Pushing the docs to dev/ for branch: main, commit 17345f9d97828f977e5039db455828cfab10836a

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -178,7 +178,7 @@
       },
       "outputs": [],
       "source": [
-        "import time\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import cross_validate, cross_val_predict\n\n\ndef plot_regression_results(ax, y_true, y_pred, title, scores, elapsed_time):\n    \"\"\"Scatter plot of the predicted vs true targets.\"\"\"\n    ax.plot(\n        [y_true.min(), y_true.max()], [y_true.min(), y_true.max()], \"--r\", linewidth=2\n    )\n    ax.scatter(y_true, y_pred, alpha=0.2)\n\n    ax.spines[\"top\"].set_visible(False)\n    ax.spines[\"right\"].set_visible(False)\n    ax.get_xaxis().tick_bottom()\n    ax.get_yaxis().tick_left()\n    ax.spines[\"left\"].set_position((\"outward\", 10))\n    ax.spines[\"bottom\"].set_position((\"outward\", 10))\n    ax.set_xlim([y_true.min(), y_true.max()])\n    ax.set_ylim([y_true.min(), y_true.max()])\n    ax.set_xlabel(\"Measured\")\n    ax.set_ylabel(\"Predicted\")\n    extra = plt.Rectangle(\n        (0, 0), 0, 0, fc=\"w\", fill=False, edgecolor=\"none\", linewidth=0\n    )\n    ax.legend([extra], [scores], loc=\"upper left\")\n    title = title + \"\\n Evaluation in {:.2f} seconds\".format(elapsed_time)\n    ax.set_title(title)\n\n\nfig, axs = plt.subplots(2, 2, figsize=(9, 7))\naxs = np.ravel(axs)\n\nfor ax, (name, est) in zip(\n    axs, estimators + [(\"Stacking Regressor\", stacking_regressor)]\n):\n    start_time = time.time()\n    score = cross_validate(\n        est, X, y, scoring=[\"r2\", \"neg_mean_absolute_error\"], n_jobs=-1, verbose=0\n    )\n    elapsed_time = time.time() - start_time\n\n    y_pred = cross_val_predict(est, X, y, n_jobs=-1, verbose=0)\n\n    plot_regression_results(\n        ax,\n        y,\n        y_pred,\n        name,\n        (r\"$R^2={:.2f} \\pm {:.2f}$\" + \"\\n\" + r\"$MAE={:.2f} \\pm {:.2f}$\").format(\n            np.mean(score[\"test_r2\"]),\n            np.std(score[\"test_r2\"]),\n            -np.mean(score[\"test_neg_mean_absolute_error\"]),\n            np.std(score[\"test_neg_mean_absolute_error\"]),\n        ),\n        elapsed_time,\n    )\n\nplt.suptitle(\"Single predictors versus stacked predictors\")\nplt.tight_layout()\nplt.subplots_adjust(top=0.9)\nplt.show()"
+        "import time\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import cross_validate, cross_val_predict\n\n\ndef plot_regression_results(ax, y_true, y_pred, title, scores, elapsed_time):\n    \"\"\"Scatter plot of the predicted vs true targets.\"\"\"\n    ax.plot(\n        [y_true.min(), y_true.max()], [y_true.min(), y_true.max()], \"--r\", linewidth=2\n    )\n    ax.scatter(y_true, y_pred, alpha=0.2)\n\n    ax.spines[\"top\"].set_visible(False)\n    ax.spines[\"right\"].set_visible(False)\n    ax.get_xaxis().tick_bottom()\n    ax.get_yaxis().tick_left()\n    ax.spines[\"left\"].set_position((\"outward\", 10))\n    ax.spines[\"bottom\"].set_position((\"outward\", 10))\n    ax.set_xlim([y_true.min(), y_true.max()])\n    ax.set_ylim([y_true.min(), y_true.max()])\n    ax.set_xlabel(\"Measured\")\n    ax.set_ylabel(\"Predicted\")\n    extra = plt.Rectangle(\n        (0, 0), 0, 0, fc=\"w\", fill=False, edgecolor=\"none\", linewidth=0\n    )\n    ax.legend([extra], [scores], loc=\"upper left\")\n    title = title + \"\\n Evaluation in {:.2f} seconds\".format(elapsed_time)\n    ax.set_title(title)\n\n\nfig, axs = plt.subplots(2, 2, figsize=(9, 7))\naxs = np.ravel(axs)\n\nfor ax, (name, est) in zip(\n    axs, estimators + [(\"Stacking Regressor\", stacking_regressor)]\n):\n    start_time = time.time()\n    score = cross_validate(\n        est, X, y, scoring=[\"r2\", \"neg_mean_absolute_error\"], n_jobs=2, verbose=0\n    )\n    elapsed_time = time.time() - start_time\n\n    y_pred = cross_val_predict(est, X, y, n_jobs=2, verbose=0)\n\n    plot_regression_results(\n        ax,\n        y,\n        y_pred,\n        name,\n        (r\"$R^2={:.2f} \\pm {:.2f}$\" + \"\\n\" + r\"$MAE={:.2f} \\pm {:.2f}$\").format(\n            np.mean(score[\"test_r2\"]),\n            np.std(score[\"test_r2\"]),\n            -np.mean(score[\"test_neg_mean_absolute_error\"]),\n            np.std(score[\"test_neg_mean_absolute_error\"]),\n        ),\n        elapsed_time,\n    )\n\nplt.suptitle(\"Single predictors versus stacked predictors\")\nplt.tight_layout()\nplt.subplots_adjust(top=0.9)\nplt.show()"
       ]
     },
     {

dev/_downloads/3c9b7bcd0b16f172ac12ffad61f3b5f0/plot_stack_predictors.ipynb

@@ -106,7 +106,7 @@
 feature_names = np.array([f"x_{i}" for i in range(X.shape[1])])
 
 rf = RandomForestClassifier(random_state=0).fit(X, y)
-result = permutation_importance(rf, X, y, n_repeats=10, random_state=0, n_jobs=-1)
+result = permutation_importance(rf, X, y, n_repeats=10, random_state=0, n_jobs=2)
 
 fig, ax = plt.subplots()
 sorted_idx = result.importances_mean.argsort()

dev/_downloads/50040ae12dd16e7d2e79135d7793c17e/plot_release_highlights_0_22_0.py

@@ -311,7 +311,7 @@
     y,
     cv=RepeatedKFold(n_splits=5, n_repeats=5),
     return_estimator=True,
-    n_jobs=-1,
+    n_jobs=2,
 )
 coefs = pd.DataFrame(
     [
@@ -366,7 +366,7 @@
     y,
     cv=RepeatedKFold(n_splits=5, n_repeats=5),
     return_estimator=True,
-    n_jobs=-1,
+    n_jobs=2,
 )
 coefs = pd.DataFrame(
     [
@@ -465,7 +465,7 @@
     y,
     cv=RepeatedKFold(n_splits=5, n_repeats=5),
     return_estimator=True,
-    n_jobs=-1,
+    n_jobs=2,
 )
 coefs = pd.DataFrame(
     [
@@ -571,7 +571,7 @@
     y,
     cv=RepeatedKFold(n_splits=5, n_repeats=5),
     return_estimator=True,
-    n_jobs=-1,
+    n_jobs=2,
 )
 coefs = pd.DataFrame(
     [

dev/_downloads/521b554adefca348463adbbe047d7e99/plot_linear_model_coefficient_interpretation.py

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Code source: Ga\u00ebl Varoquaux\n# Modified for documentation by Jaques Grobler\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport pandas as pd\n\nfrom sklearn import datasets\nfrom sklearn.decomposition import PCA\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.model_selection import GridSearchCV\n\n\n# Define a pipeline to search for the best combination of PCA truncation\n# and classifier regularization.\npca = PCA()\n# set the tolerance to a large value to make the example faster\nlogistic = LogisticRegression(max_iter=10000, tol=0.1)\npipe = Pipeline(steps=[(\"pca\", pca), (\"logistic\", logistic)])\n\nX_digits, y_digits = datasets.load_digits(return_X_y=True)\n\n# Parameters of pipelines can be set using \u2018__\u2019 separated parameter names:\nparam_grid = {\n    \"pca__n_components\": [5, 15, 30, 45, 64],\n    \"logistic__C\": np.logspace(-4, 4, 4),\n}\nsearch = GridSearchCV(pipe, param_grid, n_jobs=-1)\nsearch.fit(X_digits, y_digits)\nprint(\"Best parameter (CV score=%0.3f):\" % search.best_score_)\nprint(search.best_params_)\n\n# Plot the PCA spectrum\npca.fit(X_digits)\n\nfig, (ax0, ax1) = plt.subplots(nrows=2, sharex=True, figsize=(6, 6))\nax0.plot(\n    np.arange(1, pca.n_components_ + 1), pca.explained_variance_ratio_, \"+\", linewidth=2\n)\nax0.set_ylabel(\"PCA explained variance ratio\")\n\nax0.axvline(\n    search.best_estimator_.named_steps[\"pca\"].n_components,\n    linestyle=\":\",\n    label=\"n_components chosen\",\n)\nax0.legend(prop=dict(size=12))\n\n# For each number of components, find the best classifier results\nresults = pd.DataFrame(search.cv_results_)\ncomponents_col = \"param_pca__n_components\"\nbest_clfs = results.groupby(components_col).apply(\n    lambda g: g.nlargest(1, \"mean_test_score\")\n)\n\nbest_clfs.plot(\n    x=components_col, y=\"mean_test_score\", yerr=\"std_test_score\", legend=False, ax=ax1\n)\nax1.set_ylabel(\"Classification accuracy (val)\")\nax1.set_xlabel(\"n_components\")\n\nplt.xlim(-1, 70)\n\nplt.tight_layout()\nplt.show()"
+        "# Code source: Ga\u00ebl Varoquaux\n# Modified for documentation by Jaques Grobler\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport pandas as pd\n\nfrom sklearn import datasets\nfrom sklearn.decomposition import PCA\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.model_selection import GridSearchCV\n\n\n# Define a pipeline to search for the best combination of PCA truncation\n# and classifier regularization.\npca = PCA()\n# set the tolerance to a large value to make the example faster\nlogistic = LogisticRegression(max_iter=10000, tol=0.1)\npipe = Pipeline(steps=[(\"pca\", pca), (\"logistic\", logistic)])\n\nX_digits, y_digits = datasets.load_digits(return_X_y=True)\n\n# Parameters of pipelines can be set using \u2018__\u2019 separated parameter names:\nparam_grid = {\n    \"pca__n_components\": [5, 15, 30, 45, 64],\n    \"logistic__C\": np.logspace(-4, 4, 4),\n}\nsearch = GridSearchCV(pipe, param_grid, n_jobs=2)\nsearch.fit(X_digits, y_digits)\nprint(\"Best parameter (CV score=%0.3f):\" % search.best_score_)\nprint(search.best_params_)\n\n# Plot the PCA spectrum\npca.fit(X_digits)\n\nfig, (ax0, ax1) = plt.subplots(nrows=2, sharex=True, figsize=(6, 6))\nax0.plot(\n    np.arange(1, pca.n_components_ + 1), pca.explained_variance_ratio_, \"+\", linewidth=2\n)\nax0.set_ylabel(\"PCA explained variance ratio\")\n\nax0.axvline(\n    search.best_estimator_.named_steps[\"pca\"].n_components,\n    linestyle=\":\",\n    label=\"n_components chosen\",\n)\nax0.legend(prop=dict(size=12))\n\n# For each number of components, find the best classifier results\nresults = pd.DataFrame(search.cv_results_)\ncomponents_col = \"param_pca__n_components\"\nbest_clfs = results.groupby(components_col).apply(\n    lambda g: g.nlargest(1, \"mean_test_score\")\n)\n\nbest_clfs.plot(\n    x=components_col, y=\"mean_test_score\", yerr=\"std_test_score\", legend=False, ax=ax1\n)\nax1.set_ylabel(\"Classification accuracy (val)\")\nax1.set_xlabel(\"n_components\")\n\nplt.xlim(-1, 70)\n\nplt.tight_layout()\nplt.show()"
       ]
     }
   ],

dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -40,7 +40,7 @@
     "pca__n_components": [5, 15, 30, 45, 64],
     "logistic__C": np.logspace(-4, 4, 4),
 }
-search = GridSearchCV(pipe, param_grid, n_jobs=-1)
+search = GridSearchCV(pipe, param_grid, n_jobs=2)
 search.fit(X_digits, y_digits)
 print("Best parameter (CV score=%0.3f):" % search.best_score_)
 print(search.best_params_)

dev/_downloads/898b30acf62919d918478efbe526195f/plot_digits_pipe.ipynb

@@ -249,11 +249,11 @@ def plot_regression_results(ax, y_true, y_pred, title, scores, elapsed_time):
 ):
     start_time = time.time()
     score = cross_validate(
-        est, X, y, scoring=["r2", "neg_mean_absolute_error"], n_jobs=-1, verbose=0
+        est, X, y, scoring=["r2", "neg_mean_absolute_error"], n_jobs=2, verbose=0
     )
     elapsed_time = time.time() - start_time
 
-    y_pred = cross_val_predict(est, X, y, n_jobs=-1, verbose=0)
+    y_pred = cross_val_predict(est, X, y, n_jobs=2, verbose=0)
 
     plot_regression_results(
         ax,

dev/_downloads/ba89a400c6902f85c10199ff86947d23/plot_digits_pipe.py

@@ -314,7 +314,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.model_selection import cross_validate\nfrom sklearn.model_selection import RepeatedKFold\n\ncv_model = cross_validate(\n    model,\n    X,\n    y,\n    cv=RepeatedKFold(n_splits=5, n_repeats=5),\n    return_estimator=True,\n    n_jobs=-1,\n)\ncoefs = pd.DataFrame(\n    [\n        est.named_steps[\"transformedtargetregressor\"].regressor_.coef_\n        * X_train_preprocessed.std(axis=0)\n        for est in cv_model[\"estimator\"]\n    ],\n    columns=feature_names,\n)\nplt.figure(figsize=(9, 7))\nsns.stripplot(data=coefs, orient=\"h\", color=\"k\", alpha=0.5)\nsns.boxplot(data=coefs, orient=\"h\", color=\"cyan\", saturation=0.5)\nplt.axvline(x=0, color=\".5\")\nplt.xlabel(\"Coefficient importance\")\nplt.title(\"Coefficient importance and its variability\")\nplt.subplots_adjust(left=0.3)"
+        "from sklearn.model_selection import cross_validate\nfrom sklearn.model_selection import RepeatedKFold\n\ncv_model = cross_validate(\n    model,\n    X,\n    y,\n    cv=RepeatedKFold(n_splits=5, n_repeats=5),\n    return_estimator=True,\n    n_jobs=2,\n)\ncoefs = pd.DataFrame(\n    [\n        est.named_steps[\"transformedtargetregressor\"].regressor_.coef_\n        * X_train_preprocessed.std(axis=0)\n        for est in cv_model[\"estimator\"]\n    ],\n    columns=feature_names,\n)\nplt.figure(figsize=(9, 7))\nsns.stripplot(data=coefs, orient=\"h\", color=\"k\", alpha=0.5)\nsns.boxplot(data=coefs, orient=\"h\", color=\"cyan\", saturation=0.5)\nplt.axvline(x=0, color=\".5\")\nplt.xlabel(\"Coefficient importance\")\nplt.title(\"Coefficient importance and its variability\")\nplt.subplots_adjust(left=0.3)"
       ]
     },
     {
@@ -350,7 +350,7 @@
       },
       "outputs": [],
       "source": [
-        "column_to_drop = [\"AGE\"]\n\ncv_model = cross_validate(\n    model,\n    X.drop(columns=column_to_drop),\n    y,\n    cv=RepeatedKFold(n_splits=5, n_repeats=5),\n    return_estimator=True,\n    n_jobs=-1,\n)\ncoefs = pd.DataFrame(\n    [\n        est.named_steps[\"transformedtargetregressor\"].regressor_.coef_\n        * X_train_preprocessed.drop(columns=column_to_drop).std(axis=0)\n        for est in cv_model[\"estimator\"]\n    ],\n    columns=feature_names[:-1],\n)\nplt.figure(figsize=(9, 7))\nsns.stripplot(data=coefs, orient=\"h\", color=\"k\", alpha=0.5)\nsns.boxplot(data=coefs, orient=\"h\", color=\"cyan\", saturation=0.5)\nplt.axvline(x=0, color=\".5\")\nplt.title(\"Coefficient importance and its variability\")\nplt.xlabel(\"Coefficient importance\")\nplt.subplots_adjust(left=0.3)"
+        "column_to_drop = [\"AGE\"]\n\ncv_model = cross_validate(\n    model,\n    X.drop(columns=column_to_drop),\n    y,\n    cv=RepeatedKFold(n_splits=5, n_repeats=5),\n    return_estimator=True,\n    n_jobs=2,\n)\ncoefs = pd.DataFrame(\n    [\n        est.named_steps[\"transformedtargetregressor\"].regressor_.coef_\n        * X_train_preprocessed.drop(columns=column_to_drop).std(axis=0)\n        for est in cv_model[\"estimator\"]\n    ],\n    columns=feature_names[:-1],\n)\nplt.figure(figsize=(9, 7))\nsns.stripplot(data=coefs, orient=\"h\", color=\"k\", alpha=0.5)\nsns.boxplot(data=coefs, orient=\"h\", color=\"cyan\", saturation=0.5)\nplt.axvline(x=0, color=\".5\")\nplt.title(\"Coefficient importance and its variability\")\nplt.xlabel(\"Coefficient importance\")\nplt.subplots_adjust(left=0.3)"
       ]
     },
     {
@@ -440,7 +440,7 @@
       },
       "outputs": [],
       "source": [
-        "cv_model = cross_validate(\n    model,\n    X,\n    y,\n    cv=RepeatedKFold(n_splits=5, n_repeats=5),\n    return_estimator=True,\n    n_jobs=-1,\n)\ncoefs = pd.DataFrame(\n    [\n        est.named_steps[\"transformedtargetregressor\"].regressor_.coef_\n        for est in cv_model[\"estimator\"]\n    ],\n    columns=feature_names,\n)\nplt.figure(figsize=(9, 7))\nsns.stripplot(data=coefs, orient=\"h\", color=\"k\", alpha=0.5)\nsns.boxplot(data=coefs, orient=\"h\", color=\"cyan\", saturation=0.5)\nplt.axvline(x=0, color=\".5\")\nplt.title(\"Coefficient variability\")\nplt.subplots_adjust(left=0.3)"
+        "cv_model = cross_validate(\n    model,\n    X,\n    y,\n    cv=RepeatedKFold(n_splits=5, n_repeats=5),\n    return_estimator=True,\n    n_jobs=2,\n)\ncoefs = pd.DataFrame(\n    [\n        est.named_steps[\"transformedtargetregressor\"].regressor_.coef_\n        for est in cv_model[\"estimator\"]\n    ],\n    columns=feature_names,\n)\nplt.figure(figsize=(9, 7))\nsns.stripplot(data=coefs, orient=\"h\", color=\"k\", alpha=0.5)\nsns.boxplot(data=coefs, orient=\"h\", color=\"cyan\", saturation=0.5)\nplt.axvline(x=0, color=\".5\")\nplt.title(\"Coefficient variability\")\nplt.subplots_adjust(left=0.3)"
       ]
     },
     {
@@ -530,7 +530,7 @@
       },
       "outputs": [],
       "source": [
-        "cv_model = cross_validate(\n    model,\n    X,\n    y,\n    cv=RepeatedKFold(n_splits=5, n_repeats=5),\n    return_estimator=True,\n    n_jobs=-1,\n)\ncoefs = pd.DataFrame(\n    [\n        est.named_steps[\"transformedtargetregressor\"].regressor_.coef_\n        * X_train_preprocessed.std(axis=0)\n        for est in cv_model[\"estimator\"]\n    ],\n    columns=feature_names,\n)\n\nplt.ylabel(\"Age coefficient\")\nplt.xlabel(\"Experience coefficient\")\nplt.grid(True)\nplt.xlim(-0.4, 0.5)\nplt.ylim(-0.4, 0.5)\nplt.scatter(coefs[\"AGE\"], coefs[\"EXPERIENCE\"])\n_ = plt.title(\"Co-variations of coefficients for AGE and EXPERIENCE across folds\")"
+        "cv_model = cross_validate(\n    model,\n    X,\n    y,\n    cv=RepeatedKFold(n_splits=5, n_repeats=5),\n    return_estimator=True,\n    n_jobs=2,\n)\ncoefs = pd.DataFrame(\n    [\n        est.named_steps[\"transformedtargetregressor\"].regressor_.coef_\n        * X_train_preprocessed.std(axis=0)\n        for est in cv_model[\"estimator\"]\n    ],\n    columns=feature_names,\n)\n\nplt.ylabel(\"Age coefficient\")\nplt.xlabel(\"Experience coefficient\")\nplt.grid(True)\nplt.xlim(-0.4, 0.5)\nplt.ylim(-0.4, 0.5)\nplt.scatter(coefs[\"AGE\"], coefs[\"EXPERIENCE\"])\n_ = plt.title(\"Co-variations of coefficients for AGE and EXPERIENCE across folds\")"
       ]
     },
     {

dev/_downloads/c6ccb1a9c5f82321f082e9767a2706f3/plot_stack_predictors.py

@@ -69,7 +69,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import make_classification\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.inspection import permutation_importance\n\nX, y = make_classification(random_state=0, n_features=5, n_informative=3)\nfeature_names = np.array([f\"x_{i}\" for i in range(X.shape[1])])\n\nrf = RandomForestClassifier(random_state=0).fit(X, y)\nresult = permutation_importance(rf, X, y, n_repeats=10, random_state=0, n_jobs=-1)\n\nfig, ax = plt.subplots()\nsorted_idx = result.importances_mean.argsort()\nax.boxplot(\n    result.importances[sorted_idx].T, vert=False, labels=feature_names[sorted_idx]\n)\nax.set_title(\"Permutation Importance of each feature\")\nax.set_ylabel(\"Features\")\nfig.tight_layout()\nplt.show()"
+        "import numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import make_classification\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.inspection import permutation_importance\n\nX, y = make_classification(random_state=0, n_features=5, n_informative=3)\nfeature_names = np.array([f\"x_{i}\" for i in range(X.shape[1])])\n\nrf = RandomForestClassifier(random_state=0).fit(X, y)\nresult = permutation_importance(rf, X, y, n_repeats=10, random_state=0, n_jobs=2)\n\nfig, ax = plt.subplots()\nsorted_idx = result.importances_mean.argsort()\nax.boxplot(\n    result.importances[sorted_idx].T, vert=False, labels=feature_names[sorted_idx]\n)\nax.set_title(\"Permutation Importance of each feature\")\nax.set_ylabel(\"Features\")\nfig.tight_layout()\nplt.show()"
       ]
     },
     {