我正在尝试找到一种有效的方法来执行以下代码片段，但是在一个相当大的数据帧(2M +记录(上。 我尝试使用sapply和for loop但都不是很好。
"ACCOUNT_CLOSE_DATE"恰好是空白的，但它是给定"U_ID"的最后一个"AS_OF_DATE"。 我想将此特定值插入"U_ID"的"ACCOUNT_CLOSE_DATE"列中。 任何帮助将不胜感激！
library(reshape2)
cnames = c("Date", "999:999", "888:888", "777:777")
dates = c("31JAN2005", "28FEB2005", "31MAR2005")
val = ""
mydf = data.frame(cbind(dates, matrix(val, nrow = 3, ncol = 3)))
colnames(mydf) = cnames
nmydf = melt(mydf, id.vars = "Date")
nmydf$Date = as.character(nmydf$Date)
colnames(nmydf) = c("AS_OF_DATE", "U_ID", "ACCOUNT_CLOSE_DATE")
uvals = c("999:999", "888:888", "777:777")
nmydf[nmydf$U_ID == uvals[1],"ACCOUNT_CLOSE_DATE"] =
nmydf[nmydf$U_ID == uvals[1], "AS_OF_DATE"][length(nmydf[nmydf$U_ID == uvals[1], "AS_OF_DATE"])]
您可以执行 data.table 联接，以便获取每组 "U_ID" 到表中的结束日期，如下所示：
library(data.table)
cnames <- c("Date", "999:999", "888:888", "777:777")
dates <- c("31JAN2005", "28FEB2005", "31MAR2005")
val <- ""
mydt <- data.table(cbind(dates, matrix(val, nrow = 3, ncol = 3)))
setnames(mydt, cnames)
nmydt <- melt(mydt, id.vars = "Date")[,Date:variable]
setnames(nmydt, c("AS_OF_DATE", "U_ID"))
closing_dates <- setnames(nmydt[, .SD[.N], by=U_ID], c("U_ID", "ACCOUNT_CLOSE_DATE"))
merge(nmydt, closing_dates, by="U_ID", all.x=TRUE)
# U_ID AS_OF_DATE ACCOUNT_CLOSE_DATE
# 1: 999:999 31JAN2005 31MAR2005
# 2: 999:999 28FEB2005 31MAR2005
# 3: 999:999 31MAR2005 31MAR2005
# 4: 888:888 31JAN2005 31MAR2005
# 5: 888:888 28FEB2005 31MAR2005
# 6: 888:888 31MAR2005 31MAR2005
# 7: 777:777 31JAN2005 31MAR2005
# 8: 777:777 28FEB2005 31MAR2005
# 9: 777:777 31MAR2005 31MAR2005
该解决方案还应提高效率。