cohort_analysis(dat, obs_id = NULL, occur_time = NULL, MOB = NULL,period = "monthly", status = NULL, amount = NULL, by_out = "cnt",start_date = NULL, end_date = NULL, dead_status = 30)cohort_table(dat, obs_id = NULL, occur_time = NULL, MOB = NULL,period = "monthly", status = NULL, amount = NULL, by_out = "cnt",start_date = NULL, end_date = NULL, dead_status = 30)

#安装和加载creditmodel包
#install.packages("creditmodel")
library(creditmodel)
#使用read_data读入数据。
vin_dat = read_data("vin_dat.csv")
#使用creditmodel包的数据清晰模块主函数对数据进行清洗，关于数据清洗模块，以后会做详细接受，在此简单描述下各个参数的含义。
vin_dat = data_cleansing(vin_dat, obs_id = "loan_id",#主键occur_time = 'loan_time',#事件发生时间outlier_proc = FALSE,#不进行异常值处理missing_proc = FALSE,#不进行确实值处理remove_dup = FALSE,#不删除重复观测merge_cat = FALSE,#不对类别变量的类别进行合并low_var = 0.9999,#删除单一值比例大于0.9999的变量missing_rate = 0.9999 # 对缺失值比例大于0.9999的变量进行二值化处理)
#可使用creditmodel包的data_exploration函数来观察数据概貌
data_exploration(vin_dat)
>
* Observations      : 204697
* Numeric_variables : 7
* Category_variables: 1
* Date_variables    : 1
$numFeature  NMiss Miss_Rate        Max        75%     Median       25%        Min       Mean   Std
1   age_overdue_days 194695    95.11%        440        122         61         30          1         90    76
2 age_overdue_period     33     0.02%         15          0          0          0          0          0  0.87
3           loan_age     33     0.02%         15          6          3          1          0          4   3.2
4        loan_amount      0        0%     500000      60000      40000      30000       1000      47911 24279
5       loan_balance    823      0.4%     500000      53186      39046      27871        920      43112 22157
6          loan_time      0        0% 2017-09-30 2017-03-31 2016-12-29 2016-11-01 2016-06-01 2017-01-11    99
7   max_overdue_days 160974    78.64%        440         13          2          1          1         23    52
8 max_overdue_period      0        0%       15.0        0.0        0.0        0.0        0.0        0.3  0.93$charFeature  NMiss Miss_Rate                 Value1                 Value2              Value3              Value4              Value5              Value6
1 loan_id 204697      100% n2016060100000030 : 48 n2016060100000010 : 30 n1605300032102 : 16 n1606010034102 : 16 n1606020032402 : 16 n1606020034202 : 16Value7
1 (Other) : 204555
>
#使用plot_table画出数值型变量的数据概要
plot_table(data_exploration(vin_dat)$num)

cohort_dat = cohort_analysis(vin_dat,obs_id = 'loan_id',#放款编号occur_time = 'loan_time', #放款时间MOB = NULL,#month on book在账月份，找个可以自己定义为一个变量，默认以自然月为月份。period = 'monthly',#以月作为同一时期，也可按周weeklystatus = "age_overdue_days",#使用账龄末逾期天数作为状态，也为自己定义的0、1变量dead_status = 30, #逾期天数大于30天则为dead状态，若为0、1变量，此处应设为0.amount = "loan_amount", #如果以金额统计，则必须设置，此处按放款金额计算,也可以按余额by_out = 'amt',#如果以金额统计则为‘amt’,以笔数统计则为‘cnt’start_date = "2016-08-01",#统计日开始时间end_date = '2017-05-31'#统计日结束时间)

cohort_plot(cohort_dat)

vin_table = cohort_table(vin_dat, obs_id = 'loan_id', occur_time = 'loan_time', MOB = NULL,period = 'monthly', status = "max_overdue_days",dead_status = 30, amount = "loan_balance", by_out = 'amt',start_date = "2016-09-01", end_date = '2017-07-31')

#' cohort_table_plot
#' code{cohort_table_plot} is for ploting cohort(vintage) analysis table.
#' @param cohort_dat A data.frame generated by code{cohort_analysis}.
#' @import ggplot2
#' @export
cohort_table_plot = function(cohort_dat) {#set global variablesopt = options('warn' = -1, scipen = 200, stringsAsFactors = FALSE, digits = 6) #cohort_dat[is.na(cohort_dat)] = 0#initial parametersCohort_Group = Cohort_Period = Events = Events_rate = Opening_Total = Retention_Total = cohor_dat = final_Events = m_a = max_age = NULL#plotcohort_plot = ggplot(cohort_dat, aes(reorder(paste0(Cohort_Period), Cohort_Period),Cohort_Group, fill = Events_rate)) +geom_tile(colour = 'white') +geom_text(aes(label = as_percent(Events_rate, 4)), size = 3) +scale_fill_gradient2(limits = c(0, max(cohort_dat$Events_rate)),low = love_color('deep_red'), mid = 'white',high = love_color(),midpoint = median(cohort_dat$Events_rate,na.rm = TRUE),na.value = love_color('pale_grey')) +scale_y_discrete(limits = rev(unique(cohort_dat$Cohort_Group))) +scale_x_discrete(position = "top") +labs(x = "Cohort_Period", title = "Cohort Analysis") +theme(text = element_text(size = 15), rect = element_blank()) +plot_theme(legend.position = 'right', angle = 0)return(cohort_plot)options(opt) #reset global variables
}

vin_table = cohort_table(vin_dat, obs_id = 'loan_id', occur_time = 'loan_time', MOB = NULL,period = 'monthly', status = "max_overdue_days",dead_status = 30, amount = "loan_balance", by_out = 'amt',start_date = "2016-09-01", end_date = '2017-07-31')
cohort_table_plot(cohort_dat)