我有两张桌子:
> dat:包含数据
>日期:包含日期表
library(data.table)
dates = structure(list(date = structure(c(17562, 17590, 17621, 17651,
17682, 17712, 17743, 17774, 17804, 17835, 17865, 17896), class = "Date")),
row.names = c(NA, -12L), class = "data.frame")
dat = structure(list(date = structure(c(17546, 17743, 17778, 17901,
17536, 17806, 17901, 17981, 17532, 17722, 17969, 18234), class = "Date"),
country = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L,
3L, 3L, 3L), .Label = c("AAA", "BBB", "CCC"), class = "factor"),
state = structure(c(1L, 1L, 2L, 3L, 4L, 1L, 2L, 5L, 6L, 1L,
2L, 2L), .Label = c("S1", "S2", "S3", "S4", "S5", "S6"), class = "factor"),
item = structure(c(1L, 2L, 4L, 6L, 3L, 5L, 3L, 2L, 2L, 4L,
5L, 7L), .Label = c("M1", "M2", "M3", "M4", "M5", "M6", "M7"
), class = "factor"), value = c(67L, 10L, 50L, 52L, 93L,
50L, 62L, 46L, 6L, 30L, 30L, 14L)), row.names = c(NA, -12L
), class = "data.frame")
dates = data.table(dates)
dat = data.table(dat)
setkey(dates, date)
setkey(dat, date)
我追求的结果如下.即,对每个单独的dat行进行滚动连接,然后组合结果.
rbind(
dat[1,][dates, roll = 90],
dat[2,][dates, roll = 90],
dat[3,][dates, roll = 90],
...
dat[12,][dates, roll = 90]
)
我的实际数据集要大得多,因此列出每一行数据并不实际.没有循环,是否有一种简单的方法来做同样的事情?
最佳答案 如果我正确理解您的意图,您希望将记录翻转90天.
我使用交叉连接,然后使用翻转标准来子集
你的原始表格:
library(data.table)
dates = structure(list(date = structure(c(17562, 17590, 17621, 17651,
17682, 17712, 17743, 17774, 17804, 17835, 17865, 17896), class = "Date")),
row.names = c(NA, -12L), class = "data.frame")
dat = structure(list(date = structure(c(17546, 17743, 17778, 17901,
17536, 17806, 17901, 17981, 17532, 17722, 17969, 18234), class = "Date"),
country = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L,
3L, 3L, 3L), .Label = c("AAA", "BBB", "CCC"), class = "factor"),
state = structure(c(1L, 1L, 2L, 3L, 4L, 1L, 2L, 5L, 6L, 1L,
2L, 2L), .Label = c("S1", "S2", "S3", "S4", "S5", "S6"), class = "factor"),
item = structure(c(1L, 2L, 4L, 6L, 3L, 5L, 3L, 2L, 2L, 4L,
5L, 7L), .Label = c("M1", "M2", "M3", "M4", "M5", "M6", "M7"
), class = "factor"), value = c(67L, 10L, 50L, 52L, 93L,
50L, 62L, 46L, 6L, 30L, 30L, 14L)), row.names = c(NA, -12L
), class = "data.frame")
dates = data.table(dates)
dat = data.table(dat)
注意,我没有setkey.
CJ.table.1 <- function(X,Y)
setkey(X[,c(k=1,.SD)],k)[Y[,c(k=1,.SD)],allow.cartesian=TRUE][,k:=NULL]
然后我交叉连接,滚动连接的子集,重命名列和排序
dsn1<-CJ.table.1(dat,dates)[i.date-date<=90 & i.date-date>=0][,.(date=i.date,country, state, item, value)][order(country, state, item, value,date),]