Pushing the docs to dev/ for branch: main, commit fe7c4176828af5231f526e76683fb9bdb9ea0367

Author: sklearn-ci

dev/_downloads/02192f99342d6d1323161978b6c80bfc/plot_ols_ridge.zip

@@ -33,7 +33,7 @@
   <http://rob.schapire.net/papers/ecolmod.pdf>`_
   S. J. Phillips, R. P. Anderson, R. E. Schapire - Ecological Modelling,
   190:231-259, 2006.
-"""  # noqa: E501
+"""
 
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause

dev/_downloads/02a1306a494b46cc56c930ceec6e8c4a/plot_species_kde.py

@@ -123,7 +123,7 @@
       },
       "outputs": [],
       "source": [
-        "model_1_scores = model_scores.iloc[0].values  # scores of the best model\nmodel_2_scores = model_scores.iloc[1].values  # scores of the second-best model\n\ndifferences = model_1_scores - model_2_scores\n\nn = differences.shape[0]  # number of test sets\ndf = n - 1\nn_train = len(list(cv.split(X, y))[0][0])\nn_test = len(list(cv.split(X, y))[0][1])\n\nt_stat, p_val = compute_corrected_ttest(differences, df, n_train, n_test)\nprint(f\"Corrected t-value: {t_stat:.3f}\\nCorrected p-value: {p_val:.3f}\")"
+        "model_1_scores = model_scores.iloc[0].values  # scores of the best model\nmodel_2_scores = model_scores.iloc[1].values  # scores of the second-best model\n\ndifferences = model_1_scores - model_2_scores\n\nn = differences.shape[0]  # number of test sets\ndf = n - 1\nn_train = len(next(iter(cv.split(X, y)))[0])\nn_test = len(next(iter(cv.split(X, y)))[1])\n\nt_stat, p_val = compute_corrected_ttest(differences, df, n_train, n_test)\nprint(f\"Corrected t-value: {t_stat:.3f}\\nCorrected p-value: {p_val:.3f}\")"
       ]
     },
     {

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -17,7 +17,7 @@
 benefits of such an approximation in terms of computation time but rather to
 show that we obtain similar results on a toy dataset.
 
-"""  # noqa: E501
+"""
 
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause

dev/_downloads/0358b1921962fd7c6f5a94c5abc91476/plot_hashing_vs_dict_vectorizer.zip

@@ -105,7 +105,7 @@
       },
       "outputs": [],
       "source": [
-        "import plotly.colors as colors\nimport plotly.express as px\nfrom plotly.subplots import make_subplots\n\nfig = make_subplots(\n    rows=1,\n    cols=2,\n    shared_yaxes=True,\n    subplot_titles=[\"Train time vs score\", \"Predict time vs score\"],\n)\nmodel_names = [result[\"model\"] for result in results]\ncolors_list = colors.qualitative.Plotly * (\n    len(model_names) // len(colors.qualitative.Plotly) + 1\n)\n\nfor idx, result in enumerate(results):\n    cv_results = result[\"cv_results\"].round(3)\n    model_name = result[\"model\"]\n    param_name = list(param_grids[model_name].keys())[0]\n    cv_results[param_name] = cv_results[\"param_\" + param_name]\n    cv_results[\"model\"] = model_name\n\n    scatter_fig = px.scatter(\n        cv_results,\n        x=\"mean_fit_time\",\n        y=\"mean_test_score\",\n        error_x=\"std_fit_time\",\n        error_y=\"std_test_score\",\n        hover_data=param_name,\n        color=\"model\",\n    )\n    line_fig = px.line(\n        cv_results,\n        x=\"mean_fit_time\",\n        y=\"mean_test_score\",\n    )\n\n    scatter_trace = scatter_fig[\"data\"][0]\n    line_trace = line_fig[\"data\"][0]\n    scatter_trace.update(marker=dict(color=colors_list[idx]))\n    line_trace.update(line=dict(color=colors_list[idx]))\n    fig.add_trace(scatter_trace, row=1, col=1)\n    fig.add_trace(line_trace, row=1, col=1)\n\n    scatter_fig = px.scatter(\n        cv_results,\n        x=\"mean_score_time\",\n        y=\"mean_test_score\",\n        error_x=\"std_score_time\",\n        error_y=\"std_test_score\",\n        hover_data=param_name,\n    )\n    line_fig = px.line(\n        cv_results,\n        x=\"mean_score_time\",\n        y=\"mean_test_score\",\n    )\n\n    scatter_trace = scatter_fig[\"data\"][0]\n    line_trace = line_fig[\"data\"][0]\n    scatter_trace.update(marker=dict(color=colors_list[idx]))\n    line_trace.update(line=dict(color=colors_list[idx]))\n    fig.add_trace(scatter_trace, row=1, col=2)\n    fig.add_trace(line_trace, row=1, col=2)\n\nfig.update_layout(\n    xaxis=dict(title=\"Train time (s) - lower is better\"),\n    yaxis=dict(title=\"Test R2 score - higher is better\"),\n    xaxis2=dict(title=\"Predict time (s) - lower is better\"),\n    legend=dict(x=0.72, y=0.05, traceorder=\"normal\", borderwidth=1),\n    title=dict(x=0.5, text=\"Speed-score trade-off of tree-based ensembles\"),\n)"
+        "import plotly.colors as colors\nimport plotly.express as px\nfrom plotly.subplots import make_subplots\n\nfig = make_subplots(\n    rows=1,\n    cols=2,\n    shared_yaxes=True,\n    subplot_titles=[\"Train time vs score\", \"Predict time vs score\"],\n)\nmodel_names = [result[\"model\"] for result in results]\ncolors_list = colors.qualitative.Plotly * (\n    len(model_names) // len(colors.qualitative.Plotly) + 1\n)\n\nfor idx, result in enumerate(results):\n    cv_results = result[\"cv_results\"].round(3)\n    model_name = result[\"model\"]\n    param_name = next(iter(param_grids[model_name].keys()))\n    cv_results[param_name] = cv_results[\"param_\" + param_name]\n    cv_results[\"model\"] = model_name\n\n    scatter_fig = px.scatter(\n        cv_results,\n        x=\"mean_fit_time\",\n        y=\"mean_test_score\",\n        error_x=\"std_fit_time\",\n        error_y=\"std_test_score\",\n        hover_data=param_name,\n        color=\"model\",\n    )\n    line_fig = px.line(\n        cv_results,\n        x=\"mean_fit_time\",\n        y=\"mean_test_score\",\n    )\n\n    scatter_trace = scatter_fig[\"data\"][0]\n    line_trace = line_fig[\"data\"][0]\n    scatter_trace.update(marker=dict(color=colors_list[idx]))\n    line_trace.update(line=dict(color=colors_list[idx]))\n    fig.add_trace(scatter_trace, row=1, col=1)\n    fig.add_trace(line_trace, row=1, col=1)\n\n    scatter_fig = px.scatter(\n        cv_results,\n        x=\"mean_score_time\",\n        y=\"mean_test_score\",\n        error_x=\"std_score_time\",\n        error_y=\"std_test_score\",\n        hover_data=param_name,\n    )\n    line_fig = px.line(\n        cv_results,\n        x=\"mean_score_time\",\n        y=\"mean_test_score\",\n    )\n\n    scatter_trace = scatter_fig[\"data\"][0]\n    line_trace = line_fig[\"data\"][0]\n    scatter_trace.update(marker=dict(color=colors_list[idx]))\n    line_trace.update(line=dict(color=colors_list[idx]))\n    fig.add_trace(scatter_trace, row=1, col=2)\n    fig.add_trace(line_trace, row=1, col=2)\n\nfig.update_layout(\n    xaxis=dict(title=\"Train time (s) - lower is better\"),\n    yaxis=dict(title=\"Test R2 score - higher is better\"),\n    xaxis2=dict(title=\"Predict time (s) - lower is better\"),\n    legend=dict(x=0.72, y=0.05, traceorder=\"normal\", borderwidth=1),\n    title=dict(x=0.5, text=\"Speed-score trade-off of tree-based ensembles\"),\n)"
       ]
     },
     {

dev/_downloads/038d1885eb5f5ea53aca42da3031fe38/plot_document_clustering.zip

@@ -143,7 +143,7 @@
 for idx, result in enumerate(results):
     cv_results = result["cv_results"].round(3)
     model_name = result["model"]
-    param_name = list(param_grids[model_name].keys())[0]
+    param_name = next(iter(param_grids[model_name].keys()))
     cv_results[param_name] = cv_results["param_" + param_name]
     cv_results["model"] = model_name
 

dev/_downloads/03c018a16384c69f3a89e473650d57ee/plot_svm_margin.zip

@@ -230,8 +230,8 @@ def compute_corrected_ttest(differences, df, n_train, n_test):
 
 n = differences.shape[0]  # number of test sets
 df = n - 1
-n_train = len(list(cv.split(X, y))[0][0])
-n_test = len(list(cv.split(X, y))[0][1])
+n_train = len(next(iter(cv.split(X, y)))[0])
+n_test = len(next(iter(cv.split(X, y)))[1])
 
 t_stat, p_val = compute_corrected_ttest(differences, df, n_train, n_test)
 print(f"Corrected t-value: {t_stat:.3f}\nCorrected p-value: {p_val:.3f}")