R - 基於匹配重新排序列（模板）

Question

所以我有一個大型數據集，如下所示：

     V1       V2   V3         V4
1 Sleep Domestic  Eat Child Care
2 Sleep Domestic  Eat       Paid
3 Sleep Domestic  Eat Child Care
4 Sleep      Eat Paid       <NA>

我想做的是根據“模板” reorder列

["Sleep", "Eat", "Domestic", "Paid", "Child care"] 

獲得（輸出）

   V1    V2       V3      V4            V5
Sleep   Eat Domestic      NA    Child Care
Sleep   Eat Domestic    Paid            NA
Sleep   Eat Domestic      NA    Child Care
Sleep   Eat       NA    Paid            NA

所以在第1列Sleep ，第2列Eat ，......

我不知道從哪里開始。 任何的想法 ？

數據

x = structure(list(V1 = c("Sleep", "Sleep", "Sleep", "Sleep"), V2 = c("Domestic", 
"Domestic", "Domestic", "Eat"), V3 = c("Eat", "Eat", "Eat", "Paid"
), V4 = c("Child Care", "Paid", "Child Care", NA)), .Names = c("V1", 
"V2", "V3", "V4"), row.names = c(NA, 4L), class = "data.frame")

template = c('Sleep', 'Eat', 'Domestic', 'Paid', 'Child care')

Answer 1

檢查rowSums中的每個template值，然后再將它們拼湊在一起：

template <- c("Sleep", "Eat", "Domestic", "Paid", "Child Care")
# i've fixed this template so the case matches the values for 'Child Care'

data.frame(lapply(
  setNames(template, seq_along(template)),
  function(v) c(NA,v)[(rowSums(x==v,na.rm=TRUE)>0)+1]
))

#     X1  X2       X3   X4         X5
#1 Sleep Eat Domestic <NA> Child Care
#2 Sleep Eat Domestic Paid       <NA>
#3 Sleep Eat Domestic <NA> Child Care
#4 Sleep Eat     <NA> Paid       <NA>

或者使用pmax的替代方案：

data.frame(
  lapply(
    setNames(template, seq_along(template)), 
    function(v) do.call(pmax, c(replace(x, x != v,NA),na.rm=TRUE)) 
  )
)

Answer 2

reshape2和dplyr解決方案。 顯然不像其他人那么緊湊。 想法是融化（變高），順序因素和演員。

library(reshape2)
library(dplyr)

# make and id column 
x$id <- row.names(x)

# make a tall result id, var, value
tall <- x %>% 
  melt(id.vars="id") %>%
  select(id, value) 

# make an ordered factor with the template
tall$value <- factor(tall$value, levels=template, ordered = TRUE) 

# make wide result with dcast
result <-  tall %>%  
  filter(!is.na(value)) %>%  # drop the NAs 
  mutate(var = value) %>%    # name the column the same as the value
  dcast(id ~ var)            # make into wide format

result
#  id Sleep Eat Domestic Paid Child Care
#1  1 Sleep Eat Domestic <NA> Child Care
#2  2 Sleep Eat Domestic Paid       <NA>
#3  3 Sleep Eat Domestic <NA> Child Care
#4  4 Sleep Eat     <NA> Paid       <NA>

Answer 3

這是tidyverse一個選項

library(dplyr)
library(tidyr)
library(tibble)
rownames_to_column(x, 'id') %>% 
       gather(Var, Val, -id, na.rm = TRUE) %>% 
       mutate(Var = factor(Val, levels = template)) %>% 
       spread(Var, Val) %>% 
       select(-id) %>% 
       setNames(., paste0("V", seq_along(template)))
#     V1  V2       V3   V4         V5
#1 Sleep Eat Domestic <NA> Child Care
#2 Sleep Eat Domestic Paid       <NA>
#3 Sleep Eat Domestic <NA> Child Care
#4 Sleep Eat     <NA> Paid       <NA>