Performance tips

using DataFrames
using BenchmarkTools
using CategoricalArrays
using PooledArrays
using Random

Access by column number is faster than by name

x = DataFrame(rand(5, 1000), :auto)
@btime $x[!, 500]; ## Faster

  3.095 ns (0 allocations: 0 bytes)

@btime $x.x500;  ## Slower

  11.122 ns (0 allocations: 0 bytes)

When working with data DataFrame use barrier functions or type annotation

function f_bad() ## this function will be slow
    Random.seed!(1)
    x = DataFrame(rand(1000000, 2), :auto)
    y, z = x[!, 1], x[!, 2]
    p = 0.0
    for i in 1:nrow(x)
        p += y[i] * z[i]
    end
    p
end

@btime f_bad();
# if you run @code_warntype f_bad() then you notice
# that Julia does not know column types of `DataFrame`

  99.692 ms (5999022 allocations: 122.06 MiB)

solution 1 is to use barrier function (it should be possible to use it in almost any code) for the calculation. You will notice much less memopry allocations and faster performance.

function f_inner(y, z)
    p = 0.0
    for i in eachindex(y, z)
        p += y[i] * z[i]
    end
    p
end

function f_barrier()
    Random.seed!(1)
    x = DataFrame(rand(1000000, 2), :auto)
    f_inner(x[!, 1], x[!, 2])
end

@btime f_barrier();

  4.277 ms (44 allocations: 30.52 MiB)

or use inbuilt function if possible

using LinearAlgebra

function f_inbuilt()
    Random.seed!(1)
    x = DataFrame(rand(1000000, 2), :auto)
    dot(x[!, 1], x[!, 2])
end

@btime f_inbuilt();

  3.661 ms (44 allocations: 30.52 MiB)

solution 2 is to provide the types of extracted columns. However, there are cases in which you will not know these types.

function f_typed()
    Random.seed!(1)
    x = DataFrame(rand(1000000, 2), :auto)
    y::Vector{Float64}, z::Vector{Float64} = x[!, 1], x[!, 2]
    p = 0.0
    for i in 1:nrow(x)
        p += y[i] * z[i]
    end
    p
end

@btime f_typed();

  3.887 ms (44 allocations: 30.52 MiB)

In general for tall and narrow tables it is often useful to use Tables.rowtable, Tables.columntable or Tables.namedtupleiterator for intermediate processing of data in a type-stable way.

Consider using delayed DataFrame creation technique

also notice the difference in performance between copying vs non-copying data frame creation

function f1()
    x = DataFrame([Vector{Float64}(undef, 10^4) for i in 1:100], :auto, copycols=false) ## we work with a DataFrame directly
    for c in 1:ncol(x)
        d = x[!, c]
        for r in 1:nrow(x)
            d[r] = rand()
        end
    end
    x
end

function f1a()
    x = DataFrame([Vector{Float64}(undef, 10^4) for i in 1:100], :auto) ## we work with a DataFrame directly
    for c in 1:ncol(x)
        d = x[!, c]
        for r in 1:nrow(x)
            d[r] = rand()
        end
    end
    x
end

function f2()
    x = Vector{Any}(undef, 100)
    for c in 1:length(x)
        d = Vector{Float64}(undef, 10^4)
        for r in eachindex(d)
            d[r] = rand()
        end
        x[c] = d
    end
    DataFrame(x, :auto, copycols=false) ## we delay creation of DataFrame after we have our job done
end

function f2a()
    x = Vector{Any}(undef, 100)
    for c in eachindex(x)
        d = Vector{Float64}(undef, 10^4)
        for r in eachindex(d)
            d[r] = rand()
        end
        x[c] = d
    end
    DataFrame(x, :auto) ## we delay creation of DataFrame after we have our job done
end

@btime f1();
@btime f1a();
@btime f2();
@btime f2a();

  28.362 ms (1949728 allocations: 37.40 MiB)
  28.251 ms (1950028 allocations: 45.03 MiB)
  1.156 ms (728 allocations: 7.66 MiB)
  1.607 ms (1028 allocations: 15.29 MiB)

You can add rows to a DataFrame in place and it is fast

x = DataFrame(rand(10^6, 5), :auto)
y = DataFrame(transpose(1.0:5.0), :auto)
z = [1.0:5.0;]

@btime vcat($x, $y); ## creates a new DataFrame - slow
@btime append!($x, $y); ## in place - fast

x = DataFrame(rand(10^6, 5), :auto) ## reset to the same starting point
@btime push!($x, $z); ## add a single row in place - fast

  1.894 ms (212 allocations: 38.16 MiB)
  1.132 μs (29 allocations: 1.50 KiB)
  441.889 ns (16 allocations: 256 bytes)

Allowing missing as well as categorical slows down computations

using StatsBase

function test(data) ## uses countmap function to test performance
    println(eltype(data))
    x = rand(data, 10^6)
    y = categorical(x)
    println(" raw:")
    @btime countmap($x)
    println(" categorical:")
    @btime countmap($y)
    nothing
end

test(1:10)
test([randstring() for i in 1:10])
test(allowmissing(1:10))
test(allowmissing([randstring() for i in 1:10]))

Int64
 raw:
  1.824 ms (8 allocations: 7.63 MiB)
 categorical:
  15.564 ms (1000004 allocations: 30.52 MiB)
String
 raw:
  20.521 ms (4 allocations: 448 bytes)
 categorical:
  31.713 ms (1000004 allocations: 30.52 MiB)
Union{Missing, Int64}
 raw:
  5.983 ms (4 allocations: 464 bytes)
 categorical:
  15.494 ms (1000004 allocations: 30.52 MiB)
Union{Missing, String}
 raw:
  19.281 ms (4 allocations: 448 bytes)
 categorical:
  29.505 ms (1000004 allocations: 30.52 MiB)

When aggregating use column selector and prefer integer, categorical, or pooled array grouping variable

df = DataFrame(x=rand('a':'d', 10^7), y=1);

gdf = groupby(df, :x)

GroupedDataFrame with 4 groups based on key: x

First Group (2499892 rows): x = 'b': ASCII/Unicode U+0062 (category Ll: Letter, lowercase)

2499867 rows omitted

Row	x	y
	Char	Int64
1	b	1
2	b	1
3	b	1
4	b	1
5	b	1
6	b	1
7	b	1
8	b	1
9	b	1
10	b	1
11	b	1
12	b	1
13	b	1
⋮	⋮	⋮
2499881	b	1
2499882	b	1
2499883	b	1
2499884	b	1
2499885	b	1
2499886	b	1
2499887	b	1
2499888	b	1
2499889	b	1
2499890	b	1
2499891	b	1
2499892	b	1

⋮

Last Group (2499142 rows): x = 'c': ASCII/Unicode U+0063 (category Ll: Letter, lowercase)

2499117 rows omitted

Row	x	y
	Char	Int64
1	c	1
2	c	1
3	c	1
4	c	1
5	c	1
6	c	1
7	c	1
8	c	1
9	c	1
10	c	1
11	c	1
12	c	1
13	c	1
⋮	⋮	⋮
2499131	c	1
2499132	c	1
2499133	c	1
2499134	c	1
2499135	c	1
2499136	c	1
2499137	c	1
2499138	c	1
2499139	c	1
2499140	c	1
2499141	c	1
2499142	c	1

traditional syntax, slow

@btime combine(v -> sum(v.y), $gdf)

  17.054 ms (332 allocations: 19.09 MiB)

4×2 DataFrame

Row	x	x1
	Char	Int64
1	b	2499892
2	d	2498228
3	a	2502738
4	c	2499142

use column selector

@btime combine($gdf, :y => sum)

  6.853 ms (198 allocations: 10.14 KiB)

4×2 DataFrame

Row	x	y_sum
	Char	Int64
1	b	2499892
2	d	2498228
3	a	2502738
4	c	2499142

transform!(df, :x => categorical => :x);
gdf = groupby(df, :x)

GroupedDataFrame with 4 groups based on key: x

First Group (2502738 rows): x = CategoricalArrays.CategoricalValue{Char, UInt32} 'a'

2502713 rows omitted

Row	x	y
	Cat…	Int64
1	a	1
2	a	1
3	a	1
4	a	1
5	a	1
6	a	1
7	a	1
8	a	1
9	a	1
10	a	1
11	a	1
12	a	1
13	a	1
⋮	⋮	⋮
2502727	a	1
2502728	a	1
2502729	a	1
2502730	a	1
2502731	a	1
2502732	a	1
2502733	a	1
2502734	a	1
2502735	a	1
2502736	a	1
2502737	a	1
2502738	a	1

⋮

Last Group (2498228 rows): x = CategoricalArrays.CategoricalValue{Char, UInt32} 'd'

2498203 rows omitted

Row	x	y
	Cat…	Int64
1	d	1
2	d	1
3	d	1
4	d	1
5	d	1
6	d	1
7	d	1
8	d	1
9	d	1
10	d	1
11	d	1
12	d	1
13	d	1
⋮	⋮	⋮
2498217	d	1
2498218	d	1
2498219	d	1
2498220	d	1
2498221	d	1
2498222	d	1
2498223	d	1
2498224	d	1
2498225	d	1
2498226	d	1
2498227	d	1
2498228	d	1

@btime combine($gdf, :y => sum)

  6.883 ms (206 allocations: 10.62 KiB)

4×2 DataFrame

Row	x	y_sum
	Cat…	Int64
1	a	2502738
2	b	2499892
3	c	2499142
4	d	2498228

transform!(df, :x => PooledArray{Char} => :x)

10000000×2 DataFrame

9999975 rows omitted

Row	x	y
	Char	Int64
1	b	1
2	d	1
3	a	1
4	d	1
5	b	1
6	c	1
7	b	1
8	d	1
9	d	1
10	c	1
11	d	1
12	a	1
13	d	1
⋮	⋮	⋮
9999989	b	1
9999990	b	1
9999991	c	1
9999992	a	1
9999993	a	1
9999994	a	1
9999995	c	1
9999996	c	1
9999997	d	1
9999998	c	1
9999999	c	1
10000000	b	1

gdf = groupby(df, :x)

GroupedDataFrame with 4 groups based on key: x

First Group (2499892 rows): x = 'b': ASCII/Unicode U+0062 (category Ll: Letter, lowercase)

2499867 rows omitted

Row	x	y
	Char	Int64
1	b	1
2	b	1
3	b	1
4	b	1
5	b	1
6	b	1
7	b	1
8	b	1
9	b	1
10	b	1
11	b	1
12	b	1
13	b	1
⋮	⋮	⋮
2499881	b	1
2499882	b	1
2499883	b	1
2499884	b	1
2499885	b	1
2499886	b	1
2499887	b	1
2499888	b	1
2499889	b	1
2499890	b	1
2499891	b	1
2499892	b	1

⋮

Last Group (2499142 rows): x = 'c': ASCII/Unicode U+0063 (category Ll: Letter, lowercase)

2499117 rows omitted

Row	x	y
	Char	Int64
1	c	1
2	c	1
3	c	1
4	c	1
5	c	1
6	c	1
7	c	1
8	c	1
9	c	1
10	c	1
11	c	1
12	c	1
13	c	1
⋮	⋮	⋮
2499131	c	1
2499132	c	1
2499133	c	1
2499134	c	1
2499135	c	1
2499136	c	1
2499137	c	1
2499138	c	1
2499139	c	1
2499140	c	1
2499141	c	1
2499142	c	1

@btime combine($gdf, :y => sum)

  6.877 ms (200 allocations: 10.20 KiB)

4×2 DataFrame

Row	x	y_sum
	Char	Int64
1	b	2499892
2	d	2498228
3	a	2502738
4	c	2499142

Use views instead of materializing a new DataFrame

x = DataFrame(rand(100, 1000), :auto)
@btime $x[1:1, :]

  178.073 μs (3993 allocations: 159.03 KiB)

1×1000 DataFrame

900 columns omitted

Row	x1	x2	x3	x4	x5	x6	x7	x8	x9	x10	x11	x12	x13	x14	x15	x16	x17	x18	x19	x20	x21	x22	x23	x24	x25	x26	x27	x28	x29	x30	x31	x32	x33	x34	x35	x36	x37	x38	x39	x40	x41	x42	x43	x44	x45	x46	x47	x48	x49	x50	x51	x52	x53	x54	x55	x56	x57	x58	x59	x60	x61	x62	x63	x64	x65	x66	x67	x68	x69	x70	x71	x72	x73	x74	x75	x76	x77	x78	x79	x80	x81	x82	x83	x84	x85	x86	x87	x88	x89	x90	x91	x92	x93	x94	x95	x96	x97	x98	x99	x100	⋯
	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	⋯
1	0.134105	0.0119839	0.80118	0.29816	0.875661	0.0849515	0.319232	0.856822	0.272222	0.406149	0.793228	0.773672	0.202574	0.444473	0.359512	0.530218	0.00773591	0.896723	0.313556	0.737386	0.398533	0.39016	0.996516	0.233524	0.292958	0.349268	0.493418	0.0776396	0.603761	0.957692	0.336215	0.635226	0.203385	0.86762	0.207062	0.525631	0.604884	0.162609	0.266444	0.923934	0.0997255	0.744273	0.782608	0.400171	0.524721	0.362577	0.331129	0.619025	0.00112627	0.37121	0.329328	0.519182	0.762861	0.760448	0.82629	0.267479	0.918333	0.963585	0.910943	0.0644922	0.17805	0.187619	0.517915	0.112202	0.540578	0.526256	0.867859	0.753748	0.906489	0.828252	0.635565	0.357952	0.991087	0.421794	0.640939	0.581289	0.47546	0.986232	0.810611	0.863877	0.342379	0.314763	0.471149	0.907987	0.368039	0.0585712	0.847582	0.678445	0.978833	0.543357	0.651853	0.596623	0.273822	0.778689	0.524759	0.615975	0.222137	0.59717	0.217785	0.583383	⋯

@btime $x[1, :]

  20.670 ns (0 allocations: 0 bytes)

DataFrameRow (1000 columns)

900 columns omitted

Row	x1	x2	x3	x4	x5	x6	x7	x8	x9	x10	x11	x12	x13	x14	x15	x16	x17	x18	x19	x20	x21	x22	x23	x24	x25	x26	x27	x28	x29	x30	x31	x32	x33	x34	x35	x36	x37	x38	x39	x40	x41	x42	x43	x44	x45	x46	x47	x48	x49	x50	x51	x52	x53	x54	x55	x56	x57	x58	x59	x60	x61	x62	x63	x64	x65	x66	x67	x68	x69	x70	x71	x72	x73	x74	x75	x76	x77	x78	x79	x80	x81	x82	x83	x84	x85	x86	x87	x88	x89	x90	x91	x92	x93	x94	x95	x96	x97	x98	x99	x100	⋯
	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	⋯
1	0.134105	0.0119839	0.80118	0.29816	0.875661	0.0849515	0.319232	0.856822	0.272222	0.406149	0.793228	0.773672	0.202574	0.444473	0.359512	0.530218	0.00773591	0.896723	0.313556	0.737386	0.398533	0.39016	0.996516	0.233524	0.292958	0.349268	0.493418	0.0776396	0.603761	0.957692	0.336215	0.635226	0.203385	0.86762	0.207062	0.525631	0.604884	0.162609	0.266444	0.923934	0.0997255	0.744273	0.782608	0.400171	0.524721	0.362577	0.331129	0.619025	0.00112627	0.37121	0.329328	0.519182	0.762861	0.760448	0.82629	0.267479	0.918333	0.963585	0.910943	0.0644922	0.17805	0.187619	0.517915	0.112202	0.540578	0.526256	0.867859	0.753748	0.906489	0.828252	0.635565	0.357952	0.991087	0.421794	0.640939	0.581289	0.47546	0.986232	0.810611	0.863877	0.342379	0.314763	0.471149	0.907987	0.368039	0.0585712	0.847582	0.678445	0.978833	0.543357	0.651853	0.596623	0.273822	0.778689	0.524759	0.615975	0.222137	0.59717	0.217785	0.583383	⋯

@btime view($x, 1:1, :)

  19.745 ns (0 allocations: 0 bytes)

1×1000 SubDataFrame

900 columns omitted

Row	x1	x2	x3	x4	x5	x6	x7	x8	x9	x10	x11	x12	x13	x14	x15	x16	x17	x18	x19	x20	x21	x22	x23	x24	x25	x26	x27	x28	x29	x30	x31	x32	x33	x34	x35	x36	x37	x38	x39	x40	x41	x42	x43	x44	x45	x46	x47	x48	x49	x50	x51	x52	x53	x54	x55	x56	x57	x58	x59	x60	x61	x62	x63	x64	x65	x66	x67	x68	x69	x70	x71	x72	x73	x74	x75	x76	x77	x78	x79	x80	x81	x82	x83	x84	x85	x86	x87	x88	x89	x90	x91	x92	x93	x94	x95	x96	x97	x98	x99	x100	⋯
	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	⋯
1	0.134105	0.0119839	0.80118	0.29816	0.875661	0.0849515	0.319232	0.856822	0.272222	0.406149	0.793228	0.773672	0.202574	0.444473	0.359512	0.530218	0.00773591	0.896723	0.313556	0.737386	0.398533	0.39016	0.996516	0.233524	0.292958	0.349268	0.493418	0.0776396	0.603761	0.957692	0.336215	0.635226	0.203385	0.86762	0.207062	0.525631	0.604884	0.162609	0.266444	0.923934	0.0997255	0.744273	0.782608	0.400171	0.524721	0.362577	0.331129	0.619025	0.00112627	0.37121	0.329328	0.519182	0.762861	0.760448	0.82629	0.267479	0.918333	0.963585	0.910943	0.0644922	0.17805	0.187619	0.517915	0.112202	0.540578	0.526256	0.867859	0.753748	0.906489	0.828252	0.635565	0.357952	0.991087	0.421794	0.640939	0.581289	0.47546	0.986232	0.810611	0.863877	0.342379	0.314763	0.471149	0.907987	0.368039	0.0585712	0.847582	0.678445	0.978833	0.543357	0.651853	0.596623	0.273822	0.778689	0.524759	0.615975	0.222137	0.59717	0.217785	0.583383	⋯

@btime $x[1:1, 1:20]

  3.753 μs (70 allocations: 3.09 KiB)

1×20 DataFrame

Row	x1	x2	x3	x4	x5	x6	x7	x8	x9	x10	x11	x12	x13	x14	x15	x16	x17	x18	x19	x20
	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64
1	0.134105	0.0119839	0.80118	0.29816	0.875661	0.0849515	0.319232	0.856822	0.272222	0.406149	0.793228	0.773672	0.202574	0.444473	0.359512	0.530218	0.00773591	0.896723	0.313556	0.737386

@btime $x[1, 1:20]

  20.982 ns (0 allocations: 0 bytes)

DataFrameRow (20 columns)

Row	x1	x2	x3	x4	x5	x6	x7	x8	x9	x10	x11	x12	x13	x14	x15	x16	x17	x18	x19	x20
	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64
1	0.134105	0.0119839	0.80118	0.29816	0.875661	0.0849515	0.319232	0.856822	0.272222	0.406149	0.793228	0.773672	0.202574	0.444473	0.359512	0.530218	0.00773591	0.896723	0.313556	0.737386

@btime view($x, 1:1, 1:20)

  21.283 ns (0 allocations: 0 bytes)

1×20 SubDataFrame

Row	x1	x2	x3	x4	x5	x6	x7	x8	x9	x10	x11	x12	x13	x14	x15	x16	x17	x18	x19	x20
	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64	Float64
1	0.134105	0.0119839	0.80118	0.29816	0.875661	0.0849515	0.319232	0.856822	0.272222	0.406149	0.793228	0.773672	0.202574	0.444473	0.359512	0.530218	0.00773591	0.896723	0.313556	0.737386

---

This notebook was generated using Literate.jl.