-
Notifications
You must be signed in to change notification settings - Fork 12
/
Copy pathClassifiers.py
215 lines (154 loc) · 6.46 KB
/
Classifiers.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
from sklearn.naive_bayes import MultinomialNB
from sklearn.linear_model import PassiveAggressiveClassifier
from sklearn.svm import LinearSVC
from sklearn import metrics
from Src import Data_Preprocessing
import warnings
import time
warnings.filterwarnings("ignore")
data_obj = Data_Preprocessing.process_data()
data_obj.clean_data()
'''
Naive Bayes classifier class
'''
class Naive_Bayes_Classifier:
def __init__(self):
self.vectorizer_time = {'Count' : 0 , 'TFIDF' : 0 , 'Hash' : 0}
self.classifier_time = {'Count' : 0 , 'TFIDF' : 0 , 'Hash' : 0}
def Count_vectorizer_classifier(self):
start = time.time()
print("\n\nRunning Naive Bayes with Count Vectorizer...")
x_train, x_test = data_obj.generate_count_vectorizer()
y_train = data_obj.y_train
y_test = data_obj.y_test
self.vectorizer_time['Count'] = time.time() - start
start = time.time()
pred = self.classify(x_train, x_test, y_train, y_test)
self.classifier_time['Count'] = time.time() - start
print("Process Completed.")
return (y_test, pred)
def Tfif_vectorizer_classifier(self):
start = time.time()
print("\n\nRunning Naive Bayes with TFIDF Vectorizer...")
x_train, x_test = data_obj.generate_tfidf_vectorizer()
y_train = data_obj.y_train
y_test = data_obj.y_test
self.vectorizer_time['TFIDF'] = time.time() - start
start = time.time()
pred = self.classify(x_train, x_test, y_train, y_test)
self.classifier_time['TFIDF'] = time.time() - start
print("Process Completed.")
return (y_test, pred)
def Hash_vectorizer_classifier(self):
start = time.time()
print("\n\nRunning Naive Bayes with Hash Vectorizer...")
x_train, x_test = data_obj.generate_hashing_vectorizer()
y_train = data_obj.y_train
y_test = data_obj.y_test
self.vectorizer_time['Hash'] = time.time() - start
start = time.time()
pred = self.classify(x_train, x_test, y_train, y_test)
self.classifier_time['Hash'] = time.time() - start
print("Process Completed.")
return (y_test, pred)
def classify(self, x_train, x_test, y_train, y_test):
model = MultinomialNB()
model.fit(x_train, y_train)
pred = model.predict(x_test)
return pred
'''
SVM classifier class
'''
class SVM_Classifier:
def __init__(self):
self.vectorizer_time = {'Count': 0, 'TFIDF': 0, 'Hash': 0}
self.classifier_time = {'Count': 0, 'TFIDF': 0, 'Hash': 0}
def Count_vectorizer_classifier(self):
start = time.time()
print("\n\nRunning SVM with Count Vectorizer...")
x_train, x_test = data_obj.generate_count_vectorizer()
y_train = data_obj.y_train
y_test = data_obj.y_test
self.vectorizer_time['Count'] = time.time() - start
start = time.time()
pred = self.classify(x_train, x_test, y_train, y_test)
self.classifier_time['Count'] = time.time() - start
print("Process Completed.")
return (y_test, pred)
def Tfif_vectorizer_classifier(self):
start = time.time()
print("\n\nRunning SVM with TFIDF Vectorizer...")
x_train, x_test = data_obj.generate_tfidf_vectorizer()
y_train = data_obj.y_train
y_test = data_obj.y_test
self.vectorizer_time['TFIDF'] = time.time() - start
start = time.time()
pred = self.classify(x_train, x_test, y_train, y_test)
self.classifier_time['TFIDF'] = time.time() - start
print("Process Completed.")
return (y_test, pred)
def Hash_vectorizer_classifier(self):
start = time.time()
print("\n\nRunning SVM with Hash Vectorizer...")
x_train, x_test = data_obj.generate_hashing_vectorizer()
y_train = data_obj.y_train
y_test = data_obj.y_test
self.vectorizer_time['Hash'] = time.time() - start
start = time.time()
pred = self.classify(x_train, x_test, y_train, y_test)
self.classifier_time['Hash'] = time.time() - start
print("Process Completed.")
return (y_test, pred)
def classify(self, x_train, x_test, y_train, y_test):
model = LinearSVC( C = 0.1 , loss='hinge', penalty='l2', max_iter=1000, dual= True)
model.fit(x_train, y_train)
pred = model.predict(x_test)
return pred
'''
Passive Agressive classifier class
'''
class Passive_Agressive_Classifier:
def __init__(self):
self.vectorizer_time = {'Count': 0, 'TFIDF': 0, 'Hash': 0}
self.classifier_time = {'Count': 0, 'TFIDF': 0, 'Hash': 0}
def Count_vectorizer_classifier(self):
start = time.time()
print("\n\nRunning Passive Agressive with Count Vectorizer...")
x_train, x_test = data_obj.generate_count_vectorizer()
y_train = data_obj.y_train
y_test = data_obj.y_test
self.vectorizer_time['Count'] = time.time() - start
start = time.time()
pred = self.classify(x_train, x_test, y_train, y_test)
self.classifier_time['Count'] = time.time() - start
print("Process Completed.")
return (y_test, pred)
def Tfif_vectorizer_classifier(self):
start = time.time()
print("\n\nRunning Passive Agressive with TFIDF Vectorizer...")
x_train, x_test = data_obj.generate_tfidf_vectorizer()
y_train = data_obj.y_train
y_test = data_obj.y_test
self.vectorizer_time['TFIDF'] = time.time() - start
start = time.time()
pred = self.classify(x_train, x_test, y_train, y_test)
self.classifier_time['TFIDF'] = time.time() - start
print("Process Completed.")
return (y_test, pred)
def Hash_vectorizer_classifier(self):
start = time.time()
print("\n\nRunning Passive Agressive with Hash Vectorizer...")
x_train, x_test = data_obj.generate_hashing_vectorizer()
y_train = data_obj.y_train
y_test = data_obj.y_test
self.vectorizer_time['Hash'] = time.time() - start
start = time.time()
pred = self.classify(x_train, x_test, y_train, y_test)
self.classifier_time['Hash'] = time.time() - start
print("Process Completed.")
return (y_test, pred)
def classify(self, x_train, x_test, y_train, y_test):
model = PassiveAggressiveClassifier(max_iter=50, C = 0.7)
model.fit(x_train, y_train)
pred = model.predict(x_test)
return pred