为什么我在 R 中使用 case_when 的新列中没有得到我想要的类别？
Why do I not get my desired category in the new columns with case_when, in R?
我正在尝试创建一个新列 first_attack，其中包含基于 3 列的多个条件。我正在尝试仅使用 tidyverse 来实现这一目标。这是我的条件：
- 如果我在一列中有
Yes，而不管其他类别（No/Unknown/NA）在同一列中的相同 ID：previous_cabg, previous_pci, previous_ami 然后在测试变量中分配 Yes
- 如果我在同一 ID 的所有列中都有
No，则为测试变量分配 NO
- 如果我在一列中有
NO 并且在其他列中有相同 ID 的 NA/Unknown 然后在测试变量中分配 No
- 如果我在同一 ID 的所有列中都有
Yes，则在测试变量中分配 Yes
- if I have
Yes in one column and NA/Unknownfor the same id in each column then assignYes`in test variable
这是我拥有的数据集类型：
structure(list(id = c(112139L, 43919L, 92430L, 87137L, 95417L,
66955L, 16293L, 61396L, 25379L, 79229L, 27107L, 63243L, 50627L,
17968L, 83015L, 96549L, 7332L, 4873L, 98131L, 93506L, 52894L,
59327L, 85003L, 96623L, 82999L, 65769L, 67063L, 21744L, 62961L,
2229L, 103673L, 9367L, 60215L, 74044L, 58422L, 57530L, 100399L,
46483L, 108690L, 62017L, 46467L, 79562L, 4800L, 119158L, 103222L,
32908L, 14491L, 30293L, 52558L, 122304L, 42281L, 1553L, 111771L,
23087L, 30147L, 37842L, 51552L, 20148L, 28L, 7477L), previous_cabg = structure(c(1L,
1L, 1L, NA, 1L, NA, NA, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, NA, 1L, 1L, NA, 1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 3L,
1L, 1L, NA, 1L, 1L, 1L, 1L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 1L, 1L, 1L), .Label = c("No",
"Unknown", "Yes"), class = "factor"), previous_pci = structure(c(1L,
1L, 2L, NA, 1L, NA, NA, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
2L, NA, 2L, 1L, NA, 2L, NA, 1L, 2L, 1L, 1L, 1L, NA, 2L, 1L, 1L,
2L, 2L, NA, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 2L, 1L, 1L), .Label = c("No",
"Yes", "Unknown"), class = "factor"), previous_ami = structure(c(2L,
2L, 1L, 2L, 2L, NA, 2L, 1L, 2L, 2L, NA, 1L, 2L, 2L, 2L, 2L, 2L,
1L, NA, 1L, 2L, NA, 1L, NA, 2L, 1L, 2L, 2L, 2L, NA, 1L, 1L, 1L,
2L, 1L, NA, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 3L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, NA, 2L, 2L, 2L, 1L, 2L), .Label = c("Yes",
"No", "Unknown"), class = "factor")), row.names = c(NA, -60L), problems = structure(list(
row = c(34136L, 121773L, 121779L), col = c("1.01 Hospital identifier",
"1.01 Hospital identifier", "1.01 Hospital identifier"),
expected = c("value in level set", "value in level set",
"value in level set"), actual = c("CMH", "CMH", "CMH"), file = c("'../../data/changed/minap_2020_2021_second.csv'",
"'../../data/changed/minap_2020_2021_second.csv'", "'../../data/changed/minap_2020_2021_second.csv'"
)), row.names = c(NA, -3L), class = c("tbl_df", "tbl", "data.frame"
)), class = c("tbl_df", "tbl", "data.frame"))
我认为最好的是使用case_when。因此，我奇怪地继续了它。这是代码。
test_first_attack <- sample_n %>%
dplyr::mutate(first_attack =
dplyr::case_when(
previous_cabg == 'No' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'Yes' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'No' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'Yes' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'No' ~ 'Yes',
# deal with the unknown category
previous_cabg == 'Unknown' | previous_pci == 'Yes' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Unknown' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Yes' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'No' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'Yes' | previous_ami == 'No' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Unknown' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Yes' | previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Yes'| previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Yes'| previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'No' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'Yes'| previous_ami == 'No' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'Yes'| previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Yes'| previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Yes'| previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'No' | previous_ami == 'No' ~ 'No',
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'Yes' ~'Yes'
))
这是输出。
test_first_attack <- structure(list(id = c(112139L, 43919L, 92430L, 87137L, 95417L,
66955L, 16293L, 61396L, 25379L, 79229L, 27107L, 63243L, 50627L,
17968L, 83015L, 96549L, 7332L, 4873L, 98131L, 93506L, 52894L,
59327L, 85003L, 96623L, 82999L, 65769L, 67063L, 21744L, 62961L,
2229L, 103673L, 9367L, 60215L, 74044L, 58422L, 57530L, 100399L,
46483L, 108690L, 62017L, 46467L, 79562L, 4800L, 119158L, 103222L,
32908L, 14491L, 30293L, 52558L, 122304L, 42281L, 1553L, 111771L,
23087L, 30147L, 37842L, 51552L, 20148L, 28L, 7477L), previous_cabg = structure(c(1L,
1L, 1L, NA, 1L, NA, NA, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, NA, 1L, 1L, NA, 1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 3L,
1L, 1L, NA, 1L, 1L, 1L, 1L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 1L, 1L, 1L), .Label = c("No",
"Unknown", "Yes"), class = "factor"), previous_pci = structure(c(1L,
1L, 2L, NA, 1L, NA, NA, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
2L, NA, 2L, 1L, NA, 2L, NA, 1L, 2L, 1L, 1L, 1L, NA, 2L, 1L, 1L,
2L, 2L, NA, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 2L, 1L, 1L), .Label = c("No",
"Yes", "Unknown"), class = "factor"), previous_ami = structure(c(2L,
2L, 1L, 2L, 2L, NA, 2L, 1L, 2L, 2L, NA, 1L, 2L, 2L, 2L, 2L, 2L,
1L, NA, 1L, 2L, NA, 1L, NA, 2L, 1L, 2L, 2L, 2L, NA, 1L, 1L, 1L,
2L, 1L, NA, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 3L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, NA, 2L, 2L, 2L, 1L, 2L), .Label = c("Yes",
"No", "Unknown"), class = "factor"), first_attack = c("Yes",
"Yes", "Yes", "Yes", "Yes", NA, "Yes", "Yes", "Yes", "Yes", "Yes",
"Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", NA, "Yes", "Yes",
NA, "Yes", NA, "Yes", "Yes", "Yes", "Yes", "Yes", NA, "Yes",
"Yes", "Yes", "Yes", "Yes", NA, "Yes", "Yes", "Yes", "Yes", "Yes",
"Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes",
"Yes", "Yes", "Yes", "Yes", NA, "Yes", "Yes", "Yes", "Yes", "Yes"
)), row.names = c(NA, -60L), problems = structure(list(row = c(34136L,
121773L, 121779L), col = c("1.01 Hospital identifier", "1.01 Hospital identifier",
"1.01 Hospital identifier"), expected = c("value in level set",
"value in level set", "value in level set"), actual = c("CMH",
"CMH", "CMH"), file = c("'../../data/changed/minap_2020_2021_second.csv'",
"'../../data/changed/minap_2020_2021_second.csv'", "'../../data/changed/minap_2020_2021_second.csv'"
)), row.names = c(NA, -3L), class = c("tbl_df", "tbl", "data.frame"
)), class = c("tbl_df", "tbl", "data.frame"))
如您所见，我得到 'Yes' 作为所有列的 id 行和 NO 的列的输出。更不用说考虑更复杂的条件，如 'Unknown\NA\Yes' 或其他条件。
为什么我得不到我想要的输出？是否有另一种方法可以仅使用 tidyverse 来实现它？
如果你尝试“ifelse”会怎么样？
test <- test %>% mutate(first_attack = ifelse(previous_cabg == "Yes" | previous_pci == "Yes" | previous_ami == "Yes", "Yes", "No"))
我想你只需要：
case_when(
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'No' | previous_ami == 'No' ~ 'No',
TRUE ~ "Unknown/NA"
)
对于三个测试列中至少有一个为“是”的每一行，第一行将导致“是”。满足case_when第一行的行将不再测试任何后续条件。
在剩余的行中，第二行将导致“否”，其中三个测试列中的任何一个为“否”。满足case_when第二行的行将不再测试任何后续条件。
最后一行将“Unknown/NA”分配给所有剩余的行，这应该只是那些在三个测试列中没有任何“是”或“否”值的行。
为了完整起见，这里有一个使用您的示例数据的完整可重现示例：
library(tidyverse)
test_first_attack = structure(list(id = c(112139L, 43919L, 92430L, 87137L, 95417L,
66955L, 16293L, 61396L, 25379L, 79229L, 27107L, 63243L, 50627L,
17968L, 83015L, 96549L, 7332L, 4873L, 98131L, 93506L, 52894L,
59327L, 85003L, 96623L, 82999L, 65769L, 67063L, 21744L, 62961L,
2229L, 103673L, 9367L, 60215L, 74044L, 58422L, 57530L, 100399L,
46483L, 108690L, 62017L, 46467L, 79562L, 4800L, 119158L, 103222L,
32908L, 14491L, 30293L, 52558L, 122304L, 42281L, 1553L, 111771L,
23087L, 30147L, 37842L, 51552L, 20148L, 28L, 7477L), previous_cabg = structure(c(1L,
1L, 1L, NA, 1L, NA, NA, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, NA, 1L, 1L, NA, 1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 3L,
1L, 1L, NA, 1L, 1L, 1L, 1L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 1L, 1L, 1L), .Label = c("No",
"Unknown", "Yes"), class = "factor"), previous_pci = structure(c(1L,
1L, 2L, NA, 1L, NA, NA, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
2L, NA, 2L, 1L, NA, 2L, NA, 1L, 2L, 1L, 1L, 1L, NA, 2L, 1L, 1L,
2L, 2L, NA, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 2L, 1L, 1L), .Label = c("No",
"Yes", "Unknown"), class = "factor"), previous_ami = structure(c(2L,
2L, 1L, 2L, 2L, NA, 2L, 1L, 2L, 2L, NA, 1L, 2L, 2L, 2L, 2L, 2L,
1L, NA, 1L, 2L, NA, 1L, NA, 2L, 1L, 2L, 2L, 2L, NA, 1L, 1L, 1L,
2L, 1L, NA, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 3L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, NA, 2L, 2L, 2L, 1L, 2L), .Label = c("Yes",
"No", "Unknown"), class = "factor")), row.names = c(NA, -60L), problems = structure(list(
row = c(34136L, 121773L, 121779L), col = c("1.01 Hospital identifier",
"1.01 Hospital identifier", "1.01 Hospital identifier"),
expected = c("value in level set", "value in level set",
"value in level set"), actual = c("CMH", "CMH", "CMH"), file = c("'../../data/changed/minap_2020_2021_second.csv'",
"'../../data/changed/minap_2020_2021_second.csv'", "'../../data/changed/minap_2020_2021_second.csv'"
)), row.names = c(NA, -3L), class = c("tbl_df", "tbl", "data.frame"
)), class = c("tbl_df", "tbl", "data.frame"))
test_first_attack = test_first_attack %>%
mutate(first_attack = case_when(
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'No' | previous_ami == 'No' ~ 'No',
TRUE ~ "Unknown/NA"
))
test_first_attack
#> # A tibble: 60 x 5
#> id previous_cabg previous_pci previous_ami first_attack
#> <int> <fct> <fct> <fct> <chr>
#> 1 112139 No No No No
#> 2 43919 No No No No
#> 3 92430 No Yes Yes Yes
#> 4 87137 <NA> <NA> No No
#> 5 95417 No No No No
#> 6 66955 <NA> <NA> <NA> Unknown/NA
#> 7 16293 <NA> <NA> No No
#> 8 61396 No Yes Yes Yes
#> 9 25379 No Yes No Yes
#> 10 79229 No No No No
#> # … with 50 more rows
我正在尝试创建一个新列 first_attack，其中包含基于 3 列的多个条件。我正在尝试仅使用 tidyverse 来实现这一目标。这是我的条件：
- 如果我在一列中有
Yes，而不管其他类别（No/Unknown/NA）在同一列中的相同 ID：previous_cabg, previous_pci, previous_ami然后在测试变量中分配Yes - 如果我在同一 ID 的所有列中都有
No，则为测试变量分配 NO - 如果我在一列中有
NO并且在其他列中有相同 ID 的NA/Unknown然后在测试变量中分配No - 如果我在同一 ID 的所有列中都有
Yes，则在测试变量中分配Yes - if I have
Yes in one column andNA/Unknownfor the same id in each column then assignYes`in test variable
这是我拥有的数据集类型：
structure(list(id = c(112139L, 43919L, 92430L, 87137L, 95417L,
66955L, 16293L, 61396L, 25379L, 79229L, 27107L, 63243L, 50627L,
17968L, 83015L, 96549L, 7332L, 4873L, 98131L, 93506L, 52894L,
59327L, 85003L, 96623L, 82999L, 65769L, 67063L, 21744L, 62961L,
2229L, 103673L, 9367L, 60215L, 74044L, 58422L, 57530L, 100399L,
46483L, 108690L, 62017L, 46467L, 79562L, 4800L, 119158L, 103222L,
32908L, 14491L, 30293L, 52558L, 122304L, 42281L, 1553L, 111771L,
23087L, 30147L, 37842L, 51552L, 20148L, 28L, 7477L), previous_cabg = structure(c(1L,
1L, 1L, NA, 1L, NA, NA, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, NA, 1L, 1L, NA, 1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 3L,
1L, 1L, NA, 1L, 1L, 1L, 1L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 1L, 1L, 1L), .Label = c("No",
"Unknown", "Yes"), class = "factor"), previous_pci = structure(c(1L,
1L, 2L, NA, 1L, NA, NA, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
2L, NA, 2L, 1L, NA, 2L, NA, 1L, 2L, 1L, 1L, 1L, NA, 2L, 1L, 1L,
2L, 2L, NA, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 2L, 1L, 1L), .Label = c("No",
"Yes", "Unknown"), class = "factor"), previous_ami = structure(c(2L,
2L, 1L, 2L, 2L, NA, 2L, 1L, 2L, 2L, NA, 1L, 2L, 2L, 2L, 2L, 2L,
1L, NA, 1L, 2L, NA, 1L, NA, 2L, 1L, 2L, 2L, 2L, NA, 1L, 1L, 1L,
2L, 1L, NA, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 3L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, NA, 2L, 2L, 2L, 1L, 2L), .Label = c("Yes",
"No", "Unknown"), class = "factor")), row.names = c(NA, -60L), problems = structure(list(
row = c(34136L, 121773L, 121779L), col = c("1.01 Hospital identifier",
"1.01 Hospital identifier", "1.01 Hospital identifier"),
expected = c("value in level set", "value in level set",
"value in level set"), actual = c("CMH", "CMH", "CMH"), file = c("'../../data/changed/minap_2020_2021_second.csv'",
"'../../data/changed/minap_2020_2021_second.csv'", "'../../data/changed/minap_2020_2021_second.csv'"
)), row.names = c(NA, -3L), class = c("tbl_df", "tbl", "data.frame"
)), class = c("tbl_df", "tbl", "data.frame"))
我认为最好的是使用case_when。因此，我奇怪地继续了它。这是代码。
test_first_attack <- sample_n %>%
dplyr::mutate(first_attack =
dplyr::case_when(
previous_cabg == 'No' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'Yes' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'No' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'Yes' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'No' ~ 'Yes',
# deal with the unknown category
previous_cabg == 'Unknown' | previous_pci == 'Yes' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Unknown' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Yes' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'No' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'Yes' | previous_ami == 'No' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Unknown' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Yes' | previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Yes'| previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Yes'| previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'No' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'Yes'| previous_ami == 'No' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'No' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'Yes'| previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Yes'| previous_ami == 'Unknown' ~ 'Yes',
previous_cabg == 'Yes' | previous_pci == 'Unknown' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'Unknown' | previous_pci == 'Yes'| previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'No' | previous_ami == 'No' ~ 'No',
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'Yes' ~'Yes'
))
这是输出。
test_first_attack <- structure(list(id = c(112139L, 43919L, 92430L, 87137L, 95417L,
66955L, 16293L, 61396L, 25379L, 79229L, 27107L, 63243L, 50627L,
17968L, 83015L, 96549L, 7332L, 4873L, 98131L, 93506L, 52894L,
59327L, 85003L, 96623L, 82999L, 65769L, 67063L, 21744L, 62961L,
2229L, 103673L, 9367L, 60215L, 74044L, 58422L, 57530L, 100399L,
46483L, 108690L, 62017L, 46467L, 79562L, 4800L, 119158L, 103222L,
32908L, 14491L, 30293L, 52558L, 122304L, 42281L, 1553L, 111771L,
23087L, 30147L, 37842L, 51552L, 20148L, 28L, 7477L), previous_cabg = structure(c(1L,
1L, 1L, NA, 1L, NA, NA, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, NA, 1L, 1L, NA, 1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 3L,
1L, 1L, NA, 1L, 1L, 1L, 1L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 1L, 1L, 1L), .Label = c("No",
"Unknown", "Yes"), class = "factor"), previous_pci = structure(c(1L,
1L, 2L, NA, 1L, NA, NA, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
2L, NA, 2L, 1L, NA, 2L, NA, 1L, 2L, 1L, 1L, 1L, NA, 2L, 1L, 1L,
2L, 2L, NA, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 2L, 1L, 1L), .Label = c("No",
"Yes", "Unknown"), class = "factor"), previous_ami = structure(c(2L,
2L, 1L, 2L, 2L, NA, 2L, 1L, 2L, 2L, NA, 1L, 2L, 2L, 2L, 2L, 2L,
1L, NA, 1L, 2L, NA, 1L, NA, 2L, 1L, 2L, 2L, 2L, NA, 1L, 1L, 1L,
2L, 1L, NA, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 3L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, NA, 2L, 2L, 2L, 1L, 2L), .Label = c("Yes",
"No", "Unknown"), class = "factor"), first_attack = c("Yes",
"Yes", "Yes", "Yes", "Yes", NA, "Yes", "Yes", "Yes", "Yes", "Yes",
"Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", NA, "Yes", "Yes",
NA, "Yes", NA, "Yes", "Yes", "Yes", "Yes", "Yes", NA, "Yes",
"Yes", "Yes", "Yes", "Yes", NA, "Yes", "Yes", "Yes", "Yes", "Yes",
"Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes",
"Yes", "Yes", "Yes", "Yes", NA, "Yes", "Yes", "Yes", "Yes", "Yes"
)), row.names = c(NA, -60L), problems = structure(list(row = c(34136L,
121773L, 121779L), col = c("1.01 Hospital identifier", "1.01 Hospital identifier",
"1.01 Hospital identifier"), expected = c("value in level set",
"value in level set", "value in level set"), actual = c("CMH",
"CMH", "CMH"), file = c("'../../data/changed/minap_2020_2021_second.csv'",
"'../../data/changed/minap_2020_2021_second.csv'", "'../../data/changed/minap_2020_2021_second.csv'"
)), row.names = c(NA, -3L), class = c("tbl_df", "tbl", "data.frame"
)), class = c("tbl_df", "tbl", "data.frame"))
如您所见，我得到 'Yes' 作为所有列的 id 行和 NO 的列的输出。更不用说考虑更复杂的条件，如 'Unknown\NA\Yes' 或其他条件。
为什么我得不到我想要的输出？是否有另一种方法可以仅使用 tidyverse 来实现它？
如果你尝试“ifelse”会怎么样？
test <- test %>% mutate(first_attack = ifelse(previous_cabg == "Yes" | previous_pci == "Yes" | previous_ami == "Yes", "Yes", "No"))
我想你只需要：
case_when(
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'No' | previous_ami == 'No' ~ 'No',
TRUE ~ "Unknown/NA"
)
对于三个测试列中至少有一个为“是”的每一行，第一行将导致“是”。满足case_when第一行的行将不再测试任何后续条件。
在剩余的行中，第二行将导致“否”，其中三个测试列中的任何一个为“否”。满足case_when第二行的行将不再测试任何后续条件。
最后一行将“Unknown/NA”分配给所有剩余的行，这应该只是那些在三个测试列中没有任何“是”或“否”值的行。
为了完整起见，这里有一个使用您的示例数据的完整可重现示例：
library(tidyverse)
test_first_attack = structure(list(id = c(112139L, 43919L, 92430L, 87137L, 95417L,
66955L, 16293L, 61396L, 25379L, 79229L, 27107L, 63243L, 50627L,
17968L, 83015L, 96549L, 7332L, 4873L, 98131L, 93506L, 52894L,
59327L, 85003L, 96623L, 82999L, 65769L, 67063L, 21744L, 62961L,
2229L, 103673L, 9367L, 60215L, 74044L, 58422L, 57530L, 100399L,
46483L, 108690L, 62017L, 46467L, 79562L, 4800L, 119158L, 103222L,
32908L, 14491L, 30293L, 52558L, 122304L, 42281L, 1553L, 111771L,
23087L, 30147L, 37842L, 51552L, 20148L, 28L, 7477L), previous_cabg = structure(c(1L,
1L, 1L, NA, 1L, NA, NA, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, NA, 1L, 1L, NA, 1L, NA, 1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 3L,
1L, 1L, NA, 1L, 1L, 1L, 1L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 1L, 1L, 1L), .Label = c("No",
"Unknown", "Yes"), class = "factor"), previous_pci = structure(c(1L,
1L, 2L, NA, 1L, NA, NA, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
2L, NA, 2L, 1L, NA, 2L, NA, 1L, 2L, 1L, 1L, 1L, NA, 2L, 1L, 1L,
2L, 2L, NA, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, NA, 1L, 1L, 2L, 1L, 1L), .Label = c("No",
"Yes", "Unknown"), class = "factor"), previous_ami = structure(c(2L,
2L, 1L, 2L, 2L, NA, 2L, 1L, 2L, 2L, NA, 1L, 2L, 2L, 2L, 2L, 2L,
1L, NA, 1L, 2L, NA, 1L, NA, 2L, 1L, 2L, 2L, 2L, NA, 1L, 1L, 1L,
2L, 1L, NA, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 3L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, NA, 2L, 2L, 2L, 1L, 2L), .Label = c("Yes",
"No", "Unknown"), class = "factor")), row.names = c(NA, -60L), problems = structure(list(
row = c(34136L, 121773L, 121779L), col = c("1.01 Hospital identifier",
"1.01 Hospital identifier", "1.01 Hospital identifier"),
expected = c("value in level set", "value in level set",
"value in level set"), actual = c("CMH", "CMH", "CMH"), file = c("'../../data/changed/minap_2020_2021_second.csv'",
"'../../data/changed/minap_2020_2021_second.csv'", "'../../data/changed/minap_2020_2021_second.csv'"
)), row.names = c(NA, -3L), class = c("tbl_df", "tbl", "data.frame"
)), class = c("tbl_df", "tbl", "data.frame"))
test_first_attack = test_first_attack %>%
mutate(first_attack = case_when(
previous_cabg == 'Yes' | previous_pci == 'Yes' | previous_ami == 'Yes' ~ 'Yes',
previous_cabg == 'No' | previous_pci == 'No' | previous_ami == 'No' ~ 'No',
TRUE ~ "Unknown/NA"
))
test_first_attack
#> # A tibble: 60 x 5
#> id previous_cabg previous_pci previous_ami first_attack
#> <int> <fct> <fct> <fct> <chr>
#> 1 112139 No No No No
#> 2 43919 No No No No
#> 3 92430 No Yes Yes Yes
#> 4 87137 <NA> <NA> No No
#> 5 95417 No No No No
#> 6 66955 <NA> <NA> <NA> Unknown/NA
#> 7 16293 <NA> <NA> No No
#> 8 61396 No Yes Yes Yes
#> 9 25379 No Yes No Yes
#> 10 79229 No No No No
#> # … with 50 more rows