使用R中的Data.Table实现两个列表的行差异

我不知道你为什么特别需要把它们列在一个列表中,但我写了一个小文章,可以帮助你。

df = data.table::data.table(id = c('A','B','C','A','B','A','A','A','D','E','E','E'), 
                            Value = c(1,2,3,4,3,5,2,3,7,2,3,9))

df = df[order(id, Value)]
df = df[duplicated(Value) == FALSE, diff := Value][]
df = df[, count := uniqueN(diff, na.rm = TRUE), by = id]

结果将是:

> df
    id Value diff count
 1:  A     1    1     5
 2:  A     2    2     5
 3:  A     3    3     5
 4:  A     4    4     5
 5:  A     5    5     5
 6:  B     2   NA     0
 7:  B     3   NA     0
 8:  C     3   NA     0
 9:  D     7    7     1
10:  E     2   NA     1
11:  E     3   NA     1
12:  E     9    9     1

希望这对你有帮助,或者至少让你开始。

library(data.table)
df = data.table(
    id = c('A','B','C','A','B','A','A','A','D','E','E','E'), 
    Value = c(1,2,3,4,3,5,2,3,7,2,3,9))

valset <- c()
df[, {
        d <- setdiff(Value, valset)
        valset <- unique(c(valset, Value))
        .(Values=.(Value), Diff=.(d), Count=length(d))
    }, 
    by=.(id)]

   id    Values      Diff Count
1:  A 1,4,5,2,3 1,4,5,2,3     5
2:  B       2,3               0
3:  C         3               0
4:  D         7         7     1
5:  E     2,3,9         9     1