接著上篇的說的，爬取了大數據相關的職位信息，http://www.17bigdata.com/jobs/。

# -*- coding: utf-8 -*-
"""
Created on Thu Aug 10 07:57:56 2017

@author: lenovo
"""

from wordcloud import WordCloud
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import jieba

def cloud(root,name,stopwords):
    filepath = root +‘
 
\\‘ + name
    f = open(filepath,‘r‘,encoding=‘utf-8‘)
    txt = f.read()
    f.close()
    cut = jieba.cut(txt)
    words = []
    for i in cut:
        words.append(i)
    df = pd.DataFrame({‘words‘:words})
    s= df.groupby(df[‘words‘])[‘words‘].agg([(‘size‘,np.size)]).sort_values(by=‘size‘,ascending=False)
    s 
 
= s[~s.index.isin(stopwords[‘stopword‘])].to_dict()
    wordcloud = WordCloud(font_path =r‘E:\Python\machine learning\simhei.ttf‘,background_color=‘black‘)
    wordcloud.fit_words(s[‘size‘])
    plt.imshow(wordcloud)
    pngfile = root +‘\\‘ + name.split(‘.‘)[0] + ‘.png‘
    wordcloud.to_file(pngfile)
    
 
import os 
jieba.load_userdict(r‘E:\Python\machine learning\NLPstopwords.txt‘)
stopwords = pd.read_csv(r‘E:\Python\machine learning\StopwordsCN.txt‘,encoding=‘utf-8‘,index_col=False)
for root,dirs,file in os.walk(r‘E:\職位信息‘):
    for name in file:
        if name.split(‘.‘)[-1]==‘txt‘:
            print(name)
            cloud(root,name,stopwords)        

詞雲如圖所示：

可以看出有些噪聲詞沒能被去除，比如相關、以上學歷等無效詞匯。本想通過DF判斷停用詞，但是我爬的時候沒顧及到這個問題，外加本身記錄數也不高，就沒再找職位信息的停用詞。當然也可看出算法和經驗是很重要的。加油

python生成職業要求詞雲