https://dblab.xmu.edu.cn/blog/2707/
实验过程
数据预处理
本次实验数据集来自和鲸社区的信用卡评分模型构建数据,以数据集cs-training.csv为分析主体,其中共有15万条记录,11列属性。
每个数据包含以下字段:
字段名称 字段含义 例子
(1)SeriousDlqin2yrs 是否逾期 0,1
(2)RevolvingUtilizationOfUnsecuredLines 信用卡和个人信贷额度的总余额 0.766126609
(3)Age 年龄 45,20,30
(4)NumberOfTime30-59DaysPastDueNotWorse 借款人逾期30-59天的次数 0,2,3
(5)DebtRatio 负债比率 0.802982129
(6)MonthlyIncome 月收入 9120,3000
(7)NumberOfOpenCreditLinesAndLoans 未偿还贷款数量 ,0,4,13
(8)NumberOfTimes90DaysLate 借款人逾期90天以上的次数 0,1,3
(9)NumberRealEstateLoansOrLines 房地产贷款的数量 3,6
(10)NumberOfTime60-89DaysPastDueNotWorse 借款人逾期60-89天的次数 0,3
(11)NumberOfDependents 家庭中的家属人数 0,1,3
本次实验采用pandas库对数据进行预处理。在实验中,不对信用卡和个人信贷额度的总余额、负债比率、未偿还贷款数量、逾期90天以上的次数这4个属性进行处理分析。
具体处理步骤如下:
(1)读取数据
(2)查看数据是否具有重复值,去除重复值
(3)查看各字段缺失率,缺失值以均值填充
(4)选取要研究的属性,删除不研究的属性
(5)保存文件到本地
使用代码文件data_preprocessing.py对数据预处理,运行data_preprocessing.py文件的步骤如下:
import pandas as pd
# 读取数据
df = pd.read_csv("~/Desktop/cs-training.csv")
# 去除重复值
df.duplicated()
df.drop_duplicates()
# 查看各字段缺失率
df.info()
# 缺失值按均值填充
for col in list(df.columns[df.isnull().sum() > 0]):
mean_val = df[col].mean()
df[col].fillna(mean_val, inplace=True)
# 删除不分析的列
columns = ["RevolvingUtilizationOfUnsecuredLines","DebtRatio","NumberOfOpenCreditLinesAndLoans","NumberOfTimes90DaysLate"]
df.drop(columns,axis=1,inplace=True)
# 保存到本地
df.to_csv("~/OverDue/data.csv")
将文件上传至HDFS文件系统
# 启动Hadoop
cd /usr/local/hadoop
./sbin/start-dfs.sh
# 在HDFS文件系统中创建/OverDue目录
./bin/hdfs dfs -mkdir /data
# 上传文件到HDFS文件系统中
./bin/hdfs dfs -put ~/OverDue/data.csv /OverDue/data.csv
使用Spark对数据处理分析
我们将采用Python编程语言和Spark大数据框架对数据集“data.csv”进行处理分析,具体步骤如下:
(1)读取HDFS文件系统中的数据文件,生成DataFrame
(2)修改列名
(3)本次信用卡逾期的总体统计
(4)年龄与本次信用卡逾期的结合统计
(5)两次逾期记录与本次信用卡逾期的结合统计
(6)房产抵押数量与本次信用卡逾期的结合统计
(7)家属人数与本次信用卡逾期的结合统计
(8)月收入与本次信用卡逾期的结合统计
(9)将统计数据返回给数据可视化文件data_web.py
./bin/hdfs dfs -put ~/OverDue/data1.csv /user/hadoop
代码文件data_analysis.py的内容如下:
from pyspark.sql import SparkSession
from pyspark import SparkContext,SparkConf
from pyspark.sql import Row
from pyspark.sql.types import *
from pyspark.sql import functions
def analyse(filename):
# 读取数据
spark = SparkSession.builder.config(conf = SparkConf()).getOrCreate()
df = spark.read.format("csv").option("header","true").load(filename)
# 修改列名
df = df.withColumnRenamed('SeriousDlqin2yrs','y')
df = df.withColumnRenamed('NumberOfTime30-59DaysPastDueNotWorse','30-59days')
df = df.withColumnRenamed('NumberOfTime60-89DaysPastDueNotWorse','60-89days')
df = df.withColumnRenamed('NumberRealEstateLoansOrLines','RealEstateLoans')
df = df.withColumnRenamed('NumberOfDependents','families')
# 返回data_web.py的数据列表
all_list = []
# 本次信用卡逾期分析
# 共有逾期10026人,139974没有逾期,总人数150000
total_y = []
for i in range(2):
total_y.append(df.filter(df['y'] == i).count())
all_list.append(total_y)
# 年龄分析
df_age = df.select(df['age'],df['y'])
agenum = []
bin = [0,30,45,60,75,100]
# 统计各个年龄段的人口
for i in range(5):
agenum.append(df_age.filter(df['age'].between(bin[i],bin[i+1])).count())
all_list.append(agenum)
# 统计各个年龄段逾期与不逾期的数量
age_y = []
for i in range(5):
y0 = df_age.filter(df['age'].between(bin[i],bin[i+1])).\
filter(df['y']=='0').count()
y1 = df_age.filter(df['age'].between(bin[i],bin[i+1])).\
filter(df['y']=='1').count()
age_y.append([y0,y1])
all_list.append(age_y)
# 有逾期记录的人的本次信用卡逾期数量
df_pastDue = df.select(df['30-59days'],df['60-89days'],df['y'])
# 30-59有23982人,4985逾期,18997不逾期
numofpastdue = []
numofpastdue.append(df_pastDue.filter(df_pastDue['30-59days'] > 0).count())
y_numofpast1 = []
for i in range(2):
x = df_pastDue.filter(df_pastDue['30-59days'] > 0).\
filter(df_pastDue['y'] == i).count()
y_numofpast1.append(x)
# 60-89有7604人,2770逾期,4834不逾期
numofpastdue.append(df_pastDue.filter(df_pastDue['60-89days'] > 0).count())
y_numofpast2 = []
for i in range(2):
x = df_pastDue.filter(df_pastDue['60-89days'] > 0).\
filter(df_pastDue['y'] == i).count()
y_numofpast2.append(x)
# 两个记录都有的人有4393人,逾期1907,不逾期2486
numofpastdue.append(df_pastDue.filter(df_pastDue['30-59days'] > 0).
filter(df_pastDue['60-89days'] > 0).count())
y_numofpast3 = []
for i in range(2):
x = df_pastDue.filter(df_pastDue['30-59days'] > 0).\
filter(df_pastDue['60-89days'] > 0).filter(df_pastDue['y'] == i).count()
y_numofpast3.append(x)
all_list.append(numofpastdue)
all_list.append(y_numofpast1)
all_list.append(y_numofpast2)
all_list.append(y_numofpast3)
# 房产抵押数量分析
df_Loans = df.select(df['RealEstateLoans'],df['y'])
# 有无抵押房产人数情况
numofrealandnoreal = []
numofrealandnoreal.append(df_Loans.filter(df_Loans['RealEstateLoans']==0).count())
numofrealandnoreal.append(df_Loans.filter(df_Loans['RealEstateLoans']>0).count())
all_list.append(numofrealandnoreal)
## 房产无抵押共有56188人,逾期4672人,没逾期51516人
norealnum = []
for i in range(2):
x = df_Loans.filter(df_Loans['RealEstateLoans']==0).\
filter(df_Loans['y'] == i).count()
norealnum.append(x)
all_list.append(norealnum)
# 房产抵押共有93812人,逾期5354人,不逾期88458人
realnum = []
for i in range(2):
x = df_Loans.filter(df_Loans['RealEstateLoans']>0).\
filter(df_Loans['y'] == i).count()
realnum.append(x)
all_list.append(realnum)
# 家属人数分析
df_families = df.select(df['families'],df['y'])
# 有无家属人数统计
nofamiliesAndfamilies = []
nofamiliesAndfamilies.append(df_families.filter(df_families['families']>0).count())
nofamiliesAndfamilies.append(df_families.filter(df_families['families']==0).count())
all_list.append(nofamiliesAndfamilies)
# 有家属59174人,逾期4752人,没逾期54422人
y_families = []
y_families.append(df_families.filter(df_families['families']>0).
filter(df_families['y']==0).count())
y_families.append(df_families.filter(df_families['families']>0).
filter(df_families['y']==1).count())
all_list.append(y_families)
# 没家属90826人,逾期5274人,没逾期85552人
y_nofamilies = []
y_nofamilies.append(df_families.filter(df_families['families']==0).
filter(df_families['y']==0).count())
y_nofamilies.append(df_families.filter(df_families['families']==0).
filter(df_families['y']==1).count())
all_list.append(y_nofamilies)
# 月收入分析
df_income = df.select(df['MonthlyIncome'],df['y'])
# 获取平均值,其中先返回Row对象,再获取其中均值
mean_income = df_income.agg(functions.avg(df_income['MonthlyIncome'])).head()[0]
# 收入分布,105854人没超过均值6670,44146人超过均值6670
numofMeanincome = []
numofMeanincome.append(df_income.filter(df['MonthlyIncome'] < mean_income).count())
numofMeanincome.append(df_income.filter(df['MonthlyIncome'] > mean_income).count())
all_list.append(numofMeanincome)
# 未超过均值的逾期情况分析,97977人没逾期,7877人逾期
y_NoMeanIncome = []
y_NoMeanIncome.append(df_income.filter(df['MonthlyIncome'] < mean_income).filter(df['y']==0).count())
y_NoMeanIncome.append(df_income.filter(df['MonthlyIncome'] < mean_income).filter(df['y']==1).count())
all_list.append(y_NoMeanIncome)
# 超过均值的逾期情况分析,41997人没逾期,2149人逾期
y_MeanIncome = []
y_MeanIncome.append(df_income.filter(df['MonthlyIncome'] > mean_income).filter(df['y']==0).count())
y_MeanIncome.append(df_income.filter(df['MonthlyIncome'] > mean_income).filter(df['y']==1).count())
all_list.append(y_MeanIncome)
# 数据可视化data_web.py
return all_list
数据可视化
选择使用python第三方库pyecharts作为可视化工具,其中pyecharts版本为1.7.0。采用其中的柱状图和饼图来详细展现分析结果。
代码文件data_web.py的内容如下:
from pyecharts.charts import Bar
from pyecharts.charts import Pie
from pyecharts.charts import Page
from pyecharts import options as opts
import data_analysis
# --------总体逾期人数情况--------------
def draw_total(total_list):
attr = ["未逾期人数", "逾期人数"]
pie = (
Pie()
.add("总体逾期人数", [list(z) for z in zip(attr,total_list)])
.set_global_opts(title_opts=opts.TitleOpts(title="总体逾期人数分布"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
return pie
# --------年龄与逾期人数情况--------------
def draw_age(age_list,y_ageList):
total_pie = draw_total(all_list[0])
attr = ["0-30", "30-45", "45-60", "60-75", "75-100"]
y0_agenum = []
y1_agenum = []
for i in range(5):
y0_agenum.append(y_ageList[i][0])
y1_agenum.append(y_ageList[i][1])
bar = (
Bar()
.add_xaxis(attr)
.add_yaxis("人数分布", age_list)
.add_yaxis("未逾期人数分布", y0_agenum)
.add_yaxis("逾期人数分布", y1_agenum)
.set_global_opts(title_opts=opts.TitleOpts(title="各年龄段逾期情况"))
)
attr = ["未逾期","逾期"]
pie1 = (
Pie()
.add("0-30年龄段", [list(z) for z in zip(attr,y_ageList[0])])
.set_global_opts(title_opts=opts.TitleOpts(title="0-30年龄段逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie2 = (
Pie()
.add("30-45年龄段", [list(z) for z in zip(attr,y_ageList[1])])
.set_global_opts(title_opts=opts.TitleOpts(title="30-45年龄段逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie3 = (
Pie()
.add("45-60年龄段", [list(z) for z in zip(attr,y_ageList[2])])
.set_global_opts(title_opts=opts.TitleOpts(title="45-60年龄段逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie4 = (
Pie()
.add("60-75年龄段", [list(z) for z in zip(attr,y_ageList[3])])
.set_global_opts(title_opts=opts.TitleOpts(title="60-75年龄段逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie5 = (
Pie()
.add("75-100年龄段", [list(z) for z in zip(attr,y_ageList[4])])
.set_global_opts(title_opts=opts.TitleOpts(title="75-100年龄段逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
page = Page()
page.add(bar)
page.add(total_pie)
page.add(pie1)
page.add(pie2)
page.add(pie3)
page.add(pie4)
page.add(pie5)
page.render('age_OverDue.html')
# --------逾期记录与逾期人数情况--------------
def draw_pastdue(numofpastdue,pastdue1num,pastdue2num,pastdue12num):
total_pie = draw_total(all_list[0])
attr = ["有30-59days逾期记录的人数", "有60-89days逾期记录的人数", "有长短期逾期记录的人数"]
bar = (
Bar()
.add_xaxis(attr)
.add_yaxis("人数", numofpastdue)
.set_global_opts(title_opts=opts.TitleOpts(title="有逾期记录的人数"))
)
attr = ["未逾期","逾期"]
pie1 = (
Pie()
.add("有短期逾期记录的人的逾期情况", [list(z) for z in zip(attr,pastdue1num)])
.set_global_opts(title_opts=opts.TitleOpts(title="有短期逾期记录的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie2 = (
Pie()
.add("有长期逾期记录的人的逾期情况", [list(z) for z in zip(attr,pastdue2num)])
.set_global_opts(title_opts=opts.TitleOpts(title="有长期逾期记录的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie3 = (
Pie()
.add("长短期逾期记录都有的人的逾期情况", [list(z) for z in zip(attr,pastdue12num)])
.set_global_opts(title_opts=opts.TitleOpts(title="长短期逾期记录都有的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
page = Page()
page.add(bar)
page.add(total_pie)
page.add(pie1)
page.add(pie2)
page.add(pie3)
page.render('pastDue_OverDue.html')
# --------房产抵押与逾期人数情况--------------
def draw_realestateLoans(numofrealornoreal,y_norealnum,y_realnum):
total_pie = draw_total(all_list[0])
attr = ["无房产抵押人数", "有房产抵押人数"]
bar = (
Bar()
.add_xaxis(attr)
.add_yaxis("人数", numofrealornoreal)
.set_global_opts(title_opts=opts.TitleOpts(title="房产抵押人数分布"))
)
attr = ["未逾期","逾期"]
pie1 = (
Pie()
.add("无房产抵押的人的逾期情况", [list(z) for z in zip(attr,y_norealnum)])
.set_global_opts(title_opts=opts.TitleOpts(title="无房产抵押的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie2 = (
Pie()
.add("有房产抵押的人的逾期情况", [list(z) for z in zip(attr,y_realnum)])
.set_global_opts(title_opts=opts.TitleOpts(title="有房产抵押的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
page = Page()
page.add(bar)
page.add(total_pie)
page.add(pie1)
page.add(pie2)
page.render('realestateLoans_OverDue.html')
# --------家属人数与逾期人数情况--------------
def draw_families(nofamiliesAndfamilies,y_families,y_nofamilies):
total_pie = draw_total(all_list[0])
attr = ["有家属人数", "无家属人数"]
bar = (
Bar()
.add_xaxis(attr)
.add_yaxis("人数", nofamiliesAndfamilies)
.set_global_opts(title_opts=opts.TitleOpts(title="有无家属人数分布"))
)
attr = ["未逾期","逾期"]
pie1 = (
Pie()
.add("无家属的人的逾期情况", [list(z) for z in zip(attr,y_nofamilies)])
.set_global_opts(title_opts=opts.TitleOpts(title="无家属的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie2 = (
Pie()
.add("有家属的人的逾期情况", [list(z) for z in zip(attr,y_families)])
.set_global_opts(title_opts=opts.TitleOpts(title="有家属的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
page = Page()
page.add(bar)
page.add(total_pie)
page.add(pie1)
page.add(pie2)
page.render('families_OverDue.html')
# --------月收入与逾期人数情况--------------
def draw_income(numofMeanincome,y_NoMeanIncome,y_MeanIncome):
total_pie = draw_total(all_list[0])
attr = ["未超过均值收入人数", "超过均值收入人数"]
bar = (
Bar()
.add_xaxis(attr)
.add_yaxis("人数", numofMeanincome)
.set_global_opts(title_opts=opts.TitleOpts(title="有无超过均值收入人数分布"))
)
attr = ["未逾期","逾期"]
pie1 = (
Pie()
.add("未超过均值收入的人的逾期情况", [list(z) for z in zip(attr,y_NoMeanIncome)])
.set_global_opts(title_opts=opts.TitleOpts(title="未超过均值收入的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie2 = (
Pie()
.add("超过均值收入的人的逾期情况", [list(z) for z in zip(attr,y_MeanIncome)])
.set_global_opts(title_opts=opts.TitleOpts(title="超过均值收入的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
page = Page()
page.add(bar)
page.add(total_pie)
page.add(pie1)
page.add(pie2)
page.render('meanIncome_OverDue.html')
if __name__ == '__main__':
print("开始总程序")
Filename = "/OverDue/data.csv"
all_list = data_analysis.analyse(Filename)
# 年龄与是否逾期情况
draw_age(all_list[1],all_list[2])
# 有无逾期记录与是否逾期情况
draw_pastdue(all_list[3],all_list[4],all_list[5],all_list[6])
# 房产抵押数量与是否逾期情况
draw_realestateLoans(all_list[7],all_list[8],all_list[9])
# 家属人数与是否逾期情况
draw_families(all_list[10],all_list[11],all_list[12])
# 月收入与是否逾期情况
draw_income(all_list[13],all_list[14],all_list[15])
print("结束总程序")
完整代码
from pyspark.sql import SparkSession
from pyspark import SparkContext,SparkConf
from pyspark.sql import Row
from pyspark.sql.types import *
from pyspark.sql import functions
def analyse(filename):
# 读取数据
spark = SparkSession.builder.config(conf = SparkConf()).getOrCreate()
df = spark.read.format("csv").option("header","true").load(filename)
# 修改列名
df = df.withColumnRenamed('SeriousDlqin2yrs','y')
df = df.withColumnRenamed('NumberOfTime30-59DaysPastDueNotWorse','30-59days')
df = df.withColumnRenamed('NumberOfTime60-89DaysPastDueNotWorse','60-89days')
df = df.withColumnRenamed('NumberRealEstateLoansOrLines','RealEstateLoans')
df = df.withColumnRenamed('NumberOfDependents','families')
# 返回data_web.py的数据列表
all_list = []
# 本次信用卡逾期分析
# 共有逾期10026人,139974没有逾期,总人数150000
total_y = []
for i in range(2):
total_y.append(df.filter(df['y'] == i).count())
all_list.append(total_y)
# 年龄分析
df_age = df.select(df['age'],df['y'])
agenum = []
bin = [0,30,45,60,75,100]
# 统计各个年龄段的人口
for i in range(5):
agenum.append(df_age.filter(df['age'].between(bin[i],bin[i+1])).count())
all_list.append(agenum)
# 统计各个年龄段逾期与不逾期的数量
age_y = []
for i in range(5):
y0 = df_age.filter(df['age'].between(bin[i],bin[i+1])).\
filter(df['y']=='0').count()
y1 = df_age.filter(df['age'].between(bin[i],bin[i+1])).\
filter(df['y']=='1').count()
age_y.append([y0,y1])
all_list.append(age_y)
# 有逾期记录的人的本次信用卡逾期数量
df_pastDue = df.select(df['30-59days'],df['60-89days'],df['y'])
# 30-59有23982人,4985逾期,18997不逾期
numofpastdue = []
numofpastdue.append(df_pastDue.filter(df_pastDue['30-59days'] > 0).count())
y_numofpast1 = []
for i in range(2):
x = df_pastDue.filter(df_pastDue['30-59days'] > 0).\
filter(df_pastDue['y'] == i).count()
y_numofpast1.append(x)
# 60-89有7604人,2770逾期,4834不逾期
numofpastdue.append(df_pastDue.filter(df_pastDue['60-89days'] > 0).count())
y_numofpast2 = []
for i in range(2):
x = df_pastDue.filter(df_pastDue['60-89days'] > 0).\
filter(df_pastDue['y'] == i).count()
y_numofpast2.append(x)
# 两个记录都有的人有4393人,逾期1907,不逾期2486
numofpastdue.append(df_pastDue.filter(df_pastDue['30-59days'] > 0).
filter(df_pastDue['60-89days'] > 0).count())
y_numofpast3 = []
for i in range(2):
x = df_pastDue.filter(df_pastDue['30-59days'] > 0).\
filter(df_pastDue['60-89days'] > 0).filter(df_pastDue['y'] == i).count()
y_numofpast3.append(x)
all_list.append(numofpastdue)
all_list.append(y_numofpast1)
all_list.append(y_numofpast2)
all_list.append(y_numofpast3)
# 房产抵押数量分析
df_Loans = df.select(df['RealEstateLoans'],df['y'])
# 有无抵押房产人数情况
numofrealandnoreal = []
numofrealandnoreal.append(df_Loans.filter(df_Loans['RealEstateLoans']==0).count())
numofrealandnoreal.append(df_Loans.filter(df_Loans['RealEstateLoans']>0).count())
all_list.append(numofrealandnoreal)
## 房产无抵押共有56188人,逾期4672人,没逾期51516人
norealnum = []
for i in range(2):
x = df_Loans.filter(df_Loans['RealEstateLoans']==0).\
filter(df_Loans['y'] == i).count()
norealnum.append(x)
all_list.append(norealnum)
# 房产抵押共有93812人,逾期5354人,不逾期88458人
realnum = []
for i in range(2):
x = df_Loans.filter(df_Loans['RealEstateLoans']>0).\
filter(df_Loans['y'] == i).count()
realnum.append(x)
all_list.append(realnum)
# 家属人数分析
df_families = df.select(df['families'],df['y'])
# 有无家属人数统计
nofamiliesAndfamilies = []
nofamiliesAndfamilies.append(df_families.filter(df_families['families']>0).count())
nofamiliesAndfamilies.append(df_families.filter(df_families['families']==0).count())
all_list.append(nofamiliesAndfamilies)
# 有家属59174人,逾期4752人,没逾期54422人
y_families = []
y_families.append(df_families.filter(df_families['families']>0).
filter(df_families['y']==0).count())
y_families.append(df_families.filter(df_families['families']>0).
filter(df_families['y']==1).count())
all_list.append(y_families)
# 没家属90826人,逾期5274人,没逾期85552人
y_nofamilies = []
y_nofamilies.append(df_families.filter(df_families['families']==0).
filter(df_families['y']==0).count())
y_nofamilies.append(df_families.filter(df_families['families']==0).
filter(df_families['y']==1).count())
all_list.append(y_nofamilies)
# 月收入分析
df_income = df.select(df['MonthlyIncome'],df['y'])
# 获取平均值,其中先返回Row对象,再获取其中均值
mean_income = df_income.agg(functions.avg(df_income['MonthlyIncome'])).head()[0]
# 收入分布,105854人没超过均值6670,44146人超过均值6670
numofMeanincome = []
numofMeanincome.append(df_income.filter(df['MonthlyIncome'] < mean_income).count())
numofMeanincome.append(df_income.filter(df['MonthlyIncome'] > mean_income).count())
all_list.append(numofMeanincome)
# 未超过均值的逾期情况分析,97977人没逾期,7877人逾期
y_NoMeanIncome = []
y_NoMeanIncome.append(df_income.filter(df['MonthlyIncome'] < mean_income).filter(df['y']==0).count())
y_NoMeanIncome.append(df_income.filter(df['MonthlyIncome'] < mean_income).filter(df['y']==1).count())
all_list.append(y_NoMeanIncome)
# 超过均值的逾期情况分析,41997人没逾期,2149人逾期
y_MeanIncome = []
y_MeanIncome.append(df_income.filter(df['MonthlyIncome'] > mean_income).filter(df['y']==0).count())
y_MeanIncome.append(df_income.filter(df['MonthlyIncome'] > mean_income).filter(df['y']==1).count())
all_list.append(y_MeanIncome)
# 数据可视化data_web.py
return all_list
from pyecharts.charts import Bar
from pyecharts.charts import Pie
from pyecharts.charts import Page
from pyecharts import options as opts
# --------总体逾期人数情况--------------
def draw_total(total_list):
attr = ["未逾期人数", "逾期人数"]
pie = (
Pie()
.add("总体逾期人数", [list(z) for z in zip(attr,total_list)])
.set_global_opts(title_opts=opts.TitleOpts(title="总体逾期人数分布"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
return pie
# --------年龄与逾期人数情况--------------
def draw_age(age_list,y_ageList):
total_pie = draw_total(all_list[0])
attr = ["0-30", "30-45", "45-60", "60-75", "75-100"]
y0_agenum = []
y1_agenum = []
for i in range(5):
y0_agenum.append(y_ageList[i][0])
y1_agenum.append(y_ageList[i][1])
bar = (
Bar()
.add_xaxis(attr)
.add_yaxis("人数分布", age_list)
.add_yaxis("未逾期人数分布", y0_agenum)
.add_yaxis("逾期人数分布", y1_agenum)
.set_global_opts(title_opts=opts.TitleOpts(title="各年龄段逾期情况"))
)
attr = ["未逾期","逾期"]
pie1 = (
Pie()
.add("0-30年龄段", [list(z) for z in zip(attr,y_ageList[0])])
.set_global_opts(title_opts=opts.TitleOpts(title="0-30年龄段逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie2 = (
Pie()
.add("30-45年龄段", [list(z) for z in zip(attr,y_ageList[1])])
.set_global_opts(title_opts=opts.TitleOpts(title="30-45年龄段逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie3 = (
Pie()
.add("45-60年龄段", [list(z) for z in zip(attr,y_ageList[2])])
.set_global_opts(title_opts=opts.TitleOpts(title="45-60年龄段逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie4 = (
Pie()
.add("60-75年龄段", [list(z) for z in zip(attr,y_ageList[3])])
.set_global_opts(title_opts=opts.TitleOpts(title="60-75年龄段逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie5 = (
Pie()
.add("75-100年龄段", [list(z) for z in zip(attr,y_ageList[4])])
.set_global_opts(title_opts=opts.TitleOpts(title="75-100年龄段逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
page = Page()
page.add(bar)
page.add(total_pie)
page.add(pie1)
page.add(pie2)
page.add(pie3)
page.add(pie4)
page.add(pie5)
page.render('age_OverDue.html')
# --------逾期记录与逾期人数情况--------------
def draw_pastdue(numofpastdue,pastdue1num,pastdue2num,pastdue12num):
total_pie = draw_total(all_list[0])
attr = ["有30-59days逾期记录的人数", "有60-89days逾期记录的人数", "有长短期逾期记录的人数"]
bar = (
Bar()
.add_xaxis(attr)
.add_yaxis("人数", numofpastdue)
.set_global_opts(title_opts=opts.TitleOpts(title="有逾期记录的人数"))
)
attr = ["未逾期","逾期"]
pie1 = (
Pie()
.add("有短期逾期记录的人的逾期情况", [list(z) for z in zip(attr,pastdue1num)])
.set_global_opts(title_opts=opts.TitleOpts(title="有短期逾期记录的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie2 = (
Pie()
.add("有长期逾期记录的人的逾期情况", [list(z) for z in zip(attr,pastdue2num)])
.set_global_opts(title_opts=opts.TitleOpts(title="有长期逾期记录的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie3 = (
Pie()
.add("长短期逾期记录都有的人的逾期情况", [list(z) for z in zip(attr,pastdue12num)])
.set_global_opts(title_opts=opts.TitleOpts(title="长短期逾期记录都有的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
page = Page()
page.add(bar)
page.add(total_pie)
page.add(pie1)
page.add(pie2)
page.add(pie3)
page.render('pastDue_OverDue.html')
# --------房产抵押与逾期人数情况--------------
def draw_realestateLoans(numofrealornoreal,y_norealnum,y_realnum):
total_pie = draw_total(all_list[0])
attr = ["无房产抵押人数", "有房产抵押人数"]
bar = (
Bar()
.add_xaxis(attr)
.add_yaxis("人数", numofrealornoreal)
.set_global_opts(title_opts=opts.TitleOpts(title="房产抵押人数分布"))
)
attr = ["未逾期","逾期"]
pie1 = (
Pie()
.add("无房产抵押的人的逾期情况", [list(z) for z in zip(attr,y_norealnum)])
.set_global_opts(title_opts=opts.TitleOpts(title="无房产抵押的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie2 = (
Pie()
.add("有房产抵押的人的逾期情况", [list(z) for z in zip(attr,y_realnum)])
.set_global_opts(title_opts=opts.TitleOpts(title="有房产抵押的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
page = Page()
page.add(bar)
page.add(total_pie)
page.add(pie1)
page.add(pie2)
page.render('realestateLoans_OverDue.html')
# --------家属人数与逾期人数情况--------------
def draw_families(nofamiliesAndfamilies,y_families,y_nofamilies):
total_pie = draw_total(all_list[0])
attr = ["有家属人数", "无家属人数"]
bar = (
Bar()
.add_xaxis(attr)
.add_yaxis("人数", nofamiliesAndfamilies)
.set_global_opts(title_opts=opts.TitleOpts(title="有无家属人数分布"))
)
attr = ["未逾期","逾期"]
pie1 = (
Pie()
.add("无家属的人的逾期情况", [list(z) for z in zip(attr,y_nofamilies)])
.set_global_opts(title_opts=opts.TitleOpts(title="无家属的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie2 = (
Pie()
.add("有家属的人的逾期情况", [list(z) for z in zip(attr,y_families)])
.set_global_opts(title_opts=opts.TitleOpts(title="有家属的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
page = Page()
page.add(bar)
page.add(total_pie)
page.add(pie1)
page.add(pie2)
page.render('families_OverDue.html')
# --------月收入与逾期人数情况--------------
def draw_income(numofMeanincome,y_NoMeanIncome,y_MeanIncome):
total_pie = draw_total(all_list[0])
attr = ["未超过均值收入人数", "超过均值收入人数"]
bar = (
Bar()
.add_xaxis(attr)
.add_yaxis("人数", numofMeanincome)
.set_global_opts(title_opts=opts.TitleOpts(title="有无超过均值收入人数分布"))
)
attr = ["未逾期","逾期"]
pie1 = (
Pie()
.add("未超过均值收入的人的逾期情况", [list(z) for z in zip(attr,y_NoMeanIncome)])
.set_global_opts(title_opts=opts.TitleOpts(title="未超过均值收入的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
pie2 = (
Pie()
.add("超过均值收入的人的逾期情况", [list(z) for z in zip(attr,y_MeanIncome)])
.set_global_opts(title_opts=opts.TitleOpts(title="超过均值收入的人的逾期情况"))
.set_series_opts(
tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"),
label_opts=opts.LabelOpts(formatter="{b}: {c} ({d}%)")
)
)
page = Page()
page.add(bar)
page.add(total_pie)
page.add(pie1)
page.add(pie2)
page.render('meanIncome_OverDue.html')
if __name__ == '__main__':
print("开始总程序")
Filename = "hdfs://localhost:8020/user/hadoop/data1.csv"
all_list = analyse(Filename)
# 年龄与是否逾期情况
draw_age(all_list[1],all_list[2])
# 有无逾期记录与是否逾期情况
draw_pastdue(all_list[3],all_list[4],all_list[5],all_list[6])
# 房产抵押数量与是否逾期情况
draw_realestateLoans(all_list[7],all_list[8],all_list[9])
# 家属人数与是否逾期情况
draw_families(all_list[10],all_list[11],all_list[12])
# 月收入与是否逾期情况
draw_income(all_list[13],all_list[14],all_list[15])
print("结束总程序")
运行结果如下:(带overdue.html的文件)
数据可视化结果
# 进入OverDue目录
cd ~/OverDue
# 提交data_web.py文件到spark-submit
/usr/local/spark/bin/spark-submit --master local ~/OverDue/data_web.py
家属人数
逾期记录
房产抵押数量
月收入
### 总体
年龄