知识点普及
词频：某个词在该文档中出现的次数停用词：数据处理时过滤掉某些字或词，如：网站、的等语料库：也就是我们要分析的所有文档的集合中文分词：将汉字序列分成一个个单独的词
使用第三方库介绍
jieba jieba.cut(content) content 为分词的句子pandas pandas.DataFrame()生成DataFrame对象 pandas.DataFrame.groupby()分组统计 分组统计实例 pandas.DataFrame.groupby(by=列名数组)[统计列名数组].agg({ 统计项名称:统计函数})wordcloudpython构建词云的库文件 安装方式请自行案例
词云实现
#!/usr/bin/env python
# coding=utf-8import osimport jiebaimport codecsimport pandas as pdimport numpy as npfrom wordcloud import WordCloud,ImageColorGeneratorimport matplotlib.pyplot as plt
#导入所用库文件basefile = data存储路径
# 语料库加载
f_in = codecs.open(basefile+'an.txt','r','utf-8') content = f_in.read()
#分词,生成segments列表segments = []
segs = jieba.cut(content)for seg in segs: if len(seg)>1: segments.append(seg)
#生成DataFrame对象segmentDF = pd.DataFrame({'segment':segments})
#分组统计segStat = segmentDF.groupby( by = ['segment'] )['segment'].agg({ '计数':np.size}).reset_index().sort_values(by = ['计数'], ascending = False )
#加载停用词 stopwords = pd.read_csv( "./StopwordsCN.txt", encoding='utf8', index_col=False)
#移除停用词,并做去反操作fSegStat = segStat[ ~segStat.segment.isin(stopwords.stopword)]
#构建词云文件wordcloud = WordCloud( font_path='./simhei.ttf',
#词云展示字体 background_color="black",
#词云展示背景颜色
)
words = fSegStat.set_index('segment').to_dict()wordcloud.fit_words(words['计数'])plt.imshow(wordcloud)plt.show()
效果展示
AnnaKarenina
词云美化
from scipy.misc import imread
#读取图片背景
bimg = imread(basefile+'An.png')
wordcloud = WordCloud( background_color="white", mask=bimg, font_path='./simhei.ttf')wordcloud = wordcloud.fit_words(words['计数'])
#设置图片大小
plt.figure( num=None, figsize=(8, 6), dpi=80, facecolor='w', edgecolor='k')
#获取图片颜色
bimgColors = ImageColorGenerator(bimg)plt.axis("off")
#重置词云颜色
plt.imshow(wordcloud.recolor(color_func=bimgColors))plt.show()