Python词云生成（简单整理，不适合作为学习教程）

环境：Pycharm

包：WordCloud、numpy、jieba (文本为中文时需要)

1.生成英文词云

from wordcloud import WordCloud
import  PIL.Image as  image

with open("E:test.txt") as fp:#此处的txt文件保存格式为ANSI
    text=fp.read()
    WordCloud=WordCloud().generate(text)
    image_produce=WordCloud.to_image()
    image_produce.show()

效果图：

2.生成指定形状的词云图

代码：

from wordcloud import WordCloud
import  PIL.Image as  image
import numpy as np

with open("E:test.txt") as fp:#此处的txt文件保存格式为ANSI
    text=fp.read()
    mask=np.array(image.open("E:cd7c6fbe8ec0778bac0f3ffed304f7e7.jpg"))#导入生成图片的形状
    WordCloud=WordCloud(mask=mask).generate(text)
    image_produce=WordCloud.to_image()
    image_produce.show()

效果图：

3.生成中文的词云图

代码：

from wordcloud import WordCloud
import PIL .Image as image
import numpy as np
import jieba
import sys

def trans_CN(text):
    word_list = jieba.cut(text)
    result = " ".join(word_list)
    return result;


with open("E:test.txt") as fp:
    text = fp.read()
    text  = trans_CN(text)
    mask = np.array(image.open("E:cd7c6fbe8ec0778bac0f3ffed304f7e7.jpg"))
    wordcloud = WordCloud(
        mask=mask,
        font_path = "C:\\Windows\\Fonts\\msyh.ttc" #图片上的显示的字体
    ).generate(text)
    image_produce = wordcloud.to_image()
    image_produce.show()

 

效果：（数据来源：2020年一号文件来源）

代码：

from wordcloud import WordCloud
import matplotlib.pyplot as plt
import  jieba                

path_txt='E:test.txt'
f = open(path_txt,'r',encoding='UTF-8').read()

# 结巴分词，生成字符串，wordcloud无法直接生成正确的中文词云
cut_text = " ".join(jieba.cut(f))

wordcloud = WordCloud(
   #设置字体，不然会出现口字乱码，文字的路径是电脑的字体一般路径，可以换成别的
   font_path="C:/Windows/Fonts/simfang.ttf",
   #设置了背景，宽高
   background_color="white",width=1000,height=880).generate(cut_text)

plt.imshow(wordcloud, interpolation="bilinear")
plt.axis("off")
plt.show()

 效果图：（数据来源：2004--2020一号文件文本）

 

参考博客：https://www.cnblogs.com/ZaraNet/p/10136589.html