[Python知识库]python nlp系列-画词云图（中文）

• 数据读入
• 构建停用词表
• 自定义分词词典
• 对文本分词，去掉单字,数字,去掉停用词
• 把词和词频保存在本地cipin.csv里
• 可视化，横坐标是关键词,纵坐标是关键词对应的频数
• 绘制词云图

#!/usr/bin/python
# -*- coding: utf-8 -*-
"""
@author:
@contact:
@time:
@context:python nlp系列-画词云图（中文）
                数据读入
                构建停用词表
                自定义分词词典
                对文本分词，去掉单字,数字,去掉停用词
                把词和词频保存在本地cipin.csv里
                可视化，横坐标是关键词,纵坐标是关键词对应的频数
                绘制词云图
"""
from wordcloud import WordCloud
import jieba.posseg as jp, jieba,matplotlib.pyplot as plt
from pandas.core.frame import DataFrame


# 中文的正常显示
plt.rcParams[ 'font.sans-serif'] = [ 'Microsoft YaHei']


#数据读入
text = open('data.txt',encoding='utf-8',errors='ignore').read()


# 构建停用词表
def get_custom_stopwords(stop_words_file):
    with open(stop_words_file, encoding='utf-8') as f:
        stopwords = f.read()
    stopwords_list = stopwords.split('\n')
    custom_stopwords_list = [i for i in stopwords_list]
    return custom_stopwords_list
stop_words_file = "stopwords.txt"
stopwords = get_custom_stopwords(stop_words_file)


# 自定义分词词典
fenci_name = open('fenci_name.txt',encoding='utf-8',errors='ignore').read().split('\n')
for line in fenci_name:
    jieba.add_word(line)


# 对文本分词，去掉单字,数字,去掉停用词
words = [word.word for word in jp.cut(text) if len(word.word) > 1
             and word.word.isdigit() != True and  word.word not in stopwords]


# wordslist存储的是词
wordslist = list(set(words))

# cipin存储的是词频
cipin=[]
for item in wordslist:
    cipin.append(words.count(item))

# 词和词频合一起
dict = {"words": wordslist,"cipin": cipin}
df = DataFrame(dict)

# 按照词频降序排
df=df.sort_values(by="cipin" , ascending=False)

# 把词和词频保存在本地cipin.csv里
df.to_csv('cipin.csv')


# 可视化，横坐标是关键词,纵坐标是关键词对应的频数
p1 = plt.bar(bottom=df.iloc[[0,1,2,3,4,5,6,7,8,9],:]['words'],
             width=df.iloc[[0,1,2,3,4,5,6,7,8,9],:]['cipin'],
             color='steelblue', x=0,height=0.5, orientation='horizontal')
plt.title( '关键词和词频条形图')# 设置坐标轴标签和标题
plt.xlabel( '词频')
plt.ylabel( '关键词')
plt.show()


# 绘制词云图
result = " ".join(words)# 以空格拼接起来
wc = WordCloud(
    font_path='simhei.ttf',
    max_words=20000,
    collocations=False,
    mask=plt.imread('4.jpg') #背景图片
)
wc.generate(result)

wc.to_file('2.jpg')    #图片保存

plt.figure('陈奕迅')   ##显示图片：显示的名字
plt.imshow(wc)

plt.axis('off')        #关闭坐标

plt.show()

关键词和词频图：

词云图：