# setup adapted from a bogul blog post  https://bkamins.github.io/julialang/2022/05/27/strings.html 
using Random, BenchmarkTools,  DataFrames, TidierData, PooledArrays, CategoricalArrays, InlineStrings

Random.seed!(1234);
df = transform!(DataFrame(str=[randstring() for _ in 10:10^6]),
                       :str .=>
                       [inlinestrings, ByRow(Symbol),
                        PooledArray, CategoricalArray] .=>
                       [:istr, :sym, :pstr, :cstr]);

df.A = rand(1:10, nrow(df));
df.B = rand(1:10, nrow(df));
df.C = rand(1:10, nrow(df));
categories = ["Category1", "Category2", "Category3", "Category4"];
df.CatVar = categorical(rand(categories, nrow(df)));
strings = ["String1", "String2", "String3", "String4"];
df.StrVar = rand(strings, nrow(df));
morecats = ["Category1", "Category2", "Category3", "Category4","Category5", "Category6", "Category7", "Category8"];
df.More_Cats = categorical(rand(morecats, nrow(df)));
tweleve_cats = ["Category1", "Category2", "Category3", "Category4","Category5", "Category6", "Category7", "Category8","Category9", "Category10", "Category11", "Category12"];
df.Cats_12 = categorical(rand(tweleve_cats, nrow(df)));

@benchmark  @summarize(@group_by(df, CatVar), A_mean = mean(A)) 

BenchmarkTools.Trial: 247 samples with 1 evaluation per sample.
 Range (min … max):  11.454 ms … 148.554 ms  ┊ GC (min … max):  0.00% … 90.16%
 Time  (median):     14.436 ms               ┊ GC (median):     9.01%
 Time  (mean ± σ):   20.259 ms ±  21.745 ms  ┊ GC (mean ± σ):  34.06% ± 20.50%

   █                                                            
  ▇█▆▅▅▃▃▃▂▁▁▁▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▃ ▂
  11.5 ms         Histogram: frequency by time          117 ms <

 Memory estimate: 101.43 MiB, allocs estimate: 529.

@benchmark df |> (df -> groupby(df, :CatVar)) |> (df -> combine(df,:A => mean)) 

BenchmarkTools.Trial: 1865 samples with 1 evaluation per sample.
 Range (min … max):  2.229 ms …  10.298 ms  ┊ GC (min … max): 0.00% … 76.43%
 Time  (median):     2.482 ms               ┊ GC (median):    0.00%
 Time  (mean ± σ):   2.681 ms ± 515.947 μs  ┊ GC (mean ± σ):  8.88% ± 11.80%

     ▃█▆▆▃▁                                                    
  ▁▄███████▇▃▂▂▂▄▃▄▄▄▃▂▂▃▂▂▂▁▁▂▁▁▁▁▂▂▁▂▂▂▂▂▂▁▁▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁ ▂
  2.23 ms         Histogram: frequency by time        4.25 ms <

 Memory estimate: 7.64 MiB, allocs estimate: 286.

@benchmark  @summarize(@group_by(df, CatVar), A_mean = mean(A)) 

BenchmarkTools.Trial: 735 samples with 1 evaluation per sample.
 Range (min … max):  5.469 ms …  13.391 ms  ┊ GC (min … max):  4.81% … 52.58%
 Time  (median):     6.799 ms               ┊ GC (median):     9.00%
 Time  (mean ± σ):   6.802 ms ± 686.940 μs  ┊ GC (mean ± σ):  11.96% ±  5.91%

                     ▁▇▄▆▇▅ ▃▅ ▂ ▄█▅▆▃▄▃▆                      
  ▅▅▂▃▇▄▅▅▃▃▃▅▅▆▅▃▃▁▅██████▇██▇██████████▆▅▅▇▅▅▄▆▃▂▂▁▁▂▂▃▁▂▂▁ ▄
  5.47 ms         Histogram: frequency by time        8.22 ms <

 Memory estimate: 38.90 MiB, allocs estimate: 399.