kmeans_cluster.py 文件源码

def get_tfidf(documents):  # ??gensim????tfidf
    documents=[[word for word in document.text.split()] for document in documents]
    dictionary = corpora.Dictionary(documents)
    n_items = len(dictionary)
    corpus = [dictionary.doc2bow(text) for text in documents]
    tfidf = models.TfidfModel(corpus)
    corpus_tfidf = tfidf[corpus]

    ds = []
    for doc in corpus_tfidf:
        d = [0] * n_items
        for index, value in doc :
            d[index]  = value
        ds.append(d)
    return ds