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

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)]

其他回答

另一个基于R的解决方案是将每只猫的数据帧分割,然后使用lapply:添加一个数字为1的列:nrow(x)。最后一步是用do返回最终的数据帧。调用,即:

        df_split <- split(df, df$cat)
        df_lapply <- lapply(df_split, function(x) {
          x$num <- seq_len(nrow(x))
          return(x)
        })
        df <- do.call(rbind, df_lapply)

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

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))

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())