写程序：用python实现it-idf提取关键词

好的，下面是一个简单的Python程序，用于实现TF-IDF提取关键词：

import jieba.analyse
import jieba
import os
import codecs
from sklearn import feature_extraction
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.metrics.pairwise import cosine_similarity

# 加载停用词
def get_stopwords_list():
    stopwords_file = os.path.join(os.getcwd(), 'stopwords.txt')
    stopwords_list = [line.strip() for line in codecs.open(stopwords_file, 'r', encoding='utf-8').readlines()]
    return stopwords_list

# 分词
def cut_words(text):
    words = jieba.cut(text)
    stopwords_list = get_stopwords_list()
    result = ''
    for word in words:
        if word not in stopwords_list:
            result += word + ' '
    return result

# TF-IDF提取关键词
def tfidf_extract(texts, topK):
    corpus = []
    for text in texts:
        text = cut_words(text)
        corpus.append(text)
    vectorizer = TfidfVectorizer()
    transformer = TfidfTransformer()
    tfidf = transformer.fit_transform(vectorizer.fit_transform(corpus))
    word = vectorizer.get_feature_names()
    weight = tfidf.toarray()
    ids = []
    for i in range(len(weight)):
        ids.append(i)
    for i in range(len(weight)):
        cosine_similarities = cosine_similarity(tfidf[i], tfidf).flatten()
        related_docs_indices = [index for index in cosine_similarities.argsort()[::-1] if index != i]
        top_k = related_docs_indices[:topK]
        print("关键词：")
        for index in top_k:
            print(word[index], end=" ")
        print("\n")

if __name__ == '__main__':
    texts = ['中文语料库', '汉语分词', '自然语言处理', '机器学习', '深度学习']
    topK = 3
    tfidf_extract(texts, topK)

该程序使用了jieba库进行分词，并使用sklearn库中的TfidfVectorizer和TfidfTransformer进行TF-IDF计算和特征转换。在程序中，我们使用了一个停用词表来过滤掉一些无意义的词语，同时在输出关键词时，我们使用余弦相似度来计算相关性，并输出与当前文本最相关的前topK个关键词。