: %s" % (cm[0, 0], cm[0, 1], cm[1, 0], cm[1, 1])
er, acc, fpr, tpr = confusion_matrix_analysis(cm)
print 'Error rate: %f, accuracy: %f, FPR: %f, TPR: %f' % (er, acc, fpr, tpr)
stop = timeit.default_timer()
print "Total Run Time: %s secs" % (stop - start)
def naive_bayes_with_lda():
train, train_target, test, test_target = load_polluted_spambase()
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
start = timeit.default_timer()
lda = LDA(n_components=100)
train = lda.fit_transform(train, train_target)
test = lda.transform(test)
print lda
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
cf = GaussianNaiveBayes()
cf.fit(train, train_target)
raw_predicts = cf.predict(test)
predict_class = cf.predict_class(raw_predicts)
cm = confusion_matrix(test_target, predict_class)
print "confusion matrix: TN: %s, FP: %s, FN: %s, TP: %s" % (cm[0, 0], cm[0, 1], cm[1, 0], cm[1, 1])
er, acc, fpr, tpr = confusion_matrix_analysis(cm)
print 'Error rate: %f, accuracy: %f, FPR: %f, TPR: %f' % (er, acc, fpr, tpr)
stop = timeit.default_timer()
print "Total Run Time: %s secs" % (stop - start)
if __name__ == '__main__':
# naive_bayes_no_pca()
naive_bayes_with_pca()
# naive_bayes_with_lda()