TF-IDF关键词提取

import jieba
import jieba.analyse
from tqdm import tqdm
from sklearn.feature_extraction.text import TfidfVectorizer

# data : 文本list

# jieba 关键词提取
def key_words1(data):
    text = ' '.join(data)
    kwds = jieba.analyse.extract_tags(text, topK=20, withWeight=True)
    for i in kwds:
        print(i)

# sklearn 关键词提取
def key_words2(data):
    data = [' '.join(jieba.lcut(_)) for _ in tqdm(data)]
    vectorizer = TfidfVectorizer(ngram_range=(1, 1))
    vct = vectorizer.fit(data)
    vocabs = vct.get_feature_names()
    text = [' '.join(data)]
    result = vct.transform(text)
    result = [(i, j) for i,j in zip(result.indices, result.data)]
    result = sorted(result, key=lambda x: x[1], reverse=True)
    for i in result[:20]:
        print(vocabs[i[0]], i[1])