英文:
pivot columns with irregular names into rows
问题
df2 <- structure(list(A = c("A_1_01", "A_1_01", "A_1_01"), B = c("A", "A", "A"),
C = c("1", "1", "1"), D = c("inside", "eating", "sleeping"),
`1` = c("1", "1", "0"), `2` = c("1", "0", "0"), `3` = c("0", "0", "1"),
`4` = c("0", "1", "1"), `1_Location` = c("I", "I", "I"), `2_Location` = c("I", "I", "I"),
`3_Location` = c("O", "O", "O"), `4_Location` = c("O", "O", "O")),
class = "data.frame", row.names = c(NA, -3L))
df3 <- structure(list(H = c("1", "2", "3", "4", "1", "2", "3", "4", "1", "2", "3", "4"),
A = c("A_1_01", "A_1_01", "A_1_01", "A_1_01", "A_1_01", "A_1_01", "A_1_01", "A_1_01", "A_1_01", "A_1_01", "A_1_01", "A_1_01"),
B = c("A", "A", "A", "A", "A", "A", "A", "A", "A", "A", "A", "A"),
C = c("1", "1", "1", "1", "1", "1", "1", "1", "1", "1", "1", "1"),
D = c("inside", "inside", "inside", "inside", "eating", "eating", "eating", "eating", "sleeping", "sleeping", "sleeping", "sleeping"),
Value = c(1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 1, 1),
Location = c("I", "I", "O", "O", "I", "I", "O", "O", "I", "I", "O", "O")),
class = "data.frame", row.names = c(NA, -12L))
英文:
Using R how do I pivot the columns into rows to get the required structure in df3 from df2, while extracting new information from the previous dataframe:
df2<- structure(list(A=c("A_1_01", "A_1_01", "A_1_01"), B=c("A", "A", "A"), C=c("1", "1", "1"), D=c("inside", "eating", "sleeping"), "1"=c("1","1","0"), "2"=c("1","0","0"), "3"=c("0","0","1"), "4"=c("0","1","1"), "1_Location"=c("I","I", "I"), "2_Location"=c("I","I", "I"), "3_Location"=c("O","O", "O"), "4_Location"=c("O","O", "O")), class= "data.frame", row.names = c(NA,-3L))
df3<- structure(list(H=c("1","2","3","4","1","2","3","4","1","2","3","4"),
A=c("A_1_01", "A_1_01", "A_1_01","A_1_01", "A_1_01",
"A_1_01","A_1_01", "A_1_01", "A_1_01","A_1_01",
"A_1_01", "A_1_01"),
B=c("A", "A", "A","A", "A", "A","A", "A", "A","A", "A", "A"),
C=c("1", "1", "1","1", "1", "1","1", "1", "1","1", "1", "1"),
D=c("inside","inside","inside","inside",
"eating","eating","eating","eating",
"sleeping","sleeping","sleeping","sleeping"),
Value=c(1,1,0,0,1,0,0,1,0,0,1,1),
Location=c("I","I","O","O","I","I","O","O","I","I","O","O")),
class= "data.frame", row.names = c(NA,-12L))
Thank you
答案1
得分: 3
尝试在仅包含数字的列名称后添加后缀“_Value”后，使用pivot_longer函数进行操作：
library(stringr)
library(tidyr)
library(dplyr)
df2 %>%
rename_with(~ str_c(.x, "_Value"), matches("^\\d+$")) %>%
pivot_longer(cols = contains("_"), names_to = c("H", ".value"),
names_pattern = "(\\d+)_(.*)")
-output
# A tibble: 12 × 7
A B C D H Value Location
<chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 A_1_01 A 1 inside 1 1 I
2 A_1_01 A 1 inside 2 1 I
3 A_1_01 A 1 inside 3 0 O
4 A_1_01 A 1 inside 4 0 O
5 A_1_01 A 1 eating 1 1 I
6 A_1_01 A 1 eating 2 0 I
7 A_1_01 A 1 eating 3 0 O
8 A_1_01 A 1 eating 4 1 O
9 A_1_01 A 1 sleeping 1 0 I
10 A_1_01 A 1 sleeping 2 0 I
11 A_1_01 A 1 sleeping 3 1 O
12 A_1_01 A 1 sleeping 4 1 O
英文:
Try with pivot_longer after adding a suffix '_Value' to the digit only column names
library(stringr)
library(tidyr)
library(dplyr)
df2 %>%
rename_with(~ str_c(.x, "_Value"), matches("^\\d+$")) %>%
pivot_longer(cols = contains("_"), names_to = c("H", ".value"),
names_pattern = "(\\d+)_(.*)")
-output
# A tibble: 12 × 7
A B C D H Value Location
<chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 A_1_01 A 1 inside 1 1 I
2 A_1_01 A 1 inside 2 1 I
3 A_1_01 A 1 inside 3 0 O
4 A_1_01 A 1 inside 4 0 O
5 A_1_01 A 1 eating 1 1 I
6 A_1_01 A 1 eating 2 0 I
7 A_1_01 A 1 eating 3 0 O
8 A_1_01 A 1 eating 4 1 O
9 A_1_01 A 1 sleeping 1 0 I
10 A_1_01 A 1 sleeping 2 0 I
11 A_1_01 A 1 sleeping 3 1 O
12 A_1_01 A 1 sleeping 4 1 O
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库，让每个人都能够通过互相帮助和分享经验来进步。
评论