Merge branch 'master' into feature/generate_gaussian_quantiles

Author: filipebraida

README.md

@@ -46,6 +46,12 @@ make_gaussian_quantiles | Generate a swiss roll dataset.
 [scikit-learn](https://scikit-learn.org/stable/modules/classes.html#samples-generator) in the dataset module, but *it is not an official part
 of that project*. It is licensed under [MIT](LICENSE).
 
+### Other Functions
+
+Dataset              | Title                                                                   | Reference
+---------------------|-------------------------------------------------------------------------|--------------------------------------------------
+generate_twospirals  | Generate two spirals dataset.                                           | [link](https://la.mathworks.com/matlabcentral/fileexchange/41459-6-functions-for-generating-artificial-datasets)
+
 [travis-img]: https://travis-ci.com/ATISLabs/SyntheticDatasets.jl.svg?branch=master
 [travis-url]: https://travis-ci.com/ATISLabs/SyntheticDatasets.jl
 

src/SyntheticDatasets.jl

@@ -11,6 +11,7 @@ function __init__()
 end
 
 include("sklearn.jl")
+include("matlab.jl")
 
 function convert(features::Array{T, 2}, labels::Array{D, 1})::DataFrame where {T <: Number, D <: Number}
     df = DataFrame()

src/matlab.jl

@@ -0,0 +1,33 @@
+"""
+    generate_twospirals(;    n_samples::Int = 2000,
+                             start_degrees::Int = 90,
+                             total_degrees::Int = 570,
+                             noise::Float64 = 0.2
+Generate two spirals dataset. Return a Nx3 matrix, where each line contains the X,Y coordinates and the class of an instance.
+# Arguments
+- `n_samples::Int = 2000`: The total number of points generated.
+- `start_degrees::Int = 90`: Determines how far from the origin the spirals start.
+- `total_degrees::Int = 570`: Controls the lenght of the spirals.
+- `noise::Float64 = 0.2`: Determines the noise in the dataset.
+Reference: [link](https://la.mathworks.com/matlabcentral/fileexchange/41459-6-functions-for-generating-artificial-datasets)
+"""
+function generate_twospirals(; n_samples::Int = 2000,
+                               start_degrees::Int = 90,
+                               total_degrees::Int = 570,
+                               noise::Float64 = 0.2)
+   start_degrees = deg2rad(start_degrees);
+
+   N1 = floor(Int, n_samples / 2);
+   N2 = n_samples - N1;
+
+   n = start_degrees .+ sqrt.(rand(N1,1)) .* deg2rad(total_degrees);
+   d1 = [-cos.(n).*n + rand(N1,1).*noise sin.(n).*n+rand(N1,1).*noise];
+
+   n = start_degrees .+ sqrt.(rand(N2,1)) .* deg2rad(total_degrees);
+   d2 = [cos.(n).*n+rand(N2,1)*noise -sin.(n).*n+rand(N2,1)*noise];
+
+   features = [d1; d2]
+   labels = [zeros(Int, N1); ones(Int, N1)]
+
+   return convert(features, labels);
+end

test/runtests.jl

@@ -47,6 +47,9 @@ using Test
     @test size(data)[1] == samples
     @test size(data)[2] == features + 1
 
+    @test size(data)[1] == samples
+    @test size(data)[2] == features + 1
+
     data = SyntheticDatasets.generate_friedman1(n_samples = samples,
                                                     n_features = features)
 
@@ -86,3 +89,12 @@ using Test
     @test size(data)[1] == samples
     @test size(data)[2] == features + 1
 end
+
+@testset "Matlab Generators" begin
+    samples = 20000
+
+    data = SyntheticDatasets.generate_twospirals(n_samples = samples,
+                                                 noise = 2.2)
+
+    @test size(data)[1] == samples
+end