用Python制作词云

制作词云

准备工作：

1.下载Anaconda

2.准备好制作词云的文本

3.安装词云包 pip install coludword

4.安装jieba切词包 pip install jieba

1.引入相关的库包：

#coding:utf-8
import jieba    #分词包
import numpy    #numpy计算包
import codecs   #codecs提供的open方法来指定打开的文件的语言编码，它会在读取的时候自动转换为内部unicode 
import pandas  
import matplotlib
matplotlib.use('TKAgg')
import matplotlib.pyplot as plt
from wordcloud import WordCloud#词云包

2.导入霸王别姬文件

file=codecs.open(u"霸王别姬.txt",'r')
content=file.read()
file.close()

3.用jieba进行分词

segment=[]
segs=jieba.cut(content) #切词
for seg in segs:
    if len(seg)>1 and seg!='\r\n':
        segment.append(seg)

4.去高频语气词

words_df=pandas.DataFrame({'segment':segment})
words_df.head()
stopwords=pandas.read_csv("not.txt",index_col=False,quoting=3,sep="\t",names=['stopword'],encoding="utf8")#去掉我们不需要的高频语气词等
words_df=words_df[~words_df.segment.isin(stopwords.stopword)]

5.统计词频

words_stat=words_df.groupby(by=['segment'])['segment'].agg({"计数":numpy.size})
words_stat=words_stat.reset_index().sort_values(by="计数",ascending=False)

6.使用词云包制作词云

from scipy.misc import imread
import matplotlib.pyplot as plt
from wordcloud import WordCloud,ImageColorGenerator
%matplotlib inline
bimg=imread('timg.jpeg')
wordcloud=WordCloud(background_color="white",mask=bimg,font_path='simhei.ttf')
#wordcloud=wordcloud.fit_words(words_stat.head(4000).itertuples(index=False))
words = words_stat.set_index("segment").to_dict()
wordcloud=wordcloud.fit_words(words["计数"])
bimgColors=ImageColorGenerator(bimg)
plt.axis("off")
plt.imshow(wordcloud.recolor(color_func=bimgColors))
plt.show()

效果如下图：