-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathClassification Tests.py
148 lines (110 loc) · 4.53 KB
/
Classification Tests.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
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import sys
import datetime
from sklearn.neural_network import MLPClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn import svm
from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB
from sklearn.naive_bayes import ComplementNB
from sklearn.model_selection import train_test_split
from sklearn.metrics import plot_confusion_matrix
from sklearn.metrics import classification_report
from collections import Counter
#knei test
def kn(target, features, num):
y=target
X = features
train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.20, random_state=0)
clf = KNeighborsClassifier()
print('knei has begun')
print(datetime.datetime.now(),'\n')
clf.fit(train_X,train_y)
print('fitted')
print(datetime.datetime.now(),'\n')
yp=clf.predict(test_X)
print('predicted')
print(datetime.datetime.now(),'\n')
print('Predicted == Real: ', clf.score(test_X,test_y),'\n')
#confusion matrix
titles_options = [("Confusion matrix", None), ("Confusion matrix, normalized", 'true')]
for title, normalize in titles_options:
disp = plot_confusion_matrix(clf, test_X, test_y, cmap=plt.cm.Blues, normalize=normalize)
disp.ax_.set_title(title)
plt.savefig('C:/Users/Saulo/source/repos/Classification-Project/Figures/Classification Tests/'+title+'_KN'+num+'.png')
plt.close()
#classification report
print('Classification Report: \n\n',classification_report(test_y, yp),
'\n____________________________________________________________\n')
#knei test end
#svm test
def svm_(target, features, num):
y=target
X = features
train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.20, random_state=0)
clf = svm.SVC()
print('svm has begun')
print(datetime.datetime.now(),'\n')
clf.fit(train_X,train_y)
print('fitted')
print(datetime.datetime.now(),'\n')
yp=clf.predict(test_X)
print('predicted')
print(datetime.datetime.now(),'\n')
print('Predicted == Real: ', clf.score(test_X,test_y),'\n')
#confusion matrix
titles_options = [("Confusion matrix", None), ("Confusion matrix, normalized", 'true')]
for title, normalize in titles_options:
disp = plot_confusion_matrix(clf, test_X, test_y, cmap=plt.cm.Blues, normalize=normalize)
disp.ax_.set_title(title)
plt.savefig('C:/Users/Saulo/source/repos/Classification-Project/Figures/Classification Tests/'+title+'_SVM'+num+'.png')
plt.close()
#classification report
print('Classification Report: \n\n',classification_report(test_y, yp),
'\n____________________________________________________________\n')
#svm test end
#mlp test
def mlp(target, features, num):
y=target
X = features
train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.20, random_state=0)
clf = MLPClassifier()
print('mlp has begun')
print(datetime.datetime.now(),'\n')
clf.fit(train_X,train_y)
print('fitted')
print(datetime.datetime.now(),'\n')
yp=clf.predict(test_X)
print('predicted')
print(datetime.datetime.now(),'\n')
print('Predicted == Real: ', clf.score(test_X,test_y),'\n')
#confusion matrix
titles_options = [("Confusion matrix", None), ("Confusion matrix, normalized", 'true')]
for title, normalize in titles_options:
disp = plot_confusion_matrix(clf, test_X, test_y, cmap=plt.cm.Blues, normalize=normalize)
disp.ax_.set_title(title)
plt.savefig('C:/Users/Saulo/source/repos/Classification-Project/Figures/Classification Tests/'+title+'_MLP'+num+'.png')
plt.close()
#classification report
print('Classification Report: \n\n',classification_report(test_y, yp),
'\n____________________________________________________________\n')
#mlp test end
#open txt
sys.stdout=open('C:/Users/Saulo/source/repos/Classification-Project/classification_tests_output.txt','w')
data = pd.read_csv("encoded_loan.csv")
target = data.MIS_Status
#1
features = data.drop(columns=['MIS_Status'])
mlp(target,features,'1')
#2
features = features.drop(columns=['CreateJob','RetainedJob'])
mlp(target,features,'2')
#3
features = features.drop(columns=['NewExist'])
mlp(target,features,'3')
#close txt
sys.stdout.close()
#State, NAICS, Term, NoEmp, NewExist, CreateJob, RetainedJob, isFranchise, UrbanRural, LowDoc, GrAppv
#CreateJob and RetainedJob have very little impact according to logit, NewExist looks low as well