R：使用名称中共享模式的多个列将数据重塑为更长的格式

我用数据集挣扎了一段时间，想把它从一个全宽的格式变成一个全长的格式。我设法把它做成介于两者之间的一种形式。如下面的玩具示例所示，数据的格式基于

Cond

列。问题是度量列名称中的“\u Pre”和“\u Post”必须是另一个因素，如

Cond

，命名为

PrePost

。这就是为什么我尝试的代码会产生错误的结果，行太多：

vars_PrePost <- grep("Pre|Post", colnames(df))

df2 <-
  df %>%
  gather(variable, value, vars_PrePost, -c(ID)) %>%                                      
  tidyr::separate(variable,  c("variable", "PrePost"), "_(?=[^_]+$)") %>%                
  spread(variable, value) 

vars\u PrePost%
tidyr:：separate（变量，c（“变量”，“前置”），“（？=[^.]+$）”）”%>%
排列（变量、值）

以下是玩具数据集：

df <- data.frame(stringsAsFactors=FALSE,
               ID = c("10", "10", "11", "11", "12", "12"),
           Age = c("23", "23", "31", "31", "24", "24"),
          Gender = c("m", "m", "m", "m", "f", "f"),
         Cond = c("Cond2", "Cond1", "Cond2", "Cond1", "Cond2", "Cond1"),
         Measure1_Post = c(NA, "7", NA, "3", NA, "2"),
          Measure1_Pre = c(NA, "3", NA, "2", NA, "2"),
         Measure2_Post = c("1.3968694273826", "0.799543118218161",
                      "1.44098109351048", "0.836960160696351",
                      "1.99568500539374", "1.75138016371597"),
          Measure2_Pre = c("1.19248628113128", "0.726244170934944",
                      "1.01175268267757", "1.26415857605178",
                      "2.35250186706497", "1.27070245573958"),
    Measure3_Post = c("73", "84", "50", "40", "97", "89"),
     Measure3_Pre = c("70", "63", "50", "46", "88", "71")
)

---

df在tidyr
v1.0.0
中使用特殊动词
.value
和
names\u模式

library(tidyr) #v1.0.0
#select columns with _
pivot_longer(df, cols = matches('_'), 
                 names_to = c(".value","PrePost"), 
                 names_pattern = "(.*)_(.*)")

# A tibble: 12 x 8
   ID    Age   Gender Cond  PrePost Measure1 Measure2          Measure3
   <chr> <chr> <chr>  <chr> <chr>   <chr>    <chr>             <chr>   
 1 10    23    m      Cond2 Post    NA       1.3968694273826   73      
 2 10    23    m      Cond2 Pre     NA       1.19248628113128  70      
 3 10    23    m      Cond1 Post    7        0.799543118218161 84      
 4 10    23    m      Cond1 Pre     3        0.726244170934944 63  
 ...

library（tidyr）#v1.0.0
#选择带有_
枢轴长度（df，cols=匹配项（“'），
name_to=c（“.value”，“PrePost”），
name_pattern=“（.*）_（.*）”
#一个tibble:12x8
ID年龄性别第二前置测量1测量2测量3
1 10 23米Cond2立柱NA 1.3968694273826 73
2 10 23米秒2前NA 1.19248628113128 70
3 10 23米导管柱7 0.799543118218161 84
4 10 23米直径1 3 0.726244170934944 63之前
...

library(tidyr) #v1.0.0
#select columns with _
pivot_longer(df, cols = matches('_'), 
                 names_to = c(".value","PrePost"), 
                 names_pattern = "(.*)_(.*)")

# A tibble: 12 x 8
   ID    Age   Gender Cond  PrePost Measure1 Measure2          Measure3
   <chr> <chr> <chr>  <chr> <chr>   <chr>    <chr>             <chr>   
 1 10    23    m      Cond2 Post    NA       1.3968694273826   73      
 2 10    23    m      Cond2 Pre     NA       1.19248628113128  70      
 3 10    23    m      Cond1 Post    7        0.799543118218161 84      
 4 10    23    m      Cond1 Pre     3        0.726244170934944 63  
 ...