Python SentimentAnalyzer.train方法代码示例

# 需要导入模块: from nltk.sentiment import SentimentAnalyzer [as 别名]
# 或者: from nltk.sentiment.SentimentAnalyzer import train [as 别名]
def train():
  positive_tweets = read_tweets('positive.txt', 'positive')
  negative_tweets = read_tweets('negative.txt', 'negative')
  print len(positive_tweets)
  print len(negative_tweets)

  pos_train = positive_tweets[:len(positive_tweets)]
  neg_train = negative_tweets[:len(negative_tweets)]
  # pos_test = positive_tweets[len(positive_tweets)*80/100+1:]
  # neg_test = negative_tweets[len(positive_tweets)*80/100+1:]

  training_data = pos_train + neg_train
  # test_data = pos_test + neg_test

  sentim_analyzer = SentimentAnalyzer()
  all_words_neg = sentim_analyzer.all_words([mark_negation(doc) for doc in training_data])
  unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4)
  print len(unigram_feats)

  sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)
  training_set = sentim_analyzer.apply_features(training_data)

  # test_set = sentim_analyzer.apply_features(test_data)
  # print test_set

  trainer = NaiveBayesClassifier.train
  sentim_analyzer.train(trainer, training_set)

  # for key,value in sorted(sentim_analyzer.evaluate(test_set).items()):
  #   print('{0}: {1}'.format(key, value))
  # print sentim_analyzer.classify(tokenize_sentence('I hate driving car at night'))

  return sentim_analyzer

# 需要导入模块: from nltk.sentiment import SentimentAnalyzer [as 别名]
# 或者: from nltk.sentiment.SentimentAnalyzer import train [as 别名]
    def sentiment_analysis(self, testing_data, training_data=None):
        if training_data is None:
            training_data = self.training_data
            ## Apply sentiment analysis to data to extract new "features"

            # Initialize sentiment analyzer object
        sentiment_analyzer = SentimentAnalyzer()

        # Mark all negative words in training data, using existing list of negative words
        all_negative_words = sentiment_analyzer.all_words([mark_negation(data) for data in training_data])

        unigram_features = sentiment_analyzer.unigram_word_feats(all_negative_words, min_freq=4)
        len(unigram_features)
        sentiment_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_features)

        training_final = sentiment_analyzer.apply_features(training_data)
        testing_final = sentiment_analyzer.apply_features(testing_data)

        ## Traing model and test

        model = NaiveBayesClassifier.train
        classifer = sentiment_analyzer.train(model, training_final)

        for key, value in sorted(sentiment_analyzer.evaluate(testing_final).items()):
            print ("{0}: {1}".format(key, value))

# 需要导入模块: from nltk.sentiment import SentimentAnalyzer [as 别名]
# 或者: from nltk.sentiment.SentimentAnalyzer import train [as 别名]
def demo_subjectivity(trainer, save_analyzer=False, n_instances=None, output=None):
    """
    Train and test a classifier on instances of the Subjective Dataset by Pang and
    Lee. The dataset is made of 5000 subjective and 5000 objective sentences.
    All tokens (words and punctuation marks) are separated by a whitespace, so
    we use the basic WhitespaceTokenizer to parse the data.

    :param trainer: `train` method of a classifier.
    :param save_analyzer: if `True`, store the SentimentAnalyzer in a pickle file.
    :param n_instances: the number of total sentences that have to be used for
        training and testing. Sentences will be equally split between positive
        and negative.
    :param output: the output file where results have to be reported.
    """
    from nltk.sentiment import SentimentAnalyzer
    from nltk.corpus import subjectivity

    if n_instances is not None:
        n_instances = int(n_instances/2)

    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]]

    # We separately split subjective and objective instances to keep a balanced
    # uniform class distribution in both train and test sets.
    train_subj_docs, test_subj_docs = split_train_test(subj_docs)
    train_obj_docs, test_obj_docs = split_train_test(obj_docs)

    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])

    # Add simple unigram word features handling negation
    unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4)
    sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)

    # Apply features to obtain a feature-value representation of our datasets
    training_set = sentim_analyzer.apply_features(training_docs)
    test_set = sentim_analyzer.apply_features(testing_docs)

    classifier = sentim_analyzer.train(trainer, training_set)
    try:
        classifier.show_most_informative_features()
    except AttributeError:
        print('Your classifier does not provide a show_most_informative_features() method.')
    results = sentim_analyzer.evaluate(test_set)

    if save_analyzer == True:
        save_file(sentim_analyzer, 'sa_subjectivity.pickle')

    if output:
        extr = [f.__name__ for f in sentim_analyzer.feat_extractors]
        output_markdown(output, Dataset='subjectivity', Classifier=type(classifier).__name__,
                        Tokenizer='WhitespaceTokenizer', Feats=extr,
                        Instances=n_instances, Results=results)

    return sentim_analyzer

# 需要导入模块: from nltk.sentiment import SentimentAnalyzer [as 别名]
# 或者: from nltk.sentiment.SentimentAnalyzer import train [as 别名]
def demo_movie_reviews(trainer, n_instances=None, output=None):
    """
    Train classifier on all instances of the Movie Reviews dataset.
    The corpus has been preprocessed using the default sentence tokenizer and
    WordPunctTokenizer.
    Features are composed of:
        - most frequent unigrams

    :param trainer: `train` method of a classifier.
    :param n_instances: the number of total reviews that have to be used for
        training and testing. Reviews will be equally split between positive and
        negative.
    :param output: the output file where results have to be reported.
    """
    from nltk.corpus import movie_reviews
    from nltk.sentiment import SentimentAnalyzer

    if n_instances is not None:
        n_instances = int(n_instances/2)

    pos_docs = [(list(movie_reviews.words(pos_id)), 'pos') for pos_id in movie_reviews.fileids('pos')[:n_instances]]
    neg_docs = [(list(movie_reviews.words(neg_id)), 'neg') for neg_id in movie_reviews.fileids('neg')[:n_instances]]
    # We separately split positive and negative instances to keep a balanced
    # uniform class distribution in both train and test sets.
    train_pos_docs, test_pos_docs = split_train_test(pos_docs)
    train_neg_docs, test_neg_docs = split_train_test(neg_docs)

    training_docs = train_pos_docs+train_neg_docs
    testing_docs = test_pos_docs+test_neg_docs

    sentim_analyzer = SentimentAnalyzer()
    all_words = sentim_analyzer.all_words(training_docs)

    # Add simple unigram word features
    unigram_feats = sentim_analyzer.unigram_word_feats(all_words, min_freq=4)
    sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)
    # Apply features to obtain a feature-value representation of our datasets
    training_set = sentim_analyzer.apply_features(training_docs)
    test_set = sentim_analyzer.apply_features(testing_docs)

    classifier = sentim_analyzer.train(trainer, training_set)
    try:
        classifier.show_most_informative_features()
    except AttributeError:
        print('Your classifier does not provide a show_most_informative_features() method.')
    results = sentim_analyzer.evaluate(test_set)

    if output:
        extr = [f.__name__ for f in sentim_analyzer.feat_extractors]
        output_markdown(output, Dataset='Movie_reviews', Classifier=type(classifier).__name__,
                        Tokenizer='WordPunctTokenizer', Feats=extr, Results=results,
                        Instances=n_instances)

# 需要导入模块: from nltk.sentiment import SentimentAnalyzer [as 别名]
# 或者: from nltk.sentiment.SentimentAnalyzer import train [as 别名]
def get_objectivity_analyzer():
    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
    train_obj_docs = obj_docs
    training_docs = train_subj_docs+train_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)

    trainer = NaiveBayesClassifier.train
    sentiment_classifier = sentim_analyzer.train(trainer, training_set)
    
    return sentim_analyzer

# 需要导入模块: from nltk.sentiment import SentimentAnalyzer [as 别名]
# 或者: from nltk.sentiment.SentimentAnalyzer import train [as 别名]
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=1)
len(unigram_feats)

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))

    from nltk.sentiment.vader import SentimentIntensityAnalyzer
sentences = ["VADER is smart, handsome, and funny.", # positive sentence example
    "VADER is smart, handsome, and funny!", # punctuation emphasis handled correctly (sentiment intensity adjusted)
    "VADER is very smart, handsome, and funny.",  # booster words handled correctly (sentiment intensity adjusted)
    "VADER is VERY SMART, handsome, and FUNNY.",  # emphasis for ALLCAPS handled
    "VADER is VERY SMART, handsome, and FUNNY!!!",# combination of signals - VADER appropriately adjusts intensity
    "VADER is VERY SMART, really handsome, and INCREDIBLY FUNNY!!!",# booster words & punctuation make this close to ceiling for score
    "The book was good.",         # positive sentence
    "The book was kind of good.", # qualified positive sentence is handled correctly (intensity adjusted)
    "The plot was good, but the characters are uncompelling and the dialog is not great.", # mixed negation sentence
    "A really bad, horrible book.",       # negative sentence with booster words

# 需要导入模块: from nltk.sentiment import SentimentAnalyzer [as 别名]
# 或者: from nltk.sentiment.SentimentAnalyzer import train [as 别名]
def demo_tweets(trainer, n_instances=None, output=None):
    """
    Train and test Naive Bayes classifier on 10000 tweets, tokenized using
    TweetTokenizer.
    Features are composed of:
        - 1000 most frequent unigrams
        - 100 top bigrams (using BigramAssocMeasures.pmi)

    :param trainer: `train` method of a classifier.
    :param n_instances: the number of total tweets that have to be used for
        training and testing. Tweets will be equally split between positive and
        negative.
    :param output: the output file where results have to be reported.
    """
    from nltk.tokenize import TweetTokenizer
    from nltk.sentiment import SentimentAnalyzer
    from nltk.corpus import twitter_samples, stopwords

    # Different customizations for the TweetTokenizer
    tokenizer = TweetTokenizer(preserve_case=False)
    # tokenizer = TweetTokenizer(preserve_case=True, strip_handles=True)
    # tokenizer = TweetTokenizer(reduce_len=True, strip_handles=True)

    if n_instances is not None:
        n_instances = int(n_instances/2)

    fields = ['id', 'text']
    positive_json = twitter_samples.abspath("positive_tweets.json")
    positive_csv = 'positive_tweets.csv'
    json2csv_preprocess(positive_json, positive_csv, fields, limit=n_instances)

    negative_json = twitter_samples.abspath("negative_tweets.json")
    negative_csv = 'negative_tweets.csv'
    json2csv_preprocess(negative_json, negative_csv, fields, limit=n_instances)

    neg_docs = parse_tweets_set(negative_csv, label='neg', word_tokenizer=tokenizer)
    pos_docs = parse_tweets_set(positive_csv, label='pos', word_tokenizer=tokenizer)

    # We separately split subjective and objective instances to keep a balanced
    # uniform class distribution in both train and test sets.
    train_pos_docs, test_pos_docs = split_train_test(pos_docs)
    train_neg_docs, test_neg_docs = split_train_test(neg_docs)

    training_tweets = train_pos_docs+train_neg_docs
    testing_tweets = test_pos_docs+test_neg_docs

    sentim_analyzer = SentimentAnalyzer()
    # stopwords = stopwords.words('english')
    # all_words = [word for word in sentim_analyzer.all_words(training_tweets) if word.lower() not in stopwords]
    all_words = [word for word in sentim_analyzer.all_words(training_tweets)]

    # Add simple unigram word features
    unigram_feats = sentim_analyzer.unigram_word_feats(all_words, top_n=1000)
    sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)

    # Add bigram collocation features
    bigram_collocs_feats = sentim_analyzer.bigram_collocation_feats([tweet[0] for tweet in training_tweets],
        top_n=100, min_freq=12)
    sentim_analyzer.add_feat_extractor(extract_bigram_feats, bigrams=bigram_collocs_feats)

    training_set = sentim_analyzer.apply_features(training_tweets)
    test_set = sentim_analyzer.apply_features(testing_tweets)

    classifier = sentim_analyzer.train(trainer, training_set)
    # classifier = sentim_analyzer.train(trainer, training_set, max_iter=4)
    try:
        classifier.show_most_informative_features()
    except AttributeError:
        print('Your classifier does not provide a show_most_informative_features() method.')
    results = sentim_analyzer.evaluate(test_set)

    if output:
        extr = [f.__name__ for f in sentim_analyzer.feat_extractors]
        output_markdown(output, Dataset='labeled_tweets', Classifier=type(classifier).__name__,
                        Tokenizer=tokenizer.__class__.__name__, Feats=extr,
                        Results=results, Instances=n_instances)

# 需要导入模块: from nltk.sentiment import SentimentAnalyzer [as 别名]
# 或者: from nltk.sentiment.SentimentAnalyzer import train [as 别名]
# Now aggregate the training and test sets

training = training_subjective + training_objective
test = test_subjective + test_objective

## Apply sentiment analysis to data to extract new "features"

# Initialize sentiment analyzer object

sentiment_analyzer = SentimentAnalyzer()

# Mark all negative words in training data, using existing list of negative words

all_negative_words = sentiment_analyzer.all_words([mark_negation(data) for data in training])

unigram_features = sentiment_analyzer.unigram_word_feats(all_negative_words, min_freq=4)
len(unigram_features)
sentiment_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_features)

training_final = sentiment_analyzer.apply_features(training)
test_final = sentiment_analyzer.apply_features(test)

## Traing model and test

model = NaiveBayesClassifier.train
classifer = sentiment_analyzer.train(model, training_final)

for key, value in sorted(sentiment_analyzer.evaluate(test_final).items()):
    print("{0}: {1}".format(key, value))

# 需要导入模块: from nltk.sentiment import SentimentAnalyzer [as 别名]
# 或者: from nltk.sentiment.SentimentAnalyzer import train [as 别名]
class SuicideClassifier(object):

    def __init__(self, sentiment_only, num_phrases_to_track=20):
        # neg_phrases = filter_negative_phrases(load_csv_sentences('thoughtsandfeelings.csv'))
        # pos_phrases = filter_positive_phrases(load_csv_sentences('spiritualforums.csv'))
        # file_pos = open("pos_phrases.txt", 'w')
        # file_neg = open("neg_phrases.txt", 'w')

        # for item in pos_phrases:
        #     print>>file_pos, item
        # for item in neg_phrases:
        #     print>>file_neg, item
        self.recent_sentiment_scores = []

        neg_file = open("ALL_neg_phrases_filtered.txt", "r")
        pos_file = open("webtext_phrases_with_lots_of_words.txt", "r")
        neg_phrases = neg_file.readlines()
        pos_phrases = pos_file.readlines()

        neg_docs = []
        pos_docs = []
        for phrase in neg_phrases:
            neg_docs.append((phrase.split(), 'suicidal'))
        for phrase in pos_phrases[:len(neg_phrases)]:
            pos_docs.append((phrase.split(), 'alright'))

        print len(neg_docs)
        print len(pos_docs)
        # negcutoff = len(neg_docs) * 3 / 4
        # poscutoff = len(pos_docs) * 3 / 4
        negcutoff = -200
        poscutoff = -200

        train_pos_docs = pos_docs[:poscutoff]
        test_pos_docs = pos_docs[poscutoff:]
        train_neg_docs = neg_docs[:negcutoff]
        test_neg_docs = neg_docs[negcutoff:]
        training_docs = train_pos_docs + train_neg_docs
        testing_docs = test_pos_docs + test_neg_docs

        self.sentim_analyzer = SentimentAnalyzer()

        if not sentiment_only:
            all_words = self.sentim_analyzer.all_words([doc for doc in training_docs])
            unigram_feats = self.sentim_analyzer.unigram_word_feats(all_words, min_freq=1)
            self.sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)

        self.sentim_analyzer.add_feat_extractor(vader_sentiment_feat)

        # bigram_feats = self.sentim_analyzer.bigram_collocation_feats(all_words, min_freq=1)
        # self.sentim_analyzer.add_feat_extractor(extract_bigram_feats, bigrams=bigram_feats)

        training_set = self.sentim_analyzer.apply_features(training_docs)
        test_set = self.sentim_analyzer.apply_features(testing_docs)
        trainer = NaiveBayesClassifier.train
        self.classifier = self.sentim_analyzer.train(trainer, training_set)
        for key, value in sorted(self.sentim_analyzer.evaluate(test_set).items()):
            print('{0}: {1}'.format(key, value))
        self.classifier.show_most_informative_features(20)

    def test(self, phrase):
        return self.sentim_analyzer.classify(phrase.split())

    def update_sentiments(self, value):
        now = datetime.datetime.now()
        self.recent_sentiment_scores.append([now, value])
        self.recent_sentiment_scores = [x for x in self.recent_sentiment_scores if x[
            0] > now - datetime.timedelta(seconds=60)]
        print sum([x[1] for x in self.recent_sentiment_scores]) / len(self.recent_sentiment_scores)
        return sum([x[1] for x in self.recent_sentiment_scores]) / len(self.recent_sentiment_scores)

# 需要导入模块: from nltk.sentiment import SentimentAnalyzer [as 别名]
# 或者: from nltk.sentiment.SentimentAnalyzer import train [as 别名]

#.........这里部分代码省略.........
            if ml is True:
                d_score_updates = self.find_ml(q)

            # Weight scores with year and rating
            for i in range(len(results)):
                score = results[i][0]
                index = results[i][1]
                year = self.year_rating_dict[self.movies[i]][0]
                rating = self.year_rating_dict[self.movies[i]][1]
                results[i] = (year_rating_weight(float(year), float(rating), score), index)
                if ml is True and index in d_score_updates:
                    results[i] = (results[i][0]*0.9 + d_score_updates[index], results[i][1])

        # Sort and return results
        top_res_num = 5
        results.sort(reverse=True)
        used_quotes = []
        return_res = []
        counter = 0
        while len(return_res) <= top_res_num:  # Avoid duplicate quotes
            score, i = results[counter]
            if self.quotes[i] not in used_quotes:
                used_quotes.append(self.quotes[i])
                return_res.append((score, i))
            else:
                counter += 1

        result_quotes = [[self.quotes[i], self.movies[i], self.context[i]] for _, i in
                         return_res[:top_res_num]]
        return result_quotes

    def sentiment_analysis(self, td):
        with open('jsons/all_words_neg.pickle', 'rb') as f:
            all_words_neg = pickle.load(f)

        with open('jsons/training_docs.pickle', 'rb') as f:
            training_docs = pickle.load(f)

        genres = ['action', 'crime', 'comedy', 'drama']
        testing_docs = [(td, genre) for genre in genres]

        all_words_neg = self.sentim_analyzer.all_words([mark_negation(doc) for doc in training_docs])
        unigram_feats = self.sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4)
        all_words_neg = self.sentim_analyzer.all_words([mark_negation(doc) for doc in training_docs])
        self.sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)
        training_set = self.sentim_analyzer.apply_features(training_docs)
        test_set = self.sentim_analyzer.apply_features(testing_docs)

        trainer = NaiveBayesClassifier.train

        classifier = self.sentim_analyzer.train(trainer, training_set)
        # f = open('my_classifier_test.pickle', 'rb')
        # classifier = pickle.load(f)
        # f.close()

        # classifier = nltk.data.load("my_classifier.pickle")

        genre_accuracy = []

        for key, value in sorted(self.sentim_analyzer.evaluate(test_set).items()):
            # print('{0}: {1}'.format(key, value))
            if key == 'Precision [action]':
                genre_accuracy.append(('action', value))
            if key == 'Precision [comedy]':
                genre_accuracy.append(('comedy', value))
            if key == 'Precision [drama]':
                genre_accuracy.append(('drama', value))
            if key == 'Precision [crime]':
                genre_accuracy.append(('crime', value))

        return genre_accuracy

    # Takes in a query
    # Outputs a dictionary of movie indices movies to weights where weight is to be added to all quote scores of movies
    def find_ml(self, td):
        f_tokenizer = TreebankWordTokenizer()
        query_words = f_tokenizer.tokenize(td)
        genres = self.sentiment_analysis(query_words)
        weighted_genres = []
        genre_weights = {}
        for x in genres:
            if x[1] is not None:
                weighted_genres.append(x[0])
                genre_weights[x[0]] = x[1]

        d_score_updates = {}
        for movie in self.movies:
            g = self.genre_dict[movie][0]
            total_genre_score = 0
            if u'Comedy' in g and 'comedy' in weighted_genres:
                total_genre_score += genre_weights['comedy']
            if u'Action' in g and 'action' in weighted_genres:
                total_genre_score += genre_weights['action']
            if u'Crime' in g and 'crime' in weighted_genres:
                total_genre_score += genre_weights['crime']
            if u'Drama' in g and 'drana' in weighted_genres:
                total_genre_score += genre_weights['drama']
            d_score_updates[self.movies.index(movie)] = total_genre_score * .1

        return d_score_updates