Permalink
Cannot retrieve contributors at this time
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
BigData/GlossCount.py
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
94 lines (82 sloc)
3.84 KB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import math | |
import nltk | |
from nltk.corpus import wordnet as wn | |
import nltk.classify.util | |
from nltk.classify import NaiveBayesClassifier | |
from nltk.corpus import movie_reviews | |
from sets import Set | |
class GlossCount: | |
def demo(self): | |
def value_of(sentiment): | |
if sentiment == 'pos': return 1 | |
if sentiment == 'neg': return -1 | |
return 0 | |
def sentiment_score(review): | |
return 0 | |
#return sum ([value_of(tag) for sentence in dict_tagged_sentences for token in sentence for tag in token[2]]) | |
def expand_sets(positive,negative,neutral): | |
newPositive = set(positive) | |
newNegative = set(negative) | |
newNeutral = set(neutral) | |
# Add Syns to Positive | |
for word in positive: | |
for syn in wn.synsets(word, pos=wn.ADJ): | |
for lemma in syn.lemmas(): | |
curr = lemma.name().split('.')[0] | |
if(curr not in newNegative and curr not in newNeutral): | |
newPositive.add(curr) | |
elif( curr in newNegative): | |
newNegative.discard(curr) | |
newNeutral.add(curr) | |
# Add Syns to Negative | |
for word in negative: | |
for syn in wn.synsets(word, pos=wn.ADJ): | |
for lemma in syn.lemmas(): | |
curr = lemma.name().split('.')[0] | |
if( curr not in newPositive and curr not in newNeutral): | |
newNegative.add(curr) | |
elif(curr in newPositive): | |
newPositive.discard(curr) | |
newNeutral.add(curr) | |
return (newPositive,newNegative,newNeutral) | |
# Set up initial Sets S_p and S_n | |
positive = Set(['Good']) | |
negative = Set(['Bad']) | |
neutral = Set(['']) | |
# Expand on Sets to get S_p' and S_n' | |
for num in range(1,3): | |
newsets = expand_sets(positive,negative,neutral); | |
positive = set(newsets[0]) | |
negative = set(newsets[1]) | |
neutral = set(newsets[2]) | |
# Learn Classifier | |
trainfeats = [({word : True},"pos") for word in positive] + [({word : True},"neg") for word in negative] | |
classifier = NaiveBayesClassifier.train(trainfeats) | |
print "cat" | |
#print classifier.classify(dict([(word, True) for word in words])) | |
print classifier.classify(dict([("bad",True),("bad",True)])) | |
# Iterate through all of the reviews and find sentiment | |
count = 0.00 | |
correct = 0.00 | |
for reviews in movie_reviews.fileids(): #For every review | |
score = 0; | |
tokens = nltk.pos_tag(nltk.word_tokenize(movie_reviews.raw(fileids=[reviews]))) #Tokenize all words with POS | |
for token in tokens: | |
if (token[1]== "JJ" or token[1] == "JJR" or token[1] == "JJS"): # If adjective, check value | |
sent_value = classifier.classify(dict([(token[0], True)])) | |
if(sent_value is 'neg'): | |
score = score - 1 | |
elif(sent_value is 'pos'): | |
score = score + 1 | |
if (score < 0): | |
print "Negative at %d" % (score) | |
sentiment = 'neg' | |
else: | |
sentiment = 'pos' | |
print "Positive at %d" % (score) | |
if (sentiment == movie_reviews.categories(fileids=[reviews])[0]): | |
print "Correct" | |
correct = correct + 1.00 | |
count = count + 1.00 | |
print correct/count | |
GlossCount().demo() |