Pushing the docs to dev/ for branch: main, commit 84ac5d882d80a1edf4ea39f3f9266ad28758f1da

Author: sklearn-ci

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -64,7 +64,7 @@
         max_depth=5, n_estimators=10, max_features=1, random_state=42
     ),
     MLPClassifier(alpha=1, max_iter=1000, random_state=42),
-    AdaBoostClassifier(algorithm="SAMME", random_state=42),
+    AdaBoostClassifier(random_state=42),
     GaussianNB(),
     QuadraticDiscriminantAnalysis(),
 ]

dev/_downloads/0358b1921962fd7c6f5a94c5abc91476/plot_hashing_vs_dict_vectorizer.zip

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: 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.discriminant_analysis import QuadraticDiscriminantAnalysis\nfrom sklearn.ensemble import AdaBoostClassifier, RandomForestClassifier\nfrom sklearn.gaussian_process import GaussianProcessClassifier\nfrom sklearn.gaussian_process.kernels import RBF\nfrom sklearn.inspection import DecisionBoundaryDisplay\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.neural_network import MLPClassifier\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.svm import SVC\nfrom sklearn.tree import DecisionTreeClassifier\n\nnames = [\n    \"Nearest Neighbors\",\n    \"Linear SVM\",\n    \"RBF SVM\",\n    \"Gaussian Process\",\n    \"Decision Tree\",\n    \"Random Forest\",\n    \"Neural Net\",\n    \"AdaBoost\",\n    \"Naive Bayes\",\n    \"QDA\",\n]\n\nclassifiers = [\n    KNeighborsClassifier(3),\n    SVC(kernel=\"linear\", C=0.025, random_state=42),\n    SVC(gamma=2, C=1, random_state=42),\n    GaussianProcessClassifier(1.0 * RBF(1.0), random_state=42),\n    DecisionTreeClassifier(max_depth=5, random_state=42),\n    RandomForestClassifier(\n        max_depth=5, n_estimators=10, max_features=1, random_state=42\n    ),\n    MLPClassifier(alpha=1, max_iter=1000, random_state=42),\n    AdaBoostClassifier(algorithm=\"SAMME\", random_state=42),\n    GaussianNB(),\n    QuadraticDiscriminantAnalysis(),\n]\n\nX, y = make_classification(\n    n_features=2, n_redundant=0, n_informative=2, random_state=1, n_clusters_per_class=1\n)\nrng = np.random.RandomState(2)\nX += 2 * rng.uniform(size=X.shape)\nlinearly_separable = (X, y)\n\ndatasets = [\n    make_moons(noise=0.3, random_state=0),\n    make_circles(noise=0.2, factor=0.5, random_state=1),\n    linearly_separable,\n]\n\nfigure = plt.figure(figsize=(27, 9))\ni = 1\n# iterate over datasets\nfor ds_cnt, ds in enumerate(datasets):\n    # preprocess dataset, split into training and test part\n    X, y = ds\n    X_train, X_test, y_train, y_test = train_test_split(\n        X, y, test_size=0.4, random_state=42\n    )\n\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\n    # just plot the dataset first\n    cm = plt.cm.RdBu\n    cm_bright = ListedColormap([\"#FF0000\", \"#0000FF\"])\n    ax = plt.subplot(len(datasets), len(classifiers) + 1, i)\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    # Plot the 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(x_min, x_max)\n    ax.set_ylim(y_min, y_max)\n    ax.set_xticks(())\n    ax.set_yticks(())\n    i += 1\n\n    # iterate over classifiers\n    for name, clf in zip(names, classifiers):\n        ax = plt.subplot(len(datasets), len(classifiers) + 1, i)\n\n        clf = make_pipeline(StandardScaler(), clf)\n        clf.fit(X_train, y_train)\n        score = clf.score(X_test, y_test)\n        DecisionBoundaryDisplay.from_estimator(\n            clf, X, cmap=cm, alpha=0.8, ax=ax, eps=0.5\n        )\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        # Plot the 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\n        ax.set_xlim(x_min, x_max)\n        ax.set_ylim(y_min, y_max)\n        ax.set_xticks(())\n        ax.set_yticks(())\n        if ds_cnt == 0:\n            ax.set_title(name)\n        ax.text(\n            x_max - 0.3,\n            y_min + 0.3,\n            (\"%.2f\" % score).lstrip(\"0\"),\n            size=15,\n            horizontalalignment=\"right\",\n        )\n        i += 1\n\nplt.tight_layout()\nplt.show()"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: 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.discriminant_analysis import QuadraticDiscriminantAnalysis\nfrom sklearn.ensemble import AdaBoostClassifier, RandomForestClassifier\nfrom sklearn.gaussian_process import GaussianProcessClassifier\nfrom sklearn.gaussian_process.kernels import RBF\nfrom sklearn.inspection import DecisionBoundaryDisplay\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.neural_network import MLPClassifier\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.svm import SVC\nfrom sklearn.tree import DecisionTreeClassifier\n\nnames = [\n    \"Nearest Neighbors\",\n    \"Linear SVM\",\n    \"RBF SVM\",\n    \"Gaussian Process\",\n    \"Decision Tree\",\n    \"Random Forest\",\n    \"Neural Net\",\n    \"AdaBoost\",\n    \"Naive Bayes\",\n    \"QDA\",\n]\n\nclassifiers = [\n    KNeighborsClassifier(3),\n    SVC(kernel=\"linear\", C=0.025, random_state=42),\n    SVC(gamma=2, C=1, random_state=42),\n    GaussianProcessClassifier(1.0 * RBF(1.0), random_state=42),\n    DecisionTreeClassifier(max_depth=5, random_state=42),\n    RandomForestClassifier(\n        max_depth=5, n_estimators=10, max_features=1, random_state=42\n    ),\n    MLPClassifier(alpha=1, max_iter=1000, random_state=42),\n    AdaBoostClassifier(random_state=42),\n    GaussianNB(),\n    QuadraticDiscriminantAnalysis(),\n]\n\nX, y = make_classification(\n    n_features=2, n_redundant=0, n_informative=2, random_state=1, n_clusters_per_class=1\n)\nrng = np.random.RandomState(2)\nX += 2 * rng.uniform(size=X.shape)\nlinearly_separable = (X, y)\n\ndatasets = [\n    make_moons(noise=0.3, random_state=0),\n    make_circles(noise=0.2, factor=0.5, random_state=1),\n    linearly_separable,\n]\n\nfigure = plt.figure(figsize=(27, 9))\ni = 1\n# iterate over datasets\nfor ds_cnt, ds in enumerate(datasets):\n    # preprocess dataset, split into training and test part\n    X, y = ds\n    X_train, X_test, y_train, y_test = train_test_split(\n        X, y, test_size=0.4, random_state=42\n    )\n\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\n    # just plot the dataset first\n    cm = plt.cm.RdBu\n    cm_bright = ListedColormap([\"#FF0000\", \"#0000FF\"])\n    ax = plt.subplot(len(datasets), len(classifiers) + 1, i)\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    # Plot the 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(x_min, x_max)\n    ax.set_ylim(y_min, y_max)\n    ax.set_xticks(())\n    ax.set_yticks(())\n    i += 1\n\n    # iterate over classifiers\n    for name, clf in zip(names, classifiers):\n        ax = plt.subplot(len(datasets), len(classifiers) + 1, i)\n\n        clf = make_pipeline(StandardScaler(), clf)\n        clf.fit(X_train, y_train)\n        score = clf.score(X_test, y_test)\n        DecisionBoundaryDisplay.from_estimator(\n            clf, X, cmap=cm, alpha=0.8, ax=ax, eps=0.5\n        )\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        # Plot the 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\n        ax.set_xlim(x_min, x_max)\n        ax.set_ylim(y_min, y_max)\n        ax.set_xticks(())\n        ax.set_yticks(())\n        if ds_cnt == 0:\n            ax.set_title(name)\n        ax.text(\n            x_max - 0.3,\n            y_min + 0.3,\n            (\"%.2f\" % score).lstrip(\"0\"),\n            size=15,\n            horizontalalignment=\"right\",\n        )\n        i += 1\n\nplt.tight_layout()\nplt.show()"
       ]
     }
   ],

dev/_downloads/038d1885eb5f5ea53aca42da3031fe38/plot_document_clustering.zip

@@ -80,7 +80,6 @@
 adaboost_clf = AdaBoostClassifier(
     estimator=weak_learner,
     n_estimators=n_estimators,
-    algorithm="SAMME",
     random_state=42,
 ).fit(X_train, y_train)
 

dev/_downloads/03c018a16384c69f3a89e473650d57ee/plot_svm_margin.zip

@@ -69,7 +69,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.ensemble import AdaBoostClassifier\nfrom sklearn.tree import DecisionTreeClassifier\n\nweak_learner = DecisionTreeClassifier(max_leaf_nodes=8)\nn_estimators = 300\n\nadaboost_clf = AdaBoostClassifier(\n    estimator=weak_learner,\n    n_estimators=n_estimators,\n    algorithm=\"SAMME\",\n    random_state=42,\n).fit(X_train, y_train)"
+        "from sklearn.ensemble import AdaBoostClassifier\nfrom sklearn.tree import DecisionTreeClassifier\n\nweak_learner = DecisionTreeClassifier(max_leaf_nodes=8)\nn_estimators = 300\n\nadaboost_clf = AdaBoostClassifier(\n    estimator=weak_learner,\n    n_estimators=n_estimators,\n    random_state=42,\n).fit(X_train, y_train)"
       ]
     },
     {

dev/_downloads/041e98b4797bb4ddc34c0045e5886c3e/plot_digits_classification_exercise.zip

@@ -74,11 +74,7 @@
     DecisionTreeClassifier(max_depth=None),
     RandomForestClassifier(n_estimators=n_estimators),
     ExtraTreesClassifier(n_estimators=n_estimators),
-    AdaBoostClassifier(
-        DecisionTreeClassifier(max_depth=3),
-        n_estimators=n_estimators,
-        algorithm="SAMME",
-    ),
+    AdaBoostClassifier(DecisionTreeClassifier(max_depth=3), n_estimators=n_estimators),
 ]
 
 for pair in ([0, 1], [0, 2], [2, 3]):

dev/_downloads/04b9a7769df5b331f4d94e1d065b4311/plot_voting_decision_regions.zip

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nfrom matplotlib.colors import ListedColormap\n\nfrom sklearn.datasets import load_iris\nfrom sklearn.ensemble import (\n    AdaBoostClassifier,\n    ExtraTreesClassifier,\n    RandomForestClassifier,\n)\nfrom sklearn.tree import DecisionTreeClassifier\n\n# Parameters\nn_classes = 3\nn_estimators = 30\ncmap = plt.cm.RdYlBu\nplot_step = 0.02  # fine step width for decision surface contours\nplot_step_coarser = 0.5  # step widths for coarse classifier guesses\nRANDOM_SEED = 13  # fix the seed on each iteration\n\n# Load data\niris = load_iris()\n\nplot_idx = 1\n\nmodels = [\n    DecisionTreeClassifier(max_depth=None),\n    RandomForestClassifier(n_estimators=n_estimators),\n    ExtraTreesClassifier(n_estimators=n_estimators),\n    AdaBoostClassifier(\n        DecisionTreeClassifier(max_depth=3),\n        n_estimators=n_estimators,\n        algorithm=\"SAMME\",\n    ),\n]\n\nfor pair in ([0, 1], [0, 2], [2, 3]):\n    for model in models:\n        # We only take the two corresponding features\n        X = iris.data[:, pair]\n        y = iris.target\n\n        # Shuffle\n        idx = np.arange(X.shape[0])\n        np.random.seed(RANDOM_SEED)\n        np.random.shuffle(idx)\n        X = X[idx]\n        y = y[idx]\n\n        # Standardize\n        mean = X.mean(axis=0)\n        std = X.std(axis=0)\n        X = (X - mean) / std\n\n        # Train\n        model.fit(X, y)\n\n        scores = model.score(X, y)\n        # Create a title for each column and the console by using str() and\n        # slicing away useless parts of the string\n        model_title = str(type(model)).split(\".\")[-1][:-2][: -len(\"Classifier\")]\n\n        model_details = model_title\n        if hasattr(model, \"estimators_\"):\n            model_details += \" with {} estimators\".format(len(model.estimators_))\n        print(model_details + \" with features\", pair, \"has a score of\", scores)\n\n        plt.subplot(3, 4, plot_idx)\n        if plot_idx <= len(models):\n            # Add a title at the top of each column\n            plt.title(model_title, fontsize=9)\n\n        # Now plot the decision boundary using a fine mesh as input to a\n        # filled contour plot\n        x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1\n        y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1\n        xx, yy = np.meshgrid(\n            np.arange(x_min, x_max, plot_step), np.arange(y_min, y_max, plot_step)\n        )\n\n        # Plot either a single DecisionTreeClassifier or alpha blend the\n        # decision surfaces of the ensemble of classifiers\n        if isinstance(model, DecisionTreeClassifier):\n            Z = model.predict(np.c_[xx.ravel(), yy.ravel()])\n            Z = Z.reshape(xx.shape)\n            cs = plt.contourf(xx, yy, Z, cmap=cmap)\n        else:\n            # Choose alpha blend level with respect to the number\n            # of estimators\n            # that are in use (noting that AdaBoost can use fewer estimators\n            # than its maximum if it achieves a good enough fit early on)\n            estimator_alpha = 1.0 / len(model.estimators_)\n            for tree in model.estimators_:\n                Z = tree.predict(np.c_[xx.ravel(), yy.ravel()])\n                Z = Z.reshape(xx.shape)\n                cs = plt.contourf(xx, yy, Z, alpha=estimator_alpha, cmap=cmap)\n\n        # Build a coarser grid to plot a set of ensemble classifications\n        # to show how these are different to what we see in the decision\n        # surfaces. These points are regularly space and do not have a\n        # black outline\n        xx_coarser, yy_coarser = np.meshgrid(\n            np.arange(x_min, x_max, plot_step_coarser),\n            np.arange(y_min, y_max, plot_step_coarser),\n        )\n        Z_points_coarser = model.predict(\n            np.c_[xx_coarser.ravel(), yy_coarser.ravel()]\n        ).reshape(xx_coarser.shape)\n        cs_points = plt.scatter(\n            xx_coarser,\n            yy_coarser,\n            s=15,\n            c=Z_points_coarser,\n            cmap=cmap,\n            edgecolors=\"none\",\n        )\n\n        # Plot the training points, these are clustered together and have a\n        # black outline\n        plt.scatter(\n            X[:, 0],\n            X[:, 1],\n            c=y,\n            cmap=ListedColormap([\"r\", \"y\", \"b\"]),\n            edgecolor=\"k\",\n            s=20,\n        )\n        plot_idx += 1  # move on to the next plot in sequence\n\nplt.suptitle(\"Classifiers on feature subsets of the Iris dataset\", fontsize=12)\nplt.axis(\"tight\")\nplt.tight_layout(h_pad=0.2, w_pad=0.2, pad=2.5)\nplt.show()"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nfrom matplotlib.colors import ListedColormap\n\nfrom sklearn.datasets import load_iris\nfrom sklearn.ensemble import (\n    AdaBoostClassifier,\n    ExtraTreesClassifier,\n    RandomForestClassifier,\n)\nfrom sklearn.tree import DecisionTreeClassifier\n\n# Parameters\nn_classes = 3\nn_estimators = 30\ncmap = plt.cm.RdYlBu\nplot_step = 0.02  # fine step width for decision surface contours\nplot_step_coarser = 0.5  # step widths for coarse classifier guesses\nRANDOM_SEED = 13  # fix the seed on each iteration\n\n# Load data\niris = load_iris()\n\nplot_idx = 1\n\nmodels = [\n    DecisionTreeClassifier(max_depth=None),\n    RandomForestClassifier(n_estimators=n_estimators),\n    ExtraTreesClassifier(n_estimators=n_estimators),\n    AdaBoostClassifier(DecisionTreeClassifier(max_depth=3), n_estimators=n_estimators),\n]\n\nfor pair in ([0, 1], [0, 2], [2, 3]):\n    for model in models:\n        # We only take the two corresponding features\n        X = iris.data[:, pair]\n        y = iris.target\n\n        # Shuffle\n        idx = np.arange(X.shape[0])\n        np.random.seed(RANDOM_SEED)\n        np.random.shuffle(idx)\n        X = X[idx]\n        y = y[idx]\n\n        # Standardize\n        mean = X.mean(axis=0)\n        std = X.std(axis=0)\n        X = (X - mean) / std\n\n        # Train\n        model.fit(X, y)\n\n        scores = model.score(X, y)\n        # Create a title for each column and the console by using str() and\n        # slicing away useless parts of the string\n        model_title = str(type(model)).split(\".\")[-1][:-2][: -len(\"Classifier\")]\n\n        model_details = model_title\n        if hasattr(model, \"estimators_\"):\n            model_details += \" with {} estimators\".format(len(model.estimators_))\n        print(model_details + \" with features\", pair, \"has a score of\", scores)\n\n        plt.subplot(3, 4, plot_idx)\n        if plot_idx <= len(models):\n            # Add a title at the top of each column\n            plt.title(model_title, fontsize=9)\n\n        # Now plot the decision boundary using a fine mesh as input to a\n        # filled contour plot\n        x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1\n        y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1\n        xx, yy = np.meshgrid(\n            np.arange(x_min, x_max, plot_step), np.arange(y_min, y_max, plot_step)\n        )\n\n        # Plot either a single DecisionTreeClassifier or alpha blend the\n        # decision surfaces of the ensemble of classifiers\n        if isinstance(model, DecisionTreeClassifier):\n            Z = model.predict(np.c_[xx.ravel(), yy.ravel()])\n            Z = Z.reshape(xx.shape)\n            cs = plt.contourf(xx, yy, Z, cmap=cmap)\n        else:\n            # Choose alpha blend level with respect to the number\n            # of estimators\n            # that are in use (noting that AdaBoost can use fewer estimators\n            # than its maximum if it achieves a good enough fit early on)\n            estimator_alpha = 1.0 / len(model.estimators_)\n            for tree in model.estimators_:\n                Z = tree.predict(np.c_[xx.ravel(), yy.ravel()])\n                Z = Z.reshape(xx.shape)\n                cs = plt.contourf(xx, yy, Z, alpha=estimator_alpha, cmap=cmap)\n\n        # Build a coarser grid to plot a set of ensemble classifications\n        # to show how these are different to what we see in the decision\n        # surfaces. These points are regularly space and do not have a\n        # black outline\n        xx_coarser, yy_coarser = np.meshgrid(\n            np.arange(x_min, x_max, plot_step_coarser),\n            np.arange(y_min, y_max, plot_step_coarser),\n        )\n        Z_points_coarser = model.predict(\n            np.c_[xx_coarser.ravel(), yy_coarser.ravel()]\n        ).reshape(xx_coarser.shape)\n        cs_points = plt.scatter(\n            xx_coarser,\n            yy_coarser,\n            s=15,\n            c=Z_points_coarser,\n            cmap=cmap,\n            edgecolors=\"none\",\n        )\n\n        # Plot the training points, these are clustered together and have a\n        # black outline\n        plt.scatter(\n            X[:, 0],\n            X[:, 1],\n            c=y,\n            cmap=ListedColormap([\"r\", \"y\", \"b\"]),\n            edgecolor=\"k\",\n            s=20,\n        )\n        plot_idx += 1  # move on to the next plot in sequence\n\nplt.suptitle(\"Classifiers on feature subsets of the Iris dataset\", fontsize=12)\nplt.axis(\"tight\")\nplt.tight_layout(h_pad=0.2, w_pad=0.2, pad=2.5)\nplt.show()"
       ]
     }
   ],