我有两个数据框。一份包含一个月内的购买情况，一份包含该月播放的广告（广告）。要了解购买是否可以可靠地链接到广告 - 我想了解有多少购买日期是在广告后 4 天内发生的。我创建了一些（繁琐的）代码来执行此操作 - 基于广告数据库的每一行的扩展以覆盖相关的 4 天时间段 - 然后使用合并构造来查看哪里（缺少）重叠。这感觉是一种非常麻烦的做事方式。理想情况下 - 我希望以优雅的方式在 dplyr 中完成此操作。如果有人有任何建议请告诉我
library(dplyr)
library(lubridate)
require(data.table)
# set start and end dates to sample between
day.start <- "2007/01/01"
day.end <- "2007/01/30"
set.seed(1) # define a random date/time selection function
rand.day.time <- function(day.start,day.end,size) {
dayseq <- seq.Date(as.Date(day.start),as.Date(day.end),by="day")
dayselect <- sample(dayseq,size,replace=TRUE)
as.POSIXlt(paste(dayselect) )
}
dateval=rand.day.time(day.start,day.end,size=20)
###create initial dataframes
action=rep(c("ad","purchase"),10)
id=rep(c(1,1,2,2),5)
df=data.frame(customer=id,date=dateval,action=action)
df_pur=filter(df,action=="purchase");(df_pur=df_pur[order(df_pur$date),])
df_ad=filter(df,action=="ad");(df_ad=df_ad[order(df_ad$date),])
#expand data-frame to include all the ranges for which the ad might trigger purchases
df_ad_exp = df_ad %>%
group_by(customer,date) %>%
summarize(start=min(date),end=min(date+days(4)))
df_ad_exp=as.data.frame(df_ad_exp)
df_ad_exp2=setDT(df_ad_exp)[, list(customer=customer, range=seq(start,end,by="day")), by=1:nrow(df_ad_exp)]
###merge the dataframe, use NA values to identify those dates in which purchase was made but no ad was "active"
df_ad_exp2=as.data.frame(df_ad_exp2)
(df_ad_exp2=df_ad_exp2[,c("customer","range")])
df_ad_exp2$helpercol=0
(df_pur_m=merge(df_pur,df_ad_exp2,by.x=c("date","customer"),by.y=c("range","customer"),all.x=TRUE))
df_pur_m$ad_in_range=df_pur_m$helpercol;df_pur_m$helpercol=NULL
df_pur_m$ad_in_range[!is.na(df_pur_m$ad_in_range)]=1;df_pur_m$ad_in_range[is.na(df_pur_m$ad_in_range)]=0
#outcomes
df_pur
df_ad
df_pur_m
> df_ad
customer date action
3 1 2007-01-07 ad
6 2 2007-01-07 ad
1 1 2007-01-08 ad
10 2 2007-01-12 ad
2 2 2007-01-18 ad
5 1 2007-01-19 ad
7 1 2007-01-21 ad
9 1 2007-01-22 ad
8 2 2007-01-24 ad
4 2 2007-01-29 ad
> df_pur_m
date customer action ad_in_range
1 2007-01-02 1 purchase 0
2 2007-01-06 2 purchase 0
3 2007-01-12 1 purchase 1
4 2007-01-12 1 purchase 1
5 2007-01-15 2 purchase 1
6 2007-01-20 2 purchase 1
7 2007-01-24 2 purchase 1
8 2007-01-27 1 purchase 0
9 2007-01-28 2 purchase 1
10 2007-01-30 1 purchase 0
