test <- data.frame('prod_id'= c("shoe", "shoe", "shoe", "shoe", "shoe", "shoe", "boat", "boat","boat","boat","boat","boat"),
'seller_id'= c("a", "b", "c", "d", "e", "f", "a","g", "h", "r", "q", "b"),
'Dich'= c(1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0),
'price' = c(120, 20, 10, 4, 3, 4, 30, 43, 56, 88, 75, 44)
)
test
prod_id seller_id Dich price
1 shoe a 1 120
2 shoe b 0 20
3 shoe c 0 10
4 shoe d 0 4
5 shoe e 0 3
6 shoe f 0 4
7 boat a 0 30
8 boat g 0 43
9 boat h 1 56
10 boat r 0 88
11 boat q 0 75
12 boat b 0 44
因此，我想创建一个新列，该列基于Dich的值获取价格列中观察值之间的差异，其中每个观察值与每个prod_id组中Dich == 1的观察值之间的差异。
这是我下面想要的结果。
prod_id seller_id Dich price diff_p
1 shoe a 1 120 0
2 shoe b 0 20 -100
3 shoe c 0 10 -110
4 shoe d 0 4 -116
5 shoe e 0 3 -117
6 shoe f 0 4 -116
7 boat a 0 30 -26
8 boat g 0 43 -13
9 boat h 1 56 0
10 boat r 0 88 32
11 boat q 0 75 19
12 boat b 0 44 -12
答案 0 :(得分：1)
按“ prod_id”分组后，取“ Dich”为1的“ price”和“ price”之差
library(dplyr)
test %>%
group_by(prod_id) %>%
mutate(diff_p = price - price[Dich == 1])
# A tibble: 12 x 5
# Groups: prod_id [2]
# prod_id seller_id Dich price diff_p
# <fct> <fct> <dbl> <dbl> <dbl>
# 1 shoe a 1 120 0
# 2 shoe b 0 20 -100
# 3 shoe c 0 10 -110
# 4 shoe d 0 4 -116
# 5 shoe e 0 3 -117
# 6 shoe f 0 4 -116
# 7 boat a 0 30 -26
# 8 boat g 0 43 -13
# 9 boat h 1 56 0
#10 boat r 0 88 32
#11 boat q 0 75 19
#12 boat b 0 44 -12
或使用data.table
library(data.table)
setDT(test)[, diff_p := price - price[Dich == 1], prod_id]