计算多列到列的差异R

Question

我想根据标识符计算几列之间的差异（有关可重现的示例和目标数据框，请参见下面的脚本）。

This question 有点相似，但仅适用于成对的标识符。我想不出如何适应它。 我也可以有多个数据框，每个标识符一个，但我也不知道在这种情况下如何计算多列差异。

下面的代码允许创建一个示例数据集，并且具有我当前使用的代码。它给了我想要的东西，我只想知道是否有办法不说明我想要计算的所有差异（在我的数据集中，我的参数和深度比样本数据中的更多）。

提前感谢您的帮助！

library(tidyverse)
# sample data
create.dt <-  function(t = 0) {
   data.frame(parameter = rep(c("temperature","oxygen"), each = 3),
                  date = rep(c(Sys.Date()+t), each = 6),
                  depth = rep(1:3, times = 2),
             value = c(data.frame(x = rnorm(3, 16, 2)) %>% 
                         arrange(-x) %>% pull,
                       data.frame(x = rnorm(3, 7, 1)) %>% 
                         arrange(-x) %>% pull
                  ))
  
  }

# Multi-site dataset
dt <- rbind(
  cbind(site = "A", create.dt(t = c(-3:0))),
  cbind(site = "B", create.dt(t = c(-3:0))),
  cbind(site = "C", create.dt(t = c(-3:0))),
  cbind(site = "D", create.dt(t = c(-3:0))),
  cbind(site = "E", create.dt(t = c(-3:0))))

# Reshape the data and compute differences
dt %>% pivot_wider(id_cols = c(site,date), names_from = c(parameter,depth), values_from = value, names_sep = "_") %>%
  # do the difference, depth to depth, parameter by parameter
  # What I would like is not have to write manually each differences pair
  mutate(temperature_1_2 = temperature_1 - temperature_2,
         temperature_1_3 = temperature_1 - temperature_3,
         temperature_2_3 = temperature_2 - temperature_3,
         oxygen_1_2 = oxygen_1 - oxygen_2,
         oxygen_1_3 = oxygen_1 - oxygen_3,
         oxygen_2_3 = oxygen_2 - oxygen_3)

Answer 1

library(tidyverse)
library(rlang)

create.dt <-  function(t = 0) {
  data.frame(parameter = rep(c("temperature","oxygen"), each = 3),
             date = rep(c(Sys.Date()+t), each = 6),
             depth = rep(1:3, times = 2),
             value = c(data.frame(x = rnorm(3, 16, 2)) %>% 
                         arrange(-x) %>% pull,
                       data.frame(x = rnorm(3, 7, 1)) %>% 
                         arrange(-x) %>% pull
             ))
  
}

# Multi-site dataset
dt <- rbind(
  cbind(site = "A", create.dt(t = c(-3:0))),
  cbind(site = "B", create.dt(t = c(-3:0))),
  cbind(site = "C", create.dt(t = c(-3:0))),
  cbind(site = "D", create.dt(t = c(-3:0))),
  cbind(site = "E", create.dt(t = c(-3:0))))

# result

temperature <- str_c("temperature_", 1:3)
oxygen <- str_c("oxygen_", 1:3)

temperature_frml <- combn(temperature, m = 2, FUN = function(x) str_c(x, collapse = " - ")) 
oxygen_frml <- combn(oxygen, m = 2, FUN = function(x) str_c(x, collapse = " - ")) 
all_frml <- c(temperature_frml, oxygen_frml)

df_wider <- dt %>% pivot_wider(
  id_cols = c(site, date),
  names_from = c(parameter, depth),
  values_from = value,
  names_sep = "_"
)

bind_cols(df_wider,
          map_dfc(
            .x = all_frml,
            .f = ~ transmute(.data = df_wider,!!.x :=  eval(parse_expr(.x)))
          ))
#> # A tibble: 20 x 14
#>    site  date       temperature_1 temperature_2 temperature_3 oxygen_1 oxygen_2
#>    <chr> <date>             <dbl>         <dbl>         <dbl>    <dbl>    <dbl>
#>  1 A     2021-12-11          17.6          17.1          12.9     7.34     6.86
#>  2 A     2021-12-12          17.6          17.1          12.9     7.34     6.86
#>  3 A     2021-12-13          17.6          17.1          12.9     7.34     6.86
#>  4 A     2021-12-14          17.6          17.1          12.9     7.34     6.86
#>  5 B     2021-12-11          17.1          15.6          13.7     8.52     7.58
#>  6 B     2021-12-12          17.1          15.6          13.7     8.52     7.58
#>  7 B     2021-12-13          17.1          15.6          13.7     8.52     7.58
#>  8 B     2021-12-14          17.1          15.6          13.7     8.52     7.58
#>  9 C     2021-12-11          17.7          15.5          13.6     7.66     7.31
#> 10 C     2021-12-12          17.7          15.5          13.6     7.66     7.31
#> 11 C     2021-12-13          17.7          15.5          13.6     7.66     7.31
#> 12 C     2021-12-14          17.7          15.5          13.6     7.66     7.31
#> 13 D     2021-12-11          16.5          16.4          14.5     7.50     7.27
#> 14 D     2021-12-12          16.5          16.4          14.5     7.50     7.27
#> 15 D     2021-12-13          16.5          16.4          14.5     7.50     7.27
#> 16 D     2021-12-14          16.5          16.4          14.5     7.50     7.27
#> 17 E     2021-12-11          16.7          16.1          15.7     7.52     7.51
#> 18 E     2021-12-12          16.7          16.1          15.7     7.52     7.51
#> 19 E     2021-12-13          16.7          16.1          15.7     7.52     7.51
#> 20 E     2021-12-14          16.7          16.1          15.7     7.52     7.51
#> # ... with 7 more variables: oxygen_3 <dbl>,
#> #   temperature_1 - temperature_2 <dbl>, temperature_1 - temperature_3 <dbl>,
#> #   temperature_2 - temperature_3 <dbl>, oxygen_1 - oxygen_2 <dbl>,
#> #   oxygen_1 - oxygen_3 <dbl>, oxygen_2 - oxygen_3 <dbl>

^{由reprex package (v2.0.1) 于 2021 年 12 月 14 日创建}