Python构建词云图

1.词云图

词云图，也叫文字云，是对文本中出现频率较高的“关键词”予以视觉化的展现，词云图过滤掉大量的低频低质的文本信息，使得浏览者只要一眼扫过文本就可领略文本的主旨。

• 先看词云图

2. Python的扩展包wordcloud也可构建词云

• 安装命令

安装过程中会出现很多问题，通过pip安装时，如果出现错误，看看报的什么错误，如果在下载那个包的过程中出现问题，可以通过python包主页搜索那个包下载进行安装

#安装词云
pip install wordcloud

#安装jieba分词
pip install jieba

方法2：下载.whl文件http://www.lfd.uci.edu/~gohlke/pythonlibs/#wordcloud

使用cd命令进入whl文件的路径

运行这条命令：

python -m pip install <filename> 

#导入python画图的库，词云生成库和jieba的分词库
import matplotlib.pyplot as plt
from wordcloud import WordCloud
import jieba

#读取txt格式的文本内容
text_from_file_with_apath = open('JsIndex.txt').read()

#使用jieba进行分词，并对分词的结果以空格隔开
wordlist_after_jieba = jieba.cut(text_from_file_with_apath, cut_all = True)
wl_space_split = " ".join(wordlist_after_jieba)

#对分词后的文本生成词云
my_wordcloud = WordCloud().generate(wl_space_split)

#用pyplot展示词云图。
plt.imshow(my_wordcloud)
plt.axis("off")
plt.show()

入门可以参考文章python词云 wordcloud 入门，安装的时候建议使用依赖包安装，我用命令安装了几次一直超时失败。

3.爬取数据，制作词云图

3.1.爬取简书首页推荐文章标题

• 分析网页结构通过Xpath筛选我们想要的数据有两种方法

• 编写代码

#-*- coding:utf-8 -*-
import urllib,urllib2,re
from lxml import etree

class CrawlJs():
    #定义函数，爬取对应的数据
    def getArticle(self,url):
        print '█████████████◣开始爬取数据'
        my_headers = {
            'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.104 Safari/537.36',
        }
        request = urllib2.Request(url,headers=my_headers)
        content = urllib2.urlopen(request).read()
        return content

    #定义函数，筛选和保存爬取到的数据
    def save(self,content):
        xml = etree.HTML(content)
        datas = xml.xpath('//div[@class="content"]/a/text()')
        print datas
        for data in datas:
            print data
            with open('JsIndex.txt','a+') as f:
                f.write(data.encode('utf-8')+ '\n')
        print '█████████████◣爬取完成！'

#定义主程序接口
if __name__ == '__main__':
    url = 'http://www.jianshu.com/'
    js = CrawlJs()
    content = js.getArticle(url)
    js.save(content)

3.2.制作词云图

• 与模版图片颜色相同的词云

from os import path
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt

from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator

d = path.dirname(__file__)

# Read the whole text.
text = open(path.join(d, 'alice.txt')).read()

# read the mask / color image taken from
# http://jirkavinse.deviantart.com/art/quot-Real-Life-quot-Alice-282261010
alice_coloring = np.array(Image.open(path.join(d, "alice_color.png")))
stopwords = set(STOPWORDS)
stopwords.add("said")

wc = WordCloud(background_color="white", max_words=2000, mask=alice_coloring,
               stopwords=stopwords, max_font_size=40, random_state=42)
# generate word cloud
wc.generate(text)

# create coloring from image
image_colors = ImageColorGenerator(alice_coloring)

# show
plt.imshow(wc, interpolation="bilinear")
plt.axis("off")
plt.figure()
# recolor wordcloud and show
# we could also give color_func=image_colors directly in the constructor
plt.imshow(wc.recolor(color_func=image_colors), interpolation="bilinear")
plt.axis("off")
plt.figure()
plt.imshow(alice_coloring, cmap=plt.cm.gray, interpolation="bilinear")
plt.axis("off")
plt.show()

from os import path
from scipy.misc import imread
import matplotlib.pyplot as plt

from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator

# 获取当前文件路径
# __file__ 为当前文件, 在ide中运行此行会报错,可改为
# d = path.dirname('.')
d = path.dirname(__file__)

# 读取文本 alice.txt 在包文件的example目录下
#内容为
"""
Project Gutenberg's Alice's Adventures in Wonderland, by Lewis Carroll

This eBook is for the use of anyone anywhere at no cost and with
almost no restrictions whatsoever.  You may copy it, give it away or
re-use it under the terms of the Project Gutenberg License included
with this eBook or online at www.gutenberg.org
"""
text = open(path.join(d, 'alice.txt')).read()

# read the mask / color image
# taken from http://jirkavinse.deviantart.com/art/quot-Real-Life-quot-Alice-282261010
# 设置背景图片
alice_coloring = imread(path.join(d, "alice_color.png"))

wc = WordCloud(background_color="white", #背景颜色max_words=2000,# 词云显示的最大词数
mask=alice_coloring,#设置背景图片
stopwords=STOPWORDS.add("said"),
max_font_size=40, #字体最大值
random_state=42)
# 生成词云, 可以用generate输入全部文本(中文不好分词),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(alice_coloring)

# 以下代码显示图片
plt.imshow(wc)
plt.axis("off")
# 绘制词云
plt.figure()
# recolor wordcloud and show
# we could also give color_func=image_colors directly in the constructor
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(alice_coloring, cmap=plt.cm.gray)
plt.axis("off")
plt.show()
# 保存图片
wc.to_file(path.join(d, "名称.png"))