Pushing the docs to dev/ for branch: main, commit ff78e258ccf11068e2b3a433c51517ae56234f88

Author: sklearn-ci

dev/_downloads/02192f99342d6d1323161978b6c80bfc/plot_ols_ridge.zip

@@ -11,7 +11,7 @@
 
     See also :ref:`sphx_glr_auto_examples_miscellaneous_plot_roc_curve_visualization_api.py`
 
-"""  # noqa: E501
+"""
 
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -50,7 +50,7 @@ def plot_top_words(model, feature_names, n_top_words, title):
 
         ax = axes[topic_idx]
         ax.barh(top_features, weights, height=0.7)
-        ax.set_title(f"Topic {topic_idx +1}", fontdict={"fontsize": 30})
+        ax.set_title(f"Topic {topic_idx + 1}", fontdict={"fontsize": 30})
         ax.tick_params(axis="both", which="major", labelsize=20)
         for i in "top right left".split():
             ax.spines[i].set_visible(False)

dev/_downloads/0358b1921962fd7c6f5a94c5abc91476/plot_hashing_vs_dict_vectorizer.zip

@@ -134,7 +134,7 @@
       },
       "outputs": [],
       "source": [
-        "print(f\"y_score:\\n{y_score[0:2,:]}\")\nprint()\nprint(f\"y_score.ravel():\\n{y_score[0:2,:].ravel()}\")"
+        "print(f\"y_score:\\n{y_score[0:2, :]}\")\nprint()\nprint(f\"y_score.ravel():\\n{y_score[0:2, :].ravel()}\")"
       ]
     },
     {
@@ -271,7 +271,7 @@
       },
       "outputs": [],
       "source": [
-        "pair_scores = []\nmean_tpr = dict()\n\nfor ix, (label_a, label_b) in enumerate(pair_list):\n    a_mask = y_test == label_a\n    b_mask = y_test == label_b\n    ab_mask = np.logical_or(a_mask, b_mask)\n\n    a_true = a_mask[ab_mask]\n    b_true = b_mask[ab_mask]\n\n    idx_a = np.flatnonzero(label_binarizer.classes_ == label_a)[0]\n    idx_b = np.flatnonzero(label_binarizer.classes_ == label_b)[0]\n\n    fpr_a, tpr_a, _ = roc_curve(a_true, y_score[ab_mask, idx_a])\n    fpr_b, tpr_b, _ = roc_curve(b_true, y_score[ab_mask, idx_b])\n\n    mean_tpr[ix] = np.zeros_like(fpr_grid)\n    mean_tpr[ix] += np.interp(fpr_grid, fpr_a, tpr_a)\n    mean_tpr[ix] += np.interp(fpr_grid, fpr_b, tpr_b)\n    mean_tpr[ix] /= 2\n    mean_score = auc(fpr_grid, mean_tpr[ix])\n    pair_scores.append(mean_score)\n\n    fig, ax = plt.subplots(figsize=(6, 6))\n    plt.plot(\n        fpr_grid,\n        mean_tpr[ix],\n        label=f\"Mean {label_a} vs {label_b} (AUC = {mean_score :.2f})\",\n        linestyle=\":\",\n        linewidth=4,\n    )\n    RocCurveDisplay.from_predictions(\n        a_true,\n        y_score[ab_mask, idx_a],\n        ax=ax,\n        name=f\"{label_a} as positive class\",\n    )\n    RocCurveDisplay.from_predictions(\n        b_true,\n        y_score[ab_mask, idx_b],\n        ax=ax,\n        name=f\"{label_b} as positive class\",\n        plot_chance_level=True,\n        despine=True,\n    )\n    ax.set(\n        xlabel=\"False Positive Rate\",\n        ylabel=\"True Positive Rate\",\n        title=f\"{target_names[idx_a]} vs {label_b} ROC curves\",\n    )\n\nprint(f\"Macro-averaged One-vs-One ROC AUC score:\\n{np.average(pair_scores):.2f}\")"
+        "pair_scores = []\nmean_tpr = dict()\n\nfor ix, (label_a, label_b) in enumerate(pair_list):\n    a_mask = y_test == label_a\n    b_mask = y_test == label_b\n    ab_mask = np.logical_or(a_mask, b_mask)\n\n    a_true = a_mask[ab_mask]\n    b_true = b_mask[ab_mask]\n\n    idx_a = np.flatnonzero(label_binarizer.classes_ == label_a)[0]\n    idx_b = np.flatnonzero(label_binarizer.classes_ == label_b)[0]\n\n    fpr_a, tpr_a, _ = roc_curve(a_true, y_score[ab_mask, idx_a])\n    fpr_b, tpr_b, _ = roc_curve(b_true, y_score[ab_mask, idx_b])\n\n    mean_tpr[ix] = np.zeros_like(fpr_grid)\n    mean_tpr[ix] += np.interp(fpr_grid, fpr_a, tpr_a)\n    mean_tpr[ix] += np.interp(fpr_grid, fpr_b, tpr_b)\n    mean_tpr[ix] /= 2\n    mean_score = auc(fpr_grid, mean_tpr[ix])\n    pair_scores.append(mean_score)\n\n    fig, ax = plt.subplots(figsize=(6, 6))\n    plt.plot(\n        fpr_grid,\n        mean_tpr[ix],\n        label=f\"Mean {label_a} vs {label_b} (AUC = {mean_score:.2f})\",\n        linestyle=\":\",\n        linewidth=4,\n    )\n    RocCurveDisplay.from_predictions(\n        a_true,\n        y_score[ab_mask, idx_a],\n        ax=ax,\n        name=f\"{label_a} as positive class\",\n    )\n    RocCurveDisplay.from_predictions(\n        b_true,\n        y_score[ab_mask, idx_b],\n        ax=ax,\n        name=f\"{label_b} as positive class\",\n        plot_chance_level=True,\n        despine=True,\n    )\n    ax.set(\n        xlabel=\"False Positive Rate\",\n        ylabel=\"True Positive Rate\",\n        title=f\"{target_names[idx_a]} vs {label_b} ROC curves\",\n    )\n\nprint(f\"Macro-averaged One-vs-One ROC AUC score:\\n{np.average(pair_scores):.2f}\")"
       ]
     },
     {

dev/_downloads/038d1885eb5f5ea53aca42da3031fe38/plot_document_clustering.zip

@@ -177,8 +177,8 @@ def generate(n_samples, noise, n_repeat=1):
 
     plt.subplot(2, n_estimators, n_estimators + n + 1)
     plt.plot(X_test, y_error, "r", label="$error(x)$")
-    plt.plot(X_test, y_bias, "b", label="$bias^2(x)$"),
-    plt.plot(X_test, y_var, "g", label="$variance(x)$"),
+    plt.plot(X_test, y_bias, "b", label="$bias^2(x)$")
+    plt.plot(X_test, y_var, "g", label="$variance(x)$")
     plt.plot(X_test, y_noise, "c", label="$noise(x)$")
 
     plt.xlim([-5, 5])

dev/_downloads/03c018a16384c69f3a89e473650d57ee/plot_svm_margin.zip

@@ -40,7 +40,7 @@
 # were already standardized.
 # For a more complete example on the interpretations of the coefficients of
 # linear models, you may refer to
-# :ref:`sphx_glr_auto_examples_inspection_plot_linear_model_coefficient_interpretation.py`.  # noqa: E501
+# :ref:`sphx_glr_auto_examples_inspection_plot_linear_model_coefficient_interpretation.py`.
 import matplotlib.pyplot as plt
 import numpy as np
 

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\nfrom time import time\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\nimport numpy as np\nfrom matplotlib.ticker import NullFormatter\n\nfrom sklearn import manifold\nfrom sklearn.utils import check_random_state\n\n# Variables for manifold learning.\nn_neighbors = 10\nn_samples = 1000\n\n# Create our sphere.\nrandom_state = check_random_state(0)\np = random_state.rand(n_samples) * (2 * np.pi - 0.55)\nt = random_state.rand(n_samples) * np.pi\n\n# Sever the poles from the sphere.\nindices = (t < (np.pi - (np.pi / 8))) & (t > ((np.pi / 8)))\ncolors = p[indices]\nx, y, z = (\n    np.sin(t[indices]) * np.cos(p[indices]),\n    np.sin(t[indices]) * np.sin(p[indices]),\n    np.cos(t[indices]),\n)\n\n# Plot our dataset.\nfig = plt.figure(figsize=(15, 8))\nplt.suptitle(\n    \"Manifold Learning with %i points, %i neighbors\" % (1000, n_neighbors), fontsize=14\n)\n\nax = fig.add_subplot(251, projection=\"3d\")\nax.scatter(x, y, z, c=p[indices], cmap=plt.cm.rainbow)\nax.view_init(40, -10)\n\nsphere_data = np.array([x, y, z]).T\n\n# Perform Locally Linear Embedding Manifold learning\nmethods = [\"standard\", \"ltsa\", \"hessian\", \"modified\"]\nlabels = [\"LLE\", \"LTSA\", \"Hessian LLE\", \"Modified LLE\"]\n\nfor i, method in enumerate(methods):\n    t0 = time()\n    trans_data = (\n        manifold.LocallyLinearEmbedding(\n            n_neighbors=n_neighbors, n_components=2, method=method, random_state=42\n        )\n        .fit_transform(sphere_data)\n        .T\n    )\n    t1 = time()\n    print(\"%s: %.2g sec\" % (methods[i], t1 - t0))\n\n    ax = fig.add_subplot(252 + i)\n    plt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)\n    plt.title(\"%s (%.2g sec)\" % (labels[i], t1 - t0))\n    ax.xaxis.set_major_formatter(NullFormatter())\n    ax.yaxis.set_major_formatter(NullFormatter())\n    plt.axis(\"tight\")\n\n# Perform Isomap Manifold learning.\nt0 = time()\ntrans_data = (\n    manifold.Isomap(n_neighbors=n_neighbors, n_components=2)\n    .fit_transform(sphere_data)\n    .T\n)\nt1 = time()\nprint(\"%s: %.2g sec\" % (\"ISO\", t1 - t0))\n\nax = fig.add_subplot(257)\nplt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)\nplt.title(\"%s (%.2g sec)\" % (\"Isomap\", t1 - t0))\nax.xaxis.set_major_formatter(NullFormatter())\nax.yaxis.set_major_formatter(NullFormatter())\nplt.axis(\"tight\")\n\n# Perform Multi-dimensional scaling.\nt0 = time()\nmds = manifold.MDS(2, max_iter=100, n_init=1, random_state=42)\ntrans_data = mds.fit_transform(sphere_data).T\nt1 = time()\nprint(\"MDS: %.2g sec\" % (t1 - t0))\n\nax = fig.add_subplot(258)\nplt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)\nplt.title(\"MDS (%.2g sec)\" % (t1 - t0))\nax.xaxis.set_major_formatter(NullFormatter())\nax.yaxis.set_major_formatter(NullFormatter())\nplt.axis(\"tight\")\n\n# Perform Spectral Embedding.\nt0 = time()\nse = manifold.SpectralEmbedding(\n    n_components=2, n_neighbors=n_neighbors, random_state=42\n)\ntrans_data = se.fit_transform(sphere_data).T\nt1 = time()\nprint(\"Spectral Embedding: %.2g sec\" % (t1 - t0))\n\nax = fig.add_subplot(259)\nplt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)\nplt.title(\"Spectral Embedding (%.2g sec)\" % (t1 - t0))\nax.xaxis.set_major_formatter(NullFormatter())\nax.yaxis.set_major_formatter(NullFormatter())\nplt.axis(\"tight\")\n\n# Perform t-distributed stochastic neighbor embedding.\nt0 = time()\ntsne = manifold.TSNE(n_components=2, random_state=0)\ntrans_data = tsne.fit_transform(sphere_data).T\nt1 = time()\nprint(\"t-SNE: %.2g sec\" % (t1 - t0))\n\nax = fig.add_subplot(2, 5, 10)\nplt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)\nplt.title(\"t-SNE (%.2g sec)\" % (t1 - t0))\nax.xaxis.set_major_formatter(NullFormatter())\nax.yaxis.set_major_formatter(NullFormatter())\nplt.axis(\"tight\")\n\nplt.show()"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nfrom time import time\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\nimport numpy as np\nfrom matplotlib.ticker import NullFormatter\n\nfrom sklearn import manifold\nfrom sklearn.utils import check_random_state\n\n# Variables for manifold learning.\nn_neighbors = 10\nn_samples = 1000\n\n# Create our sphere.\nrandom_state = check_random_state(0)\np = random_state.rand(n_samples) * (2 * np.pi - 0.55)\nt = random_state.rand(n_samples) * np.pi\n\n# Sever the poles from the sphere.\nindices = (t < (np.pi - (np.pi / 8))) & (t > (np.pi / 8))\ncolors = p[indices]\nx, y, z = (\n    np.sin(t[indices]) * np.cos(p[indices]),\n    np.sin(t[indices]) * np.sin(p[indices]),\n    np.cos(t[indices]),\n)\n\n# Plot our dataset.\nfig = plt.figure(figsize=(15, 8))\nplt.suptitle(\n    \"Manifold Learning with %i points, %i neighbors\" % (1000, n_neighbors), fontsize=14\n)\n\nax = fig.add_subplot(251, projection=\"3d\")\nax.scatter(x, y, z, c=p[indices], cmap=plt.cm.rainbow)\nax.view_init(40, -10)\n\nsphere_data = np.array([x, y, z]).T\n\n# Perform Locally Linear Embedding Manifold learning\nmethods = [\"standard\", \"ltsa\", \"hessian\", \"modified\"]\nlabels = [\"LLE\", \"LTSA\", \"Hessian LLE\", \"Modified LLE\"]\n\nfor i, method in enumerate(methods):\n    t0 = time()\n    trans_data = (\n        manifold.LocallyLinearEmbedding(\n            n_neighbors=n_neighbors, n_components=2, method=method, random_state=42\n        )\n        .fit_transform(sphere_data)\n        .T\n    )\n    t1 = time()\n    print(\"%s: %.2g sec\" % (methods[i], t1 - t0))\n\n    ax = fig.add_subplot(252 + i)\n    plt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)\n    plt.title(\"%s (%.2g sec)\" % (labels[i], t1 - t0))\n    ax.xaxis.set_major_formatter(NullFormatter())\n    ax.yaxis.set_major_formatter(NullFormatter())\n    plt.axis(\"tight\")\n\n# Perform Isomap Manifold learning.\nt0 = time()\ntrans_data = (\n    manifold.Isomap(n_neighbors=n_neighbors, n_components=2)\n    .fit_transform(sphere_data)\n    .T\n)\nt1 = time()\nprint(\"%s: %.2g sec\" % (\"ISO\", t1 - t0))\n\nax = fig.add_subplot(257)\nplt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)\nplt.title(\"%s (%.2g sec)\" % (\"Isomap\", t1 - t0))\nax.xaxis.set_major_formatter(NullFormatter())\nax.yaxis.set_major_formatter(NullFormatter())\nplt.axis(\"tight\")\n\n# Perform Multi-dimensional scaling.\nt0 = time()\nmds = manifold.MDS(2, max_iter=100, n_init=1, random_state=42)\ntrans_data = mds.fit_transform(sphere_data).T\nt1 = time()\nprint(\"MDS: %.2g sec\" % (t1 - t0))\n\nax = fig.add_subplot(258)\nplt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)\nplt.title(\"MDS (%.2g sec)\" % (t1 - t0))\nax.xaxis.set_major_formatter(NullFormatter())\nax.yaxis.set_major_formatter(NullFormatter())\nplt.axis(\"tight\")\n\n# Perform Spectral Embedding.\nt0 = time()\nse = manifold.SpectralEmbedding(\n    n_components=2, n_neighbors=n_neighbors, random_state=42\n)\ntrans_data = se.fit_transform(sphere_data).T\nt1 = time()\nprint(\"Spectral Embedding: %.2g sec\" % (t1 - t0))\n\nax = fig.add_subplot(259)\nplt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)\nplt.title(\"Spectral Embedding (%.2g sec)\" % (t1 - t0))\nax.xaxis.set_major_formatter(NullFormatter())\nax.yaxis.set_major_formatter(NullFormatter())\nplt.axis(\"tight\")\n\n# Perform t-distributed stochastic neighbor embedding.\nt0 = time()\ntsne = manifold.TSNE(n_components=2, random_state=0)\ntrans_data = tsne.fit_transform(sphere_data).T\nt1 = time()\nprint(\"t-SNE: %.2g sec\" % (t1 - t0))\n\nax = fig.add_subplot(2, 5, 10)\nplt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)\nplt.title(\"t-SNE (%.2g sec)\" % (t1 - t0))\nax.xaxis.set_major_formatter(NullFormatter())\nax.yaxis.set_major_formatter(NullFormatter())\nplt.axis(\"tight\")\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/053b58bbfc8177072856c743b2c93424/plot_varimax_fa.zip

@@ -285,7 +285,7 @@
       },
       "outputs": [],
       "source": [
-        "quantile_list = [0.05, 0.5, 0.95]\n\nfor quantile in quantile_list:\n    model = HistGradientBoostingRegressor(loss=\"quantile\", quantile=quantile)\n    cv_results = cross_validate(\n        model,\n        X,\n        y,\n        cv=ts_cv,\n        scoring=scoring,\n        n_jobs=2,\n    )\n    time = cv_results[\"fit_time\"]\n    scores[\"fit_time\"].append(f\"{time.mean():.2f} \u00b1 {time.std():.2f} s\")\n\n    scores[\"loss\"].append(f\"quantile {int(quantile*100)}\")\n    for key, value in cv_results.items():\n        if key.startswith(\"test_\"):\n            metric = key.split(\"test_\")[1]\n            scores = consolidate_scores(cv_results, scores, metric)\n\nscores_df = pl.DataFrame(scores)\nscores_df"
+        "quantile_list = [0.05, 0.5, 0.95]\n\nfor quantile in quantile_list:\n    model = HistGradientBoostingRegressor(loss=\"quantile\", quantile=quantile)\n    cv_results = cross_validate(\n        model,\n        X,\n        y,\n        cv=ts_cv,\n        scoring=scoring,\n        n_jobs=2,\n    )\n    time = cv_results[\"fit_time\"]\n    scores[\"fit_time\"].append(f\"{time.mean():.2f} \u00b1 {time.std():.2f} s\")\n\n    scores[\"loss\"].append(f\"quantile {int(quantile * 100)}\")\n    for key, value in cv_results.items():\n        if key.startswith(\"test_\"):\n            metric = key.split(\"test_\")[1]\n            scores = consolidate_scores(cv_results, scores, metric)\n\nscores_df = pl.DataFrame(scores)\nscores_df"
       ]
     },
     {

dev/_downloads/06c18f4675ecd124f98537d05e10abd0/plot_nca_dim_reduction.zip

@@ -109,7 +109,7 @@ def create_species_bunch(species_name, train, test, coverages, xgrid, ygrid):
 
 
 def plot_species_distribution(
-    species=("bradypus_variegatus_0", "microryzomys_minutus_0")
+    species=("bradypus_variegatus_0", "microryzomys_minutus_0"),
 ):
     """
     Plot the species distribution.

dev/_downloads/06e5cfec52777b1f220312b4ada9469d/plot_document_classification_20newsgroups.zip

@@ -60,7 +60,7 @@
     Proceedings of the National Academy of Sciences of the United States
     of America, 17, 684-688.
 
-"""  # noqa: E501
+"""
 
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause

dev/_downloads/07882f339cdda68a73e6335f34418af6/plot_theilsen.zip

@@ -191,7 +191,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "We now train and test the datasets with 8 different classification models and\nget performance results for each model. The goal of this study is to highlight\nthe computation/accuracy tradeoffs of different types of classifiers for\nsuch a multi-class text classification problem.\n\nNotice that the most important hyperparameters values were tuned using a grid\nsearch procedure not shown in this notebook for the sake of simplicity. See\nthe example script\n`sphx_glr_auto_examples_model_selection_plot_grid_search_text_feature_extraction.py`  # noqa: E501\nfor a demo on how such tuning can be done.\n\n"
+        "We now train and test the datasets with 8 different classification models and\nget performance results for each model. The goal of this study is to highlight\nthe computation/accuracy tradeoffs of different types of classifiers for\nsuch a multi-class text classification problem.\n\nNotice that the most important hyperparameters values were tuned using a grid\nsearch procedure not shown in this notebook for the sake of simplicity. See\nthe example script\n`sphx_glr_auto_examples_model_selection_plot_grid_search_text_feature_extraction.py`\nfor a demo on how such tuning can be done.\n\n"
       ]
     },
     {

dev/_downloads/07f60cdd0b8c83dd80140be675140b02/plot_face_compress.zip

@@ -152,9 +152,9 @@
 #
 # We can briefly demo the effect of :func:`numpy.ravel`:
 
-print(f"y_score:\n{y_score[0:2,:]}")
+print(f"y_score:\n{y_score[0:2, :]}")
 print()
-print(f"y_score.ravel():\n{y_score[0:2,:].ravel()}")
+print(f"y_score.ravel():\n{y_score[0:2, :].ravel()}")
 
 # %%
 # In a multi-class classification setup with highly imbalanced classes,
@@ -359,7 +359,7 @@
     plt.plot(
         fpr_grid,
         mean_tpr[ix],
-        label=f"Mean {label_a} vs {label_b} (AUC = {mean_score :.2f})",
+        label=f"Mean {label_a} vs {label_b} (AUC = {mean_score:.2f})",
         linestyle=":",
         linewidth=4,
     )

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -606,8 +606,9 @@ def score_estimator(
             "predicted, frequency*severity model": np.sum(
                 exposure * glm_freq.predict(X) * glm_sev.predict(X)
             ),
-            "predicted, tweedie, power=%.2f"
-            % glm_pure_premium.power: np.sum(exposure * glm_pure_premium.predict(X)),
+            "predicted, tweedie, power=%.2f" % glm_pure_premium.power: np.sum(
+                exposure * glm_pure_premium.predict(X)
+            ),
         }
     )
 

dev/_downloads/0919b8971cbb94ffb3b06c80621a3283/plot_label_propagation_structure.zip

@@ -40,7 +40,7 @@ class proportion than the target application.
 from sklearn.datasets import make_classification
 
 X, y = make_classification(n_samples=10_000, weights=[0.9, 0.1], random_state=0)
-print(f"Percentage of people carrying the disease: {100*y.mean():.2f}%")
+print(f"Percentage of people carrying the disease: {100 * y.mean():.2f}%")
 
 # %%
 # A machine learning model is built to diagnose if a person with some given