Polarity.py

from nltk.classify import NaiveBayesClassifier
from nltk.corpus import subjectivity
from nltk.sentiment import SentimentAnalyzer
from nltk.sentiment.util import *
from nltk.sentiment.vader import SentimentIntensityAnalyzer
import nltk, re


class Polarity:
	def __init__(self):
		n_instances = 100 
		subj_docs = [(sent, 'subj') for sent in subjectivity.sents(categories='subj')[:n_instances]]
		obj_docs = [(sent, 'obj') for sent in subjectivity.sents(categories='obj')[:n_instances]]
		train_subj_docs = subj_docs[:80]
		test_subj_docs = subj_docs[80:100]
		train_obj_docs = obj_docs[:80]
		test_obj_docs = obj_docs[80:100]
		training_docs = train_subj_docs + train_obj_docs 
		testing_docs = test_subj_docs + test_obj_docs
		sentim_analyzer = SentimentAnalyzer()
		all_words_neg = sentim_analyzer.all_words([mark_negation(doc) for doc in training_docs])
		unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4)
		sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)
		training_set = sentim_analyzer.apply_features(training_docs)
		test_set = sentim_analyzer.apply_features(testing_docs)
		trainer = NaiveBayesClassifier.train 
		classifier = sentim_analyzer.train(trainer, training_set)
		for key, value in sorted(sentim_analyzer.evaluate(test_set).items()):
				print("{0} : {1}".format(key, value))

	def preProcess(self, article_text):
		formatted_article_text = re.sub('[^a-zA-Z]', ' ', article_text )  
		formatted_article_text = re.sub(r'\s+', ' ', formatted_article_text)  
		print formatted_article_text
		return formatted_article_text

	def polarity(self, text):
		text = self.preProcess(text)
		sid = SentimentIntensityAnalyzer() 
		ss = sid.polarity_scores(text)
		for k in sorted(ss):
			print "{0}:{1}".format(k, ss[k])

P = Polarity() 
P.polarity('I really hate it when a book ends.')