根据条件计算各行的值

Question

我正在寻找在R中跨列计算“YES”的帮助--最好是寻找一个“整洁”的解决方案。

我有一个数据集df_help，需要创建一个新的变量，它根据对象dim_1求值并计算匹配的总数，在df_help_reprex中表示为dim_1。

是否有dplyr解决方案，或者使用apply函数作为函数是更好的方法？

谢谢!

> df_help_reprex <- df_help %>% 
+   mutate(dim_1 = c(1, 0, 2, 0, 0, 0, 0, 1, 2, 0))
> df_help
# A tibble: 10 x 8
   symp_ams symp_nvd symp_pain symp_fever vitals_gcs vitals_rr_10_24 vitals_temp_38 vitals_hr_100
   <fct>    <fct>    <fct>     <fct>      <fct>      <fct>           <fct>          <fct>        
 1 NO       YES      NO        NO         NO         NO              NO             YES          
 2 NO       NO       NO        NO         NO         NO              NO             NO           
 3 YES      NO       NO        NO         YES        NO              UNK            YES          
 4 NO       NO       NO        NO         NO         NO              UNK            YES          
 5 NO       NO       NO        YES        YES        NO              YES            NO           
 6 NO       NO       NO        NO         NO         NO              NO             NO           
 7 NO       NO       NO        YES        NO         NO              NO             NO           
 8 NO       YES      NO        NO         NO         NO              NO             NO           
 9 YES      NO       NO        NO         YES        NO              NO             YES          
10 NO       NO       NO        YES        NO         YES             YES            YES          
> dim_1
[1] "symp_ams"   "symp_nvd"   "symp_pain"  "vitals_gcs"
> df_help_reprex
# A tibble: 10 x 9
   symp_ams symp_nvd symp_pain symp_fever vitals_gcs vitals_rr_10_24 vitals_temp_38 vitals_hr_100 dim_1
   <fct>    <fct>    <fct>     <fct>      <fct>      <fct>           <fct>          <fct>         <dbl>
 1 NO       YES      NO        NO         NO         NO              NO             YES               1
 2 NO       NO       NO        NO         NO         NO              NO             NO                0
 3 YES      NO       NO        NO         YES        NO              UNK            YES               2
 4 NO       NO       NO        NO         NO         NO              UNK            YES               0
 5 NO       NO       NO        YES        YES        NO              YES            NO                0
 6 NO       NO       NO        NO         NO         NO              NO             NO                0
 7 NO       NO       NO        YES        NO         NO              NO             NO                0
 8 NO       YES      NO        NO         NO         NO              NO             NO                1
 9 YES      NO       NO        NO         YES        NO              NO             YES               2
10 NO       NO       NO        YES        NO         YES             YES            YES               0

Answer 1

我建议使用tidyverse方法重塑数据，然后计算匹配值的数量。代码如下：

library(tidyverse)
#Data
df_help <- structure(list(symp_ams = c("NO", "NO", "YES", "NO", "NO", "NO", 
"NO", "NO", "YES", "NO"), symp_nvd = c("YES", "NO", "NO", "NO", 
"NO", "NO", "NO", "YES", "NO", "NO"), symp_pain = c("NO", "NO", 
"NO", "NO", "NO", "NO", "NO", "NO", "NO", "NO"), symp_fever = c("NO", 
"NO", "NO", "NO", "YES", "NO", "YES", "NO", "NO", "YES"), vitals_gcs = c("NO", 
"NO", "YES", "NO", "YES", "NO", "NO", "NO", "YES", "NO"), vitals_rr_10_24 = c("NO", 
"NO", "NO", "NO", "NO", "NO", "NO", "NO", "NO", "YES"), vitals_temp_38 = c("NO", 
"NO", "UNK", "UNK", "YES", "NO", "NO", "NO", "NO", "YES"), vitals_hr_100 = c("YES", 
"NO", "YES", "YES", "NO", "NO", "NO", "NO", "YES", "YES")), row.names = c(NA, 
-10L), class = "data.frame")
#Vector for match
dim_1 <- c("symp_ams","symp_nvd","symp_pain","vitals_gcs")

接下来是使用tidyverse函数的解决方案。我们重塑数据，处理每一行计算一个id。之后，我们检查条件，聚合值，最后将结果绑定到初始数据帧：

#Reshape
df_help %>% bind_cols(df_help %>% mutate(id=1:n()) %>%
                        pivot_longer(cols = -id) %>%
                        mutate(Num=ifelse(name %in% dim_1 & value=='YES',1,0)) %>%
                        group_by(id) %>% summarise(Dim1=sum(Num)) %>% select(-id))

输出：

   symp_ams symp_nvd symp_pain symp_fever vitals_gcs vitals_rr_10_24 vitals_temp_38 vitals_hr_100 Dim1
1        NO      YES        NO         NO         NO              NO             NO           YES    1
2        NO       NO        NO         NO         NO              NO             NO            NO    0
3       YES       NO        NO         NO        YES              NO            UNK           YES    2
4        NO       NO        NO         NO         NO              NO            UNK           YES    0
5        NO       NO        NO        YES        YES              NO            YES            NO    1
6        NO       NO        NO         NO         NO              NO             NO            NO    0
7        NO       NO        NO        YES         NO              NO             NO            NO    0
8        NO      YES        NO         NO         NO              NO             NO            NO    1
9       YES       NO        NO         NO        YES              NO             NO           YES    2
10       NO       NO        NO        YES         NO             YES            YES           YES    0

顺便提一下，在您的最终输出中，第5行应该有一个拼写错误，因为vitals_gcs列被定义为YES并与向量dim_1匹配。