Skip to content

replace DataFrames with TypedTables. Write testes for Select and Reject. #6

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Oct 29, 2021
Merged

replace DataFrames with TypedTables. Write testes for Select and Reject. #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e31afd3
replace DataFrames with TypedTables. Write testes for Select and Reject.
mrr00b00t Oct 29, 2021
03535f5
rewrite test
mrr00b00t Oct 29, 2021
006d2b6
more tests to Select and Reject
mrr00b00t Oct 29, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion test/Project.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
[deps]
DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"
GR = "28b8d3ca-fb5f-59d9-8090-bfdbd6d07a71"
ImageIO = "82e4d734-157c-48bb-816b-45c225c6df19"
Expand All @@ -10,6 +9,7 @@ ReferenceTests = "324d217c-45ce-50fc-942e-d289b448e8cf"
Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
TypedTables = "9d95f2ec-7b3d-5a63-8d20-e2491e220bb9"

[compat]
Plots = "=1.22.4"
Expand Down
2 changes: 1 addition & 1 deletion test/runtests.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
using TableTransforms
using Distributions
using Tables
using DataFrames
using TypedTables
using LinearAlgebra
using Statistics
using Test, Random, Plots
Expand Down
98 changes: 84 additions & 14 deletions test/transforms.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,24 +2,94 @@
@testset "Identity" begin
x = rand(4000)
y = rand(4000)
t = DataFrame(:x => x, :y => y)
t = Table(; x, y)
n, c = apply(Identity(), t)
@test t == n
tₒ = revert(Identity(), n, c)
@test t == tₒ
end

@testset "Select" begin
a = rand(4000)
b = rand(4000)
c = rand(4000)
d = rand(4000)
e = rand(4000)
f = rand(4000)
t = Table(; a, b, c, d, e, f)

n₁, c₁ = apply(Select(:f, :d), t)
n₂, c₂ = apply(Select(:f, :d, :b), t)
n₃, c₃ = apply(Select(:d, :c, :b), t)
n₄, c₄ = apply(Select(:e, :c, :b, :a), t)

u₁ = Tables.columnnames(n₁)
u₂ = Tables.columnnames(n₂)
u₃ = Tables.columnnames(n₃)
u₄ = Tables.columnnames(n₄)

@test u₁ == (:f, :d)
@test u₂ == (:f, :d, :b)
@test u₃ == (:d, :c, :b)
@test u₄ == (:e, :c, :b, :a)

tₒ₁ = revert(Select(:f, :d), n₁, c₁)
tₒ₂ = revert(Select(:f, :d, :b), n₂, c₂)
tₒ₃ = revert(Select(:d, :c, :b), n₃, c₃)
tₒ₄ = revert(Select(:e, :c, :b, :a), n₄, c₄)

@test t == tₒ₁
@test t == tₒ₂
@test t == tₒ₃
@test t == tₒ₄
end

@testset "Reject" begin
a = rand(4000)
b = rand(4000)
c = rand(4000)
d = rand(4000)
e = rand(4000)
f = rand(4000)
t = Table(; a, b, c, d, e, f)

n₁, c₁ = apply(Reject(:f, :d), t)
n₂, c₂ = apply(Reject(:f, :d, :b), t)
n₃, c₃ = apply(Reject(:d, :c, :b), t)
n₄, c₄ = apply(Reject(:e, :c, :b, :a), t)

u₁ = Tables.columnnames(n₁)
u₂ = Tables.columnnames(n₂)
u₃ = Tables.columnnames(n₃)
u₄ = Tables.columnnames(n₄)

@test u₁ == (:a, :b, :c, :e)
@test u₂ == (:a, :c, :e)
@test u₃ == (:a, :e, :f)
@test u₄ == (:d, :f)

tₒ₁ = revert(Reject(:f, :d), n₁, c₁)
tₒ₂ = revert(Reject(:f, :d, :b), n₂, c₂)
tₒ₃ = revert(Reject(:d, :c, :b), n₃, c₃)
tₒ₄ = revert(Reject(:e, :c, :b, :a), n₄, c₄)

@test t == tₒ₁
@test t == tₒ₂
@test t == tₒ₃
@test t == tₒ₄
end

@testset "Center" begin
Random.seed!(42) # to reproduce the results
x = rand(Normal(2,1), 4000)
y = rand(Normal(5,1), 4000)
t = DataFrame(:x => x, :y => y)
t = Table(; x, y)
n, c = apply(Center(), t)
μ = mean(Tables.matrix(n), dims=1)
@test isapprox(μ[1], 0; atol=1e-6)
@test isapprox(μ[2], 0; atol=1e-6)
tₒ = revert(Center(), n, c)
@test t ≈ tₒ
@test Tables.matrix(t) ≈ Tables.matrix(tₒ)

# visual tests
if visualtests
Expand All @@ -35,14 +105,14 @@
Random.seed!(42) # to reproduce the results
x = rand(Normal(4,3), 4000)
y = rand(Normal(7,5), 4000)
t = DataFrame(:x => x, :y => y)
t = Table(; x, y)
n, c = apply(Scale(low=0, high=1), t)
@test all(x -> x <= 1, n.x)
@test all(x -> x >= 0, n.x)
@test all(y -> y <= 1, n.y)
@test all(y -> y >= 0, n.y)
tₒ = revert(Scale(low=0, high=1), n, c)
@test t ≈ tₒ
@test Tables.matrix(t) ≈ Tables.matrix(tₒ)

# visual tests
if visualtests
Expand All @@ -58,7 +128,7 @@
Random.seed!(42) # to reproduce the results
x = rand(Normal(7,10), 4000)
y = rand(Normal(15,2), 4000)
t = DataFrame(:x => x, :y => y)
t = Table(; x, y)
n, c = apply(ZScore(), t)
μ = mean(Tables.matrix(n), dims=1)
σ = std(Tables.matrix(n), dims=1)
Expand All @@ -67,7 +137,7 @@
@test isapprox(μ[2], 0; atol=1e-6)
@test isapprox(σ[2], 1; atol=1e-6)
tₒ = revert(ZScore(), n, c)
@test t ≈ tₒ
@test Tables.matrix(t) ≈ Tables.matrix(tₒ)

# visual tests
if visualtests
Expand All @@ -83,46 +153,46 @@
# PCA test
x = rand(Normal(0,10), 1500)
y = x + rand(Normal(0,2), 1500)
t = DataFrame(:x => x, :y => y)
t = Table(; x, y)
n, c = apply(EigenAnalysis(:V), t)
Σ = cov(Tables.matrix(n))
@test Σ[1,1] > 1
@test isapprox(Σ[1,2], 0; atol=1e-6)
@test isapprox(Σ[2,1], 0; atol=1e-6)
@test Σ[2,2] > 1
tₒ = revert(EigenAnalysis(:V), n, c)
@test t ≈ tₒ
@test Tables.matrix(t) ≈ Tables.matrix(tₒ)

# DRS test
x = rand(Normal(0,10), 1500)
y = x + rand(Normal(0,2), 1500)
t = DataFrame(:x => x, :y => y)
t = Table(; x, y)
n, c = apply(EigenAnalysis(:VD), t)
Σ = cov(Tables.matrix(n))
@test isapprox(Σ[1,2], 0; atol=1e-6)
@test isapprox(Σ[2,1], 0; atol=1e-6)
@test isapprox(Σ[1,1], 1; atol=1e-6)
@test isapprox(Σ[2,2], 1; atol=1e-6)
tₒ = revert(EigenAnalysis(:VD), n, c)
@test t ≈ tₒ
@test Tables.matrix(t) ≈ Tables.matrix(tₒ)

# SDS test
x = rand(Normal(0,10), 1500)
y = x + rand(Normal(0,2), 1500)
t = DataFrame(:x => x, :y => y)
t = Table(; x, y)
n, c = apply(EigenAnalysis(:VDV), t)
Σ = cov(Tables.matrix(n))
@test isapprox(Σ[1,2], 0; atol=1e-6)
@test isapprox(Σ[2,1], 0; atol=1e-6)
@test isapprox(Σ[1,1], 1; atol=1e-6)
@test isapprox(Σ[2,2], 1; atol=1e-6)
tₒ = revert(EigenAnalysis(:VDV), n, c)
@test t ≈ tₒ
@test Tables.matrix(t) ≈ Tables.matrix(tₒ)

Random.seed!(42) # to reproduce the results
x = rand(Normal(0,10), 4000)
y = x + rand(Normal(0,2), 4000)
t₁ = DataFrame(:x => x, :y => y)
t₁ = Table(; x, y)
t₂, c₂ = apply(EigenAnalysis(:V), t₁)
t₃, c₃ = apply(EigenAnalysis(:VD), t₁)
t₄, c₄ = apply(EigenAnalysis(:VDV), t₁)
Expand Down