-
Notifications
You must be signed in to change notification settings - Fork 0
/
Movie_reviews_1.py
173 lines (109 loc) · 5.53 KB
/
Movie_reviews_1.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
import nltk
import random
from nltk.corpus import movie_reviews
import pickle
from nltk.classify.scikitlearn import SklearnClassifier
from sklearn.naive_bayes import MultinomialNB, GaussianNB, BernoulliNB
from sklearn.linear_model import LogisticRegression, SGDClassifier
from sklearn.svm import SVC, LinearSVC, NuSVC
from nltk.classify import ClassifierI
from statistics import mode
class VoteClassifier(ClassifierI):
def __init__(self, *classifiers):
self._classifiers = classifiers
def classify(self, features):
votes = []
for c in self._classifiers:
v = c.classify(features)
votes.append(v)
return mode(votes)
def confidence(self, features):
votes = []
for c in self._classifiers:
v = c.classify(features)
votes.append(v)
choice_votes = votes.count(mode(votes))
conf = choice_votes / len(votes)
return conf
##documents = []
##
##for category in movie_reviews.categories():
## for fileid in movie_reviews.fileids(category):
## documents.append(list(movie_reviews.words(fileid)), category)
documents = [(list(movie_reviews.words(fileid)), category)
for category in movie_reviews.categories()
for fileid in movie_reviews.fileids(category)]
random.shuffle(documents)
#print(documents[1])
all_words = []
for w in movie_reviews.words():
all_words.append(w.lower())
all_words = nltk.FreqDist(all_words)
#print(all_words.most_common(15))
#print(all_words["stupid"])
### limit on the number of words.upto 3000 words, top 15 included dashes, periods, 3000 would have sufficent words to classify into +ve and -ve
word_features = list(all_words.keys())[:3000]
def find_features(document):
words = set(document) ##every single word will be included in the set
features = {}
for w in word_features:
features[w] = (w in words) # creates a boolean with either true or false
return features
#print((find_features(movie_reviews.words('neg/cv000_29416.txt'))))
featuresets = [(find_features(rev), category) for (rev, category) in documents]
# find features in the categories... converting it into anothe reviews with true or false, whether top 3000 words are present in the reviews
training_set = featuresets[:1900]
testing_set = featuresets[1900:]
#classifier = nltk.NaiveBayesClassifier.train(training_set)
classifier_f = open("naive_bayes.picke", "rb")
classifier = pickle.load(classifier_f)
classifier_f.close()
print("Accuracy :" , (nltk.classify.accuracy(classifier, testing_set)))
### Multinomial Naive Bayes
MNB_classifier = SklearnClassifier(MultinomialNB())
MNB_classifier.train(training_set)
print("MNB_classfier:", (nltk.classify.accuracy(classifier, testing_set)))
##### Gaussian Naive Bayes
##Gaussian_NB_classifier = SklearnClassifier(GaussianNB())
##Gaussian_NB_classifier.train(training_set)
##print("GNB_classfier:", (nltk.classify.accuracy(Gaussian_NB_classifier, testing_set)))
### Bernoulli Naive Bayes
BernoulliNB_classifier = SklearnClassifier(BernoulliNB())
BernoulliNB_classifier.train(training_set)
print("BNB_classfier:", (nltk.classify.accuracy(BernoulliNB_classifier, testing_set)))
#LogisticRegression, SGDClassifier
#SVC, LinearSVC, NuSVC
#Logistic_Classifier
LogisticRegression_classifier = SklearnClassifier(LogisticRegression())
LogisticRegression_classifier.train(training_set)
print("LogisticRegression_classifier:", (nltk.classify.accuracy(LogisticRegression_classifier, testing_set)))
#SGD
SGDClassifier_classifier = SklearnClassifier(SGDClassifier())
SGDClassifier_classifier.train(training_set)
print("SGDClassifier_classifier:", (nltk.classify.accuracy(SGDClassifier_classifier, testing_set)))
###SVC
##SVC_classifier = SklearnClassifier(SVC())
##SVC_classifier.train(training_set)
##print("SVC_classifier:", (nltk.classify.accuracy(SVC_classifier, testing_set)))
##
#LinearSVC_classifier
LinearSVC_classifier = SklearnClassifier(LinearSVC())
LinearSVC_classifier.train(training_set)
print("LinearSVC_classifier:", (nltk.classify.accuracy(LinearSVC_classifier, testing_set)))
#NuSVC_classifier
NuSVC_classifier = SklearnClassifier(NuSVC())
NuSVC_classifier.train(training_set)
print("NuSVC_classifier:", (nltk.classify.accuracy(NuSVC_classifier, testing_set)))
voted_classifier = VoteClassifier(classifier, MNB_classifier, BernoulliNB_classifier, LogisticRegression_classifier, SGDClassifier_classifier, LinearSVC_classifier, NuSVC_classifier)
print("voted_classifier:", (nltk.classify.accuracy(voted_classifier, testing_set))*100)
print("Classification:" , voted_classifier.classify(testing_set[0][0]), "Confidence %", voted_classifier.confidence(testing_set[0][0]))
print("Classification:" , voted_classifier.classify(testing_set[1][0]), "Confidence %", voted_classifier.confidence(testing_set[1][0]))
print("Classification:" , voted_classifier.classify(testing_set[2][0]), "Confidence %", voted_classifier.confidence(testing_set[2][0]))
print("Classification:" , voted_classifier.classify(testing_set[3][0]), "Confidence %", voted_classifier.confidence(testing_set[3][0]))
print("Classification:" , voted_classifier.classify(testing_set[4][0]), "Confidence %", voted_classifier.confidence(testing_set[4][0]))
classifier.show_most_informative_features(15)
##save_classifier = open("naive_bayes.picke", "wb")
##
##pickle.dump(classifier, save_classifier)
##
##save_classifier.close()