How to combine input variables and various functions in dplyr summarize

Question

I need to group and summarize a data frame using various summation functions depending on the variable that I am summing up. These functions can have different main and optional arguments, and I would like to code a function that can do all this.

Here are the simpler functions that I managed to code to show their logic.

require(tidyverse)
require(magrittr)
require(rlang)

example <- data.frame(y = as.factor(c('A','B','C','A','B')),
                      x1 = c(7, 10, NA, NA, 2),
                      x2 = c(13, 0, 0, 2, 1),
                      z = c(0, 1, 0, 1, 0))

# Summarise variables with common prefix
do_summary_prefix <- function(dataset, y, prefix, fun, ...){
    y <- enquo(y)
    prefix <- quo_name(enquo(prefix))
    fun <- match.fun(fun)
    dataset  %<>%  
       group_by(!!y) %>% 
       summarise_at(vars(starts_with(prefix)), funs(fun), ...) %>% 
       ungroup()
    return(dataset)
}
do_summary_prefix(example, y, x, 'quantile', probs = 0.25, na.rm = T) 

# Summarise variables with different names, one at a time
do_summary_x <- function(dataset, y, x, fun, ...){
    y <- enquo(y)
    x <- enquo(x)

    dataset  %<>%  
       group_by(!!y) %>% 
       summarise(!!paste(quo_name(x), fun, sep = '_') := do.call(match.fun(fun), list(x = !!x, ...))) %>% 
       ungroup()
    return(dataset)
}
do_summary_x(example, y, x1, fun = 'mean', na.rm = F)

This is normal for me, and I could use it do_summary_xas a loop over the variables that I want to generalize in order to do the job. But I would like to integrate the loop into a higher level function, using ..., while still having the ability to use various parameters for my generic functions.

, ... , ( , ) , do.call. ... , , . , :

#install.packages('plyr') # if needed
join_all <- plyr::join_all

do_summary <- function(dataset, y, ..., fun, other_args = list(NULL = 
    NULL)){
    y_quo <- enquo(y)
    y_name <- quo_name(y_quo)

    values <- quos(...)

    datasets <- lapply(values, function(value){
      summarised_data <- dataset %>% 
      group_by(!!y_quo) %>% 
      summarise(calcul = do.call(fun, 
                                 unlist(list(list(x = !!value),
                                             other_args),
                                        recursive = F))) %>%
      ungroup() %>%
      rename(!!paste(quo_name(value), stat, sep = '_') := calcul)
    return(summarised_data)
  })
  finished <- join_all(datasets, by = y_name, type = 'left')
  return(finished)
}
do_summary(example, y,
           x1, x2, z,
           stat = 'quantile',
           other_args = list(probs = 0.1, na.rm = T))
do_summary(example, y,
           x1, x2, z,
           fun = 'mean')

, , , x.

, fun, x . ?

, < <24 > - changing_arg = !!x, list(!!changing_arg := !!x)

Answer 1

:

library(dplyr)
library(rlang)

do_summary <- function(dataset, y, ..., fun, other_args = list(NULL = NULL)){

  y_quo <- enquo(y)
  values <- quos(...)

  datasets <- dataset %>% 
      group_by(!!y_quo) %>% 
      summarise_at(vars(!!!values), .funs = fun, !!!other_args) %>%
      rename_at(vars(!!!values), paste, fun, sep = "_")

  return(datasets)
}

do_summary(example, y,
           x1, x2, z,
           fun = 'quantile',
           other_args = list(probs = 0.1, na.rm = T))

do_summary(example, y,
           x1, x2, z,
           fun = 'mean')

:

# A tibble: 3 x 4
       y x1_quantile x2_quantile z_quantile
  <fctr>       <dbl>       <dbl>      <dbl>
1      A         7.0         3.1        0.1
2      B         2.8         0.1        0.1
3      C          NA         0.0        0.0

# A tibble: 3 x 4
       y x1_mean x2_mean z_mean
  <fctr>   <dbl>   <dbl>  <dbl>
1      A      NA     7.5    0.5
2      B       6     0.5    0.5
3      C      NA     0.0    0.0

:

• , lapply values, summarise_at rename_at values vars !!!.

• fun .funs summarise_at, other_args !!!. , list(probs = 0.1, na.rm = T) probs = 0.1, na.rm = T.

• rename_at. vars values. rename_at(vars(-y_name), ...), summarise_at .

• lapply, do.call summarise join_all (y_name, , ).

• do_summary quantile stat = "quantile", , fun = "quantile"

• , , .