我试图根据数据集中另一列 measurement_type 的值创建一个新列 Jar。
如果列 Jar = blank 并且 Jar 的前一个值（在上面的行中）是 8，那么我希望测量类型发生变化。
我已经试过了，但我无法让它工作
addmeasurementVector <- function(df)
{
measurement <- c("a", "b", "c", "d", "e")
#initial values
measurement_type <- vector() #will become a new column
previousJar <- 0
current_measurement_type <- "a"
#loops through every row to create a new column
for (row in 1:nrow(dt))
{
currentJar <- df[row, "Jar"]
#criteria for a change of measurement_type
if (previousJar == "8" & currentJar == "blank")
current_measurement_type <- measurement[match(current_measurement_type, measurement) + 1] #change of measurement_type to next type
measurement_type <- c(measurement_type, current_measurement_type) #adds the new column item
previousJar <- currentJar #for the next iteration
}
df <- cbind(df, measurement) #adds the new column
return(df)
}
有什么想法吗？
df 看起来像这样
df <- structure(list(Jar = c("blank", "1", "2", "3", "4", "blank",
"5", "6", "7", "8", "blank", "1", "2", "3", "4", "blank", "5",
"6", "7", "8", "blank", "1", "2", "3", "4", "blank", "5", "6",
"7", "8", "blank", "1", "2", "3", "4", "blank", "5", "6", "7",
"8", "blank", "1", "2", "3", "4", "blank", "5", "6", "7", "8"
)), row.names = c(NA, -50L), class = "data.frame")
预期的 df 看起来像这样
expected_df <- structure(list(Jar = c("blank", "1", "2", "3", "4", "blank",
"5", "6", "7", "8", "blank", "1", "2", "3", "4", "blank", "5",
"6", "7", "8", "blank", "1", "2", "3", "4", "blank", "5", "6",
"7", "8", "blank", "1", "2", "3", "4", "blank", "5", "6", "7",
"8", "blank", "1", "2", "3", "4", "blank", "5", "6", "7", "8"
), measurement_type = c("a", "a", "a", "a", "a", "a", "a", "a",
"a", "a", "b", "b", "b", "b", "b", "b", "b", "b", "b", "b", "c",
"c", "c", "c", "c", "c", "c", "c", "c", "c", "d", "d", "d", "d",
"d", "d", "d", "d", "d", "d", "e", "e", "e", "e", "e", "e", "e",
"e", "e", "e")), class = "data.frame", row.names = c(NA, -50L
))
答案 0 :(得分：2)
这个就行了
df$measurement_type <- letters[cumsum(df$Jar == 'blank' & c("1", df$Jar[-nrow(df)]) == '8') +1]
Jar measurement_type
1 blank a
2 1 a
3 2 a
4 3 a
5 4 a
6 blank a
7 5 a
8 6 a
9 7 a
10 8 a
11 blank b
12 1 b
13 2 b
14 3 b
15 4 b
16 blank b
17 5 b
18 6 b
19 7 b
20 8 b
21 blank c
22 1 c
23 2 c
24 3 c
25 4 c
26 blank c
27 5 c
28 6 c
29 7 c
30 8 c
31 blank d
32 1 d
33 2 d
34 3 d
35 4 d
36 blank d
37 5 d
38 6 d
39 7 d
40 8 d
41 blank e
42 1 e
43 2 e
44 3 e
45 4 e
46 blank e
47 5 e
48 6 e
49 7 e
50 8 e
library(dplyr)
df %>% mutate(measurement_type = cumsum(Jar == 'blank' & lag(Jar, default = "1") == "8"))
Jar measurement_type
1 blank 0
2 1 0
3 2 0
4 3 0
5 4 0
6 blank 0
7 5 0
8 6 0
9 7 0
10 8 0
11 blank 1
12 1 1
13 2 1
14 3 1
15 4 1
16 blank 1
17 5 1
18 6 1
19 7 1
20 8 1
21 blank 2
22 1 2
23 2 2
24 3 2
25 4 2
26 blank 2
27 5 2
28 6 2
29 7 2
30 8 2
31 blank 3
32 1 3
33 2 3
34 3 3
35 4 3
36 blank 3
37 5 3
38 6 3
39 7 3
40 8 3
41 blank 4
42 1 4
43 2 4
44 3 4
45 4 4
46 blank 4
47 5 4
48 6 4
49 7 4
50 8 4
或
df %>% mutate(measurement_type = cumsum(Jar == 'blank' & lag(Jar, default = "1") == "8"),
measurement_type = letters[measurement_type +1])
Jar measurement_type
1 blank a
2 1 a
3 2 a
4 3 a
5 4 a
6 blank a
7 5 a
8 6 a
9 7 a
10 8 a
11 blank b
12 1 b
13 2 b
14 3 b
15 4 b
16 blank b
17 5 b
18 6 b
19 7 b
20 8 b
21 blank c
22 1 c
23 2 c
24 3 c
25 4 c
26 blank c
27 5 c
28 6 c
29 7 c
30 8 c
31 blank d
32 1 d
33 2 d
34 3 d
35 4 d
36 blank d
37 5 d
38 6 d
39 7 d
40 8 d
41 blank e
42 1 e
43 2 e
44 3 e
45 4 e
46 blank e
47 5 e
48 6 e
49 7 e
50 8 e