在 R 中的分组数据帧中使用来自大型数据帧的多分位数组

Question

I have the next problem, I have a large dataframe, in which I have to extract the quantiles from a variable but by group, by instance:

list_q <- list()

for (i in 3:5){

  tmp <- mtcars %>% 
    filter(gear == i) %>% 
    pull(mpg) %>% 
    quantile(probs = seq(0, 1, 0.25), na.rm = TRUE)

  list_q[[i]] <- tmp  

}

list_q

With this output:

[[3]]
  0%  25%  50%  75% 100% 
10.4 14.5 15.5 18.4 21.5 

[[4]]
    0%    25%    50%    75%   100% 
17.800 21.000 22.800 28.075 33.900 

[[5]]
  0%  25%  50%  75% 100% 
15.0 15.8 19.7 26.0 30.4 

Now, I need to group the variable means and determine which quantile it belongs but using the original measures:

a <- mtcars %>% 
  group_by(gear, carb) %>% 
  summarize(mpg_mean = mean(mpg)) %>% 
  ungroup()

    gear  carb mpg_mean
   <dbl> <dbl>    <dbl>
 1     3     1     20.3
 2     3     2     17.2
 3     3     3     16.3
 4     3     4     12.6
 5     4     1     29.1
 6     4     2     24.8
 7     4     4     19.8
 8     5     2     28.2
 9     5     4     15.8
10     5     6     19.7
11     5     8     15 

So I could do this:

g3 <- a %>% 
  filter(gear == 3) %>% 
  mutate(quantile = cut(mpg_mean, list_q[[3]], labels = FALSE, include.lowest = TRUE))

g4 <- a %>% 
  filter(gear == 4) %>% 
  mutate(quantile = cut(mpg_mean, list_q[[4]], labels = FALSE, include.lowest = TRUE))

g5 <- a %>% 
  filter(gear == 5) %>% 
  mutate(quantile = cut(mpg_mean, list_q[[5]], labels = FALSE, include.lowest = TRUE))

bind_rows(g3, g4, g5)

Obtaining:

# A tibble: 11 x 4
    gear  carb mpg_mean quantile
   <dbl> <dbl>    <dbl>    <int>
 1     3     1     20.3        4
 2     3     2     17.2        3
 3     3     3     16.3        3
 4     3     4     12.6        1
 5     4     1     29.1        4
 6     4     2     24.8        3
 7     4     4     19.8        1
 8     5     2     28.2        4
 9     5     4     15.8        1
10     5     6     19.7        2
11     5     8     15          1

I wish to know if there is a way to do this more efficiently

Answer 1

We can first group_by gear and store the quantiles for mpg in a list. We can then also group_by carb to get mean of mpg value and use the quantiles stored in the list previously to cut this mean of mpg column.

library(dplyr)

mtcars %>% 
  group_by(gear) %>% 
  mutate(gear_q = list(quantile(mpg))) %>%
  group_by(carb, add = TRUE) %>%
  summarize(mpg_mean = mean(mpg), 
            gear_q = list(first(gear_q))) %>%
  mutate(quantile = cut(mpg_mean, first(gear_q), 
                        labels = FALSE, include.lowest = TRUE)) %>%
  select(-gear_q)

#    gear  carb mpg_mean quantile
#   <dbl> <dbl>    <dbl>    <int>
# 1     3     1     20.3        4
# 2     3     2     17.2        3
# 3     3     3     16.3        3
# 4     3     4     12.6        1
# 5     4     1     29.1        4
# 6     4     2     24.8        3
# 7     4     4     19.8        1
# 8     5     2     28.2        4
# 9     5     4     15.8        1
#10     5     6     19.7        2
#11     5     8     15          1