-
Notifications
You must be signed in to change notification settings - Fork 0
/
model_primer_any.py
134 lines (115 loc) · 3.32 KB
/
model_primer_any.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
import pandas
from pandas.plotting import scatter_matrix
import matplotlib.pyplot as plt
from sklearn import model_selection
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
import numpy as np
seed = 123456
Ncross = 1000
data = pandas.read_excel(open('./data/results_new.xlsx','rb'), sheet_name=0);
result = pandas.read_excel(open('./data/results_new.xlsx','rb'), sheet_name=1);
f = open('./data/errors.txt','w');
X = data.values
print X.shape
Y=result.values[:,0]
print Y.shape
validation_size=0.15
N = int(len(Y)*validation_size)
errorSVM = np.zeros(Ncross*N)
errorLR = np.zeros(Ncross*N)
errorLDA = np.zeros(Ncross*N)
errorKNC = np.zeros(Ncross*N)
errorDTC = np.zeros(Ncross*N)
errorGNB = np.zeros(Ncross*N)
errorRF = np.zeros(Ncross*N)
classificationDTC = np.zeros(11)
classificationRFC = np.zeros(11)
k=0
print N
for nn in range(Ncross):
X_t, X_v, Y_t, Y_v = model_selection.train_test_split(X, Y, test_size=validation_size)
# Suport Vector Machine
clf = SVC()
clf.fit(X_t,Y_t)
Y_p = clf.predict(X_v)
for i in range(0,N):
errorSVM[k+i] = abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
# Logistic Regression
logreg = LogisticRegression()
logreg.fit(X_t, Y_t)
Y_p = logreg.predict(X_v)
for i in range(0,N):
errorLR[k+i] = abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
# Linear Discriminant Analysis
lda = LinearDiscriminantAnalysis()
lda.fit(X_t, Y_t)
Y_p = lda.predict(X_v)
for i in range(0,N):
errorLDA[k+i] = abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
# K Neighbors Classifier
KNC = KNeighborsClassifier()
KNC.fit(X_t, Y_t)
Y_p = KNC.predict(X_v)
for i in range(0,N):
errorKNC[k+i] = abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
# Decision Tree Classifier
DTC = DecisionTreeClassifier()
DTC.fit(X_t, Y_t)
Y_p = DTC.predict(X_v)
for i in range(0,N):
errorDTC[k+i] = abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
classificationDTC = classificationDTC + DTC.feature_importances_
# Gaussian Naive Bayes
GNB = GaussianNB()
GNB.fit(X_t, Y_t)
Y_p = GNB.predict(X_v)
for i in range(0,N):
errorGNB[k+i] = abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
# Random Forest
RFC = RandomForestClassifier()
RFC.fit(X_t, Y_t)
Y_p = RFC.predict(X_v)
for i in range(0,N):
errorRF[k+i] = abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
classificationRFC = classificationRFC + RFC.feature_importances_
k=k+N
for err in errorSVM:
f.write('%.4f ' % err)
f.write('\n')
for err in errorLR:
f.write('%.4f ' % err)
f.write('\n')
for err in errorLDA:
f.write('%.4f ' % err)
f.write('\n')
for err in errorKNC:
f.write('%.4f ' % err)
f.write('\n')
for err in errorDTC:
f.write('%.4f ' % err)
f.write('\n')
for err in errorGNB:
f.write('%.4f ' % err)
f.write('\n')
for err in errorRF:
f.write('%.4f ' % err)
f.write('\n')
f.close()
print sum(errorSVM)/N/Ncross
print sum(errorLR)/N/Ncross
print sum(errorLDA)/N/Ncross
print sum(errorKNC)/N/Ncross
print sum(errorDTC)/N/Ncross
print sum(errorGNB)/N/Ncross
print sum(errorRF)/N/Ncross
print classificationDTC/Ncross
print classificationRFC/Ncross