将R中数据表中的连续行分组

Mod运算符 %/%

df[, group := (1:.N - 1) %/% 3]
df
#    X1 X2 group
# 1:  1  A     0
# 2:  2  B     0
# 3:  3  C     0
# 4:  4  D     1
# 5:  5  E     1
# 6:  6  F     1
# 7:  7  G     2
# 8:  8  H     2
# 9:  9  I     2
#10: 10  J     3
#11: 11  K     3
#12: 12  L     3

你也可以使用 rep

df[, group := rep(1:(.N / 3) - 1, each = 3)]
df
#    X1 X2 group
# 1:  1  A     0
# 2:  2  B     0
# 3:  3  C     0
# 4:  4  D     1
# 5:  5  E     1
# 6:  6  F     1
# 7:  7  G     2
# 8:  8  H     2
# 9:  9  I     2
#10: 10  J     3
#11: 11  K     3
#12: 12  L     3

consecutive_groups <- function(df, group_length = 3) {
  n_groups <- if_else(nrow(df) %% group_length == 0L, 
                      nrow(df) / group_length, 
                      as.integer(nrow(df) / group_length) + 1 )
  df %>% mutate(row_number = row_number(), 
                group = ntile(row_number, n_groups) - 1) %>% 
         select(-row_number)
}




 consecutive_groups(df, 3)
   #     X1 X2 group
   # 1   1  A     0
   # 2   2  B     0
   # 3   3  C     0
   # 4   4  D     1
   # 5   5  E     1
   # 6   6  F     1
   # 7   7  G     2
   # 8   8  H     2
   # 9   9  I     2
   # 10 10  J     3
   # 11 11  K     3
   # 12 12  L     3

对于此具有快速功能的特定情况:

   group <- function(dt,groupsize)
    {
      if(nrow(dt) %% groupsize != 0){
        print("Groupsize must be divisor of nrow!")
        return()
      }
    return(cbind(dt,data.frame(group=unlist(lapply(1:(nrow(dt) / groupsize),function(i){rep(i,groupsize)}))))))
    }