Merge pull request #26 from ATISLabs/feature/generate_hastie_10_2

[#1] Feature/generate_hastie_10_2

Author: filipebraida

Diff for: README.md

@@ -40,6 +40,7 @@ make_regression      | Generate a random regression problem.
 make_classification  | Generate a random n-class classification problem.                       | [link](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_classification.html)
 make_low_rank_matrix | Generate a mostly low rank matrix with bell-shaped singular values.     | [link](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_low_rank_matrix.html)
 make_swiss_roll      | Generate a swiss roll dataset.                                          | [link](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_swiss_roll.html)
+make_hastie_10_2     | Generates data for binary classification used in Hastie et al.          |[link](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_hastie_10_2.html)
 make_gaussian_quantiles | Generate a swiss roll dataset.                                          | [link](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_gaussian_quantiles.html)
 
 **Disclaimer**: SyntheticDatasets.jl borrows code and documentation from

Diff for: src/sklearn.jl

@@ -362,6 +362,24 @@ function generate_swiss_roll(;  n_samples::Int = 100,
    return convert(features, labels)
 end
 
+"""
+function generate_hastie_10_2(;  n_samples::Int = 12000,
+                                 random_state::Union{Int,Nothing} = nothing)
+Generates data for binary classification used in Hastie et al. 2009, Example 10.2.
+#Arguments
+- `n_samples::Int = 100`: The number of samples..
+- `random_state::Union{Int, Nothing} = nothing`: Determines random number generation for dataset creation. Pass an int for reproducible output across multiple function calls. See Glossary.
+Reference: [link](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_hastie_10_2.html)
+"""
+function generate_hastie_10_2(;  n_samples::Int = 12000,
+                               random_state::Union{Int,Nothing} = nothing)
+
+   (features, labels) = datasets.make_hastie_10_2(  n_samples = n_samples,
+                                                   random_state = random_state)
+
+   return convert(features, labels)
+end
+
 """
 function generate_gaussian_quantiles(; mean::Array{<:Union{Number, Nothing}, 1} = [nothing],
                                        cov::Float64 = 1,
@@ -398,5 +416,5 @@ function generate_gaussian_quantiles(; mean::Union{Array{<:Number, 1}, Nothing}
                                                           shuffle = shuffle,
                                                           random_state = random_state)
 
-      return convert(features, labels)
+    return convert(features, labels)
 end

Diff for: test/runtests.jl

@@ -40,15 +40,15 @@ using Test
     @test size(data)[1] == samples
     @test size(data)[2] == features + 1
 
-    data = SyntheticDatasets.generate_classification(n_samples = samples,
-                                                    n_features = features,
-                                                    n_classes = 1)
+    data = SyntheticDatasets.generate_classification(   n_samples = samples,
+                                                        n_features = features,
+                                                        n_classes = 1)
 
     @test size(data)[1] == samples
     @test size(data)[2] == features + 1
 
     data = SyntheticDatasets.generate_friedman1(n_samples = samples,
-                                                    n_features = features)
+                                                n_features = features)
 
     @test size(data)[1] == samples
     @test size(data)[2] == features + 1
@@ -63,26 +63,32 @@ using Test
     @test size(data)[1] == samples
     @test size(data)[2] == 5
 
-    data = SyntheticDatasets.generate_low_rank_matrix(n_samples = samples,
-                                                    n_features = features,
-                                                    effective_rank = 10,
-                                                    tail_strength = 0.5,
-                                                    random_state = 5)
+    data = SyntheticDatasets.generate_low_rank_matrix(  n_samples = samples,
+                                                        n_features = features,
+                                                        effective_rank = 10,
+                                                        tail_strength = 0.5,
+                                                        random_state = 5)
 
     @test size(data)[1] == samples
     @test size(data)[2] == features
 
-    data = SyntheticDatasets.generate_swiss_roll(n_samples =samples,
+    data = SyntheticDatasets.generate_swiss_roll(n_samples = samples,
                                                  noise = 2.2,
                                                  random_state = 5)
 
     @test size(data)[1] == samples
     @test size(data)[2] == 4
 
-    data = SyntheticDatasets.generate_gaussian_quantiles(n_samples = samples,
-                                                    n_features = features,
+    data = SyntheticDatasets.generate_hastie_10_2(  n_samples = samples,
                                                     random_state = 5)
 
+    @test size(data)[1] == samples
+    @test size(data)[2] == 11
+
+    data = SyntheticDatasets.generate_gaussian_quantiles(   n_samples = samples,
+                                                            n_features = features,
+                                                            random_state = 5)
+
     @test size(data)[1] == samples
     @test size(data)[2] == features + 1
 end