Pushing the docs to dev/ for branch: main, commit 4b64e3fb64cf4885cc6…

…d552fabea9cf642682963
scikit-learn · Oct 23, 2023 · 942042f · 942042f
1 parent 6636174
commit 942042f
Show file tree

Hide file tree

Showing 1,304 changed files with 5,731 additions and 5,731 deletions.
diff --git a/dev/.buildinfo b/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: affa80f8cb8d5c1c5e087aa5055c7767
+config: 22332a40d68b565d5e7e7c04d5291efe
 tags: 645f666f9bcd5a90fca523b33c5a78b7
diff --git a/dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip b/dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip
diff --git a/dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip b/dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip
diff --git a/dev/_downloads/7012baed63b9a27f121bae611b8285c2/plot_cyclical_feature_engineering.ipynb b/dev/_downloads/7012baed63b9a27f121bae611b8285c2/plot_cyclical_feature_engineering.ipynb
@@ -275,7 +275,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "All is well. We are now ready to do some predictive modeling!\n\n## Gradient Boosting\n\nGradient Boosting Regression with decision trees is often flexible enough to\nefficiently handle heteorogenous tabular data with a mix of categorical and\nnumerical features as long as the number of samples is large enough.\n\nHere, we use the modern\n:class:`~sklearn.ensemble.HistGradientBoostingRegressor` with native support\nfor categorical features. Therefore, we only do minimal ordinal encoding for\nthe categorical variables and then\nlet the model know that it should treat those as categorical variables by\nusing a dedicated tree splitting rule. Since we use an ordinal encoder, we\npass the list of categorical values explicitly to use a logical order when\nencoding the categories as integers instead of the lexicographical order.\nThis also has the added benefit of preventing any issue with unknown\ncategories when using cross-validation.\n\nThe numerical variables need no preprocessing and, for the sake of simplicity,\nwe only try the default hyper-parameters for this model:\n\n"
+        "All is well. We are now ready to do some predictive modeling!\n\n## Gradient Boosting\n\nGradient Boosting Regression with decision trees is often flexible enough to\nefficiently handle heterogenous tabular data with a mix of categorical and\nnumerical features as long as the number of samples is large enough.\n\nHere, we use the modern\n:class:`~sklearn.ensemble.HistGradientBoostingRegressor` with native support\nfor categorical features. Therefore, we only do minimal ordinal encoding for\nthe categorical variables and then\nlet the model know that it should treat those as categorical variables by\nusing a dedicated tree splitting rule. Since we use an ordinal encoder, we\npass the list of categorical values explicitly to use a logical order when\nencoding the categories as integers instead of the lexicographical order.\nThis also has the added benefit of preventing any issue with unknown\ncategories when using cross-validation.\n\nThe numerical variables need no preprocessing and, for the sake of simplicity,\nwe only try the default hyper-parameters for this model:\n\n"
       ]
     },
     {
@@ -682,7 +682,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "First, note that trees can naturally model non-linear feature interactions\nsince, by default, decision trees are allowed to grow beyond a depth of 2\nlevels.\n\nHere, we can observe that the combinations of spline features and non-linear\nkernels works quite well and can almost rival the accuracy of the gradient\nboosting regression trees.\n\nOn the contrary, one-hot encoded time features do not perform that well with\nthe low rank kernel model. In particular, they significantly over-estimate\nthe low demand hours more than the competing models.\n\nWe also observe that none of the models can successfully predict some of the\npeak rentals at the rush hours during the working days. It is possible that\naccess to additional features would be required to further improve the\naccuracy of the predictions. For instance, it could be useful to have access\nto the geographical repartition of the fleet at any point in time or the\nfraction of bikes that are immobilized because they need servicing.\n\nLet us finally get a more quantative look at the prediction errors of those\nthree models using the true vs predicted demand scatter plots:\n\n"
+        "First, note that trees can naturally model non-linear feature interactions\nsince, by default, decision trees are allowed to grow beyond a depth of 2\nlevels.\n\nHere, we can observe that the combinations of spline features and non-linear\nkernels works quite well and can almost rival the accuracy of the gradient\nboosting regression trees.\n\nOn the contrary, one-hot encoded time features do not perform that well with\nthe low rank kernel model. In particular, they significantly over-estimate\nthe low demand hours more than the competing models.\n\nWe also observe that none of the models can successfully predict some of the\npeak rentals at the rush hours during the working days. It is possible that\naccess to additional features would be required to further improve the\naccuracy of the predictions. For instance, it could be useful to have access\nto the geographical repartition of the fleet at any point in time or the\nfraction of bikes that are immobilized because they need servicing.\n\nLet us finally get a more quantitative look at the prediction errors of those\nthree models using the true vs predicted demand scatter plots:\n\n"
       ]
     },
     {

diff --git a/dev/_downloads/9fcbbc59ab27a20d07e209a711ac4f50/plot_cyclical_feature_engineering.py b/dev/_downloads/9fcbbc59ab27a20d07e209a711ac4f50/plot_cyclical_feature_engineering.py
@@ -167,7 +167,7 @@
 # -----------------
 #
 # Gradient Boosting Regression with decision trees is often flexible enough to
-# efficiently handle heteorogenous tabular data with a mix of categorical and
+# efficiently handle heterogenous tabular data with a mix of categorical and
 # numerical features as long as the number of samples is large enough.
 #
 # Here, we use the modern
@@ -795,7 +795,7 @@ def periodic_spline_transformer(period, n_splines=None, degree=3):
 # to the geographical repartition of the fleet at any point in time or the
 # fraction of bikes that are immobilized because they need servicing.
 #
-# Let us finally get a more quantative look at the prediction errors of those
+# Let us finally get a more quantitative look at the prediction errors of those
 # three models using the true vs predicted demand scatter plots:
 from sklearn.metrics import PredictionErrorDisplay
 

diff --git a/dev/_downloads/scikit-learn-docs.zip b/dev/_downloads/scikit-learn-docs.zip
diff --git a/dev/_images/sphx_glr_plot_agglomerative_clustering_001.png b/dev/_images/sphx_glr_plot_agglomerative_clustering_001.png
diff --git a/dev/_images/sphx_glr_plot_agglomerative_clustering_002.png b/dev/_images/sphx_glr_plot_agglomerative_clustering_002.png
diff --git a/dev/_images/sphx_glr_plot_agglomerative_clustering_003.png b/dev/_images/sphx_glr_plot_agglomerative_clustering_003.png
diff --git a/dev/_images/sphx_glr_plot_agglomerative_clustering_004.png b/dev/_images/sphx_glr_plot_agglomerative_clustering_004.png
diff --git a/dev/_images/sphx_glr_plot_agglomerative_clustering_thumb.png b/dev/_images/sphx_glr_plot_agglomerative_clustering_thumb.png
diff --git a/dev/_images/sphx_glr_plot_anomaly_comparison_001.png b/dev/_images/sphx_glr_plot_anomaly_comparison_001.png
diff --git a/dev/_images/sphx_glr_plot_anomaly_comparison_thumb.png b/dev/_images/sphx_glr_plot_anomaly_comparison_thumb.png
diff --git a/dev/_images/sphx_glr_plot_caching_nearest_neighbors_001.png b/dev/_images/sphx_glr_plot_caching_nearest_neighbors_001.png
diff --git a/dev/_images/sphx_glr_plot_caching_nearest_neighbors_thumb.png b/dev/_images/sphx_glr_plot_caching_nearest_neighbors_thumb.png
diff --git a/dev/_images/sphx_glr_plot_cluster_comparison_001.png b/dev/_images/sphx_glr_plot_cluster_comparison_001.png
diff --git a/dev/_images/sphx_glr_plot_cluster_comparison_thumb.png b/dev/_images/sphx_glr_plot_cluster_comparison_thumb.png
diff --git a/dev/_images/sphx_glr_plot_coin_segmentation_001.png b/dev/_images/sphx_glr_plot_coin_segmentation_001.png
diff --git a/dev/_images/sphx_glr_plot_coin_segmentation_002.png b/dev/_images/sphx_glr_plot_coin_segmentation_002.png
diff --git a/dev/_images/sphx_glr_plot_coin_segmentation_003.png b/dev/_images/sphx_glr_plot_coin_segmentation_003.png
diff --git a/dev/_images/sphx_glr_plot_coin_segmentation_thumb.png b/dev/_images/sphx_glr_plot_coin_segmentation_thumb.png
diff --git a/dev/_images/sphx_glr_plot_compare_calibration_001.png b/dev/_images/sphx_glr_plot_compare_calibration_001.png
diff --git a/dev/_images/sphx_glr_plot_compare_calibration_thumb.png b/dev/_images/sphx_glr_plot_compare_calibration_thumb.png
diff --git a/dev/_images/sphx_glr_plot_dict_face_patches_001.png b/dev/_images/sphx_glr_plot_dict_face_patches_001.png
diff --git a/dev/_images/sphx_glr_plot_dict_face_patches_thumb.png b/dev/_images/sphx_glr_plot_dict_face_patches_thumb.png
diff --git a/dev/_images/sphx_glr_plot_digits_pipe_001.png b/dev/_images/sphx_glr_plot_digits_pipe_001.png
diff --git a/dev/_images/sphx_glr_plot_digits_pipe_thumb.png b/dev/_images/sphx_glr_plot_digits_pipe_thumb.png
diff --git a/dev/_images/sphx_glr_plot_document_classification_20newsgroups_005.png b/dev/_images/sphx_glr_plot_document_classification_20newsgroups_005.png
diff --git a/dev/_images/sphx_glr_plot_document_classification_20newsgroups_006.png b/dev/_images/sphx_glr_plot_document_classification_20newsgroups_006.png
diff --git a/dev/_images/sphx_glr_plot_document_clustering_001.png b/dev/_images/sphx_glr_plot_document_clustering_001.png
diff --git a/dev/_images/sphx_glr_plot_document_clustering_thumb.png b/dev/_images/sphx_glr_plot_document_clustering_thumb.png
diff --git a/dev/_images/sphx_glr_plot_gmm_init_001.png b/dev/_images/sphx_glr_plot_gmm_init_001.png
diff --git a/dev/_images/sphx_glr_plot_gmm_init_thumb.png b/dev/_images/sphx_glr_plot_gmm_init_thumb.png
diff --git a/dev/_images/sphx_glr_plot_gradient_boosting_categorical_001.png b/dev/_images/sphx_glr_plot_gradient_boosting_categorical_001.png
diff --git a/dev/_images/sphx_glr_plot_gradient_boosting_categorical_002.png b/dev/_images/sphx_glr_plot_gradient_boosting_categorical_002.png
diff --git a/dev/_images/sphx_glr_plot_gradient_boosting_categorical_thumb.png b/dev/_images/sphx_glr_plot_gradient_boosting_categorical_thumb.png
diff --git a/dev/_images/sphx_glr_plot_gradient_boosting_early_stopping_002.png b/dev/_images/sphx_glr_plot_gradient_boosting_early_stopping_002.png
diff --git a/dev/_images/sphx_glr_plot_hashing_vs_dict_vectorizer_001.png b/dev/_images/sphx_glr_plot_hashing_vs_dict_vectorizer_001.png
diff --git a/dev/_images/sphx_glr_plot_hashing_vs_dict_vectorizer_002.png b/dev/_images/sphx_glr_plot_hashing_vs_dict_vectorizer_002.png
diff --git a/dev/_images/sphx_glr_plot_hashing_vs_dict_vectorizer_thumb.png b/dev/_images/sphx_glr_plot_hashing_vs_dict_vectorizer_thumb.png
diff --git a/dev/_images/sphx_glr_plot_image_denoising_002.png b/dev/_images/sphx_glr_plot_image_denoising_002.png
diff --git a/dev/_images/sphx_glr_plot_image_denoising_004.png b/dev/_images/sphx_glr_plot_image_denoising_004.png
diff --git a/dev/_images/sphx_glr_plot_image_denoising_005.png b/dev/_images/sphx_glr_plot_image_denoising_005.png
diff --git a/dev/_images/sphx_glr_plot_kernel_approximation_001.png b/dev/_images/sphx_glr_plot_kernel_approximation_001.png
diff --git a/dev/_images/sphx_glr_plot_kernel_approximation_thumb.png b/dev/_images/sphx_glr_plot_kernel_approximation_thumb.png
diff --git a/dev/_images/sphx_glr_plot_kernel_ridge_regression_001.png b/dev/_images/sphx_glr_plot_kernel_ridge_regression_001.png
diff --git a/dev/_images/sphx_glr_plot_kernel_ridge_regression_002.png b/dev/_images/sphx_glr_plot_kernel_ridge_regression_002.png
diff --git a/dev/_images/sphx_glr_plot_kernel_ridge_regression_thumb.png b/dev/_images/sphx_glr_plot_kernel_ridge_regression_thumb.png
diff --git a/dev/_images/sphx_glr_plot_lasso_model_selection_002.png b/dev/_images/sphx_glr_plot_lasso_model_selection_002.png
diff --git a/dev/_images/sphx_glr_plot_learning_curve_002.png b/dev/_images/sphx_glr_plot_learning_curve_002.png
diff --git a/dev/_images/sphx_glr_plot_learning_curve_003.png b/dev/_images/sphx_glr_plot_learning_curve_003.png
diff --git a/dev/_images/sphx_glr_plot_linear_model_coefficient_interpretation_001.png b/dev/_images/sphx_glr_plot_linear_model_coefficient_interpretation_001.png
diff --git a/dev/_images/sphx_glr_plot_linear_model_coefficient_interpretation_thumb.png b/dev/_images/sphx_glr_plot_linear_model_coefficient_interpretation_thumb.png
diff --git a/dev/_images/sphx_glr_plot_linkage_comparison_001.png b/dev/_images/sphx_glr_plot_linkage_comparison_001.png
diff --git a/dev/_images/sphx_glr_plot_linkage_comparison_thumb.png b/dev/_images/sphx_glr_plot_linkage_comparison_thumb.png
diff --git a/dev/_images/sphx_glr_plot_lle_digits_005.png b/dev/_images/sphx_glr_plot_lle_digits_005.png
diff --git a/dev/_images/sphx_glr_plot_lle_digits_006.png b/dev/_images/sphx_glr_plot_lle_digits_006.png
diff --git a/dev/_images/sphx_glr_plot_lle_digits_007.png b/dev/_images/sphx_glr_plot_lle_digits_007.png
diff --git a/dev/_images/sphx_glr_plot_lle_digits_008.png b/dev/_images/sphx_glr_plot_lle_digits_008.png
diff --git a/dev/_images/sphx_glr_plot_lle_digits_009.png b/dev/_images/sphx_glr_plot_lle_digits_009.png
diff --git a/dev/_images/sphx_glr_plot_lle_digits_010.png b/dev/_images/sphx_glr_plot_lle_digits_010.png
diff --git a/dev/_images/sphx_glr_plot_lle_digits_011.png b/dev/_images/sphx_glr_plot_lle_digits_011.png
diff --git a/dev/_images/sphx_glr_plot_lle_digits_012.png b/dev/_images/sphx_glr_plot_lle_digits_012.png
diff --git a/dev/_images/sphx_glr_plot_lle_digits_013.png b/dev/_images/sphx_glr_plot_lle_digits_013.png
diff --git a/dev/_images/sphx_glr_plot_lle_digits_014.png b/dev/_images/sphx_glr_plot_lle_digits_014.png
diff --git a/dev/_images/sphx_glr_plot_manifold_sphere_001.png b/dev/_images/sphx_glr_plot_manifold_sphere_001.png
diff --git a/dev/_images/sphx_glr_plot_manifold_sphere_thumb.png b/dev/_images/sphx_glr_plot_manifold_sphere_thumb.png
diff --git a/dev/_images/sphx_glr_plot_model_complexity_influence_001.png b/dev/_images/sphx_glr_plot_model_complexity_influence_001.png
diff --git a/dev/_images/sphx_glr_plot_model_complexity_influence_002.png b/dev/_images/sphx_glr_plot_model_complexity_influence_002.png
diff --git a/dev/_images/sphx_glr_plot_model_complexity_influence_003.png b/dev/_images/sphx_glr_plot_model_complexity_influence_003.png
diff --git a/dev/_images/sphx_glr_plot_model_complexity_influence_thumb.png b/dev/_images/sphx_glr_plot_model_complexity_influence_thumb.png
diff --git a/dev/_images/sphx_glr_plot_out_of_core_classification_002.png b/dev/_images/sphx_glr_plot_out_of_core_classification_002.png
diff --git a/dev/_images/sphx_glr_plot_out_of_core_classification_003.png b/dev/_images/sphx_glr_plot_out_of_core_classification_003.png
diff --git a/dev/_images/sphx_glr_plot_out_of_core_classification_004.png b/dev/_images/sphx_glr_plot_out_of_core_classification_004.png
diff --git a/dev/_images/sphx_glr_plot_prediction_latency_001.png b/dev/_images/sphx_glr_plot_prediction_latency_001.png
diff --git a/dev/_images/sphx_glr_plot_prediction_latency_002.png b/dev/_images/sphx_glr_plot_prediction_latency_002.png
diff --git a/dev/_images/sphx_glr_plot_prediction_latency_003.png b/dev/_images/sphx_glr_plot_prediction_latency_003.png
diff --git a/dev/_images/sphx_glr_plot_prediction_latency_004.png b/dev/_images/sphx_glr_plot_prediction_latency_004.png
diff --git a/dev/_images/sphx_glr_plot_prediction_latency_thumb.png b/dev/_images/sphx_glr_plot_prediction_latency_thumb.png
diff --git a/dev/_images/sphx_glr_plot_release_highlights_0_24_0_001.png b/dev/_images/sphx_glr_plot_release_highlights_0_24_0_001.png
diff --git a/dev/_images/sphx_glr_plot_release_highlights_0_24_0_thumb.png b/dev/_images/sphx_glr_plot_release_highlights_0_24_0_thumb.png
diff --git a/dev/_images/sphx_glr_plot_scalable_poly_kernels_001.png b/dev/_images/sphx_glr_plot_scalable_poly_kernels_001.png
diff --git a/dev/_images/sphx_glr_plot_scalable_poly_kernels_thumb.png b/dev/_images/sphx_glr_plot_scalable_poly_kernels_thumb.png
diff --git a/dev/_images/sphx_glr_plot_sgd_early_stopping_002.png b/dev/_images/sphx_glr_plot_sgd_early_stopping_002.png
diff --git a/dev/_images/sphx_glr_plot_sparse_logistic_regression_20newsgroups_001.png b/dev/_images/sphx_glr_plot_sparse_logistic_regression_20newsgroups_001.png
diff --git a/dev/_images/sphx_glr_plot_sparse_logistic_regression_20newsgroups_thumb.png b/dev/_images/sphx_glr_plot_sparse_logistic_regression_20newsgroups_thumb.png
diff --git a/dev/_images/sphx_glr_plot_stack_predictors_001.png b/dev/_images/sphx_glr_plot_stack_predictors_001.png
diff --git a/dev/_images/sphx_glr_plot_stack_predictors_thumb.png b/dev/_images/sphx_glr_plot_stack_predictors_thumb.png
diff --git a/dev/_images/sphx_glr_plot_successive_halving_heatmap_001.png b/dev/_images/sphx_glr_plot_successive_halving_heatmap_001.png
diff --git a/dev/_images/sphx_glr_plot_successive_halving_heatmap_thumb.png b/dev/_images/sphx_glr_plot_successive_halving_heatmap_thumb.png
diff --git a/dev/_images/sphx_glr_plot_svm_scale_c_001.png b/dev/_images/sphx_glr_plot_svm_scale_c_001.png
diff --git a/dev/_images/sphx_glr_plot_svm_scale_c_thumb.png b/dev/_images/sphx_glr_plot_svm_scale_c_thumb.png
diff --git a/dev/_images/sphx_glr_plot_theilsen_001.png b/dev/_images/sphx_glr_plot_theilsen_001.png
diff --git a/dev/_images/sphx_glr_plot_theilsen_002.png b/dev/_images/sphx_glr_plot_theilsen_002.png
diff --git a/dev/_images/sphx_glr_plot_theilsen_thumb.png b/dev/_images/sphx_glr_plot_theilsen_thumb.png
diff --git a/dev/_sources/auto_examples/applications/plot_cyclical_feature_engineering.rst.txt b/dev/_sources/auto_examples/applications/plot_cyclical_feature_engineering.rst.txt
@@ -1469,7 +1469,7 @@ Gradient Boosting
 -----------------
 
 Gradient Boosting Regression with decision trees is often flexible enough to
-efficiently handle heteorogenous tabular data with a mix of categorical and
+efficiently handle heterogenous tabular data with a mix of categorical and
 numerical features as long as the number of samples is large enough.
 
 Here, we use the modern
@@ -2489,7 +2489,7 @@ accuracy of the predictions. For instance, it could be useful to have access
 to the geographical repartition of the fleet at any point in time or the
 fraction of bikes that are immobilized because they need servicing.
 
-Let us finally get a more quantative look at the prediction errors of those
+Let us finally get a more quantitative look at the prediction errors of those
 three models using the true vs predicted demand scatter plots:
 
 .. GENERATED FROM PYTHON SOURCE LINES 800-835
@@ -2585,7 +2585,7 @@ instead of `RidgeCV`.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 14.684 seconds)
+   **Total running time of the script:** (0 minutes 14.747 seconds)
 
 
 .. _sphx_glr_download_auto_examples_applications_plot_cyclical_feature_engineering.py:

diff --git a/dev/_sources/auto_examples/applications/plot_digits_denoising.rst.txt b/dev/_sources/auto_examples/applications/plot_digits_denoising.rst.txt
@@ -312,7 +312,7 @@ will depend of the parameters `n_components`, `gamma`, and `alpha`.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 7.966 seconds)
+   **Total running time of the script:** (0 minutes 8.540 seconds)
 
 
 .. _sphx_glr_download_auto_examples_applications_plot_digits_denoising.py:

diff --git a/dev/_sources/auto_examples/applications/plot_face_recognition.rst.txt b/dev/_sources/auto_examples/applications/plot_face_recognition.rst.txt
@@ -159,7 +159,7 @@ dataset): unsupervised feature extraction / dimensionality reduction
  .. code-block:: none
 
     Extracting the top 150 eigenfaces from 966 faces
-    done in 0.078s
+    done in 0.070s
     Projecting the input data on the eigenfaces orthonormal basis
     done in 0.008s
 
@@ -199,7 +199,7 @@ Train a SVM classification model
  .. code-block:: none
 
     Fitting the classifier to the training set
-    done in 5.535s
+    done in 5.300s
     Best estimator found by grid search:
     SVC(C=76823.03433306456, class_weight='balanced', gamma=0.0034189458230957995)
 
@@ -242,7 +242,7 @@ Quantitative evaluation of the model quality on the test set
  .. code-block:: none
 
     Predicting people's names on the test set
-    done in 0.046s
+    done in 0.045s
                        precision    recall  f1-score   support
 
          Ariel Sharon       0.75      0.69      0.72        13
@@ -359,7 +359,7 @@ tensorflow to implement such models.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 6.371 seconds)
+   **Total running time of the script:** (0 minutes 6.290 seconds)
 
 
 .. _sphx_glr_download_auto_examples_applications_plot_face_recognition.py:

diff --git a/dev/_sources/auto_examples/applications/plot_model_complexity_influence.rst.txt b/dev/_sources/auto_examples/applications/plot_model_complexity_influence.rst.txt
@@ -388,49 +388,49 @@ ensemble is not as detrimental.
 
     Benchmarking SGDClassifier(alpha=0.001, l1_ratio=0.25, loss='modified_huber',
                   n_iter_no_change=2, penalty='elasticnet', tol=0.1)
-    Complexity: 4948 | Hamming Loss (Misclassification Ratio): 0.2675 | Pred. Time: 0.059541s
+    Complexity: 4948 | Hamming Loss (Misclassification Ratio): 0.2675 | Pred. Time: 0.060755s
 
     Benchmarking SGDClassifier(alpha=0.001, l1_ratio=0.5, loss='modified_huber',
                   n_iter_no_change=2, penalty='elasticnet', tol=0.1)
-    Complexity: 1847 | Hamming Loss (Misclassification Ratio): 0.3264 | Pred. Time: 0.045062s
+    Complexity: 1847 | Hamming Loss (Misclassification Ratio): 0.3264 | Pred. Time: 0.045140s
 
     Benchmarking SGDClassifier(alpha=0.001, l1_ratio=0.75, loss='modified_huber',
                   n_iter_no_change=2, penalty='elasticnet', tol=0.1)
-    Complexity: 997 | Hamming Loss (Misclassification Ratio): 0.3383 | Pred. Time: 0.037325s
+    Complexity: 997 | Hamming Loss (Misclassification Ratio): 0.3383 | Pred. Time: 0.038667s
 
     Benchmarking SGDClassifier(alpha=0.001, l1_ratio=0.9, loss='modified_huber',
                   n_iter_no_change=2, penalty='elasticnet', tol=0.1)
-    Complexity: 802 | Hamming Loss (Misclassification Ratio): 0.3582 | Pred. Time: 0.034283s
+    Complexity: 802 | Hamming Loss (Misclassification Ratio): 0.3582 | Pred. Time: 0.034703s
 
     Benchmarking NuSVR(C=1000.0, gamma=3.0517578125e-05, nu=0.05)
-    Complexity: 18 | MSE: 5558.7313 | Pred. Time: 0.000179s
+    Complexity: 18 | MSE: 5558.7313 | Pred. Time: 0.000183s
 
     Benchmarking NuSVR(C=1000.0, gamma=3.0517578125e-05, nu=0.1)
-    Complexity: 36 | MSE: 5289.8022 | Pred. Time: 0.000257s
+    Complexity: 36 | MSE: 5289.8022 | Pred. Time: 0.000262s
 
     Benchmarking NuSVR(C=1000.0, gamma=3.0517578125e-05, nu=0.2)
-    Complexity: 72 | MSE: 5193.8353 | Pred. Time: 0.000417s
+    Complexity: 72 | MSE: 5193.8353 | Pred. Time: 0.000419s
 
     Benchmarking NuSVR(C=1000.0, gamma=3.0517578125e-05, nu=0.35)
-    Complexity: 124 | MSE: 5131.3279 | Pred. Time: 0.000647s
+    Complexity: 124 | MSE: 5131.3279 | Pred. Time: 0.000666s
 
     Benchmarking NuSVR(C=1000.0, gamma=3.0517578125e-05)
-    Complexity: 178 | MSE: 5149.0779 | Pred. Time: 0.000878s
+    Complexity: 178 | MSE: 5149.0779 | Pred. Time: 0.000915s
 
     Benchmarking GradientBoostingRegressor(learning_rate=0.05, max_depth=2, n_estimators=10)
-    Complexity: 10 | MSE: 4066.4812 | Pred. Time: 0.000169s
+    Complexity: 10 | MSE: 4066.4812 | Pred. Time: 0.000167s
 
     Benchmarking GradientBoostingRegressor(learning_rate=0.05, max_depth=2, n_estimators=25)
-    Complexity: 25 | MSE: 3551.1723 | Pred. Time: 0.000192s
+    Complexity: 25 | MSE: 3551.1723 | Pred. Time: 0.000194s
 
     Benchmarking GradientBoostingRegressor(learning_rate=0.05, max_depth=2, n_estimators=50)
-    Complexity: 50 | MSE: 3445.2171 | Pred. Time: 0.000229s
+    Complexity: 50 | MSE: 3445.2171 | Pred. Time: 0.000230s
 
     Benchmarking GradientBoostingRegressor(learning_rate=0.05, max_depth=2, n_estimators=75)
-    Complexity: 75 | MSE: 3433.0358 | Pred. Time: 0.000265s
+    Complexity: 75 | MSE: 3433.0358 | Pred. Time: 0.000258s
 
     Benchmarking GradientBoostingRegressor(learning_rate=0.05, max_depth=2)
-    Complexity: 100 | MSE: 3456.0602 | Pred. Time: 0.000297s
+    Complexity: 100 | MSE: 3456.0602 | Pred. Time: 0.000293s
 
 
 
@@ -453,7 +453,7 @@ under-fitting or over-fitting.
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 5.261 seconds)
+   **Total running time of the script:** (0 minutes 5.277 seconds)
 
 
 .. _sphx_glr_download_auto_examples_applications_plot_model_complexity_influence.py: