clouds.py 文件源码

def texts_tfidf(ids, important_texts, citations_texts) :
    '''
    Generates tf-idf vectors for each text then calculates cosine similarity between the vectors. 
    '''

    tfidf = TfidfVectorizer(strip_accents='ascii',
                                                    stop_words='english', 
                                                    ngram_range=(1,2),
                                                    min_df=2)

    freqs1 = tfidf.fit_transform(important_texts)
    terms1 = tfidf.get_feature_names()

    freqs2 = tfidf.fit_transform(citations_texts)
    terms2 = tfidf.get_feature_names()

    return terms1, terms2, freqs1, freqs2