Group a data.frame by percentile ranges in variable with constant upper bound

This function is a wrapper around percentify. Given a width`` and a n`, it will generate a number of random interval with fixed width.

percentify_random(data, var, width, n = 10)

Arguments

data	A data.frame or tibble,
var	Variable to do grouping by as string or symbol.
width	Numerical values for the width of the interval. Must be between 0 and 1.
n	Integer, number of intervals to create.

Value

percentile grouped tibble

Details

There is a ggplot2::autoplot() to visualize the the percentile ranges.

See also

Other percentile samplers: autoplot.percentiled_df, percentify_cut, percentify_max, percentify_min

Examples

library(dplyr)
library(broom)
set.seed(1234)
percent_mtcars <- percentify_random(mtcars, mpg, 0.4, 10)

percent_mtcars
#> # A tibble: 32 x 11
#> # Groups:   .percentile_mpg [10]
#>      mpg   cyl  disp    hp  drat    wt  qsec    vs    am  gear  carb
#>    <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#>  1  21       6  160    110  3.9   2.62  16.5     0     1     4     4
#>  2  21       6  160    110  3.9   2.88  17.0     0     1     4     4
#>  3  22.8     4  108     93  3.85  2.32  18.6     1     1     4     1
#>  4  21.4     6  258    110  3.08  3.22  19.4     1     0     3     1
#>  5  18.7     8  360    175  3.15  3.44  17.0     0     0     3     2
#>  6  18.1     6  225    105  2.76  3.46  20.2     1     0     3     1
#>  7  14.3     8  360    245  3.21  3.57  15.8     0     0     3     4
#>  8  24.4     4  147.    62  3.69  3.19  20       1     0     4     2
#>  9  22.8     4  141.    95  3.92  3.15  22.9     1     0     4     2
#> 10  19.2     6  168.   123  3.92  3.44  18.3     1     0     4     4
#> # … with 22 more rows

summarize(percent_mtcars,
          mean_hp = mean(hp),
          mean_wt = mean(wt),
          n_obs = n()
          )
#> # A tibble: 10 x 4
#>    .percentile_mpg mean_hp mean_wt n_obs
#>    <chr>             <dbl>   <dbl> <int>
#>  1 6.8%-46.8%        193.     3.71    12
#>  2 37.3%-77.3%       123.     3.06    13
#>  3 36.6%-76.6%       123.     3.06    13
#>  4 37.4%-77.4%       123.     3.06    13
#>  5 51.7%-91.7%        98.7    2.51    13
#>  6 38.4%-78.4%       123.     3.06    13
#>  7 0.6%-40.6%        208.     4.01    13
#>  8 14%-54%           178.     3.58    12
#>  9 40%-80%           123.     3.03    12
#> 10 30.9%-70.9%       140.     3.31    12

percent_mtcars %>%
  group_modify(~tidy(lm(disp ~ wt + cyl, data = .x)))
#> # A tibble: 30 x 6
#> # Groups:   .percentile_mpg [10]
#>    .percentile_mpg term        estimate std.error statistic p.value
#>    <chr>           <chr>          <dbl>     <dbl>     <dbl>   <dbl>
#>  1 6.8%-46.8%      (Intercept)   -306.      154.      -1.99 0.0778 
#>  2 6.8%-46.8%      wt              44.9      25.8      1.74 0.115  
#>  3 6.8%-46.8%      cyl             57.9      18.6      3.12 0.0123 
#>  4 37.3%-77.3%     (Intercept)   -235.       90.7     -2.59 0.0269 
#>  5 37.3%-77.3%     wt              58.3      41.3      1.41 0.188  
#>  6 37.3%-77.3%     cyl             44.2      13.8      3.21 0.00939
#>  7 36.6%-76.6%     (Intercept)   -235.       90.7     -2.59 0.0269 
#>  8 36.6%-76.6%     wt              58.3      41.3      1.41 0.188  
#>  9 36.6%-76.6%     cyl             44.2      13.8      3.21 0.00939
#> 10 37.4%-77.4%     (Intercept)   -235.       90.7     -2.59 0.0269 
#> # … with 20 more rows

library(ggplot2)
autoplot(percent_mtcars)