处理类似这样的数据帧:

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  
   cat        val  
1  aaa 0.05638315  
2  aaa 0.25767250  
3  aaa 0.30776611  
4  aaa 0.46854928  
5  aaa 0.55232243  
6  bbb 0.17026205  
7  bbb 0.37032054  
8  bbb 0.48377074  
9  bbb 0.54655860  
10 bbb 0.81240262  
11 ccc 0.28035384  
12 ccc 0.39848790  
13 ccc 0.62499648  
14 ccc 0.76255108  
15 ccc 0.88216552 

我试图在每个组中添加一个编号列。这样做显然没有使用R的幂:

 df$num <- 1  
 for (i in 2:(length(df[,1]))) {  
   if (df[i,"cat"]==df[(i-1),"cat"]) {  
     df[i,"num"]<-df[i-1,"num"]+1  
     }  
 }  
 df  
   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  
15 ccc 0.88216552   5  

做这件事的好方法是什么?


当前回答

下面是一个按组而不是按行使用for循环的选项(就像OP那样)

for (i in unique(df$cat)) df$num[df$cat == i] <- seq_len(sum(df$cat == i))

其他回答

另一个dplyr可能是:

df %>%
 group_by(cat) %>%
 mutate(num = 1:n())

   cat      val   num
   <fct>  <dbl> <int>
 1 aaa   0.0564     1
 2 aaa   0.258      2
 3 aaa   0.308      3
 4 aaa   0.469      4
 5 aaa   0.552      5
 6 bbb   0.170      1
 7 bbb   0.370      2
 8 bbb   0.484      3
 9 bbb   0.547      4
10 bbb   0.812      5
11 ccc   0.280      1
12 ccc   0.398      2
13 ccc   0.625      3
14 ccc   0.763      4
15 ccc   0.882      5

在dplyr的devel版本中

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

下面是一个按组而不是按行使用for循环的选项(就像OP那样)

for (i in unique(df$cat)) df$num[df$cat == i] <- seq_len(sum(df$cat == i))

非常简单,整洁的解决方案。

整个data.frame的行号

library(tidyverse)

iris %>%
  mutate(row_num = seq_along(Sepal.Length)) %>%
  head

    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species row_num
1            5.1         3.5          1.4         0.2     setosa       1
2            4.9         3.0          1.4         0.2     setosa       2
3            4.7         3.2          1.3         0.2     setosa       3
..           ...         ...          ...         ...     ......     ...
148          6.5         3.0          5.2         2.0  virginica     148
149          6.2         3.4          5.4         2.3  virginica     149
150          5.9         3.0          5.1         1.8  virginica     150

在data.frame中按组进行行号

iris %>% 
  group_by(Species) %>% 
  mutate(num_in_group=seq_along(Species)) %>% 
  as.data.frame


    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species num_in_group
1            5.1         3.5          1.4         0.2     setosa            1
2            4.9         3.0          1.4         0.2     setosa            2
3            4.7         3.2          1.3         0.2     setosa            3
..           ...         ...          ...         ...     ......           ..
48           4.6         3.2          1.4         0.2     setosa           48
49           5.3         3.7          1.5         0.2     setosa           49
50           5.0         3.3          1.4         0.2     setosa           50
51           7.0         3.2          4.7         1.4 versicolor            1
52           6.4         3.2          4.5         1.5 versicolor            2
53           6.9         3.1          4.9         1.5 versicolor            3
..           ...         ...          ...         ...     ......           ..
98           6.2         2.9          4.3         1.3 versicolor           48
99           5.1         2.5          3.0         1.1 versicolor           49
100          5.7         2.8          4.1         1.3 versicolor           50
101          6.3         3.3          6.0         2.5  virginica            1
102          5.8         2.7          5.1         1.9  virginica            2
103          7.1         3.0          5.9         2.1  virginica            3
..           ...         ...          ...         ...     ......           ..
148          6.5         3.0          5.2         2.0  virginica           48
149          6.2         3.4          5.4         2.3  virginica           49
150          5.9         3.0          5.1         1.8  virginica           50

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)