Python2.7+wordcloud+jieba绘制中文词云

# ciyun1.py  这段代码可以生成词云，但是生成的词云中已经没有完整的词了，但是这段代码中有我初次学习的内容，所以将它贴出来，日后可以不断的改进。

# __*__ encoding:utf-8 __*__

import matplotlib.pyplot as plt
from scipy.misc import imread
from wordcloud import WordCloud
import jieba, codecs
from collections import Counter

jieba.load_userdict("C:\Users\Administrator\Desktop\\fire_word.txt")

fo = open('C:\Users\Administrator\Desktop\\fire_safe_event_clearned.txt', 'ab+')
safevent = fo.read()

mywordlist = []
wordlist = jieba.cut(safevent, cut_all=True)
liststr = " ".join(wordlist)

f_stop = open('C:\Users\Administrator\Desktop\stop_word.txt','r')
try:
    f_stop_text = f_stop.read()
finally:
    f_stop.close()
f_stop_seg_list = f_stop_text.split('\n')
for myword in liststr.split(' '):
    if not(myword.strip() in f_stop_seg_list) and len(myword.strip())>1:
         mywordlist.append(myword)
text_jieba = ' '.join(mywordlist)
c = Counter(text_jieba)  # 计数
word = c.most_common(800)  # 取前500

bg_pic = imread('D:\Pictures\\falling_background.png')
wc = WordCloud(
    font_path='C:\Windows\Fonts\SIMYOU.TTF',  # 指定中文字体
    background_color='white',  # 设置背景颜色
    max_words=2000,  # 设置最大显示的字数
    mask=bg_pic,  # 设置背景图片
    max_font_size=200,  # 设置字体最大值
    random_state=20  # 设置多少种随机状态，即多少种配色
)
wc.generate_from_frequencies(dict(word))  # 生成词云


wc.to_file('result.jpg')

# show
plt.imshow(wc)
plt.axis("off")
plt.figure()
plt.imshow(bg_pic, cmap=plt.cm.gray)
plt.axis("off")
plt.show()

 

 

 

下段代码参考别人写的使用wordcloud库和jieba库绘制中文词云代码：

# __*__ encoding:utf-8 __*__

from os import path
from scipy.misc import imread
import matplotlib.pyplot as plt
import jieba
# jieba.load_userdict("txt\userdict.txt")
# 添加用户词库为主词典,原词典变为非主词典
from wordcloud import WordCloud, ImageColorGenerator

d = path.dirname(__file__)

stopwords = {}
isCN = 1 #默认启用中文分词
back_coloring_path = "D:\Pictures\\falling_background.png" # 设置背景图片路径
text_path = 'C:\Users\Administrator\Desktop\\fire_safe_event_clearned.txt' #设置要分析的文本路径
font_path = 'D:\Fonts\simkai.ttf' # 为matplotlib设置中文字体路径没
stopwords_path = 'C:\Users\Administrator\Desktop\\stop_word.txt' # 停用词词表
imgname1 = "WordCloudDefautColors.png" # 保存的图片名字1(只按照背景图片形状)

back_coloring = imread(path.join(d, back_coloring_path))# 设置背景图片

# 设置词云属性
wc = WordCloud(font_path=font_path,  # 设置字体
               background_color="white",  # 背景颜色
               max_words=2000,  # 词云显示的最大词数
               mask=back_coloring,  # 设置背景图片
               max_font_size=100,  # 字体最大值
               random_state=42,
               width=1000, height=860, margin=2,# 设置图片默认的大小,但是如果使用背景图片的话,那么保存的图片大小将会按照其大小保存,margin为词语边缘距离
               )

# 添加自己的词库分词
def add_word(list):
    for items in list:
        jieba.add_word(items)

text = open(path.join(d, text_path)).read()

def jiebaclearText(text):
    mywordlist = []
    seg_list = jieba.cut(text, cut_all=False)
    liststr="/ ".join(seg_list)
    f_stop = open(stopwords_path)
    try:
        f_stop_text = f_stop.read( )
        f_stop_text=unicode(f_stop_text,'utf-8')
    finally:
        f_stop.close( )
    f_stop_seg_list=f_stop_text.split('\n')
    for myword in liststr.split('/'):
        if not(myword.strip() in f_stop_seg_list) and len(myword.strip())>1:
            mywordlist.append(myword)
    return ''.join(mywordlist)

if isCN:
    text = jiebaclearText(text)

# 生成词云, 可以用generate输入全部文本(wordcloud对中文分词支持不好,建议启用中文分词),也可以我们计算好词频后使用generate_from_frequencies函数
wc.generate(text)
# wc.generate_from_frequencies(txt_freq)
# txt_freq例子为[('词a', 100),('词b', 90),('词c', 80)]
# 从背景图片生成颜色值
image_colors = ImageColorGenerator(back_coloring)

plt.figure()
# 以下代码显示图片
plt.imshow(wc)
plt.axis("off")
plt.show()
# 绘制词云

# 保存图片
wc.to_file(path.join(d, imgname1))

image_colors = ImageColorGenerator(back_coloring)

plt.imshow(wc.recolor(color_func=image_colors))
plt.axis("off")
# 绘制背景图片为颜色的图片
plt.figure()
plt.imshow(back_coloring, cmap=plt.cm.gray)
plt.axis("off")
plt.show()
# 保存图片
wc.to_file(path.join(d, imgname2))