R中数据框中数百个变量的计数、条件和星座变量

Question

我正在处理一个数据集，我需要在其中同时评估数百列，以创建按行计算的新变量。我有三个新变量，一个需要“或”运算符来决定 ~100 列中是否有任何“是”。第二个需要计算变量中我总共有多少个“是”，第三个需要创建一个星座变量，向我显示具有“是”值的变量的名称，所有这些都是按行显示的。我有前两个的代码，但第三个我卡住了。此外，出于示例目的，我仅使用了几个变量，但我需要使用约 100 个变量。我的代码如下：

#making the data - I am using actually ~100 variables 

test.data <- data.frame(var1 = c("yes", "no", "no", "N/A", NA, NA),
                        var2 = c(NA, NA, "yes", "no", "yes", NA),
                        var3 = c("yes", "yes", "yes", "no", "yes", "N/A"),
                        var4 = c("N/A", "yes", "no", "no", "yes", NA))

# code for the first two variables: is.positive and number.pos - not elegant nor efficient since I #need to work with ~100 vars

final.data <- data.frame(test.data %>%
              mutate(is.positive = ifelse(var1=="yes" | var2=="yes" | var3=="yes" | var4=="yes", 1,
                                       ifelse((is.na(var1) | var1=="N/A") & 
                                                (is.na(var2) | var2=="N/A") & 
                                                (is.na(var3) | var3=="N/A") & 
                                                (is.na(var4) | var4=="N/A"), NA, 0))) %>%
              rowwise() %>%
              mutate(number.pos = sum(c_across(c(var1, var2, var3, var4))=="yes",na.rm=TRUE)))

Answer 1

您可以通过创建一个列表列来实现，其中一些是正数，然后从中导出其他值。

library(tidyverse)
test.data <- data.frame(var1 = c("yes", "no", "no", "N/A", NA, NA),
                        var2 = c(NA, NA, "yes", "no", "yes", NA),
                        var3 = c("yes", "yes", "yes", "no", "yes", "N/A"),
                        var4 = c("N/A", "yes", "no", "no", "yes", NA))


nv <- test.data %>% 
  select(var1:var4) %>% 
  names()
out <- test.data %>% 
  rowwise() %>% 
  mutate(which_pos = list(nv[which(c_across(var1:var4) == "yes")]), 
         num.positive = length(which_pos), 
         is.positive = num.positive > 0) 

out
#> # A tibble: 6 × 7
#> # Rowwise: 
#>   var1  var2  var3  var4  which_pos num.positive is.positive
#>   <chr> <chr> <chr> <chr> <list>           <int> <lgl>      
#> 1 yes   <NA>  yes   N/A   <chr [2]>            2 TRUE       
#> 2 no    <NA>  yes   yes   <chr [2]>            2 TRUE       
#> 3 no    yes   yes   no    <chr [2]>            2 TRUE       
#> 4 N/A   no    no    no    <chr [0]>            0 FALSE      
#> 5 <NA>  yes   yes   yes   <chr [3]>            3 TRUE       
#> 6 <NA>  <NA>  N/A   <NA>  <chr [0]>            0 FALSE
out$which_pos
#> [[1]]
#> [1] "var1" "var3"
#> 
#> [[2]]
#> [1] "var3" "var4"
#> 
#> [[3]]
#> [1] "var2" "var3"
#> 
#> [[4]]
#> character(0)
#> 
#> [[5]]
#> [1] "var2" "var3" "var4"
#> 
#> [[6]]
#> character(0)

^{由 reprex package (v2.0.1)}

于 2022-05-26 创建

如果您想要一个用于标识哪些变量为正的变量的普通列，您可以简单地将名称粘贴在一起以创建一个具有 comma-separated 个名称的字符串：

library(tidyverse)
test.data <- data.frame(var1 = c("yes", "no", "no", "N/A", NA, NA),
                        var2 = c(NA, NA, "yes", "no", "yes", NA),
                        var3 = c("yes", "yes", "yes", "no", "yes", "N/A"),
                        var4 = c("N/A", "yes", "no", "no", "yes", NA))


nv <- test.data %>% 
  select(var1:var4) %>% 
  names()
out <- test.data %>% 
  rowwise() %>% 
  mutate(which_pos = paste(nv[which(c_across(var1:var4) == "yes")], collapse=","), 
         num.positive = sum(c_across(var1:var4) == "yes", na.rm=TRUE), 
         is.positive = num.positive > 0) 

out
#> # A tibble: 6 × 7
#> # Rowwise: 
#>   var1  var2  var3  var4  which_pos        num.positive is.positive
#>   <chr> <chr> <chr> <chr> <chr>                   <int> <lgl>      
#> 1 yes   <NA>  yes   N/A   "var1,var3"                 2 TRUE       
#> 2 no    <NA>  yes   yes   "var3,var4"                 2 TRUE       
#> 3 no    yes   yes   no    "var2,var3"                 2 TRUE       
#> 4 N/A   no    no    no    ""                          0 FALSE      
#> 5 <NA>  yes   yes   yes   "var2,var3,var4"            3 TRUE       
#> 6 <NA>  <NA>  N/A   <NA>  ""                          0 FALSE

^{由 reprex package (v2.0.1)}

于 2022-05-26 创建

如果需要，列表列可能更易于在后续分析中使用，但 comma-separated 变量可能更易于用于目视检查。

Answer 2

使用基础 R：

is.na(test.data) <- test.data == 'N/A'
idx <- test.data == 'yes'
test.data['num.positive'] <- rowSums(idx, na.rm = TRUE)
test.data['is.positive'] <- +(test.data[['num.positive']] > 0)

idx2 <- data.frame(which(idx, TRUE))
df1 <- aggregate(col~row, idx2, \(x)paste(names(test.data)[x], collapse = '-'))
df2 <- merge(cbind(test.data, row = seq(nrow(test.data))), df1, all.x =TRUE)

df2

  row var1 var2 var3 var4 num.positive is.positive            col
1   1  yes <NA>  yes <NA>            2           1      var1-var3
2   2   no <NA>  yes  yes            2           1      var3-var4
3   3   no  yes  yes   no            2           1      var2-var3
4   4 <NA>   no   no   no            0           0           <NA>
5   5 <NA>  yes  yes  yes            3           1 var2-var3-var4
6   6 <NA> <NA> <NA> <NA>            0           0           <NA>

R中数据框中数百个变量的计数、条件和星座变量

Counting, conditionals and constellation variable for hundred of variables in a data frame in R

r

count

multiple-columns

rowwise