pandas 数据分析部分

pandas数据分析部分共8题

import pandas as pd
df =pd.read_csv("qiancheng.csv")
print(df.shape)
df = df[~df['work_name'].str.contains('-')]#~取反
df = df[~df['work_name'].str.contains('/')]
df = df[~df['work_name'].str.contains('\(')]
df = df[~df['work_name'].str.contains('（')]df = df[~df['work_location'].str.contains('异地招聘')]
df=df.dropna(subset=['work_location'])
df = df[~df['work_location'].str.contains('空')]
df = df.reset_index().drop('index', axis=1)#清洗 链接起来去空的数据
salary_min=[]
salary_max=[]
for i in range(len(df)):salary=df['salary'][i].split('-')if '万'in salary[1]:salary1=salary[1].split('万')[0]salary_min.append(str(float(salary[0])*10000)+"元/月")salary_max.append(str(float(salary1) * 10000)+"元/月")else:salary1 = salary[1].split('千')[0]salary_min.append(str(float(salary[0]) * 1000) + "元/月")salary_max.append(str(float(salary1) * 1000) + "元/月")
df['salary_min']=salary_min
df['salary_max']=salary_max
del df['salary']
#无   初中及以下 高中/中技/中专   大专  本科  硕士  博士
df1=df[df["edu_level"].str.contains("无")|df["edu_level"].str.contains("空")]
df1['edu_level']="无"
df2=df[df["edu_level"].str.contains("初中及以下")|df["edu_level"].str.contains("高中")|df["edu_level"].str.contains("中技")|df["edu_level"].str.contains("中专")]
df2['edu_level']="初中及以下 高中/中技/中专"
df3=df[df["edu_level"].str.contains("大专")]
df3['edu_level']="大专"
df4=df[df["edu_level"].str.contains("本科")]
df4['edu_level']="本科"
df5=df[df["edu_level"].str.contains("硕士")]
df5['edu_level']="硕士"
df6=df[df["edu_level"].str.contains("博士")]
df6['edu_level']="博士"
df=pd.concat([df1,df2,df2,df4,df5,df6],ignore_index=True)
people_list=[]
for i in range(len(df)):people=df['work_require_people'][i].split('招')[1]people=people.split('人')[0]if '若干'in people:people_list.append(1)else:people_list.append(people)
df['work_require_people']=people_listexp_list=[]
for i in range(len(df)):exp=df['work_exp'][i]if '年' in exp:exp=exp.split('年')[0]exp=exp.split('-')if len(exp)==2:exp_list.append(exp[0])else:exp_list.append(exp[0])else:exp_list.append(0)
df['work_exp']=exp_listcompany_industry_list=[]
for i in range(len(df)):company_industry=df['company_industry'][i]if '/' in company_industry:company_industry=company_industry.split('/')[0]company_industry_list.append(company_industry)else:company_industry_list.append(company_industry)
df['company_industry']=company_industry_list
print(df)

本文来自互联网用户投稿，文章观点仅代表作者本人，不代表本站立场，不承担相关法律责任。如若转载，请注明出处。 如若内容造成侵权/违法违规/事实不符，请点击【内容举报】进行投诉反馈！