根据列字符串匹配和另一个列条件过滤 R 中的数据帧

Question

我有一个名为 df 的数据框：

warning    = c("HAS","NO","HAS","HAS","HAS")
validation = c("OK","OK","WARNING","WARNING","WARNING") 
a_b_c_messages1 = c(NA,NA,"good catch",NA,NA)
D_E_f_messages2 = c(NA,NA,NA,"NOT BAD",NA)
g_h_I_messages3 = c(NA,NA,NA,NA,"BETTER")
j_k_l_messages4 = c(NA,NA,NA,NA,NA)

df = tibble(warning,validation,a_b_c_messages1,
            D_E_f_messages2,g_h_I_messages3,
            j_k_l_messages4)
 A tibble: 5 × 6
  warning validation a_b_c_messages1 D_E_f_messages2 g_h_I_messages3 j_k_l_messages4
  <chr>   <chr>      <chr>           <chr>           <chr>           <lgl>          
1 HAS     OK         NA              NA              NA              NA             
2 NO      OK         NA              NA              NA              NA             
3 HAS     WARNING    good catch      NA              NA              NA             
4 HAS     WARNING    NA              NOT BAD         NA              NA             
5 HAS     WARNING    NA              NA              BETTER          NA  

我想过滤此 df 并保留列警告包含单词“HAS”的行以及包含字符串“Message”且不是 NA 的任何列。

理想情况下我希望结果 df 是这样的：

  warning validation a_b_c_messages1 D_E_f_messages2 g_h_I_messages3 
  <chr>   <chr>      <chr>           <chr>           <chr>                       
3 HAS     WARNING    good catch      NA              NA                          
4 HAS     WARNING    NA              NOT BAD         NA                          
5 HAS     WARNING    NA              NA              BETTER                             

Answer 1

warning    = c("HAS","NO","HAS","HAS","HAS")
validation = c("OK","OK","WARNING","WARNING","WARNING") 
a_b_c_messages1 = c(NA,NA,"good catch",NA,NA)
D_E_f_messages2 = c(NA,NA,NA,"NOT BAD",NA)
g_h_I_messages3 = c(NA,NA,NA,NA,"BETTER")
j_k_l_messages4 = c(NA,NA,NA,NA,NA)

library(tidyverse)
df = tibble(warning,validation,a_b_c_messages1,
            D_E_f_messages2,g_h_I_messages3,
            j_k_l_messages4)

df %>% 
  rownames_to_column(var = "rn") %>% 
  pivot_longer(-c(rn, warning, validation), values_drop_na = T) %>% 
  pivot_wider(id_cols = c(rn, warning, validation), names_from = name, values_from = value)
#> # A tibble: 3 × 6
#>   rn    warning validation a_b_c_messages1 D_E_f_messages2 g_h_I_messages3
#>   <chr> <chr>   <chr>      <chr>           <chr>           <chr>          
#> 1 3     HAS     WARNING    good catch      <NA>            <NA>           
#> 2 4     HAS     WARNING    <NA>            NOT BAD         <NA>           
#> 3 5     HAS     WARNING    <NA>            <NA>            BETTER

^{创建于 2024-11-08，使用 reprex v2.1.1}