用python处理28万条人人贷数据，告诉你最详细的借款人结构分布情况

目录

一、import 

二、导入数据

三、借款人籍贯分布图

四、性别分布

五、教育程度分布

六、借款人年龄分布

七、借款人职位分布

​八、借款人行业分布

九、借款金额分布图

十、借款人收入分布

十一、婚姻状况分布

十二、车贷情况

十三、房贷情况

---

零、写在前面 

①28W条数据我会尽快传到CSDN的资源里，大家有兴趣的可以自己下载

②文章只是列举最简单的分布情况，比如还可以看看各年龄段学历组成等

③数据里有一条贷款理由，可以画出词云图

④数据里有对各个借款人的信用进行评级，可以尝试使用深度学习等方法训练预测模型

⑤pandas、matplotlib都是较为基础的用法，不做过多注释

⑥爬虫参考代码：人人贷散标爬虫实例进阶-使用异步io_小zhan柯基-CSDN博客、人人贷散标爬虫实例_小zhan柯基-CSDN博客

一、import 

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
            
import matplotlib.ticker as ticker
import mpl_toolkits.axisartist as AA
from mpl_toolkits.axisartist.axislines import SubplotZero
import pylab

import jieba   
from wordcloud import WordCloud

pylab.mpl.rcParams['font.sans-serif'] = ['SimHei'] #显示中文
plt.rcParams['axes.unicode_minus']=False  #用于解决不能显示负号的问题

二、导入数据

①使用read_csv导入数据

②设置列名

③花式索引

④将“id”设置为索引index

⑤去除所有都是nan的数据

data = pd.read_csv("all.csv",encoding="gbk",header=None,parse_dates=True)
data.columns = ["id","借款时间（月）","剩余还款时间（月）","借款金额","notPayInterest","productRepayType",
               "贷款类型","利率","性别","籍贯","出生日期","教育程度","工作单位","行业","公司规模","职位","收入",
               "车贷","汽车数量","婚姻状况","房贷","房子数量","信用等级","none","none","none","借款理由"]

conciseData = data[["id","借款时间（月）","剩余还款时间（月）","借款金额","贷款类型","利率","性别","籍贯","出生日期","教育程度","工作单位","行业","公司规模","职位","收入",
               "车贷","汽车数量","婚姻状况","房贷","房子数量","信用等级","借款理由"]]
conciseData = conciseData.set_index("id")
conciseData = conciseData.dropna(how="all")

三、借款人籍贯分布图

reigon = (conciseData["籍贯"].dropna().apply(lambda x:x.split(":")[0])\
        .apply(lambda x:x.replace("省","").replace("市","").replace("壮族自治区","").replace("古",""))\
            .value_counts()/(len(conciseData["籍贯"].dropna().apply(lambda x:x.split(":")[0])))*100).drop(index=["保密","null","请选择","深圳"])[:31]
reigon = reigon[["上海","北京","浙江","天津","江苏","广东","福建","山东","辽宁",
                "内蒙","重庆","湖南","安徽","江西","海南","湖北","河北","四川","陕西",
                "吉林","宁夏","山西","黑龙江","河南","广西","青海","新疆","云南","贵州","西藏","甘肃"]]
plt.figure(figsize=(16,8))
plt.title("借款人籍贯分布图（按2020年各省人均可支配收入排序）",fontsize=20)
plt.ylabel("百分比/%",size=20)
# plt.tick_params(labelsize=15)
plt.xticks(rotation=45,fontsize=15)
plt.yticks(fontsize=15)
# plt.grid(linestyle=":", color="b", linewidth=1)
plt.bar(reigon.index,reigon,
        color=["grey","gold","darkviolet","turquoise","r","g","b","c",
               "k","darkorange","lightgreen","plum", "tan","khaki", "pink", "skyblue","lawngreen","salmon"])
plt.savefig("借款人籍贯分布图.jpg",dpi=500,bbox_inches = "tight")
                                                                                 

四、性别分布

conciseData["性别"].dropna().value_counts().plot.pie(figsize=(5,5),autopct='%.2f%%',textprops = {'fontsize':17, 'color':'black'})
plt.ylabel("性别分布",fontsize=20)
plt.legend(loc=2, bbox_to_anchor=(1.05,1.0),fontsize=15)
plt.savefig("性别分布图.jpg",dpi=500,bbox_inches = "tight")

 

五、教育程度分布

conciseData["教育程度"] = conciseData["教育程度"].apply(lambda x:x.replace(",","").replace(" ","").replace("短期周转","") \
                                                .replace("","")if isinstance(x,str) else "")
conciseData["教育程度"] = conciseData[~conciseData["教育程度"].isin(["其他借款","投资创业","短期周转","装修借款","请选择","购车借款","专科","大专高中或以下",""])]["教育程度"].dropna()
(conciseData["教育程度"].value_counts()/sum(conciseData["教育程度"].value_counts())).plot.pie(
                    figsize=(5,5),autopct='%.1f%%',textprops = {'fontsize':17, 'color':'black'})

plt.title("教育程度分布图",fontsize=20)
plt.ylabel("")
plt.legend(loc=2, bbox_to_anchor=(1.05,1.0),fontsize=15)
plt.savefig("教育程度分布图.jpg",dpi=500,bbox_inches = "tight")

六、借款人年龄分布

year = conciseData["出生日期"].apply(lambda x:x.split("/")[0]).value_counts()/len(conciseData["出生日期"])*100

year = year.sort_index()[10:-5]
plt.figure(figsize=(16,8))
plt.title("借款人年龄分布图",fontsize=20)
plt.ylabel("百分比/%",size=20)
# plt.tick_params(labelsize=15)
plt.xticks(rotation=45,fontsize=15)
plt.yticks(fontsize=15)
# plt.grid(linestyle=":", color="b", linewidth=1)
plt.bar(year.index,year,
        color=["grey","gold","darkviolet","turquoise","r","g","b","c",
               "k","darkorange","lightgreen","plum", "tan","khaki", "pink", "skyblue","lawngreen","salmon"])
plt.savefig("借款人年龄分布图.jpg",dpi=500,bbox_inches = "tight")

七、借款人职位分布

position = (conciseData["职位"].value_counts()/len(conciseData["职位"])*100)[:25]
    
plt.figure(figsize=(16,8))
plt.title("借款人职位分布图",fontsize=20)
plt.ylabel("百分比/%",size=20)
# plt.tick_params(labelsize=15)
plt.xticks(rotation=60,fontsize=14)
plt.yticks(fontsize=15)
# plt.grid(linestyle=":", color="b", linewidth=1)
plt.bar(position.index,position,
        color=["grey","gold","darkviolet","turquoise","r","g","b","c",
               "k","darkorange","lightgreen","plum", "tan","khaki", "pink", "skyblue","lawngreen","salmon"])
plt.savefig("借款人职位分布图.jpg",dpi=500,bbox_inches = "tight")

八、借款人行业分布

ind = (conciseData["行业"].value_counts()/len(conciseData["职位"])*100)[:15]
plt.figure(figsize=(16,8))
plt.title("借款人行业分布图",fontsize=20)
plt.ylabel("百分比/%",size=20)
# plt.tick_params(labelsize=15)
plt.xticks(rotation=60,fontsize=20)
plt.yticks(fontsize=20)
# plt.grid(linestyle=":", color="b", linewidth=1)
plt.bar(ind.index,ind,
        color=["grey","gold","darkviolet","turquoise","r","g","b","c",
               "k","darkorange","lightgreen","plum", "tan","khaki", "pink", "skyblue","lawngreen","salmon"])
plt.savefig("借款人行业分布图.jpg",dpi=500,bbox_inches = "tight")

九、借款金额分布图

conciseData["借款金额"] = conciseData["借款金额"].apply(lambda x:str(int(x))+"元")
loanAmount = conciseData["借款金额"].value_counts().iloc[:10]/sum(conciseData["借款金额"].value_counts().iloc[:10])*100
# plt.figure(figsize=(16,8))
plt.title("借款金额分布图",fontsize=20)
plt.ylabel("百分比/%",size=20)
plt.xticks(rotation=60,fontsize=20)
plt.yticks(fontsize=15)
# plt.grid(linestyle=":", color="b", linewidth=1)
plt.bar(loanAmount.index,loanAmount,
        color=["grey","gold","darkviolet","turquoise","r","g","b","c",
               "k","darkorange","lightgreen","plum", "tan","khaki", "pink", "skyblue","lawngreen","salmon"])
plt.savefig("借款人金额分布图.jpg",dpi=500,bbox_inches = "tight")

十、借款人收入分布

salary = (conciseData["收入"].value_counts()[:7]/sum(conciseData["收入"].value_counts()[:7]))*100
salary = salary[["1000元以下","1001-2000元","2000-5000元","5000-10000元","10000-20000元","20000-50000元","50000元以上"]]                                 
# plt.figure(figsize=(16,8))
plt.title("借款人收入分布图",fontsize=20)
plt.ylabel("百分比/%",size=20)
# plt.tick_params(labelsize=15)
plt.xticks(rotation=60,fontsize=20)
plt.yticks(fontsize=15)
# plt.grid(linestyle=":", color="b", linewidth=1)
plt.bar(salary.index,salary,
        color=["grey","gold","darkviolet","turquoise","r","g","b","c",
               "k","darkorange","lightgreen","plum", "tan","khaki", "pink", "skyblue","lawngreen","salmon"])
plt.savefig("借款人收入分布图.jpg",dpi=500,bbox_inches = "tight")

十一、婚姻状况分布

conciseData["婚姻状况"].dropna().value_counts().plot.pie(figsize=(5,5),autopct='%.1f%%',textprops = {'fontsize':17, 'color':'black'})
plt.title("婚姻状况分布图",fontsize=20)
plt.ylabel("")
plt.legend(loc=2, bbox_to_anchor=(1.05,1.0),fontsize=15)
plt.savefig("婚姻状况分布图.jpg",dpi=500,bbox_inches = "tight")

十二、车贷情况

conciseData["车贷"].dropna().value_counts().plot.pie(figsize=(5,5),autopct='%.1f%%',textprops = {'fontsize':17, 'color':'black'})
plt.title("车贷情况分布图",fontsize=20)
plt.ylabel("")
plt.legend(loc=2, bbox_to_anchor=(1.05,1.0),fontsize=15)
plt.savefig("车贷情况分布图.jpg",dpi=500,bbox_inches = "tight")

十三、房贷情况

conciseData["房贷"].dropna().value_counts().plot.pie(figsize=(5,5),autopct='%.1f%%',textprops = {'fontsize':17, 'color':'black'})
plt.title("房贷情况分布图",fontsize=20)
plt.ylabel("")
plt.legend(loc=2, bbox_to_anchor=(1.05,1.0),fontsize=15)
plt.savefig("房贷情况分布图.jpg",dpi=500,bbox_inches = "tight")