【NLP】生成词云

from imageio import imread
import warnings
warnings.filterwarnings("ignore")
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 as pd  
import matplotlib.pyplot as plt
%matplotlib inline
import matplotlib
matplotlib.rcParams['figure.figsize'] = (10.0, 5.0)
from wordcloud import WordCloud#词云包
#词云大小
matplotlib.rcParams['figure.figsize'] = (15.0, 15.0)
 
from wordcloud import WordCloud,ImageColorGenerator
 
def createSuperWordCloud(text_path,image_path):
#"./data/entertainment_news.csv"
    df = pd.read_csv(text_path, encoding='utf-8')
    # 去掉空行
    df = df.dropna()
#df.head()
    #将数据变成List
    content=df.content.values.tolist()
    segment=[]
    for line in content:
        try:
            #列表
            segs=jieba.lcut(line) 
            for seg in segs:
                #判断是否为空或者是不是换行词
                if len(seg)>1 and seg!='\r\n':
                    segment.append(seg)
        except:
            print(line)
            continue
    words_df=pd.DataFrame({
    'segment':segment})
 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

#先抽取在停用词里面的分词词组，然后再将它去掉
    words_df=words_df[~words_df.segment.isin(stopwords.stopword)]
    # 这一块是个难点,词频统计
    words_stat = words_df.groupby('segment').agg(计数=pd.NamedAgg(column='segment', aggfunc='size')).reset_index().sort_values(
    by='计数', ascending=False)
    #读取图片生成背景
    bimg=imread(image_path)
    # 生成词云
wordcloud=WordCloud(background_color="white",mask=bimg,font_path='data/simhei.ttf',max_font_size=200)
    #生成词频
    word_frequence = {
    x[0]:x[1] for x in words_stat.head(1000).values}
    wordcloud=wordcloud.fit_words(word_frequence)
    # 重新上色
    bimgColors=ImageColorGenerator(bimg)
    # 去掉off
    plt.axis("off")
    #重新填写背景
    plt.imshow(wordcloud.recolor(color_func=bimgColors))

 # 调用 
createSuperWordCloud("./data/entertainment_news.csv",'image/entertainment.jpeg')

结果