通过变量列表执行滚动求和的优雅,快速方法

Question

有没有人开发出一种优雅,快速的方式来按日期执行滚动总和？例如,如果我想通过Cust_ID为以下数据集创建一个180天的滚动总计,有没有办法更快地完成它(比如data.table中的某些内容).我一直在使用以下示例来计算滚动总和,但恐怕效率低得多.

library("zoo")
library("plyr")
library("lubridate")

##Make some sample variables
set.seed(1)
Trans_Dates <- as.Date(c(31,33,65,96,150,187,210,212,240,273,293,320,
                         32,34,66,97,151,188,211,213,241,274,294,321,
                         33,35,67,98,152,189,212,214,242,275,295,322),origin="2010-01-01")
Cust_ID <- c(rep(1,12),rep(2,12),rep(3,12))
Target <- rpois(36,3)

##Combine into one dataset
Example.Data <- data.frame(Trans_Dates,Cust_ID,Target)

##Create extra variable with 180 day rolling sum
Example.Data2 <- ddply(Example.Data, .(Cust_ID), 
  function(datc) adply(datc, 1, 
   function(x) data.frame(Target_Running_Total =
    sum(subset(datc, Trans_Dates>(as.Date(x$Trans_Dates)-180) & Trans_Dates<=x$Trans_Dates)$Target))))

#Print new data
Example.Data2 

Answer 1

我想我偶然发现了一个相当有效的答案..

set.seed(1)
Trans_Dates <- as.Date(c(31,33,65,96,150,187,210,212,240,273,293,320,
                         32,34,66,97,151,188,211,213,241,274,294,321,
                         33,35,67,98,152,189,212,214,242,275,295,322),origin="2010-01-01")
Cust_ID <- c(rep(1,12),rep(2,12),rep(3,12))
Target <- rpois(36,3)

##Make simulated data into a data.table
library(data.table)
data <- data.table(Cust_ID,Trans_Dates,Target)

##Assign each customer an number that ranks them
data[,Cust_No:=.GRP,by=c("Cust_ID")]

##Create "list" of comparison dates
Ref <- data[,list(Compare_Value=list(I(Target)),Compare_Date=list(I(Trans_Dates))), by=c("Cust_No")]

##Compare two lists and see of the compare date is within N days
data$Roll.Val <- mapply(FUN = function(RD, NUM) {
  d <- as.numeric(Ref$Compare_Date[[NUM]] - RD)
  sum((d <= 0 & d >= -180)*Ref$Compare_Value[[NUM]])
}, RD = data$Trans_Dates,NUM=data$Cust_No)

##Print out data
data <- data[,list(Cust_ID,Trans_Dates,Target,Roll.Val)][order(Cust_ID,Trans_Dates)]
data