詞雲的使用

使用wordcloud模塊進行生成詞雲。一般可以生成兩種類型的詞雲：

一、默認圖片生成

import warnings
warnings.filterwarnings("ignore")
import jieba    #分詞包
import numpy    #numpy計算包
import codecs   #codecs提供的open方法來指定打開的文件的語言編碼，它會在讀取的時候自動轉換為內部unicode 
import pandas as pd  
import matplotlib.pyplot as plt
%matplotlib inline
import matplotlib
matplotlib.rcParams['figure.figsize'] = (10.0, 5.0)
from wordcloud import WordCloud#詞雲包

#導入娛樂新聞數據，分詞：
df = pd.read_csv("./data/entertainment_news.csv", encoding='utf-8')
df = df.dropna()
content=df.content.values.tolist()
#jieba.load_userdict(u"data/user_dic.txt")
segment=[]
for line in content:
    try:
        segs=jieba.lcut(line)
        for seg in segs:
            if len(seg)>1 and seg!='\r\n':
                segment.append(seg)
    except:
        print line
        continue

#去停用詞
words_df=pd.DataFrame({'segment':segment})
#words_df.head()
stopwords=pd.read_csv("data/stopwords.txt",index_col=False,\
　　　　　　　　quoting=3,sep="\t",names=['stopword'], encoding='utf-8')#quoting=3全不引用
#stopwords.head()
words_df=words_df[~words_df.segment.isin(stopwords.stopword)]

#統計詞頻
words_stat=words_df.groupby(by=['segment'])['segment'].agg({"計數":numpy.size})
words_stat=words_stat.reset_index().sort_values(by=["計數"],ascending=False)
words_stat.head()

#做詞雲
wordcloud=WordCloud(font_path="data/simhei.ttf",background_color="white",\
　　　　max_font_size=80)
word_frequence = {x[0]:x[1] for x in words_stat.head(1000).values}
wordcloud=wordcloud.fit_words(word_frequence)
plt.imshow(wordcloud)

效果：

 

二、生成自定義圖片的詞雲

from scipy.misc import imread
matplotlib.rcParams['figure.figsize'] = (15.0, 15.0)
from wordcloud import WordCloud,ImageColorGenerator
bimg=imread('image/entertainment.jpeg')
wordcloud=WordCloud(background_color="white",mask=bimg,font_path='data/simhei.ttf',max_font_size=200)
word_frequence = {x[0]:x[1] for x in words_stat.head(1000).values}
wordcloud=wordcloud.fit_words(word_frequence)
bimgColors=ImageColorGenerator(bimg)
plt.axis("off")
plt.imshow(wordcloud.recolor(color_func=bimgColors))

效果：