コード例 #1
0
def extract_keywords(tfidf, processed_text):

    mapping = {}

    for i in range(len(tfidf)):
        for j in range(len(tfidf[i])):

            mapping[processed_text[i][j]] = tfidf[i][j]

    #print(mapping)

    word_scores = sorted(mapping.values(), reverse=True)
    words = []

    scores_to_word = {}

    for i in range(len(tfidf)):
        for j in range(len(tfidf[i])):

            scores_to_word[tfidf[i][j]] = processed_text[i][j]

    for i in range(len(word_scores)):
        if (word_scores[i] != 0):
            words.append(scores_to_word[word_scores[i]])
        else:
            words.append(scores_to_word[word_scores[i]])
            break

    # print(words)

    words = OrderedSet(words)

    for i in mapping:
        if (mapping[i] == 0):
            words.append(i)

    return words, mapping