机器学习入门-提取文章的主题词 1.jieba.analyse.extract_tags(提取主题词)

import pandas as pd
import numpy as np
import jieba

# 1.导入数据语料的新闻数据
df_data = pd.read_table(‘data/val.txt‘, names=[‘category‘, ‘theme‘, ‘URL‘, ‘content‘], encoding=‘utf-8‘)

# 2.对语料库进行分词操作
df_contents = df_data.content.values.tolist()

# list of list 结构
Jie_content = []
for df_content in df_contents:
    split_content = jieba.lcut(df_content)
    if len(split_content) > 1 and split_content != ‘\t\n‘:
        Jie_content.append(split_content)

# 3. 导入停止词的语料库, sep=‘\t‘表示分隔符， quoting控制引号的常量， names=列名， index_col=False，不用第一列做为行的列名， encoding
stopwords = pd.read_csv(‘stopwords.txt‘, sep=‘\t‘, quoting=3, names=[‘stopwords‘], index_col=False, encoding=‘utf-8‘)
print(stopwords.head())

# 对文本进行停止词的去除
def drop_stops(Jie_content, stopwords):
    clean_content = []
    all_words = []
    for j_content in Jie_content:
        line_clean = []
        for line in j_content:
            if line in stopwords:
                continue
            line_clean.append(line)
            all_words.append(line)
        clean_content.append(line_clean)

    return clean_content, all_words
# 将DateFrame的stopwords数据转换为list形式
stopwords = stopwords.stopwords.values.tolist()
clean_content, all_words = drop_stops(Jie_content, stopwords)
print(clean_content[0])

#4.  使用jieba分词器，提取文本的关键字
import jieba.analyse
index = 2000
content_word = ‘‘.join(clean_content[index])


content_text = ‘ ‘.join(jieba.analyse.extract_tags(content_word, topK=5, withWeight=False))
print(content_word)
print(content_text)