create wordcloud with chinese

Wordcloud is a very good tool, but if you want to create Chinese wordcloud only wordcloud is not enough. The file shows how to use wordcloud with Chinese. First, you need a Chinese word segmentation library jieba, jieba is now the most elegant the most popular Chinese word segmentation tool in python. You can use ‘PIP install jieba’. To install it. As you can see, at the same time using wordcloud with jieba very convenient

  • wordcloud cn
  • wordcloud cn


Building prefix dict from the default dictionary ...
Dumping model to file cache /tmp/jieba.cache
Loading model cost 1.544 seconds.
Prefix dict has been built successfully.

<wordcloud.wordcloud.WordCloud object at 0x7f4b76d4efd0>

import jieba
# Setting up parallel processes :4 ,but unable to run on Windows
from os import path
from imageio import imread
import matplotlib.pyplot as plt
import os
# jieba.load_userdict("txt\userdict.txt")
# add userdict by load_userdict()
from wordcloud import WordCloud, ImageColorGenerator

# get data directory (using getcwd() is needed to support running example in generated IPython notebook)
d = path.dirname(__file__) if "__file__" in locals() else os.getcwd()

stopwords_path = d + '/wc_cn/stopwords_cn_en.txt'
# Chinese fonts must be set
font_path = d + '/fonts/SourceHanSerif/SourceHanSerifK-Light.otf'

# the path to save worldcloud
imgname1 = d + '/wc_cn/LuXun.jpg'
imgname2 = d + '/wc_cn/LuXun_colored.jpg'
# read the mask / color image taken from
back_coloring = imread(path.join(d, d + '/wc_cn/LuXun_color.jpg'))

# Read the whole text.
text = open(path.join(d, d + '/wc_cn/CalltoArms.txt')).read()

# if you want use wordCloud,you need it
# add userdict by add_word()
userdict_list = ['阿Q', '孔乙己', '单四嫂子']

# The function for processing text with Jieba
def jieba_processing_txt(text):
    for word in userdict_list:

    mywordlist = []
    seg_list = jieba.cut(text, cut_all=False)
    liststr = "/ ".join(seg_list)

    with open(stopwords_path, encoding='utf-8') as f_stop:
        f_stop_text =
        f_stop_seg_list = f_stop_text.splitlines()

    for myword in liststr.split('/'):
        if not (myword.strip() in f_stop_seg_list) and len(myword.strip()) > 1:
    return ' '.join(mywordlist)

wc = WordCloud(font_path=font_path, background_color="white", max_words=2000, mask=back_coloring,
               max_font_size=100, random_state=42, width=1000, height=860, margin=2,)


# create coloring from image
image_colors_default = ImageColorGenerator(back_coloring)

# recolor wordcloud and show
plt.imshow(wc, interpolation="bilinear")

# save wordcloud
wc.to_file(path.join(d, imgname1))

# create coloring from image
image_colors_byImg = ImageColorGenerator(back_coloring)

# show
# we could also give color_func=image_colors directly in the constructor
plt.imshow(wc.recolor(color_func=image_colors_byImg), interpolation="bilinear")
plt.imshow(back_coloring, interpolation="bilinear")

# save wordcloud
wc.to_file(path.join(d, imgname2))

Total running time of the script: ( 0 minutes 14.144 seconds)

Gallery generated by Sphinx-Gallery