From 0bc06faf3e4d8f5930f41b8261afb563d17dd2d1 Mon Sep 17 00:00:00 2001 From: ArturoAmorQ Date: Mon, 6 Feb 2023 14:28:06 +0100 Subject: [PATCH 1/6] DOC Add docstring example to make_regression --- sklearn/datasets/_samples_generator.py | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/sklearn/datasets/_samples_generator.py b/sklearn/datasets/_samples_generator.py index ffe81d9c13a18..24278f7a99302 100644 --- a/sklearn/datasets/_samples_generator.py +++ b/sklearn/datasets/_samples_generator.py @@ -609,6 +609,21 @@ def make_regression( coef : ndarray of shape (n_features,) or (n_features, n_targets) The coefficient of the underlying linear model. It is returned only if coef is True. + + Examples + -------- + >>> from sklearn.datasets import make_regression + >>> X, y = make_regression( + >>> n_samples=5, n_features=2, n_informative=0, noise=1, random_state=42 + >>> ) + >>> X + array([[ 0.49671415, -0.1382643 ], + [ 1.57921282, 0.76743473], + [ 0.64768854, 1.52302986], + [-0.46947439, 0.54256004], + [-0.23415337, -0.23413696]]) + >>> y + array([-0.46341769, -1.91328024, -0.46572975, -1.72491783, 0.24196227]) """ n_informative = min(n_features, n_informative) generator = check_random_state(random_state) From fe8d65b30ff4ebce32ff4dad0bcfa966744e8c13 Mon Sep 17 00:00:00 2001 From: ArturoAmorQ Date: Tue, 7 Feb 2023 14:56:31 +0100 Subject: [PATCH 2/6] Fix format --- sklearn/datasets/_samples_generator.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sklearn/datasets/_samples_generator.py b/sklearn/datasets/_samples_generator.py index 24278f7a99302..2fa4c1e65d199 100644 --- a/sklearn/datasets/_samples_generator.py +++ b/sklearn/datasets/_samples_generator.py @@ -614,8 +614,8 @@ def make_regression( -------- >>> from sklearn.datasets import make_regression >>> X, y = make_regression( - >>> n_samples=5, n_features=2, n_informative=0, noise=1, random_state=42 - >>> ) + ... n_samples=5, n_features=2, n_informative=0, noise=1, random_state=42 + ... ) >>> X array([[ 0.49671415, -0.1382643 ], [ 1.57921282, 0.76743473], From 44317017322b6fe2e98ed8d65c0839a8df91e3aa Mon Sep 17 00:00:00 2001 From: ArturoAmorQ Date: Tue, 7 Feb 2023 17:24:03 +0100 Subject: [PATCH 3/6] Remove n_informative=0 setting --- sklearn/datasets/_samples_generator.py | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/sklearn/datasets/_samples_generator.py b/sklearn/datasets/_samples_generator.py index 2fa4c1e65d199..d47a5996fc3a2 100644 --- a/sklearn/datasets/_samples_generator.py +++ b/sklearn/datasets/_samples_generator.py @@ -613,17 +613,15 @@ def make_regression( Examples -------- >>> from sklearn.datasets import make_regression - >>> X, y = make_regression( - ... n_samples=5, n_features=2, n_informative=0, noise=1, random_state=42 - ... ) + >>> X, y = make_regression(n_samples=5, n_features=2, noise=1, random_state=42) >>> X array([[ 0.49671415, -0.1382643 ], - [ 1.57921282, 0.76743473], [ 0.64768854, 1.52302986], + [-0.23415337, -0.23413696], [-0.46947439, 0.54256004], - [-0.23415337, -0.23413696]]) + [ 1.57921282, 0.76743473]]) >>> y - array([-0.46341769, -1.91328024, -0.46572975, -1.72491783, 0.24196227]) + array([ 6.73763609, 37.79636891, -10.27658818, 0.40174828, 42.22684334]) """ n_informative = min(n_features, n_informative) generator = check_random_state(random_state) From c2d24aeb7787b607e00006724aba03925b888286 Mon Sep 17 00:00:00 2001 From: Arturo Amor <86408019+ArturoAmorQ@users.noreply.github.com> Date: Wed, 8 Feb 2023 10:11:04 +0100 Subject: [PATCH 4/6] Update sklearn/datasets/_samples_generator.py Co-authored-by: Thomas J. Fan --- sklearn/datasets/_samples_generator.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sklearn/datasets/_samples_generator.py b/sklearn/datasets/_samples_generator.py index d47a5996fc3a2..e2ebaf3ef73ac 100644 --- a/sklearn/datasets/_samples_generator.py +++ b/sklearn/datasets/_samples_generator.py @@ -615,7 +615,7 @@ def make_regression( >>> from sklearn.datasets import make_regression >>> X, y = make_regression(n_samples=5, n_features=2, noise=1, random_state=42) >>> X - array([[ 0.49671415, -0.1382643 ], + array([[ 0.4967..., -0.1382... ], [ 0.64768854, 1.52302986], [-0.23415337, -0.23413696], [-0.46947439, 0.54256004], From 15f3466323399b237eb7bdef19ec364325e54fd3 Mon Sep 17 00:00:00 2001 From: ArturoAmorQ Date: Wed, 8 Feb 2023 10:13:40 +0100 Subject: [PATCH 5/6] Show four significant figures only --- sklearn/datasets/_samples_generator.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/sklearn/datasets/_samples_generator.py b/sklearn/datasets/_samples_generator.py index e2ebaf3ef73ac..25e332f7b0073 100644 --- a/sklearn/datasets/_samples_generator.py +++ b/sklearn/datasets/_samples_generator.py @@ -616,12 +616,12 @@ def make_regression( >>> X, y = make_regression(n_samples=5, n_features=2, noise=1, random_state=42) >>> X array([[ 0.4967..., -0.1382... ], - [ 0.64768854, 1.52302986], - [-0.23415337, -0.23413696], - [-0.46947439, 0.54256004], - [ 1.57921282, 0.76743473]]) + [ 0.6476..., 1.5230...], + [-0.2341..., -0.2341...], + [-0.4694..., 0.5425...], + [ 1.5792..., 0.7674...]]) >>> y - array([ 6.73763609, 37.79636891, -10.27658818, 0.40174828, 42.22684334]) + array([ 6.7376..., 37.7963..., -10.2765..., 0.4017..., 42.2268...]) """ n_informative = min(n_features, n_informative) generator = check_random_state(random_state) From bbdb17838e52ee262b2b86ea95c89200ff076876 Mon Sep 17 00:00:00 2001 From: Arturo Amor <86408019+ArturoAmorQ@users.noreply.github.com> Date: Wed, 8 Feb 2023 15:30:23 +0100 Subject: [PATCH 6/6] Apply suggestions from code review MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Co-authored-by: Jérémie du Boisberranger <34657725+jeremiedbb@users.noreply.github.com> --- sklearn/datasets/_samples_generator.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/sklearn/datasets/_samples_generator.py b/sklearn/datasets/_samples_generator.py index 25e332f7b0073..bc2cf1bcb521b 100644 --- a/sklearn/datasets/_samples_generator.py +++ b/sklearn/datasets/_samples_generator.py @@ -616,12 +616,12 @@ def make_regression( >>> X, y = make_regression(n_samples=5, n_features=2, noise=1, random_state=42) >>> X array([[ 0.4967..., -0.1382... ], - [ 0.6476..., 1.5230...], + [ 0.6476..., 1.523...], [-0.2341..., -0.2341...], [-0.4694..., 0.5425...], - [ 1.5792..., 0.7674...]]) + [ 1.579..., 0.7674...]]) >>> y - array([ 6.7376..., 37.7963..., -10.2765..., 0.4017..., 42.2268...]) + array([ 6.737..., 37.79..., -10.27..., 0.4017..., 42.22...]) """ n_informative = min(n_features, n_informative) generator = check_random_state(random_state)