Pushing the docs to dev/ for branch: main, commit bbc73cfd7f5a85f6ac63432d3294abecdcb81d2a

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: 0196bdeb140758540138776c646854be
+config: d0f46beb81ff4ac48bf0a44b4a9db458
 tags: 645f666f9bcd5a90fca523b33c5a78b7

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -15,7 +15,75 @@
       },
       "outputs": [],
       "source": [
-        "# Code source: Ga\u00ebl Varoquaux\n# Modified for documentation by Jaques Grobler\n# License: BSD 3 clause\n\nimport matplotlib.pyplot as plt\n\n# unused but required import for doing 3d projections with matplotlib < 3.2\nimport mpl_toolkits.mplot3d  # noqa: F401\n\nfrom sklearn import datasets\nfrom sklearn.decomposition import PCA\n\n# import some data to play with\niris = datasets.load_iris()\nX = iris.data[:, :2]  # we only take the first two features.\ny = iris.target\n\nx_min, x_max = X[:, 0].min() - 0.5, X[:, 0].max() + 0.5\ny_min, y_max = X[:, 1].min() - 0.5, X[:, 1].max() + 0.5\n\nplt.figure(2, figsize=(8, 6))\nplt.clf()\n\n# Plot the training points\nplt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Set1, edgecolor=\"k\")\nplt.xlabel(\"Sepal length\")\nplt.ylabel(\"Sepal width\")\n\nplt.xlim(x_min, x_max)\nplt.ylim(y_min, y_max)\nplt.xticks(())\nplt.yticks(())\n\n# To getter a better understanding of interaction of the dimensions\n# plot the first three PCA dimensions\nfig = plt.figure(1, figsize=(8, 6))\nax = fig.add_subplot(111, projection=\"3d\", elev=-150, azim=110)\n\nX_reduced = PCA(n_components=3).fit_transform(iris.data)\nax.scatter(\n    X_reduced[:, 0],\n    X_reduced[:, 1],\n    X_reduced[:, 2],\n    c=y,\n    cmap=plt.cm.Set1,\n    edgecolor=\"k\",\n    s=40,\n)\n\nax.set_title(\"First three PCA directions\")\nax.set_xlabel(\"1st eigenvector\")\nax.xaxis.set_ticklabels([])\nax.set_ylabel(\"2nd eigenvector\")\nax.yaxis.set_ticklabels([])\nax.set_zlabel(\"3rd eigenvector\")\nax.zaxis.set_ticklabels([])\n\nplt.show()"
+        "# Code source: Ga\u00ebl Varoquaux\n# Modified for documentation by Jaques Grobler\n# License: BSD 3 clause"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Loading the iris dataset\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "from sklearn import datasets\n\niris = datasets.load_iris()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Scatter Plot of the Iris dataset\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "import matplotlib.pyplot as plt\n\n_, ax = plt.subplots()\nscatter = ax.scatter(iris.data[:, 0], iris.data[:, 1], c=iris.target)\nax.set(xlabel=iris.feature_names[0], ylabel=iris.feature_names[1])\n_ = ax.legend(\n    scatter.legend_elements()[0], iris.target_names, loc=\"lower right\", title=\"Classes\"\n)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Each point in the scatter plot refers to one of the 150 iris flowers\nin the dataset, with the color indicating their respective type\n(Setosa, Versicolour, and Virginica).\nYou can already see a pattern regarding the Setosa type, which is\neasily identifiable based on its short and wide sepal. Only\nconsidering these 2 dimensions, sepal width and length, there's still\noverlap between the Versicolor and Virginica types.\n\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Plot a PCA representation\nLet's apply a Principal Component Analysis (PCA) to the iris dataset\nand then plot the irises across the first three PCA dimensions.\nThis will allow us to better differentiate between the three types!\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "# unused but required import for doing 3d projections with matplotlib < 3.2\nimport mpl_toolkits.mplot3d  # noqa: F401\n\nfrom sklearn.decomposition import PCA\n\nfig = plt.figure(1, figsize=(8, 6))\nax = fig.add_subplot(111, projection=\"3d\", elev=-150, azim=110)\n\nX_reduced = PCA(n_components=3).fit_transform(iris.data)\nax.scatter(\n    X_reduced[:, 0],\n    X_reduced[:, 1],\n    X_reduced[:, 2],\n    c=iris.target,\n    s=40,\n)\n\nax.set_title(\"First three PCA dimensions\")\nax.set_xlabel(\"1st Eigenvector\")\nax.xaxis.set_ticklabels([])\nax.set_ylabel(\"2nd Eigenvector\")\nax.yaxis.set_ticklabels([])\nax.set_zlabel(\"3rd Eigenvector\")\nax.zaxis.set_ticklabels([])\n\nplt.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "PCA will create 3 new features that are a linear combination of the\n4 original features. In addition, this transform maximizes the variance.\nWith this transformation, we see that we can identify each species using\nonly the first feature (i.e. first eigenvalues).\n\n"
       ]
     }
   ],

dev/_downloads/26998096b90db15754e891c733ae032c/plot_iris_dataset.ipynb

@@ -66,7 +66,7 @@
         max_depth=5, n_estimators=10, max_features=1, random_state=42
     ),
     MLPClassifier(alpha=1, max_iter=1000, random_state=42),
-    AdaBoostClassifier(random_state=42),
+    AdaBoostClassifier(algorithm="SAMME", random_state=42),
     GaussianNB(),
     QuadraticDiscriminantAnalysis(),
 ]

dev/_downloads/2c8a162a0e436f4ca9af35453585fc81/plot_adaboost_hastie_10_2.py

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Code source: Ga\u00ebl Varoquaux\n#              Andreas M\u00fcller\n# Modified for documentation by Jaques Grobler\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.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()"
+        "# Code source: Ga\u00ebl Varoquaux\n#              Andreas M\u00fcller\n# Modified for documentation by Jaques Grobler\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.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()"
       ]
     }
   ],