-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathsentiment_mod.py
125 lines (80 loc) · 2.96 KB
/
sentiment_mod.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
# -*- coding: utf-8 -*-
"""
Created on Wed Aug 1 19:16:19 2018
@author: NAMRA
"""
#File: sentiment_mod.py
import nltk
import random
#from nltk.corpus import movie_reviews
from nltk.classify.scikitlearn import SklearnClassifier
import pickle
from sklearn.naive_bayes import MultinomialNB, BernoulliNB
from sklearn.linear_model import LogisticRegression, SGDClassifier
from sklearn.svm import SVC, LinearSVC, NuSVC
from nltk.classify import ClassifierI
from statistics import mode
from nltk.tokenize import word_tokenize
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_f = open("pickled_algos/documents.pickle", "rb")
documents = pickle.load(documents_f)
documents_f.close()
word_features5k_f = open("pickled_algos/word_features5k.pickle", "rb")
word_features = pickle.load(word_features5k_f)
word_features5k_f.close()
def find_features(document):
words = word_tokenize(document)
features = {}
for w in word_features:
features[w] = (w in words)
return features
featuresets_f = open("pickled_algos/featuresets.pickle", "rb")
featuresets = pickle.load(featuresets_f)
featuresets_f.close()
random.shuffle(featuresets)
print(len(featuresets))
testing_set = featuresets[10000:]
training_set = featuresets[:10000]
open_file = open("pickled_algos/originalnaivebayes5k.pickle", "rb")
classifier = pickle.load(open_file)
open_file.close()
open_file = open("pickled_algos/MNB_classifier5k.pickle", "rb")
MNB_classifier = pickle.load(open_file)
open_file.close()
open_file = open("pickled_algos/BernoulliNB_classifier5k.pickle", "rb")
BernoulliNB_classifier = pickle.load(open_file)
open_file.close()
open_file = open("pickled_algos/LogisticRegression_classifier5k.pickle", "rb")
LogisticRegression_classifier = pickle.load(open_file)
open_file.close()
open_file = open("pickled_algos/LinearSVC_classifier5k.pickle", "rb")
LinearSVC_classifier = pickle.load(open_file)
open_file.close()
open_file = open("pickled_algos/SGDC_classifier5k.pickle", "rb")
SGDC_classifier = pickle.load(open_file)
open_file.close()
voted_classifier = VoteClassifier(
classifier,
LinearSVC_classifier,
MNB_classifier,
BernoulliNB_classifier,
LogisticRegression_classifier)
def sentiment(text):
feats = find_features(text)
return voted_classifier.classify(feats),voted_classifier.confidence(feats)