create_sentiment_featuresets.py 文件源码

def sample_handling(sample, lexicon, classification):
    featureset = []

    with io.open(sample, 'r', encoding='utf-8') as f:
        contents = f.readlines()
        for l in contents[:hm_lines]:
            current_words = word_tokenize(l.lower())
            current_words = [lemmatizer.lemmatize(i) for i in current_words]
            features = np.zeros(len(lexicon))

            for word in current_words:
                if word.lower() in lexicon:
                    index_value = lexicon.index(word.lower())
                    features[index_value] += 1
            features = list(features)
            featureset.append([features, classification])
    return featureset