Pushing the docs to dev/ for branch: main, commit 5cdbbf15e3fade7cc2462ef66dc4ea0f37f390e3

Author: sklearn-ci

dev/_downloads/02192f99342d6d1323161978b6c80bfc/plot_ols_ridge.zip

@@ -98,10 +98,10 @@ def generate_data(n_samples, n_features):
 plt.legend(loc="lower left")
 plt.ylim((0.65, 1.0))
 plt.suptitle(
-    "LDA (Linear Discriminant Analysis) vs. "
-    + "\n"
-    + "LDA with Ledoit Wolf vs. "
-    + "\n"
-    + "LDA with OAS (1 discriminative feature)"
+    "LDA (Linear Discriminant Analysis) vs."
+    "\n"
+    "LDA with Ledoit Wolf vs."
+    "\n"
+    "LDA with OAS (1 discriminative feature)"
 )
 plt.show()

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -123,8 +123,8 @@
             warnings.filterwarnings(
                 "ignore",
                 message="the number of connected components of the "
-                + "connectivity matrix is [0-9]{1,2}"
-                + " > 1. Completing it to avoid stopping the tree early.",
+                "connectivity matrix is [0-9]{1,2}"
+                " > 1. Completing it to avoid stopping the tree early.",
                 category=UserWarning,
             )
             algorithm.fit(X)

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 as mpl\nimport matplotlib.gridspec as gridspec\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.mixture import BayesianGaussianMixture\n\n\ndef plot_ellipses(ax, weights, means, covars):\n    for n in range(means.shape[0]):\n        eig_vals, eig_vecs = np.linalg.eigh(covars[n])\n        unit_eig_vec = eig_vecs[0] / np.linalg.norm(eig_vecs[0])\n        angle = np.arctan2(unit_eig_vec[1], unit_eig_vec[0])\n        # Ellipse needs degrees\n        angle = 180 * angle / np.pi\n        # eigenvector normalization\n        eig_vals = 2 * np.sqrt(2) * np.sqrt(eig_vals)\n        ell = mpl.patches.Ellipse(\n            means[n], eig_vals[0], eig_vals[1], angle=180 + angle, edgecolor=\"black\"\n        )\n        ell.set_clip_box(ax.bbox)\n        ell.set_alpha(weights[n])\n        ell.set_facecolor(\"#56B4E9\")\n        ax.add_artist(ell)\n\n\ndef plot_results(ax1, ax2, estimator, X, y, title, plot_title=False):\n    ax1.set_title(title)\n    ax1.scatter(X[:, 0], X[:, 1], s=5, marker=\"o\", color=colors[y], alpha=0.8)\n    ax1.set_xlim(-2.0, 2.0)\n    ax1.set_ylim(-3.0, 3.0)\n    ax1.set_xticks(())\n    ax1.set_yticks(())\n    plot_ellipses(ax1, estimator.weights_, estimator.means_, estimator.covariances_)\n\n    ax2.get_xaxis().set_tick_params(direction=\"out\")\n    ax2.yaxis.grid(True, alpha=0.7)\n    for k, w in enumerate(estimator.weights_):\n        ax2.bar(\n            k,\n            w,\n            width=0.9,\n            color=\"#56B4E9\",\n            zorder=3,\n            align=\"center\",\n            edgecolor=\"black\",\n        )\n        ax2.text(k, w + 0.007, \"%.1f%%\" % (w * 100.0), horizontalalignment=\"center\")\n    ax2.set_xlim(-0.6, 2 * n_components - 0.4)\n    ax2.set_ylim(0.0, 1.1)\n    ax2.tick_params(axis=\"y\", which=\"both\", left=False, right=False, labelleft=False)\n    ax2.tick_params(axis=\"x\", which=\"both\", top=False)\n\n    if plot_title:\n        ax1.set_ylabel(\"Estimated Mixtures\")\n        ax2.set_ylabel(\"Weight of each component\")\n\n\n# Parameters of the dataset\nrandom_state, n_components, n_features = 2, 3, 2\ncolors = np.array([\"#0072B2\", \"#F0E442\", \"#D55E00\"])\n\ncovars = np.array(\n    [[[0.7, 0.0], [0.0, 0.1]], [[0.5, 0.0], [0.0, 0.1]], [[0.5, 0.0], [0.0, 0.1]]]\n)\nsamples = np.array([200, 500, 200])\nmeans = np.array([[0.0, -0.70], [0.0, 0.0], [0.0, 0.70]])\n\n# mean_precision_prior= 0.8 to minimize the influence of the prior\nestimators = [\n    (\n        \"Finite mixture with a Dirichlet distribution\\nprior and \" r\"$\\gamma_0=$\",\n        BayesianGaussianMixture(\n            weight_concentration_prior_type=\"dirichlet_distribution\",\n            n_components=2 * n_components,\n            reg_covar=0,\n            init_params=\"random\",\n            max_iter=1500,\n            mean_precision_prior=0.8,\n            random_state=random_state,\n        ),\n        [0.001, 1, 1000],\n    ),\n    (\n        \"Infinite mixture with a Dirichlet process\\n prior and\" r\"$\\gamma_0=$\",\n        BayesianGaussianMixture(\n            weight_concentration_prior_type=\"dirichlet_process\",\n            n_components=2 * n_components,\n            reg_covar=0,\n            init_params=\"random\",\n            max_iter=1500,\n            mean_precision_prior=0.8,\n            random_state=random_state,\n        ),\n        [1, 1000, 100000],\n    ),\n]\n\n# Generate data\nrng = np.random.RandomState(random_state)\nX = np.vstack(\n    [\n        rng.multivariate_normal(means[j], covars[j], samples[j])\n        for j in range(n_components)\n    ]\n)\ny = np.concatenate([np.full(samples[j], j, dtype=int) for j in range(n_components)])\n\n# Plot results in two different figures\nfor title, estimator, concentrations_prior in estimators:\n    plt.figure(figsize=(4.7 * 3, 8))\n    plt.subplots_adjust(\n        bottom=0.04, top=0.90, hspace=0.05, wspace=0.05, left=0.03, right=0.99\n    )\n\n    gs = gridspec.GridSpec(3, len(concentrations_prior))\n    for k, concentration in enumerate(concentrations_prior):\n        estimator.weight_concentration_prior = concentration\n        estimator.fit(X)\n        plot_results(\n            plt.subplot(gs[0:2, k]),\n            plt.subplot(gs[2, k]),\n            estimator,\n            X,\n            y,\n            r\"%s$%.1e$\" % (title, concentration),\n            plot_title=k == 0,\n        )\n\nplt.show()"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib as mpl\nimport matplotlib.gridspec as gridspec\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.mixture import BayesianGaussianMixture\n\n\ndef plot_ellipses(ax, weights, means, covars):\n    for n in range(means.shape[0]):\n        eig_vals, eig_vecs = np.linalg.eigh(covars[n])\n        unit_eig_vec = eig_vecs[0] / np.linalg.norm(eig_vecs[0])\n        angle = np.arctan2(unit_eig_vec[1], unit_eig_vec[0])\n        # Ellipse needs degrees\n        angle = 180 * angle / np.pi\n        # eigenvector normalization\n        eig_vals = 2 * np.sqrt(2) * np.sqrt(eig_vals)\n        ell = mpl.patches.Ellipse(\n            means[n], eig_vals[0], eig_vals[1], angle=180 + angle, edgecolor=\"black\"\n        )\n        ell.set_clip_box(ax.bbox)\n        ell.set_alpha(weights[n])\n        ell.set_facecolor(\"#56B4E9\")\n        ax.add_artist(ell)\n\n\ndef plot_results(ax1, ax2, estimator, X, y, title, plot_title=False):\n    ax1.set_title(title)\n    ax1.scatter(X[:, 0], X[:, 1], s=5, marker=\"o\", color=colors[y], alpha=0.8)\n    ax1.set_xlim(-2.0, 2.0)\n    ax1.set_ylim(-3.0, 3.0)\n    ax1.set_xticks(())\n    ax1.set_yticks(())\n    plot_ellipses(ax1, estimator.weights_, estimator.means_, estimator.covariances_)\n\n    ax2.get_xaxis().set_tick_params(direction=\"out\")\n    ax2.yaxis.grid(True, alpha=0.7)\n    for k, w in enumerate(estimator.weights_):\n        ax2.bar(\n            k,\n            w,\n            width=0.9,\n            color=\"#56B4E9\",\n            zorder=3,\n            align=\"center\",\n            edgecolor=\"black\",\n        )\n        ax2.text(k, w + 0.007, \"%.1f%%\" % (w * 100.0), horizontalalignment=\"center\")\n    ax2.set_xlim(-0.6, 2 * n_components - 0.4)\n    ax2.set_ylim(0.0, 1.1)\n    ax2.tick_params(axis=\"y\", which=\"both\", left=False, right=False, labelleft=False)\n    ax2.tick_params(axis=\"x\", which=\"both\", top=False)\n\n    if plot_title:\n        ax1.set_ylabel(\"Estimated Mixtures\")\n        ax2.set_ylabel(\"Weight of each component\")\n\n\n# Parameters of the dataset\nrandom_state, n_components, n_features = 2, 3, 2\ncolors = np.array([\"#0072B2\", \"#F0E442\", \"#D55E00\"])\n\ncovars = np.array(\n    [[[0.7, 0.0], [0.0, 0.1]], [[0.5, 0.0], [0.0, 0.1]], [[0.5, 0.0], [0.0, 0.1]]]\n)\nsamples = np.array([200, 500, 200])\nmeans = np.array([[0.0, -0.70], [0.0, 0.0], [0.0, 0.70]])\n\n# mean_precision_prior= 0.8 to minimize the influence of the prior\nestimators = [\n    (\n        \"Finite mixture with a Dirichlet distribution\\n\" r\"prior and $\\gamma_0=$\",\n        BayesianGaussianMixture(\n            weight_concentration_prior_type=\"dirichlet_distribution\",\n            n_components=2 * n_components,\n            reg_covar=0,\n            init_params=\"random\",\n            max_iter=1500,\n            mean_precision_prior=0.8,\n            random_state=random_state,\n        ),\n        [0.001, 1, 1000],\n    ),\n    (\n        \"Infinite mixture with a Dirichlet process\\n\" r\"prior and $\\gamma_0=$\",\n        BayesianGaussianMixture(\n            weight_concentration_prior_type=\"dirichlet_process\",\n            n_components=2 * n_components,\n            reg_covar=0,\n            init_params=\"random\",\n            max_iter=1500,\n            mean_precision_prior=0.8,\n            random_state=random_state,\n        ),\n        [1, 1000, 100000],\n    ),\n]\n\n# Generate data\nrng = np.random.RandomState(random_state)\nX = np.vstack(\n    [\n        rng.multivariate_normal(means[j], covars[j], samples[j])\n        for j in range(n_components)\n    ]\n)\ny = np.concatenate([np.full(samples[j], j, dtype=int) for j in range(n_components)])\n\n# Plot results in two different figures\nfor title, estimator, concentrations_prior in estimators:\n    plt.figure(figsize=(4.7 * 3, 8))\n    plt.subplots_adjust(\n        bottom=0.04, top=0.90, hspace=0.05, wspace=0.05, left=0.03, right=0.99\n    )\n\n    gs = gridspec.GridSpec(3, len(concentrations_prior))\n    for k, concentration in enumerate(concentrations_prior):\n        estimator.weight_concentration_prior = concentration\n        estimator.fit(X)\n        plot_results(\n            plt.subplot(gs[0:2, k]),\n            plt.subplot(gs[2, k]),\n            estimator,\n            X,\n            y,\n            r\"%s$%.1e$\" % (title, concentration),\n            plot_title=k == 0,\n        )\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/038d1885eb5f5ea53aca42da3031fe38/plot_document_clustering.zip

@@ -103,7 +103,7 @@ def plot_results(ax1, ax2, estimator, X, y, title, plot_title=False):
 # mean_precision_prior= 0.8 to minimize the influence of the prior
 estimators = [
     (
-        "Finite mixture with a Dirichlet distribution\nprior and " r"$\gamma_0=$",
+        "Finite mixture with a Dirichlet distribution\n" r"prior and $\gamma_0=$",
         BayesianGaussianMixture(
             weight_concentration_prior_type="dirichlet_distribution",
             n_components=2 * n_components,
@@ -116,7 +116,7 @@ def plot_results(ax1, ax2, estimator, X, y, title, plot_title=False):
         [0.001, 1, 1000],
     ),
     (
-        "Infinite mixture with a Dirichlet process\n prior and" r"$\gamma_0=$",
+        "Infinite mixture with a Dirichlet process\n" r"prior and $\gamma_0=$",
         BayesianGaussianMixture(
             weight_concentration_prior_type="dirichlet_process",
             n_components=2 * n_components,

dev/_downloads/03c018a16384c69f3a89e473650d57ee/plot_svm_margin.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\n\nfrom sklearn.covariance import OAS\nfrom sklearn.datasets import make_blobs\nfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n\nn_train = 20  # samples for training\nn_test = 200  # samples for testing\nn_averages = 50  # how often to repeat classification\nn_features_max = 75  # maximum number of features\nstep = 4  # step size for the calculation\n\n\ndef generate_data(n_samples, n_features):\n    \"\"\"Generate random blob-ish data with noisy features.\n\n    This returns an array of input data with shape `(n_samples, n_features)`\n    and an array of `n_samples` target labels.\n\n    Only one feature contains discriminative information, the other features\n    contain only noise.\n    \"\"\"\n    X, y = make_blobs(n_samples=n_samples, n_features=1, centers=[[-2], [2]])\n\n    # add non-discriminative features\n    if n_features > 1:\n        X = np.hstack([X, np.random.randn(n_samples, n_features - 1)])\n    return X, y\n\n\nacc_clf1, acc_clf2, acc_clf3 = [], [], []\nn_features_range = range(1, n_features_max + 1, step)\nfor n_features in n_features_range:\n    score_clf1, score_clf2, score_clf3 = 0, 0, 0\n    for _ in range(n_averages):\n        X, y = generate_data(n_train, n_features)\n\n        clf1 = LinearDiscriminantAnalysis(solver=\"lsqr\", shrinkage=None).fit(X, y)\n        clf2 = LinearDiscriminantAnalysis(solver=\"lsqr\", shrinkage=\"auto\").fit(X, y)\n        oa = OAS(store_precision=False, assume_centered=False)\n        clf3 = LinearDiscriminantAnalysis(solver=\"lsqr\", covariance_estimator=oa).fit(\n            X, y\n        )\n\n        X, y = generate_data(n_test, n_features)\n        score_clf1 += clf1.score(X, y)\n        score_clf2 += clf2.score(X, y)\n        score_clf3 += clf3.score(X, y)\n\n    acc_clf1.append(score_clf1 / n_averages)\n    acc_clf2.append(score_clf2 / n_averages)\n    acc_clf3.append(score_clf3 / n_averages)\n\nfeatures_samples_ratio = np.array(n_features_range) / n_train\n\nplt.plot(\n    features_samples_ratio,\n    acc_clf1,\n    linewidth=2,\n    label=\"LDA\",\n    color=\"gold\",\n    linestyle=\"solid\",\n)\nplt.plot(\n    features_samples_ratio,\n    acc_clf2,\n    linewidth=2,\n    label=\"LDA with Ledoit Wolf\",\n    color=\"navy\",\n    linestyle=\"dashed\",\n)\nplt.plot(\n    features_samples_ratio,\n    acc_clf3,\n    linewidth=2,\n    label=\"LDA with OAS\",\n    color=\"red\",\n    linestyle=\"dotted\",\n)\n\nplt.xlabel(\"n_features / n_samples\")\nplt.ylabel(\"Classification accuracy\")\n\nplt.legend(loc=\"lower left\")\nplt.ylim((0.65, 1.0))\nplt.suptitle(\n    \"LDA (Linear Discriminant Analysis) vs. \"\n    + \"\\n\"\n    + \"LDA with Ledoit Wolf vs. \"\n    + \"\\n\"\n    + \"LDA with OAS (1 discriminative feature)\"\n)\nplt.show()"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.covariance import OAS\nfrom sklearn.datasets import make_blobs\nfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n\nn_train = 20  # samples for training\nn_test = 200  # samples for testing\nn_averages = 50  # how often to repeat classification\nn_features_max = 75  # maximum number of features\nstep = 4  # step size for the calculation\n\n\ndef generate_data(n_samples, n_features):\n    \"\"\"Generate random blob-ish data with noisy features.\n\n    This returns an array of input data with shape `(n_samples, n_features)`\n    and an array of `n_samples` target labels.\n\n    Only one feature contains discriminative information, the other features\n    contain only noise.\n    \"\"\"\n    X, y = make_blobs(n_samples=n_samples, n_features=1, centers=[[-2], [2]])\n\n    # add non-discriminative features\n    if n_features > 1:\n        X = np.hstack([X, np.random.randn(n_samples, n_features - 1)])\n    return X, y\n\n\nacc_clf1, acc_clf2, acc_clf3 = [], [], []\nn_features_range = range(1, n_features_max + 1, step)\nfor n_features in n_features_range:\n    score_clf1, score_clf2, score_clf3 = 0, 0, 0\n    for _ in range(n_averages):\n        X, y = generate_data(n_train, n_features)\n\n        clf1 = LinearDiscriminantAnalysis(solver=\"lsqr\", shrinkage=None).fit(X, y)\n        clf2 = LinearDiscriminantAnalysis(solver=\"lsqr\", shrinkage=\"auto\").fit(X, y)\n        oa = OAS(store_precision=False, assume_centered=False)\n        clf3 = LinearDiscriminantAnalysis(solver=\"lsqr\", covariance_estimator=oa).fit(\n            X, y\n        )\n\n        X, y = generate_data(n_test, n_features)\n        score_clf1 += clf1.score(X, y)\n        score_clf2 += clf2.score(X, y)\n        score_clf3 += clf3.score(X, y)\n\n    acc_clf1.append(score_clf1 / n_averages)\n    acc_clf2.append(score_clf2 / n_averages)\n    acc_clf3.append(score_clf3 / n_averages)\n\nfeatures_samples_ratio = np.array(n_features_range) / n_train\n\nplt.plot(\n    features_samples_ratio,\n    acc_clf1,\n    linewidth=2,\n    label=\"LDA\",\n    color=\"gold\",\n    linestyle=\"solid\",\n)\nplt.plot(\n    features_samples_ratio,\n    acc_clf2,\n    linewidth=2,\n    label=\"LDA with Ledoit Wolf\",\n    color=\"navy\",\n    linestyle=\"dashed\",\n)\nplt.plot(\n    features_samples_ratio,\n    acc_clf3,\n    linewidth=2,\n    label=\"LDA with OAS\",\n    color=\"red\",\n    linestyle=\"dotted\",\n)\n\nplt.xlabel(\"n_features / n_samples\")\nplt.ylabel(\"Classification accuracy\")\n\nplt.legend(loc=\"lower left\")\nplt.ylim((0.65, 1.0))\nplt.suptitle(\n    \"LDA (Linear Discriminant Analysis) vs.\"\n    \"\\n\"\n    \"LDA with Ledoit Wolf vs.\"\n    \"\\n\"\n    \"LDA with OAS (1 discriminative feature)\"\n)\nplt.show()"
       ]
     }
   ],