使用变量名中的值重塑数据

Question

我有一个非常广泛的数据集（2000 多个变量），我试图整理这些数据集，但我在试图从变量名中提取一个值时遇到了困难。如果我有一个变量是"E1Time1_Date"，我想将它重塑为三个变量：E=1、Time=1 和Date=原始日期值。

这甚至可能吗？我试过使用gather()，但我猜我需要先做一个我错过的步骤。感谢您的帮助！

如果有人想让魔法发生，这里是示例数据集：

structure(list(ID = c(123, 225), UnrelatedV1 = c("Unrelated1", 
"Unrelated1"), UnrelatedV2 = c("Unrelated2", "Unrelated2"), E1T1_Date = structure(c(1506816000, 
1513296000), class = c("POSIXct", "POSIXt"), tzone = "UTC"), 
    E1T1_v1 = c(10, 20), E1T1_v2 = c(20, 20), E1T1_v3 = c(30, 
    20), E1T1_v4 = c(40, 20), E1T2_Date = structure(c(1512086400, 
    NA), class = c("POSIXct", "POSIXt"), tzone = "UTC"), E1T2_v1 = c(10, 
    NA), E1T2_v2 = c(10, NA), E1T2_v3 = c(10, NA), E1T2_v4 = c(10, 
    NA), E2T1_Date = structure(c(1522540800, 1525132800), class = c("POSIXct", 
    "POSIXt"), tzone = "UTC"), E2T1_v1 = c(10, 20), E2T1_v2 = c(20, 
    20), E2T1_v3 = c(10, 20), E2T1_v4 = c(10, 20), E2T2_Date = structure(c(1533859200, 
    NA), class = c("POSIXct", "POSIXt"), tzone = "UTC"), E2T2_v1 = c(10, 
    NA), E2T2_v2 = c(30, NA), E2T2_v3 = c(10, NA), E2T2_v4 = c(10, 
    NA)), .Names = c("ID", "UnrelatedV1", "UnrelatedV2", "E1T1_Date", 
"E1T1_v1", "E1T1_v2", "E1T1_v3", "E1T1_v4", "E1T2_Date", "E1T2_v1", 
"E1T2_v2", "E1T2_v3", "E1T2_v4", "E2T1_Date", "E2T1_v1", "E2T1_v2", 
"E2T1_v3", "E2T1_v4", "E2T2_Date", "E2T2_v1", "E2T2_v2", "E2T2_v3", 
"E2T2_v4"), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-2L))

Answer 1

看起来您混合了数字和日期值，这会使收集有点棘手。一种方法是暂时将日期转换为数字，然后您可以在达到最终格式后将它们改回来。这应该可以帮助您入门。

library(tidyverse)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    -2L))
data %>%  
  #convert dates to numeric so we can gather them in the same column
  mutate_if(is.POSIXct, as.integer) %>%
  gather(-ID, -contains("Unrelated"), key = variable, value = value) %>% 

  #add an underscore between E and T to make separating them easier
  mutate(loc = gregexpr("T", variable)[[1]],
         variable = paste0(substr(variable, 1, loc - 1), "_",
                           substr(variable, loc, nchar(variable)))) %>% 
  select(-loc) %>% 

  #separate into three distinct columns
  separate(variable, into = c("E", "T", "vDate"), sep = "_")

# A tibble: 40 x 7
ID      UnrelatedV1 UnrelatedV2     E     T vDate      value
<dbl>       <chr>       <chr>   <chr> <chr> <chr>      <dbl>
1   123  Unrelated1  Unrelated2    E1    T1  Date 1506816000
2   225  Unrelated1  Unrelated2    E1    T1  Date 1513296000
3   123  Unrelated1  Unrelated2    E1    T1    v1         10
4   225  Unrelated1  Unrelated2    E1    T1    v1         20
5   123  Unrelated1  Unrelated2    E1    T1    v2         20
6   225  Unrelated1  Unrelated2    E1    T1    v2         20
7   123  Unrelated1  Unrelated2    E1    T1    v3         30
8   225  Unrelated1  Unrelated2    E1    T1    v3         20
9   123  Unrelated1  Unrelated2    E1    T1    v4         40
10   225  Unrelated1  Unrelated2    E1    T1    v4         20