Pushing the docs to dev/ for branch: main, commit 5763e5adf6c769c134647dc95e0760c128e9cc8f

Author: sklearn-ci

dev/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 6c4d83364794080b68900dc8ca3ed494
+config: e77cfb196fa5da77d099af55c5fec29d
 tags: 645f666f9bcd5a90fca523b33c5a78b7

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -33,28 +33,28 @@
 from sklearn import cluster, datasets
 from sklearn.preprocessing import StandardScaler
 
-np.random.seed(0)
-
 # %%
 # Generate datasets. We choose the size big enough to see the scalability
 # of the algorithms, but not too big to avoid too long running times
 
 n_samples = 1500
-noisy_circles = datasets.make_circles(n_samples=n_samples, factor=0.5, noise=0.05)
-noisy_moons = datasets.make_moons(n_samples=n_samples, noise=0.05)
-blobs = datasets.make_blobs(n_samples=n_samples, random_state=8)
-no_structure = np.random.rand(n_samples, 2), None
+noisy_circles = datasets.make_circles(
+    n_samples=n_samples, factor=0.5, noise=0.05, random_state=170
+)
+noisy_moons = datasets.make_moons(n_samples=n_samples, noise=0.05, random_state=170)
+blobs = datasets.make_blobs(n_samples=n_samples, random_state=170)
+rng = np.random.RandomState(170)
+no_structure = rng.rand(n_samples, 2), None
 
 # Anisotropicly distributed data
-random_state = 170
-X, y = datasets.make_blobs(n_samples=n_samples, random_state=random_state)
+X, y = datasets.make_blobs(n_samples=n_samples, random_state=170)
 transformation = [[0.6, -0.6], [-0.4, 0.8]]
 X_aniso = np.dot(X, transformation)
 aniso = (X_aniso, y)
 
 # blobs with varied variances
 varied = datasets.make_blobs(
-    n_samples=n_samples, cluster_std=[1.0, 2.5, 0.5], random_state=random_state
+    n_samples=n_samples, cluster_std=[1.0, 2.5, 0.5], random_state=170
 )
 
 # %%

dev/_downloads/2338f6e7d44c2931a41926d4f9726d9b/plot_linkage_comparison.py

@@ -102,11 +102,15 @@
     ),
     (
         "Data after quantile transformation (uniform pdf)",
-        QuantileTransformer(output_distribution="uniform").fit_transform(X),
+        QuantileTransformer(
+            output_distribution="uniform", random_state=42
+        ).fit_transform(X),
     ),
     (
         "Data after quantile transformation (gaussian pdf)",
-        QuantileTransformer(output_distribution="normal").fit_transform(X),
+        QuantileTransformer(
+            output_distribution="normal", random_state=42
+        ).fit_transform(X),
     ),
     ("Data after sample-wise L2 normalizing", Normalizer().fit_transform(X)),
 ]

dev/_downloads/24475810034a0d0d190a9de0f87d72b5/plot_all_scaling.py

@@ -74,7 +74,7 @@ def get_name(estimator):
     (
         make_pipeline(
             StandardScaler(),
-            KBinsDiscretizer(encode="onehot"),
+            KBinsDiscretizer(encode="onehot", random_state=0),
             LogisticRegression(random_state=0),
         ),
         {
@@ -85,7 +85,7 @@ def get_name(estimator):
     (
         make_pipeline(
             StandardScaler(),
-            KBinsDiscretizer(encode="onehot"),
+            KBinsDiscretizer(encode="onehot", random_state=0),
             LinearSVC(random_state=0, dual="auto"),
         ),
         {

dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Code source: Tom Dupr\u00e9 la Tour\n# Adapted from plot_classifier_comparison by Ga\u00ebl Varoquaux and Andreas M\u00fcller\n#\n# License: BSD 3 clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nfrom matplotlib.colors import ListedColormap\n\nfrom sklearn.datasets import make_circles, make_classification, make_moons\nfrom sklearn.ensemble import GradientBoostingClassifier\nfrom sklearn.exceptions import ConvergenceWarning\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import GridSearchCV, train_test_split\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import KBinsDiscretizer, StandardScaler\nfrom sklearn.svm import SVC, LinearSVC\nfrom sklearn.utils._testing import ignore_warnings\n\nh = 0.02  # step size in the mesh\n\n\ndef get_name(estimator):\n    name = estimator.__class__.__name__\n    if name == \"Pipeline\":\n        name = [get_name(est[1]) for est in estimator.steps]\n        name = \" + \".join(name)\n    return name\n\n\n# list of (estimator, param_grid), where param_grid is used in GridSearchCV\n# The parameter spaces in this example are limited to a narrow band to reduce\n# its runtime. In a real use case, a broader search space for the algorithms\n# should be used.\nclassifiers = [\n    (\n        make_pipeline(StandardScaler(), LogisticRegression(random_state=0)),\n        {\"logisticregression__C\": np.logspace(-1, 1, 3)},\n    ),\n    (\n        make_pipeline(StandardScaler(), LinearSVC(random_state=0, dual=\"auto\")),\n        {\"linearsvc__C\": np.logspace(-1, 1, 3)},\n    ),\n    (\n        make_pipeline(\n            StandardScaler(),\n            KBinsDiscretizer(encode=\"onehot\"),\n            LogisticRegression(random_state=0),\n        ),\n        {\n            \"kbinsdiscretizer__n_bins\": np.arange(5, 8),\n            \"logisticregression__C\": np.logspace(-1, 1, 3),\n        },\n    ),\n    (\n        make_pipeline(\n            StandardScaler(),\n            KBinsDiscretizer(encode=\"onehot\"),\n            LinearSVC(random_state=0, dual=\"auto\"),\n        ),\n        {\n            \"kbinsdiscretizer__n_bins\": np.arange(5, 8),\n            \"linearsvc__C\": np.logspace(-1, 1, 3),\n        },\n    ),\n    (\n        make_pipeline(\n            StandardScaler(), GradientBoostingClassifier(n_estimators=5, random_state=0)\n        ),\n        {\"gradientboostingclassifier__learning_rate\": np.logspace(-2, 0, 5)},\n    ),\n    (\n        make_pipeline(StandardScaler(), SVC(random_state=0)),\n        {\"svc__C\": np.logspace(-1, 1, 3)},\n    ),\n]\n\nnames = [get_name(e).replace(\"StandardScaler + \", \"\") for e, _ in classifiers]\n\nn_samples = 100\ndatasets = [\n    make_moons(n_samples=n_samples, noise=0.2, random_state=0),\n    make_circles(n_samples=n_samples, noise=0.2, factor=0.5, random_state=1),\n    make_classification(\n        n_samples=n_samples,\n        n_features=2,\n        n_redundant=0,\n        n_informative=2,\n        random_state=2,\n        n_clusters_per_class=1,\n    ),\n]\n\nfig, axes = plt.subplots(\n    nrows=len(datasets), ncols=len(classifiers) + 1, figsize=(21, 9)\n)\n\ncm_piyg = plt.cm.PiYG\ncm_bright = ListedColormap([\"#b30065\", \"#178000\"])\n\n# iterate over datasets\nfor ds_cnt, (X, y) in enumerate(datasets):\n    print(f\"\\ndataset {ds_cnt}\\n---------\")\n\n    # split into training and test part\n    X_train, X_test, y_train, y_test = train_test_split(\n        X, y, test_size=0.5, random_state=42\n    )\n\n    # create the grid for background colors\n    x_min, x_max = X[:, 0].min() - 0.5, X[:, 0].max() + 0.5\n    y_min, y_max = X[:, 1].min() - 0.5, X[:, 1].max() + 0.5\n    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))\n\n    # plot the dataset first\n    ax = axes[ds_cnt, 0]\n    if ds_cnt == 0:\n        ax.set_title(\"Input data\")\n    # plot the training points\n    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright, edgecolors=\"k\")\n    # and testing points\n    ax.scatter(\n        X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6, edgecolors=\"k\"\n    )\n    ax.set_xlim(xx.min(), xx.max())\n    ax.set_ylim(yy.min(), yy.max())\n    ax.set_xticks(())\n    ax.set_yticks(())\n\n    # iterate over classifiers\n    for est_idx, (name, (estimator, param_grid)) in enumerate(zip(names, classifiers)):\n        ax = axes[ds_cnt, est_idx + 1]\n\n        clf = GridSearchCV(estimator=estimator, param_grid=param_grid)\n        with ignore_warnings(category=ConvergenceWarning):\n            clf.fit(X_train, y_train)\n        score = clf.score(X_test, y_test)\n        print(f\"{name}: {score:.2f}\")\n\n        # plot the decision boundary. For that, we will assign a color to each\n        # point in the mesh [x_min, x_max]*[y_min, y_max].\n        if hasattr(clf, \"decision_function\"):\n            Z = clf.decision_function(np.column_stack([xx.ravel(), yy.ravel()]))\n        else:\n            Z = clf.predict_proba(np.column_stack([xx.ravel(), yy.ravel()]))[:, 1]\n\n        # put the result into a color plot\n        Z = Z.reshape(xx.shape)\n        ax.contourf(xx, yy, Z, cmap=cm_piyg, alpha=0.8)\n\n        # plot the training points\n        ax.scatter(\n            X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright, edgecolors=\"k\"\n        )\n        # and testing points\n        ax.scatter(\n            X_test[:, 0],\n            X_test[:, 1],\n            c=y_test,\n            cmap=cm_bright,\n            edgecolors=\"k\",\n            alpha=0.6,\n        )\n        ax.set_xlim(xx.min(), xx.max())\n        ax.set_ylim(yy.min(), yy.max())\n        ax.set_xticks(())\n        ax.set_yticks(())\n\n        if ds_cnt == 0:\n            ax.set_title(name.replace(\" + \", \"\\n\"))\n        ax.text(\n            0.95,\n            0.06,\n            (f\"{score:.2f}\").lstrip(\"0\"),\n            size=15,\n            bbox=dict(boxstyle=\"round\", alpha=0.8, facecolor=\"white\"),\n            transform=ax.transAxes,\n            horizontalalignment=\"right\",\n        )\n\n\nplt.tight_layout()\n\n# Add suptitles above the figure\nplt.subplots_adjust(top=0.90)\nsuptitles = [\n    \"Linear classifiers\",\n    \"Feature discretization and linear classifiers\",\n    \"Non-linear classifiers\",\n]\nfor i, suptitle in zip([1, 3, 5], suptitles):\n    ax = axes[0, i]\n    ax.text(\n        1.05,\n        1.25,\n        suptitle,\n        transform=ax.transAxes,\n        horizontalalignment=\"center\",\n        size=\"x-large\",\n    )\nplt.show()"
+        "# Code source: Tom Dupr\u00e9 la Tour\n# Adapted from plot_classifier_comparison by Ga\u00ebl Varoquaux and Andreas M\u00fcller\n#\n# License: BSD 3 clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nfrom matplotlib.colors import ListedColormap\n\nfrom sklearn.datasets import make_circles, make_classification, make_moons\nfrom sklearn.ensemble import GradientBoostingClassifier\nfrom sklearn.exceptions import ConvergenceWarning\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import GridSearchCV, train_test_split\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import KBinsDiscretizer, StandardScaler\nfrom sklearn.svm import SVC, LinearSVC\nfrom sklearn.utils._testing import ignore_warnings\n\nh = 0.02  # step size in the mesh\n\n\ndef get_name(estimator):\n    name = estimator.__class__.__name__\n    if name == \"Pipeline\":\n        name = [get_name(est[1]) for est in estimator.steps]\n        name = \" + \".join(name)\n    return name\n\n\n# list of (estimator, param_grid), where param_grid is used in GridSearchCV\n# The parameter spaces in this example are limited to a narrow band to reduce\n# its runtime. In a real use case, a broader search space for the algorithms\n# should be used.\nclassifiers = [\n    (\n        make_pipeline(StandardScaler(), LogisticRegression(random_state=0)),\n        {\"logisticregression__C\": np.logspace(-1, 1, 3)},\n    ),\n    (\n        make_pipeline(StandardScaler(), LinearSVC(random_state=0, dual=\"auto\")),\n        {\"linearsvc__C\": np.logspace(-1, 1, 3)},\n    ),\n    (\n        make_pipeline(\n            StandardScaler(),\n            KBinsDiscretizer(encode=\"onehot\", random_state=0),\n            LogisticRegression(random_state=0),\n        ),\n        {\n            \"kbinsdiscretizer__n_bins\": np.arange(5, 8),\n            \"logisticregression__C\": np.logspace(-1, 1, 3),\n        },\n    ),\n    (\n        make_pipeline(\n            StandardScaler(),\n            KBinsDiscretizer(encode=\"onehot\", random_state=0),\n            LinearSVC(random_state=0, dual=\"auto\"),\n        ),\n        {\n            \"kbinsdiscretizer__n_bins\": np.arange(5, 8),\n            \"linearsvc__C\": np.logspace(-1, 1, 3),\n        },\n    ),\n    (\n        make_pipeline(\n            StandardScaler(), GradientBoostingClassifier(n_estimators=5, random_state=0)\n        ),\n        {\"gradientboostingclassifier__learning_rate\": np.logspace(-2, 0, 5)},\n    ),\n    (\n        make_pipeline(StandardScaler(), SVC(random_state=0)),\n        {\"svc__C\": np.logspace(-1, 1, 3)},\n    ),\n]\n\nnames = [get_name(e).replace(\"StandardScaler + \", \"\") for e, _ in classifiers]\n\nn_samples = 100\ndatasets = [\n    make_moons(n_samples=n_samples, noise=0.2, random_state=0),\n    make_circles(n_samples=n_samples, noise=0.2, factor=0.5, random_state=1),\n    make_classification(\n        n_samples=n_samples,\n        n_features=2,\n        n_redundant=0,\n        n_informative=2,\n        random_state=2,\n        n_clusters_per_class=1,\n    ),\n]\n\nfig, axes = plt.subplots(\n    nrows=len(datasets), ncols=len(classifiers) + 1, figsize=(21, 9)\n)\n\ncm_piyg = plt.cm.PiYG\ncm_bright = ListedColormap([\"#b30065\", \"#178000\"])\n\n# iterate over datasets\nfor ds_cnt, (X, y) in enumerate(datasets):\n    print(f\"\\ndataset {ds_cnt}\\n---------\")\n\n    # split into training and test part\n    X_train, X_test, y_train, y_test = train_test_split(\n        X, y, test_size=0.5, random_state=42\n    )\n\n    # create the grid for background colors\n    x_min, x_max = X[:, 0].min() - 0.5, X[:, 0].max() + 0.5\n    y_min, y_max = X[:, 1].min() - 0.5, X[:, 1].max() + 0.5\n    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))\n\n    # plot the dataset first\n    ax = axes[ds_cnt, 0]\n    if ds_cnt == 0:\n        ax.set_title(\"Input data\")\n    # plot the training points\n    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright, edgecolors=\"k\")\n    # and testing points\n    ax.scatter(\n        X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6, edgecolors=\"k\"\n    )\n    ax.set_xlim(xx.min(), xx.max())\n    ax.set_ylim(yy.min(), yy.max())\n    ax.set_xticks(())\n    ax.set_yticks(())\n\n    # iterate over classifiers\n    for est_idx, (name, (estimator, param_grid)) in enumerate(zip(names, classifiers)):\n        ax = axes[ds_cnt, est_idx + 1]\n\n        clf = GridSearchCV(estimator=estimator, param_grid=param_grid)\n        with ignore_warnings(category=ConvergenceWarning):\n            clf.fit(X_train, y_train)\n        score = clf.score(X_test, y_test)\n        print(f\"{name}: {score:.2f}\")\n\n        # plot the decision boundary. For that, we will assign a color to each\n        # point in the mesh [x_min, x_max]*[y_min, y_max].\n        if hasattr(clf, \"decision_function\"):\n            Z = clf.decision_function(np.column_stack([xx.ravel(), yy.ravel()]))\n        else:\n            Z = clf.predict_proba(np.column_stack([xx.ravel(), yy.ravel()]))[:, 1]\n\n        # put the result into a color plot\n        Z = Z.reshape(xx.shape)\n        ax.contourf(xx, yy, Z, cmap=cm_piyg, alpha=0.8)\n\n        # plot the training points\n        ax.scatter(\n            X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright, edgecolors=\"k\"\n        )\n        # and testing points\n        ax.scatter(\n            X_test[:, 0],\n            X_test[:, 1],\n            c=y_test,\n            cmap=cm_bright,\n            edgecolors=\"k\",\n            alpha=0.6,\n        )\n        ax.set_xlim(xx.min(), xx.max())\n        ax.set_ylim(yy.min(), yy.max())\n        ax.set_xticks(())\n        ax.set_yticks(())\n\n        if ds_cnt == 0:\n            ax.set_title(name.replace(\" + \", \"\\n\"))\n        ax.text(\n            0.95,\n            0.06,\n            (f\"{score:.2f}\").lstrip(\"0\"),\n            size=15,\n            bbox=dict(boxstyle=\"round\", alpha=0.8, facecolor=\"white\"),\n            transform=ax.transAxes,\n            horizontalalignment=\"right\",\n        )\n\n\nplt.tight_layout()\n\n# Add suptitles above the figure\nplt.subplots_adjust(top=0.90)\nsuptitles = [\n    \"Linear classifiers\",\n    \"Feature discretization and linear classifiers\",\n    \"Non-linear classifiers\",\n]\nfor i, suptitle in zip([1, 3, 5], suptitles):\n    ax = axes[0, i]\n    ax.text(\n        1.05,\n        1.25,\n        suptitle,\n        transform=ax.transAxes,\n        horizontalalignment=\"center\",\n        size=\"x-large\",\n    )\nplt.show()"
       ]
     }
   ],

dev/_downloads/74caedf3eb449b80f3f00e66c1c576bd/plot_discretization_classification.py

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "import time\nimport warnings\nfrom itertools import cycle, islice\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn import cluster, datasets\nfrom sklearn.preprocessing import StandardScaler\n\nnp.random.seed(0)"
+        "import time\nimport warnings\nfrom itertools import cycle, islice\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn import cluster, datasets\nfrom sklearn.preprocessing import StandardScaler"
       ]
     },
     {
@@ -33,7 +33,7 @@
       },
       "outputs": [],
       "source": [
-        "n_samples = 1500\nnoisy_circles = datasets.make_circles(n_samples=n_samples, factor=0.5, noise=0.05)\nnoisy_moons = datasets.make_moons(n_samples=n_samples, noise=0.05)\nblobs = datasets.make_blobs(n_samples=n_samples, random_state=8)\nno_structure = np.random.rand(n_samples, 2), None\n\n# Anisotropicly distributed data\nrandom_state = 170\nX, y = datasets.make_blobs(n_samples=n_samples, random_state=random_state)\ntransformation = [[0.6, -0.6], [-0.4, 0.8]]\nX_aniso = np.dot(X, transformation)\naniso = (X_aniso, y)\n\n# blobs with varied variances\nvaried = datasets.make_blobs(\n    n_samples=n_samples, cluster_std=[1.0, 2.5, 0.5], random_state=random_state\n)"
+        "n_samples = 1500\nnoisy_circles = datasets.make_circles(\n    n_samples=n_samples, factor=0.5, noise=0.05, random_state=170\n)\nnoisy_moons = datasets.make_moons(n_samples=n_samples, noise=0.05, random_state=170)\nblobs = datasets.make_blobs(n_samples=n_samples, random_state=170)\nrng = np.random.RandomState(170)\nno_structure = rng.rand(n_samples, 2), None\n\n# Anisotropicly distributed data\nX, y = datasets.make_blobs(n_samples=n_samples, random_state=170)\ntransformation = [[0.6, -0.6], [-0.4, 0.8]]\nX_aniso = np.dot(X, transformation)\naniso = (X_aniso, y)\n\n# blobs with varied variances\nvaried = datasets.make_blobs(\n    n_samples=n_samples, cluster_std=[1.0, 2.5, 0.5], random_state=170\n)"
       ]
     },
     {