Community

NLTK - Sentiment analysis

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._classifier = 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

short_pos = open("positive.txt", "r").read()
short_neg = open("negative.txt", "r").read()

all_words = []
documents = []

#  j is adject, r is adverb, and v is verb
#allowed_word_types = ["J","R","V"]
allowed_word_types = ["J"]

for p in short_pos.split('n'):
    documents.append((p, "pos"))
    words = word_tokenize(p)
    pos = nltk.pos_tag(words)
    for w in pos:
        if w[1][0] in allowed_word_types:
            all_words.append(w[0].lower())


for p in short_neg.split('n'):
    documents.append((p, "neg"))
    words = word_tokenize(p)
    pos = nltk.pos_tag(words)
    for w in pos:
        if w[1][0] in allowed_word_types:
            all_words.append(w[0].lower())
    
save_documents = open("documents.pickle", "wb")
pickle.dump(documents, save_documents)
save_documents.close()

all_words = nltk.FreqDist(all_words)

word_features = list(all_words.keys())[:3000]

save_word_features = open("word_features5k.pickle","wb")
pickle.dump(word_features, save_word_features)
save_word_features.close()


def find_features(document):
    words = word_tokenize(document)
    feature = {}
    for w in word_features:
        feature[w] = (w in words)

    return feature

featuresets = [(find_features(rev), category) for (rev, category) in documents]

random.shuffle(featuresets)
print(len(featuresets))

testing_set = featuresets[10000:]
training_set = featuresets[:10000]


classifier = nltk.NaiveBayesClassifier.train(training_set)
print("Original Naive Bayes Algo accuracy percent:", (nltk.classify.accuracy(classifier, testing_set))*100)
classifier.show_most_informative_features(15)

###############
save_classifier = open("originalnaivebayes5k.pickle","wb")
pickle.dump(classifier, save_classifier)
save_classifier.close()

MNB_classifier = SklearnClassifier(MultinomialNB())
MNB_classifier.train(training_set)
print("MNB_classifier accuracy percent:", (nltk.classify.accuracy(MNB_classifier, testing_set))*100)

getting the following error at MNB_classifier.train: -

Traceback (most recent call last):
  File "D:Userssiddharth.uDocumentsNatural Language ProcessingCreating a module for Sentiment Analysis with NLTKCreating a module for Sentiment Analysis with NLTK.py", line 103, in <module>
    MNB_classifier.train(training_set)
  File "D:Userssiddharth.uAppDataLocalContinuumAnaconda3libsite-packagesnltkclassifyscikitlearn.py", line 117, in train
    X = self._vectorizer.fit_transform(X)
  File "D:Userssiddharth.uAppDataLocalContinuumAnaconda3libsite-packagessklearnfeature_extractiondict_vectorizer.py", line 230, in fit_transform
    return self._transform(X, fitting=True)
  File "D:Userssiddharth.uAppDataLocalContinuumAnaconda3libsite-packagessklearnfeature_extractiondict_vectorizer.py", line 171, in _transform
    indices.append(vocab[f])
MemoryError