为了使这个R -faq问题更完整，一个带sequence和rle的base R替代方案:

df$num <- sequence(rle(df$cat)$lengths)

给出了预期的结果:

> df 猫val num 4是0.05638315 2是0.25767250 2 1是0.30776611 结果是0.46854928 3是0.55232243 5 10 BBB 0.17026205 8 BBB 0.37032054 6 BBB 0.48377074 9 bb 0.54655860 7 Bob 0.81240262 13 c 0.28035384 14 CCC 0.39848790 11 cc 0.62499648 15 cc 0.76255108 12 c 0.88216552

如果df$cat是一个因子变量，则需要将其包装为。性格:

df$num <- sequence(rle(as.character(df$cat))$lengths)

我想增加一个数据。使用rank()函数的表变体，它提供了额外的可能性来改变排序，从而使它比seq_len()解决方案更灵活，并且非常类似于RDBMS中的row_number函数。

# Variant with ascending ordering
library(data.table)
dt <- data.table(df)
dt[, .( val
   , num = rank(val))
    , by = list(cat)][order(cat, num),]

    cat        val num
 1: aaa 0.05638315   1
 2: aaa 0.25767250   2
 3: aaa 0.30776611   3
 4: aaa 0.46854928   4
 5: aaa 0.55232243   5
 6: bbb 0.17026205   1
 7: bbb 0.37032054   2
 8: bbb 0.48377074   3
 9: bbb 0.54655860   4
10: bbb 0.81240262   5
11: ccc 0.28035384   1
12: ccc 0.39848790   2
13: ccc 0.62499648   3
14: ccc 0.76255108   4

# Variant with descending ordering
dt[, .( val
   , num = rank(desc(val)))
    , by = list(cat)][order(cat, num),]

在2021-04-16进行编辑，使降序和升序之间的切换更加安全

在data.table中使用rowid()函数:

> set.seed(100)  
> df <- data.frame(cat = c(rep("aaa", 5), rep("bbb", 5), rep("ccc", 5)), val = runif(15))
> df <- df[order(df$cat, df$val), ]  
> df$num <- data.table::rowid(df$cat)
> df
   cat        val num
4  aaa 0.05638315   1
2  aaa 0.25767250   2
1  aaa 0.30776611   3
5  aaa 0.46854928   4
3  aaa 0.55232243   5
10 bbb 0.17026205   1
8  bbb 0.37032054   2
6  bbb 0.48377074   3
9  bbb 0.54655860   4
7  bbb 0.81240262   5
13 ccc 0.28035384   1
14 ccc 0.39848790   2
11 ccc 0.62499648   3
15 ccc 0.76255108   4
12 ccc 0.88216552   5

在dplyr的devel版本中

library(dplyr)
df %>%
  mutate(num = row_number(), .by = "cat")

使用ave, ddply, dplyr或data.table:

df$num <- ave(df$val, df$cat, FUN = seq_along)

or:

library(plyr)
ddply(df, .(cat), mutate, id = seq_along(val))

or:

library(dplyr)
df %>% group_by(cat) %>% mutate(id = row_number())

or(最有效的内存，因为它在DT中通过引用分配):

library(data.table)
DT <- data.table(df)

DT[, id := seq_len(.N), by = cat]
DT[, id := rowid(cat)]

这里有一个小的改进技巧，允许在组内排序'val':

# 1. Data set
set.seed(100)
df <- data.frame(
  cat = c(rep("aaa", 5), rep("ccc", 5), rep("bbb", 5)), 
  val = runif(15))             

# 2. 'dplyr' approach
df %>% 
  arrange(cat, val) %>% 
  group_by(cat) %>% 
  mutate(id = row_number())