给大厨写的R数据分析代码

###************************************** 新老客户统计 ***************************************###
dachu <- read.csv("D:\\Dasktop\\bigdata_game\\天池\\大厨\\qijiandiankehu.csv", header = T, encoding = "utf-8", colClasses = c("character", "Date"))
str(dachu)
head(dachu,20)
temp <- table(dachu$买家昵称)
plot(table(sort(temp))/length(temp))
#library(data.table)
#month(dachu$下单日期[nrow(dachu)])

min(dachu$下单日期)
max(dachu$下单日期)

dachu$ym <- substr(dachu$下单日期, 1,7); head(dachu)
newcusts <- c()
oldcusts <- c()
ss <- sort(unique(dachu$ym))
#新客户满足一下两个条件：1）当月购买一次；2）之前无购买记录
#老客户满足一下两个条件之一：1）当月购买两次及以上；2）当月购买一次且之前有购买记录
for(i in 1:length(ss)){
  #date1 = as.Date(paste(substr(kk, 1, 6), paste(as.integer(substr(kk, 7, 7))+1,"-01", sep = ""), sep = ""))
  
  if(i == 1){
    date2 = as.Date(paste(ss[i+1], "-01", sep = ""))
    now = dachu$买家昵称[dachu$下单日期 < date2]
    temp = table(now)
    uniq = unique(now)
    newcusts = c(newcusts, sum(temp == 1))
    oldcusts = c(oldcusts, sum(temp > 1))
  }else if(i < length(ss)){
    date1 = as.Date(paste(ss[i], "-01", sep = ""))
    date2 = as.Date(paste(ss[i+1], "-01", sep = ""))
    now = dachu$买家昵称[(dachu$下单日期 < date2) & (dachu$下单日期 >= date1)]
    temp = table(now)
    #old_now = names(temp)[temp>1]
    new_now = names(temp)[temp==1]
    temp2 = table(c(uniq, new_now))
    newcusts = c(newcusts, (length(new_now) - sum(temp2 > 1)))
    #oldcusts = c(oldcusts, (length(old_now) + sum(temp2 > 1)))
    oldcusts = c(oldcusts, (length(temp) - length(new_now) + sum(temp2 > 1)))
    #uniq = unique(c(uniq, old_now, new_now))
    uniq = unique(c(uniq, names(temp)))
    
  }else{
    date1 = as.Date(paste(ss[i], "-01", sep = ""))
    now = dachu$买家昵称[dachu$下单日期 >= date1]
    temp = table(now)
    #old_now = names(temp)[temp>1]
    new_now = names(temp)[temp==1]
    temp2 = table(c(uniq, new_now))
    newcusts = c(newcusts, (length(new_now) - sum(temp2 > 1)))
    #oldcusts = c(oldcusts, (length(old_now) + sum(temp2 > 1)))
    oldcusts = c(oldcusts, (length(temp) - length(new_now) + sum(temp2 > 1)))
    #uniq = unique(c(uniq, old_now, new_now))
    uniq = unique(c(uniq, names(temp)))
  }
  
}
newcusts
oldcusts
(newcusts1 = cbind(date=ss, newcusts))
(oldcusts1 = cbind(date=ss, oldcusts))
write.csv(newcusts1, "C:\\Users\\hasee\\Desktop\\newcusts.csv",quote = F)
write.csv(oldcusts1, "C:\\Users\\hasee\\Desktop\\oldcusts.csv",quote = F)

#library(timeSeries)
win.graph()
opar <- par(no.readonly=TRUE)
par(lty=1, pch=1)  #par("cex") 查看默认值
# plot.ts(ts(newcusts+oldcusts, start = c(2014, 3), frequency = 12),main="薏凡特月度新老客户购买数量变化趋势", col=1)
# lines(ts(newcusts, start = c(2014, 3), frequency = 12), col=2)
# lines(ts(oldcusts, start = c(2014, 3), frequency = 12), col=3)
time <- seq.Date(as.Date("2014/3/1"), by = "month", length = length(ss))
plot(time, newcusts+oldcusts, xlab="月份", ylab="客户数", main="薏凡特月度新老客户购买数量变化趋势", 
     type = "o", col=1) 
# type画点/线, "p" for points, "l" for lines, "b" for both points and lines, "c" for empty points joined by lines, 
# "o" for overplotted points and lines, "s" and "S" for stair steps and "h" for histogram-like vertical lines. 
# Finally, "n" does not produce any points or lines. 
# pch点型, 
# cex点大小： 
# lty线型：0=blank, 1=solid (default), 2=dashed, 3=dotted, 4=dotdash, 5=longdash, 6=twodash)
# lwd线宽
lines(time, newcusts, type = "o", col=2)
lines(time, oldcusts, type = "o", col=3)
legend("topright", c("总体客户", "新客户", "老客户"), col=1:3, lty=1, pch=1)
# “bottomright”, “bottom”, “bottomleft”, “left”, “topleft”, “top”, “topright”, “right”, “center”
par(opar)
#par(new=TRUE)


###************************************** 当月回购率 ***************************************###
# 月初统计购买一次的客户数，月末统计这部分人回购人数。
# 当月新进的客户且购买2次以上的不计入新客户
# 新客户可直接table=1的sum，但是当月回购的客户如何计算是难点。(可以unique内连接计数)
#数据导入
dachu <- read.csv("D:\\Dasktop\\bigdata_game\\天池\\大厨\\qijiandiankehu.csv", header = T, encoding = "utf-8", colClasses = c("character", "Date"))
str(dachu)

#定义保存新客户回购数据
new_customer <- data.frame()

min(dachu$下单时间)
max(dachu$下单时间)
ss=sort(unique(substr(dachu$下单时间,1,7)))

#从第二个月开始，首月新客数和回购数均为0
for(i in seq(length(ss))[-1]){
  data1 = as.Date(paste(ss[i], "-01", sep = ""))
  
  #月初之前客户购买记录
  data2 = max(i-12,1)
  data2 = as.Date(paste(ss[data2], "-01", sep = ""))
  temp <- table(dachu$买家昵称[(dachu$下单时间 >= data2)&(dachu$下单时间 < data1)])
  
  #月内客户购买记录
  if(i < length(ss)){
    data2 = as.Date(paste(ss[i+1], "-01", sep = ""))
    temp2 <- table(dachu$买家昵称[(dachu$下单时间 >= data1)&(dachu$下单时间 < data2)])
  }else{
    temp2 <- table(dachu$买家昵称[dachu$下单时间 >= data1])
  }

  #月内回购记录
  temp2 = merge(data.frame(k=names(temp)[temp==1]),
                data.frame(k=names(temp2)),
                by=c(‘k‘))
  
  #保存日期、月初新客数、月内回购数
  new_customer = rbind(new_customer, data.frame(date=ss[i], counts=sum(temp==1), repurchase=nrow(temp2)))
  
}
#计算回购率
new_customer$rate <- new_customer[[3]] / new_customer[[2]]
#colnames(new_customer) = c(‘date‘,‘counts‘,‘repurchase‘,‘rate‘)

win.graph()
opar<-par(mfrow=c(2,2))
plot(new_customer$date,new_customer$counts)
plot(new_customer$date,new_customer$repurchase);plot(new_customer$date,new_customer$rate)
par(opar)

write.csv(new_customer,"C:\\Users\\hasee\\Desktop\\new_customer.csv")



###****************************************** 季度转化率 ****************************************###
#数据导入
dachu <- read.csv("C:\\Users\\hasee\\Desktop\\qijiandiankehu.csv", header = T, encoding = "utf-8", colClasses = c("character", "Date"))
str(dachu)

#定义保存新客户回购数据
new_customer <- data.frame()

min(dachu$下单时间)
max(dachu$下单时间)
ss=sort(unique(substr(dachu$下单时间,1,7)))

#从第二个月开始，首月新客数和回购数均为0
for(i in seq(length(ss)-2)[-1]){
  data1 = as.Date(paste(ss[i], "-01", sep = ""))
  
  #季度初之前客户购买记录
  temp <- table(dachu$买家昵称[dachu$下单时间 < data1])
  
  #季度内客户购买记录
  if(i < length(ss)-2){
    data2 = as.Date(paste(ss[i+3], "-01", sep = ""))
    temp2 <- table(dachu$买家昵称[(dachu$下单时间 >= data1)&(dachu$下单时间 < data2)])
  }else{
    temp2 <- table(dachu$买家昵称[dachu$下单时间 >= data1])
  }
  
  #季度内回购记录
  temp2 = merge(data.frame(k=names(temp)[temp==1]),
                data.frame(k=names(temp2)),
                by=c(‘k‘))
  
  #保存日期、季度初新客数、月内回购数
  new_customer = rbind(new_customer, data.frame(date=ss[i], counts=sum(temp==1), repurchase=nrow(temp2)))
  
}
#计算回购率
new_customer$rate <- new_customer[[3]] / new_customer[[2]]
#colnames(new_customer) = c(‘date‘,‘counts‘,‘repurchase‘,‘rate‘)

win.graph()
opar<-par(mfrow=c(2,2))
plot(new_customer$date,new_customer$counts)
plot(new_customer$date,new_customer$repurchase);plot(new_customer$date,new_customer$rate)
par(opar)

write.csv(new_customer,"C:\\Users\\hasee\\Desktop\\new_customer.csv")




###************************************ 客户连带率：该段代码貌似有问题 ***********************************###
# 只针对所有一次客户
# 月连带率=本月发生连带的客户数/本月成交总客户数
# 产品连带率=购买该产品连带的客户数/购买该产品总体客户数
# 成交总客户=1次多件客户+一次一件客户
#数据导入
library(readxl)
# dachu <- read.csv("C:\\Users\\hasee\\Desktop\\liandailv.xlsx", header = T, encoding = "utf-8", colClasses = c("character", "Date", "character"))
# read_excel(path, sheet = 1, col_names = TRUE, col_types = NULL, na = "", skip = 0)
dachu <- read_excel("C:\\Users\\hasee\\Desktop\\liandailv.xlsx", sheet = 1, col_names = TRUE, col_types = c("text", "text", "text"), na = "", skip = 0)
dachu$下单日期 <- as.Date(dachu$下单日期)
str(dachu)
unique(dachu$商品ID)

#定义保存月度连带率
min(dachu$下单日期)
max(dachu$下单日期)
month_set=sort(unique(substr(dachu$下单日期,1,7)))

#月度连带率
month_associate_rate = data.frame()
date1 = min(dachu$下单日期)
for(i in seq(length(month_set))){
  if(i < length(month_set)){
    date2 = as.Date(paste(month_set[i+1], "-01", sep = ""))
    temp <- table(dachu$买家昵称[(dachu$下单日期 >= date1)&(dachu$下单日期 < date2)])
    date1 = date2
  }else{
    temp = table(dachu$买家昵称[dachu$下单日期 >= date1])
  }
  month_associate_rate = rbind(month_associate_rate, data.frame(month=month_set[i], count = length(temp), count2= sum(temp>1), rate=(sum(temp>1)/length(temp))))
}
month_associate_rate

#产品连带率
dachu$flag <- 0
head(dachu)
temp = table(dachu$买家昵称)
# library(dplyr)
# temp2 = left_join(dachu, data.frame(x = names(temp)[temp>1], flag.y = 1), by= c("买家昵称" = "x"),suffix = c("", ".y"))
temp2 = merge(dachu, data.frame(x = names(temp)[temp>1], flag.x = 1), by.x = "买家昵称", by.y = "x", all.x = TRUE)
temp2$flag[temp2$flag.x==1] = 1
temp2$flag.x = NULL
temp2

#定义保存产品连带率
prod_set=unique(dachu$商品ID)
product_associate_rate = data.frame()

#产品连带率
for(pi in prod_set){
  temp <- temp2$flag[temp2$商品ID == pi]
  product_associate_rate = rbind(product_associate_rate, data.frame(product=pi, count = length(temp), count2= sum(temp==1), rate=(sum(temp==1)/length(temp))))
    
}
  
product_associate_rate = product_associate_rate[order(product_associate_rate$count, decreasing = TRUE),]
product_associate_rate$product = as.character(product_associate_rate$product)
head(product_associate_rate)  

#验证
dachu[dachu$买家昵称 %in% dachu[dachu$商品ID=="42303520877",]$买家昵称,]

#产品连带率前五月度变化
#temp2为产品连带率里计算的那个
prod_set = product_associate_rate$product[1:5]
product_associate_rate_top5 = data.frame()
date1 = min(temp2$下单日期)
for(i in seq(length(month_set))){
  if(i < length(month_set)){
    date2 = as.Date(paste(month_set[i+1], "-01", sep = ""))
    temp <- temp2[(temp2$下单日期 >= date1)&(temp2$下单日期 < date2),]
    date1 = date2
  }else{
    temp = temp2[temp2$下单日期 >= date1,]
  }
  
  temp3 = data.frame(month=month_set[i])
  for(pi in prod_set){
    temp4 = temp$flag[temp$商品ID==pi]
    temp3 = cbind(temp3, length(temp4), sum(temp4==1), ifelse(length(temp4)==0,0,sum(temp4==1)/length(temp4)))
  }
  
  product_associate_rate_top5 = rbind(product_associate_rate_top5, temp3)
}
colnames(product_associate_rate_top5)[-1] <- paste(‘top‘,rep(1:5,each=3),c(‘count‘,‘count2‘,‘rate‘),sep = ‘‘)
product_associate_rate_top5



#图形展示
win.graph()
opar<-par(mfrow=c(1,2))
plot(month_associate_rate$month, month_associate_rate$rate, type="l", col = "blue", main = "月度连带率", xlab = "月份", ylab="连带率")
plot(product_associate_rate$rate, main = "产品连带率", xlab = "产品", ylab="连带率")
par(opar)

write.csv(month_associate_rate,"C:\\Users\\hasee\\Desktop\\month_associate_rate.csv")
write.csv(product_associate_rate,"C:\\Users\\hasee\\Desktop\\product_associate_rate.csv") #, quote = TRUE
write.csv(product_associate_rate_top5,"C:\\Users\\hasee\\Desktop\\product_associate_rate_top5.csv") #, quote = TRUE



# dplyr包包含了各种关联查询的函数，如inner_join,left_join,full_join,rigth_join......
library(dplyr)
library("nycflights13")
# Drop unimportant variables so it‘s easier to understand the join results.
flights2 <- 
  flights %>% 
  select(year:day,tailnum, carrier)
flights2 %>% 
  left_join(airlines,by= "carrier")

#merge(data.frame(x=1:3,y=0,z=2),data.frame(x=2:3,y=1:2),by=c("x"),all.x = T)



###******************************************* 回购率与首次消费金额关系 ********************************************###
dachu <- read.csv("D:\\Dasktop\\bigdata_game\\天池\\大厨\\suoyoukehushuju.csv", header = T, encoding = "utf-8", colClasses = c("character", "Date", "numeric"))
str(dachu)
head(dachu,20)

library(dplyr)
temp=head(dachu,20)
temp = head(arrange(dachu, 买家昵称, desc(下单时间)), 100);temp
#flights[order(flights$year, flights$month, flights$day), ]
#flights[order(desc(flights$arr_delay)), ]
#filter(group_by(temp, 买家昵称))

temp <- dachu%>%
  arrange(买家昵称, 下单时间) %>%
  group_by(买家昵称)%>%
  mutate(count = n())%>%
  slice(1)%>%
  filter()

win.graph()
opar<-par(mfrow=c(1,2))
#实付金额——购买次数分布图
plot(temp$实付金额, temp$count)
#实付金额——频数(人次)分布图
plot(table(temp$实付金额))
par(opar)

#通过第一个图，暂且分组0-1000等距每200,1000-2000,2000以上
temp$group <- 0
temp[temp$实付金额 < 1000, ]$group <- temp[temp$实付金额 < 1000, ]$实付金额 %/% 100
temp[(temp$实付金额 >= 1000) & (temp$实付金额 < 2000), ]$group <- 10
temp[temp$实付金额 >= 2000, ]$group <- 11
head(temp,20)
temp2 <- temp%>%
  group_by(group)%>%
  summarise(n1=sum(count>1), n2=n(), rate = n1/n2)

win.graph()
#各组回购率分布图
plot(temp2$group, temp2$rate)

# i <- c("gamma","a")
# switch(i,
#        beta = "You typed beta",
#        alpha = "You typed alpha",
#        gamma = "You typed gamma",
#        delta = "You typed delta" 
# )




###******************************************* 客户联带对回购的影响 *******************************************###
t0 <- Sys.time()
dachu <- read.csv("D:\\Dasktop\\bigdata_game\\天池\\大厨\\AnalysisOrderDownLoad-订单信息-子订单（全量）-10027396-8025-107.csv", 
                  header = T, encoding = "utf-8", colClasses = c(rep("character",4), rep("Date",3), rep("character",5), "integer","numeric","character",rep("numeric",2)))
str(dachu)
dachu <- dachu[,4:5]
head(dachu)
dachu$买家昵称 <- substr(dachu$买家昵称,3,nchar(dachu$买家昵称)-1)
head(dachu,20)

library(dplyr)
#首单购买件数回购率
temp <- dachu %>%
  group_by(买家昵称, 下单时间) %>%
  summarise(count=n()) %>%
  arrange(买家昵称, 下单时间) %>%
  group_by(买家昵称) %>%
  mutate(count2=n()) %>%
  slice(1) %>%
  group_by(count) %>%
  mutate(n1 = n(), n2 = sum(count2>1), rate = n2/n1) %>%
  slice(1) %>%
  select(count, n1, n2, rate)

temp

win.graph()
plot(temp$count, temp$rate, main="首单购买件数与回购率", xlab = "首单购买件数",
     ylab = "回购客户占比", col="red")

#按月计算新客中回购客户占比
temp <- dachu %>%
  group_by(买家昵称, 下单时间) %>%
  summarise(count=n()) %>%  #连带件数
  mutate(year=as.integer(substr(下单时间,1,4)),
         month=as.integer(substr(下单时间,6,7))) %>%
  arrange(买家昵称, 下单时间) %>%
  group_by(买家昵称) %>%
  mutate(count2=n()) %>%  #回购次数
  slice(1) %>%  #第一次出现(前面的按时间排序不可少)即为新客
  group_by(year, month) %>%
  mutate(n1 = n(), n2 = sum(count>1), rate = n2/n1) %>%
  slice(1) %>%
  select(下单时间, year, month, n1, n2, rate)
  
temp
win.graph()
time <- seq.Date(as.Date(paste(substr(min(temp$下单时间),1,7), "-01", sep = "")), 
                 by = "month", length = nrow(temp))
plot(time, temp$rate, main = "各月新客中连带客户占比", xlab = "月份",
     ylab = "首单购买多件客户占比", type = "l")


#按订单统计连带率(即购买多件订单与总订单之比)
temp <- dachu %>%
  group_by(买家昵称, 下单时间) %>%
  summarise(count=n())

sum(temp$count>1)/nrow(temp)

Sys.time()-t0





###############################################################################################################
#setwd("H:/数据分析/内部数据/薏凡特旗舰店数据/旗舰店客户数据分析/0803")
setwd("D:\\Dasktop\\bigdata_game\\天池\\大厨")
dat <- read.csv("kehushuju.csv",header=TRUE,encoding="utf-8",colClasses=c("character","Date","integer","numeric","integer"),stringsAsFactors = F)
dat <- arrange(dat, 买家昵称, 下单日期)
head(dat)
# new_dat<-unique(dat)  #数据量多时，计算量很大，而且基本不会出现重复记录，所以可以省略
# head(new_dat)
library(dplyr)

##回购次数与回购概率
###
temp <- dat %>%
  group_by(买家昵称)%>%
  summarise(count=n())
head(temp)
rr1 <- c()
rr2 <- c()
rate <- c()
max_count <- max(temp$count)
for (i in 1:(max_count-1)){    ###可能会出错，rate分母=0
  # rr1[i] <- summarise(filter(temp,count==i+1),n())
  # rr2[i] <- summarise(filter(temp,count>=i),n())
  # rate[i] <- summarise(filter(temp,count==i+1),n())/summarise(filter(temp,count>=i),n())
  rr1 <- c(rr1, sum(temp$count == i+1))  #效率更高
  rr2 <- c(rr2, sum(temp$count >= i))
  rate <- c(rate, rr1[i]/rr2[i])  #避免重复计算
}
temp2<-filter(temp,count>=2)
head(temp2)
rrr<-cbind(rr1,rr2,rate)

rrr
# write.csv(rrr,"H:/数据分析/内部数据/薏凡特旗舰店数据/旗舰店客户数据分析/0803/rrr.csv")


#计算回购周期#####

#添加购买次数列

new_dat2 <- select(dat, 买家昵称,下单日期, 下单时点)
# new_dat2<-data.frame(new_dat2)   #已经是数据框结构，而且即便转换格式此处也不对，应该为：new_dat2<-as.data.frame(new_dat2)
# new_dat2<-unique(new_dat2)
# head(new_dat2)

# temp2<-group_by(new_dat2,买家昵称)
# temp2<-summarise(temp2,count=n())
# temp2 <- new_dat2 %>%
#   group_by(买家昵称) %>%
#   summarise(count=n())
# head(temp2)
# count2<-unique(temp2$count)
# 
# new_dat2$counts=0  
# for(i in count2){  
#   rg<-temp[temp2$count==i,]$买家昵称;
#   new_dat2[new_dat2$买家昵称 %in% rg,]$counts=i
#   
# }

new_dat2 <- merge(new_dat2, temp, by=c(‘买家昵称‘))



head(new_dat2)
# old_dat<-filter(new_dat2,counts>=2)
# old_dat<-arrange(old_dat,下单日期)
# old_dat <- new_dat2 %>%    ##此处太慢，后面给出改进方法
#   filter(count>=2) %>%
#   arrange(下单日期)
# # old_dat<-unique(old_dat)
# head(old_dat)
# #max_count2<-max(old_dat$counts)
# #num<-c(1:max_count2)
# rebuy<-c()
# redays<-c()
# # t=1
# for(i in unique(old_dat$买家昵称) ){
#   rg<-filter(old_dat,old_dat$买家昵称==i)
#   
#   for(j in 1:(rg$count[1]-1))
#   {
#     #t_diff <- rg$下单日期[j+1] - rg$下单日期[j]
#     t_diff <- as.integer(rg$下单日期[j+1] - rg$下单日期[j])
#     # rebuy[t]=j+1
#     # redays[t]=t_diff
#     # t=t+1
#     rebuy = c(rebuy,j+1)
#     redays = c(redays,t_diff)
#   }
# }
# 
# head(rebuy)
# head(redays)
# mydata<-data.frame(rebuy,redays)
# #write.csv(mydata,"H:/数据分析/内部数据/薏凡特旗舰店数据/旗舰店客户数据分析/0803/mydata.csv")
# head(mydata)


###各时点回购人数占比
#不考虑时间因素时
rate <- data.frame()
for(i in sort(unique(dat$下单时点))){
  temp2 = new_dat2[new_dat2$下单时点 == i,]$count
  rate = rbind(rate, c(i, sum(temp2>1)/length(temp2)))
}
colnames(rate) <- c("下单时点", "rate")
rate

#考虑时间因素时
###如果考虑时间因素，则需加以下代码
new_dat3 <- arrange(new_dat2, 买家昵称, 下单日期)  #最好加排序，防止出错
head(new_dat3, 50)
# for(i in temp$买家昵称){  #由于循环较大故运行时间较长
#   new_dat3[new_dat3$买家昵称 == i,]$count <- 1:(temp[temp$买家昵称 == i,]$count)
# }
# head(new_dat3, 50)

#改进后,此方法必须对数据先排序！！
# t0 <- Sys.time()
# i <- 1; nmax <- nrow(new_dat3)
# repeat{
#   #m = i
#   n = new_dat3[i,4]
#   #ss = new_dat3[i,1]
#   # repeat{
#   #   i <- i + 1
#   #   if((new_dat3[i,1] != ss) | (i > nmax)){
#   #     new_dat3[m:(i-1),4] <- 1:new_dat3[m,4]
#   #     break
#   #   }
#   # }
#   new_dat3[i:(i + n - 1),4] <- 1:n
#   i = i+n
#   if(i > nmax)  break
# }
# Sys.time()-t0
# 
# t0 <- Sys.time()
# i <- 1; nmax <- nrow(new_dat3)
# while(i <= nmax){
#   #m = i
#   n = new_dat3[i,4]
#   #ss = new_dat3[i,1]
#   # repeat{
#   #   i <- i + 1
#   #   if((new_dat3[i,1] != ss) | (i > nmax)){
#   #     new_dat3[m:(i-1),4] <- 1:new_dat3[m,4]
#   #     break
#   #   }
#   # }
#   new_dat3[i:(i + n - 1),4] <- 1:n
#   i = i+n
# }
# Sys.time()-t0


t0 <- Sys.time()
for(i in sort(unique(temp$count))){  #必须加sort排序
  df = (new_dat3$count == i)
  new_dat3[df, 4] <- rep(1:i, sum(df)/i)
}
Sys.time()-t0
head(new_dat3, 50)
tail(new_dat3,50)

#计算
rate2 <- data.frame(下单时点=c(), rate=c())
for(i in sort(unique(dat$下单时点))){
  temp2 = new_dat3[new_dat3$下单时点 == i,]$count
  rate2 = rbind(rate2, c(i, sum(temp2>1)/length(temp2)))
}
colnames(rate2) <- c("下单时点", "rate")
rate2


#改进方法
new_dat3$t_diff <- as.integer(new_dat3$下单日期 - c(new_dat3$下单日期[1], new_dat3$下单日期[-nrow(new_dat3)]))
head(new_dat3)
new_dat3$t_diff[new_dat3$count==1] <- 0
mydata <- new_dat3 %>%
  select(count, t_diff) %>%
  filter(count > 1) %>%
  rename(rebuy = count, redays = t_diff)
head(mydata)

plot(mydata)


#各次购买5天内回购情况
new_dat3$m5 <- (new_dat3$t_diff <5)
new_dat3$m5[new_dat3$count == 1] <- 0



setwd("H:/数据分析/内部数据/薏凡特旗舰店数据/旗舰店客户数据分析/0803/自我研究")
dat<-read.csv("kehushuju.csv",header=T,encoding="utf-8",colClasses=c("character","Date","integer","numeric","integer"))
head(dat)
library(dplyr)
dat1<-arrange(dat,下单日期)
head(dat1)
m=5 #定义回购周期，M=5表示客户在5天内回购
counts<-c(rep(0,length(dat1[,2])))
t0<-Sys.time()
for(i in 1:length(dat1[,2])){
  t_run<-dat1[,2][i]+m
  goal_dat1<-filter(dat1,下单日期<=t_run)
  if(length(filter(goal_dat1,goal_dat1$买家昵称==dat1[,1][i])[,1])>=2){
    counts[i]<-1
  }
}
tt<-Sys.time()-t0
head(counts)
end_dat5<-cbind(dat1,counts)
write.csv(end_dat5,"H:/数据分析/内部数据/薏凡特旗舰店数据/旗舰店客户数据分析/0803/自我研究/end_dat5.csv")