0

考虑一个数据框，显示对照结果和男性和女性的两种实验处理以及每种处理的大小：

library(tidyverse)
mydf <- data_frame( treatment = c('ctrl','low','high','ctrl','low','high'), 
                gender = c('male','male','male','female','female','female'),
                size = c(10,20,30,10,20,30),
                result = c(0.11, 0.32, 0.25, 0.15, 0.38, 0.55) )

treatment  gender   size results
 ctrl       male     10    0.11
 low        male     20    0.32
 high       male     30    0.25
 ctrl       female   10    0.15
 low        female   20    0.35
 high       female   30    0.55

为了并排比较控制与实验治疗，我想重塑数据框如下：

treatment gender   ctrl_size    size   ctrl_result  result
   low     female        10      20        0.15      0.38
  high     female        10      30        0.15      0.55
   low     male          10      20        0.11      0.32
  high     male          10      30        0.11      0.25

我在下面的尝试有效，但对我来说似乎很麻烦，因为它在将辅助数据框合并到最后一个之前创建了辅助数据框：

mydf_result <- mydf %>%
  select(-size) %>% 
  spread(treatment, result) %>%
  gather(treatment, result, c(low, high) ) %>% 
  rename(ctrl_result = ctrl)

mydf_size <- mydf %>%
  select(-result) %>%  
  spread(treatment, size) %>% 
  gather(treatment, size, c(low, high))  %>% 
  rename(ctrl_size = ctrl)

mydf_final <- 
  full_join(mydf_result, mydf_size, by = c('treatment', 'gender')) %>% 
  select(treatment, gender, ctrl_size, size, ctrl_result, result) %>%
  arrange(gender)

# A tibble: 4 × 6
  treatment gender ctrl_size  size ctrl_result result
      <chr>  <chr>     <dbl> <dbl>       <dbl>  <dbl>
1       low female        10    20        0.15   0.38
2      high female        10    30        0.15   0.55
3       low   male        10    20        0.11   0.32
4      high   male        10    30        0.11   0.25

可以在一个管道内实现上述目标吗？

4

2 回答 2

2

虽然我不确定所需的结果是最整洁的排列，但您可以像这样重新排列：

library(tidyverse)

mydf %>% gather(var, val, size, result) %>%    # gather all numbers into one column
    spread(treatment, val) %>%    # spread treatment so ctrl can be separated
    gather(treatment, ttmt, high, low) %>%    # regather high and low separately
    gather(ct_tm, val, ctrl, ttmt) %>%    # regather numbers, now with ctrl/ttmt separated
    unite(var, ct_tm, var) %>%    # join column labels
    spread(var, val)    # spread to wide

## # A tibble: 4 × 6
##   gender treatment ctrl_result ctrl_size ttmt_result ttmt_size
## *  <chr>     <chr>       <dbl>     <dbl>       <dbl>     <dbl>
## 1 female      high        0.15        10        0.55        30
## 2 female       low        0.15        10        0.38        20
## 3   male      high        0.11        10        0.25        30
## 4   male       low        0.11        10        0.32        20
于 2016-11-01T22:49:12.510 回答
1

这可以通过加入来完成data.table

library(data.table)
setnames(setDT(mydf)[treatment!="ctrl"][mydf[treatment=="ctrl"],
  on = "gender"], c("i.size", "i.result"), c("ctrl_size", "ctrl_result"))[,
                  i.treatment := NULL][]
#    treatment gender size result ctrl_size ctrl_result
#1:       low   male   20   0.32        10        0.11
#2:      high   male   30   0.25        10        0.11
#3:       low female   20   0.38        10        0.15
#4:      high female   30   0.55        10        0.15
于 2016-11-02T01:01:57.777 回答