python招聘网站爬虫与seaborn可视化职业前景分析

# coding: utf-8 # In[196]: import pandas as pd import re import numpy as np a=pd.read_csv('F:\\xiaofang\\1.csv') t=[] for i in a['salary']: t1=re.sub('K','',str(i)) t2=re.sub('k','',t1).split('-') t.append(np.mean([int(tt) for tt in t2])) a.loc[:,'salary_average']=t #print(a.loc[:,'salary_average']) y=-1 for i in a['workYear']: y+=1 pat='.*\-.*' p=re.compile(pat) p2=re.compile('.*年[以上|以下].*') p3=re.compile('.*[应届毕业生|不限].*') if(p.match(i)): t1=re.sub('年','',str(i)) t2=re.sub('y','',t1).split('-') vb=np.mean([int(tt) for tt in t2]) a.loc[y,'workyear_average']=vb elif(p2.match(i)): t1=re.sub('年以上','',str(i)) t2=re.sub('年以下','',t1) vb=np.mean([int(tt) for tt in t2]) a.loc[y,'workyear_average']=vb elif(p3.match(i)): t1=re.sub('应届毕业生','0',str(i)) t2=re.sub('不限','0',t1) vb=np.mean([int(tt) for tt in t2]) a.loc[y,'workyear_average']=vb else: a.loc[y,'workyear_average']=0 #print(a['workyear_average']) import seaborn as sns import matplotlib.pyplot as plt #1. 薪酬分布 fig=plt.figure() sns.distplot(a['salary_average'].tolist()) fig.savefig("F:\\tupian\\xinchou.png") print("薪酬分布") print(a['salary_average'].describe()) import operator # 第一类型类别占比+pie b=[] for t in a['firstType']: b.extend(t.split('|')) print(b) t=set(b) dic={} for i in t: dic[i]=b.count(i) print("企业招聘类型数目：") print(dic) fig=plt.figure() #print(dic.values()) #sum=np.sum(list(dic.values())) ddd=[i/380.0 for i in list (dic.values())] plt.rcParams['font.sans-serif']=['SimHei'] plt.rcParams['axes.unicode_minus'] = False dic2=sorted(dic.items(),key=operator.itemgetter(1),reverse=True) dic2=pd.DataFrame(dic2,columns=['key','values']) print("企业类型描述：") print(dic2.describe()) sns.barplot(dic2['key'][:9], dic2['values'][:9]) plt.xlabel('一级职业分类') plt.ylabel('数量') fig.savefig("F:\\tupian\\gongsileixing.png") b2=[] po=[] for t in a['secondType']: b2.extend(t.split('|')) print(b2) t2=set(b2) dic2={} dic33={} for i in t2: po=[] dic2[i]=b2.count(i) for t in a['secondType']: if i in (t.split('|')): po.append(True) else: po.append(False) dic33[i]=a[po]['salary_average'].mean() print("职业类型：") print(dic2) print("职业平均薪酬：") print(dic33) fig=plt.figure() plt.rcParams['font.sans-serif']=['SimHei'] plt.rcParams['axes.unicode_minus'] = False dic2=sorted(dic2.items(),key=operator.itemgetter(1),reverse=True) dic2=pd.DataFrame(dic2,columns=['key','values']) #print("职业2数目描述") #print(dic2.describe()) sns.barplot(dic2['key'][:9], dic2['values'][:9]) plt.xlabel('二级职业分类',fontsize=15) plt.ylabel('数量',fontsize=15) fig.savefig("F:\\tupian\\zhiyebar.png") fig=plt.figure() plt.rcParams['font.sans-serif']=['SimHei'] plt.rcParams['axes.unicode_minus'] = False dic33=sorted(dic33.items(),key=operator.itemgetter(1),reverse=True) dic33=pd.DataFrame(dic33,columns=['key','values']) print("职业薪酬描述") print(dic33.describe()) sns.barplot(dic33['key'][:9], dic33['values'][:9]) plt.xlabel('二级职业分类',fontsize=15) plt.ylabel('工资',fontsize=15) fig.savefig("F:\\tupian\\zhiyexinchou.png") b3=[] dic2={} for t in a['industryField']: b3.extend(re.split('[,、 ]', str(t))) print("工业领域：") print(b3) t3=set(b3) dic3={} dic333={} for i in t3: dic3[i]=b3.count(i) print("工业领域统计") print(dic3) fig=plt.figure() plt.rcParams['font.sans-serif']=['SimHei'] plt.rcParams['axes.unicode_minus'] = False dic2=sorted(dic3.items(),key=operator.itemgetter(1),reverse=True) dic2=pd.DataFrame(dic2,columns=['key','values']) print("工业领域描述") print(dic2.describe()) sns.barplot(dic2['key'][:9], dic2['values'][:9]) plt.xlabel('领域') plt.ylabel('数量') fig.savefig("F:\\tupian\\gongyelingyu.png") dic2={} for i in t3: po=[] dic2[i]=b3.count(i) for t in a['industryField']: if i in (re.split('[,、 ]', str(t))): po.append(True) else: po.append(False) dic333[i]=a[po]['salary_average'].mean() print("工业平均薪酬：") print(dic333) fig=plt.figure() plt.rcParams['font.sans-serif']=['SimHei'] plt.rcParams['axes.unicode_minus'] = False dic333=sorted(dic333.items(),key=operator.itemgetter(1),reverse=True) dic333=pd.DataFrame(dic333,columns=['key','values']) print("工业薪酬描述") print(dic333.describe()) sns.barplot(dic333['key'][:9], dic333['values'][:9]) plt.xlabel('工业领域分类',fontsize=15) plt.ylabel('工资',fontsize=15) fig.savefig("F:\\tupian\\gongyexinchou.png") print("工作经验需求：") print(a['workYear'].describe()) h={} h2={} for i in set(a['workYear']): h[i]=(list(a['workYear']).count(i)) h2[i]=(a[a['workYear']==i]['salary_average']).mean() print("工作经验统计") print(h) fig=plt.figure() plt.pie(list(h.values()),labels=list(h.keys())) fig.savefig("F:\\tupian\\gongzuopie.png") plt.figure() print("工作经验薪酬") print(h2) fig=plt.figure() sns.barplot(list(h2.keys()),list(h2.values()),order=['应届毕业生','1年以下','1-3年','3-5年','5-10年','10年以上']) fig.savefig("F:\\tupian\\jingyanxinchou.png") plt.figure() print("工作经验要求描述: ") fig=plt.figure() print(a['workyear_average'].describe()) sns.swarmplot(a['workYear'],a['salary_average']) plt.ylabel('工资',fontsize=15) plt.xlabel('工作经验',fontsize=15) fig.savefig("F:\\tupian\\gongzixin.png") fig=plt.figure() sns.violinplot(a['workyear_average'],a['salary_average']) fig.savefig("F:\\tupian\\violinjingyan.png") fig=plt.figure() sns.boxplot(a['workYear'],a['salary_average'],order=['应届毕业生','1年以下','1-3年','3-5年','5-10年','10年以上']) fig.savefig("F:\\tupian\\boxjingyan.png") b3=[] b3=list(a['education']) print(b3) t3=set(b3) dic3={} h3={} for i in t3: dic3[i]=b3.count(i) print("教育经历：") print(dic3) for i in set(a['education']): h3[i]=(a[a['education']==i]['salary_average']).mean() print("教育经历薪酬所有") print(h3) fig=plt.figure() sns.barplot(list(h3.keys()),list(h3.values()),order=['大专','不限','本科','硕士']) fig.savefig("F:\\tupian\\jiaoyuxinchoubar.png") plt.rcParams['font.sans-serif']=['SimHei'] plt.rcParams['axes.unicode_minus'] = False dic2=sorted(dic3.items(),key=operator.itemgetter(1),reverse=True) dic2=pd.DataFrame(dic2,columns=['key','values']) print("教育经历描述：") print(dic2.describe()) #sns.barplot(dic2['key'][:9], dic2['values'][:9]) fig=plt.figure() plt.pie(list(dic3.values()),labels=list(dic3.keys())) plt.xlabel('学历') plt.ylabel('数量') plt.figure() sns.violinplot(a['education'],a['salary_average']) fig.savefig("F:\\tupian\\jiaoyuliviolin.png") fig=plt.figure() sns.boxplot(a['education'],a['salary_average'],order=['大专','不限','本科','硕士']) fig.savefig("F:\\tupian\\jiaobox.png") a.to_excel("F:\\xiaofang\\4.xls") plt.show() # In[197]: b=[] for t in a['positionAdvantage']: b.extend(re.split('[,，、]',t)) print(b) t=set(b) dic={} for i in t: dic[i]=b.count(i) print("福利") print(dic) fig=plt.figure(figsize=(8,8)) #print(dic.values()) #sum=np.sum(list(dic.values())) #ddd=[i/380.0 for i in list (dic.values())] plt.rcParams['font.sans-serif']=['SimHei'] plt.rcParams['axes.unicode_minus'] = False dic2=sorted(dic.items(),key=operator.itemgetter(1),reverse=True) dic2=pd.DataFrame(dic2,columns=['key','values']) print("福利描述：") print(dic2.describe()) sns.barplot(dic2['key'][:9], dic2['values'][:9]) plt.xlabel('福利关键词') plt.ylabel('数量') fig.savefig("F:\\tupian\\fuli.png") # In[ ]: