Pushing the docs to dev/ for branch: main, commit 798e4339b02214de745c3d46a02d878fa34b1575

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: 39c816aaa582b3ac6dda7a6bace93052
+config: 30edc959a4dbded8e664e342536c9952
 tags: 645f666f9bcd5a90fca523b33c5a78b7

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -15,7 +15,7 @@
       },
       "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# Though the following import is not directly being used, it is required\n# for 3D projection to work with matplotlib < 3.2\nimport mpl_toolkits.mplot3d  # noqa: F401\nimport numpy as np\n\nfrom sklearn import datasets\nfrom sklearn.cluster import KMeans\n\nnp.random.seed(5)\n\niris = datasets.load_iris()\nX = iris.data\ny = iris.target\n\nestimators = [\n    (\"k_means_iris_8\", KMeans(n_clusters=8, n_init=\"auto\")),\n    (\"k_means_iris_3\", KMeans(n_clusters=3, n_init=\"auto\")),\n    (\"k_means_iris_bad_init\", KMeans(n_clusters=3, n_init=1, init=\"random\")),\n]\n\nfig = plt.figure(figsize=(10, 8))\ntitles = [\"8 clusters\", \"3 clusters\", \"3 clusters, bad initialization\"]\nfor idx, ((name, est), title) in enumerate(zip(estimators, titles)):\n    ax = fig.add_subplot(2, 2, idx + 1, projection=\"3d\", elev=48, azim=134)\n    est.fit(X)\n    labels = est.labels_\n\n    ax.scatter(X[:, 3], X[:, 0], X[:, 2], c=labels.astype(float), edgecolor=\"k\")\n\n    ax.xaxis.set_ticklabels([])\n    ax.yaxis.set_ticklabels([])\n    ax.zaxis.set_ticklabels([])\n    ax.set_xlabel(\"Petal width\")\n    ax.set_ylabel(\"Sepal length\")\n    ax.set_zlabel(\"Petal length\")\n    ax.set_title(title)\n\n# Plot the ground truth\nax = fig.add_subplot(2, 2, 4, projection=\"3d\", elev=48, azim=134)\n\nfor name, label in [(\"Setosa\", 0), (\"Versicolour\", 1), (\"Virginica\", 2)]:\n    ax.text3D(\n        X[y == label, 3].mean(),\n        X[y == label, 0].mean(),\n        X[y == label, 2].mean() + 2,\n        name,\n        horizontalalignment=\"center\",\n        bbox=dict(alpha=0.2, edgecolor=\"w\", facecolor=\"w\"),\n    )\n# Reorder the labels to have colors matching the cluster results\ny = np.choose(y, [1, 2, 0]).astype(float)\nax.scatter(X[:, 3], X[:, 0], X[:, 2], c=y, edgecolor=\"k\")\n\nax.xaxis.set_ticklabels([])\nax.yaxis.set_ticklabels([])\nax.zaxis.set_ticklabels([])\nax.set_xlabel(\"Petal width\")\nax.set_ylabel(\"Sepal length\")\nax.set_zlabel(\"Petal length\")\nax.set_title(\"Ground Truth\")\n\nplt.subplots_adjust(wspace=0.25, hspace=0.25)\nplt.show()"
+        "# 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# Though the following import is not directly being used, it is required\n# for 3D projection to work with matplotlib < 3.2\nimport mpl_toolkits.mplot3d  # noqa: F401\nimport numpy as np\n\nfrom sklearn import datasets\nfrom sklearn.cluster import KMeans\n\nnp.random.seed(5)\n\niris = datasets.load_iris()\nX = iris.data\ny = iris.target\n\nestimators = [\n    (\"k_means_iris_8\", KMeans(n_clusters=8)),\n    (\"k_means_iris_3\", KMeans(n_clusters=3)),\n    (\"k_means_iris_bad_init\", KMeans(n_clusters=3, n_init=1, init=\"random\")),\n]\n\nfig = plt.figure(figsize=(10, 8))\ntitles = [\"8 clusters\", \"3 clusters\", \"3 clusters, bad initialization\"]\nfor idx, ((name, est), title) in enumerate(zip(estimators, titles)):\n    ax = fig.add_subplot(2, 2, idx + 1, projection=\"3d\", elev=48, azim=134)\n    est.fit(X)\n    labels = est.labels_\n\n    ax.scatter(X[:, 3], X[:, 0], X[:, 2], c=labels.astype(float), edgecolor=\"k\")\n\n    ax.xaxis.set_ticklabels([])\n    ax.yaxis.set_ticklabels([])\n    ax.zaxis.set_ticklabels([])\n    ax.set_xlabel(\"Petal width\")\n    ax.set_ylabel(\"Sepal length\")\n    ax.set_zlabel(\"Petal length\")\n    ax.set_title(title)\n\n# Plot the ground truth\nax = fig.add_subplot(2, 2, 4, projection=\"3d\", elev=48, azim=134)\n\nfor name, label in [(\"Setosa\", 0), (\"Versicolour\", 1), (\"Virginica\", 2)]:\n    ax.text3D(\n        X[y == label, 3].mean(),\n        X[y == label, 0].mean(),\n        X[y == label, 2].mean() + 2,\n        name,\n        horizontalalignment=\"center\",\n        bbox=dict(alpha=0.2, edgecolor=\"w\", facecolor=\"w\"),\n    )\n# Reorder the labels to have colors matching the cluster results\ny = np.choose(y, [1, 2, 0]).astype(float)\nax.scatter(X[:, 3], X[:, 0], X[:, 2], c=y, edgecolor=\"k\")\n\nax.xaxis.set_ticklabels([])\nax.yaxis.set_ticklabels([])\nax.zaxis.set_ticklabels([])\nax.set_xlabel(\"Petal width\")\nax.set_ylabel(\"Sepal length\")\nax.set_zlabel(\"Petal length\")\nax.set_title(\"Ground Truth\")\n\nplt.subplots_adjust(wspace=0.25, hspace=0.25)\nplt.show()"
       ]
     }
   ],

dev/_downloads/18eb95af29bd5554020a8428b3ceac54/plot_cluster_iris.ipynb

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.cm as cm\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.cluster import KMeans\nfrom sklearn.datasets import make_blobs\nfrom sklearn.metrics import silhouette_samples, silhouette_score\n\n# Generating the sample data from make_blobs\n# This particular setting has one distinct cluster and 3 clusters placed close\n# together.\nX, y = make_blobs(\n    n_samples=500,\n    n_features=2,\n    centers=4,\n    cluster_std=1,\n    center_box=(-10.0, 10.0),\n    shuffle=True,\n    random_state=1,\n)  # For reproducibility\n\nrange_n_clusters = [2, 3, 4, 5, 6]\n\nfor n_clusters in range_n_clusters:\n    # Create a subplot with 1 row and 2 columns\n    fig, (ax1, ax2) = plt.subplots(1, 2)\n    fig.set_size_inches(18, 7)\n\n    # The 1st subplot is the silhouette plot\n    # The silhouette coefficient can range from -1, 1 but in this example all\n    # lie within [-0.1, 1]\n    ax1.set_xlim([-0.1, 1])\n    # The (n_clusters+1)*10 is for inserting blank space between silhouette\n    # plots of individual clusters, to demarcate them clearly.\n    ax1.set_ylim([0, len(X) + (n_clusters + 1) * 10])\n\n    # Initialize the clusterer with n_clusters value and a random generator\n    # seed of 10 for reproducibility.\n    clusterer = KMeans(n_clusters=n_clusters, n_init=\"auto\", random_state=10)\n    cluster_labels = clusterer.fit_predict(X)\n\n    # The silhouette_score gives the average value for all the samples.\n    # This gives a perspective into the density and separation of the formed\n    # clusters\n    silhouette_avg = silhouette_score(X, cluster_labels)\n    print(\n        \"For n_clusters =\",\n        n_clusters,\n        \"The average silhouette_score is :\",\n        silhouette_avg,\n    )\n\n    # Compute the silhouette scores for each sample\n    sample_silhouette_values = silhouette_samples(X, cluster_labels)\n\n    y_lower = 10\n    for i in range(n_clusters):\n        # Aggregate the silhouette scores for samples belonging to\n        # cluster i, and sort them\n        ith_cluster_silhouette_values = sample_silhouette_values[cluster_labels == i]\n\n        ith_cluster_silhouette_values.sort()\n\n        size_cluster_i = ith_cluster_silhouette_values.shape[0]\n        y_upper = y_lower + size_cluster_i\n\n        color = cm.nipy_spectral(float(i) / n_clusters)\n        ax1.fill_betweenx(\n            np.arange(y_lower, y_upper),\n            0,\n            ith_cluster_silhouette_values,\n            facecolor=color,\n            edgecolor=color,\n            alpha=0.7,\n        )\n\n        # Label the silhouette plots with their cluster numbers at the middle\n        ax1.text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))\n\n        # Compute the new y_lower for next plot\n        y_lower = y_upper + 10  # 10 for the 0 samples\n\n    ax1.set_title(\"The silhouette plot for the various clusters.\")\n    ax1.set_xlabel(\"The silhouette coefficient values\")\n    ax1.set_ylabel(\"Cluster label\")\n\n    # The vertical line for average silhouette score of all the values\n    ax1.axvline(x=silhouette_avg, color=\"red\", linestyle=\"--\")\n\n    ax1.set_yticks([])  # Clear the yaxis labels / ticks\n    ax1.set_xticks([-0.1, 0, 0.2, 0.4, 0.6, 0.8, 1])\n\n    # 2nd Plot showing the actual clusters formed\n    colors = cm.nipy_spectral(cluster_labels.astype(float) / n_clusters)\n    ax2.scatter(\n        X[:, 0], X[:, 1], marker=\".\", s=30, lw=0, alpha=0.7, c=colors, edgecolor=\"k\"\n    )\n\n    # Labeling the clusters\n    centers = clusterer.cluster_centers_\n    # Draw white circles at cluster centers\n    ax2.scatter(\n        centers[:, 0],\n        centers[:, 1],\n        marker=\"o\",\n        c=\"white\",\n        alpha=1,\n        s=200,\n        edgecolor=\"k\",\n    )\n\n    for i, c in enumerate(centers):\n        ax2.scatter(c[0], c[1], marker=\"$%d$\" % i, alpha=1, s=50, edgecolor=\"k\")\n\n    ax2.set_title(\"The visualization of the clustered data.\")\n    ax2.set_xlabel(\"Feature space for the 1st feature\")\n    ax2.set_ylabel(\"Feature space for the 2nd feature\")\n\n    plt.suptitle(\n        \"Silhouette analysis for KMeans clustering on sample data with n_clusters = %d\"\n        % n_clusters,\n        fontsize=14,\n        fontweight=\"bold\",\n    )\n\nplt.show()"
+        "import matplotlib.cm as cm\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.cluster import KMeans\nfrom sklearn.datasets import make_blobs\nfrom sklearn.metrics import silhouette_samples, silhouette_score\n\n# Generating the sample data from make_blobs\n# This particular setting has one distinct cluster and 3 clusters placed close\n# together.\nX, y = make_blobs(\n    n_samples=500,\n    n_features=2,\n    centers=4,\n    cluster_std=1,\n    center_box=(-10.0, 10.0),\n    shuffle=True,\n    random_state=1,\n)  # For reproducibility\n\nrange_n_clusters = [2, 3, 4, 5, 6]\n\nfor n_clusters in range_n_clusters:\n    # Create a subplot with 1 row and 2 columns\n    fig, (ax1, ax2) = plt.subplots(1, 2)\n    fig.set_size_inches(18, 7)\n\n    # The 1st subplot is the silhouette plot\n    # The silhouette coefficient can range from -1, 1 but in this example all\n    # lie within [-0.1, 1]\n    ax1.set_xlim([-0.1, 1])\n    # The (n_clusters+1)*10 is for inserting blank space between silhouette\n    # plots of individual clusters, to demarcate them clearly.\n    ax1.set_ylim([0, len(X) + (n_clusters + 1) * 10])\n\n    # Initialize the clusterer with n_clusters value and a random generator\n    # seed of 10 for reproducibility.\n    clusterer = KMeans(n_clusters=n_clusters, random_state=10)\n    cluster_labels = clusterer.fit_predict(X)\n\n    # The silhouette_score gives the average value for all the samples.\n    # This gives a perspective into the density and separation of the formed\n    # clusters\n    silhouette_avg = silhouette_score(X, cluster_labels)\n    print(\n        \"For n_clusters =\",\n        n_clusters,\n        \"The average silhouette_score is :\",\n        silhouette_avg,\n    )\n\n    # Compute the silhouette scores for each sample\n    sample_silhouette_values = silhouette_samples(X, cluster_labels)\n\n    y_lower = 10\n    for i in range(n_clusters):\n        # Aggregate the silhouette scores for samples belonging to\n        # cluster i, and sort them\n        ith_cluster_silhouette_values = sample_silhouette_values[cluster_labels == i]\n\n        ith_cluster_silhouette_values.sort()\n\n        size_cluster_i = ith_cluster_silhouette_values.shape[0]\n        y_upper = y_lower + size_cluster_i\n\n        color = cm.nipy_spectral(float(i) / n_clusters)\n        ax1.fill_betweenx(\n            np.arange(y_lower, y_upper),\n            0,\n            ith_cluster_silhouette_values,\n            facecolor=color,\n            edgecolor=color,\n            alpha=0.7,\n        )\n\n        # Label the silhouette plots with their cluster numbers at the middle\n        ax1.text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))\n\n        # Compute the new y_lower for next plot\n        y_lower = y_upper + 10  # 10 for the 0 samples\n\n    ax1.set_title(\"The silhouette plot for the various clusters.\")\n    ax1.set_xlabel(\"The silhouette coefficient values\")\n    ax1.set_ylabel(\"Cluster label\")\n\n    # The vertical line for average silhouette score of all the values\n    ax1.axvline(x=silhouette_avg, color=\"red\", linestyle=\"--\")\n\n    ax1.set_yticks([])  # Clear the yaxis labels / ticks\n    ax1.set_xticks([-0.1, 0, 0.2, 0.4, 0.6, 0.8, 1])\n\n    # 2nd Plot showing the actual clusters formed\n    colors = cm.nipy_spectral(cluster_labels.astype(float) / n_clusters)\n    ax2.scatter(\n        X[:, 0], X[:, 1], marker=\".\", s=30, lw=0, alpha=0.7, c=colors, edgecolor=\"k\"\n    )\n\n    # Labeling the clusters\n    centers = clusterer.cluster_centers_\n    # Draw white circles at cluster centers\n    ax2.scatter(\n        centers[:, 0],\n        centers[:, 1],\n        marker=\"o\",\n        c=\"white\",\n        alpha=1,\n        s=200,\n        edgecolor=\"k\",\n    )\n\n    for i, c in enumerate(centers):\n        ax2.scatter(c[0], c[1], marker=\"$%d$\" % i, alpha=1, s=50, edgecolor=\"k\")\n\n    ax2.set_title(\"The visualization of the clustered data.\")\n    ax2.set_xlabel(\"Feature space for the 1st feature\")\n    ax2.set_ylabel(\"Feature space for the 2nd feature\")\n\n    plt.suptitle(\n        \"Silhouette analysis for KMeans clustering on sample data with n_clusters = %d\"\n        % n_clusters,\n        fontsize=14,\n        fontweight=\"bold\",\n    )\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/2434f000f4405168e6285a3e410c709f/plot_kmeans_silhouette_analysis.ipynb

@@ -193,7 +193,6 @@ def plot_gallery(title, images, n_col=n_col, n_row=n_row, cmap=plt.cm.gray):
     batch_size=20,
     max_iter=50,
     random_state=rng,
-    n_init="auto",
 )
 kmeans_estimator.fit(faces_centered)
 plot_gallery(

dev/_downloads/4825fc8223d1af0f3b61080c3dea3a62/plot_faces_decomposition.py

@@ -69,7 +69,7 @@
 
     # Initialize the clusterer with n_clusters value and a random generator
     # seed of 10 for reproducibility.
-    clusterer = KMeans(n_clusters=n_clusters, n_init="auto", random_state=10)
+    clusterer = KMeans(n_clusters=n_clusters, random_state=10)
     cluster_labels = clusterer.fit_predict(X)
 
     # The silhouette_score gives the average value for all the samples.