Pushing the docs to dev/ for branch: main, commit 13a179113a61573c45b3e657f1f74f9b106b3f7f

Author: sklearn-ci

Diff for: dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -22,7 +22,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.inspection import permutation_importance\n\n\ndef plot_permutation_importance(clf, X, y, ax):\n    result = permutation_importance(clf, X, y, n_repeats=10, random_state=42, n_jobs=2)\n    perm_sorted_idx = result.importances_mean.argsort()\n\n    ax.boxplot(\n        result.importances[perm_sorted_idx].T,\n        vert=False,\n        labels=X.columns[perm_sorted_idx],\n    )\n    ax.axvline(x=0, color=\"k\", linestyle=\"--\")\n    return ax"
+        "import matplotlib\n\nfrom sklearn.inspection import permutation_importance\nfrom sklearn.utils.fixes import parse_version\n\n\ndef plot_permutation_importance(clf, X, y, ax):\n    result = permutation_importance(clf, X, y, n_repeats=10, random_state=42, n_jobs=2)\n    perm_sorted_idx = result.importances_mean.argsort()\n\n    # `labels` argument in boxplot is deprecated in matplotlib 3.9 and has been\n    # renamed to `tick_labels`. The following code handles this, but as a\n    # scikit-learn user you probably can write simpler code by using `labels=...`\n    # (matplotlib < 3.9) or `tick_labels=...` (matplotlib >= 3.9).\n    tick_labels_parameter_name = (\n        \"tick_labels\"\n        if parse_version(matplotlib.__version__) >= parse_version(\"3.9\")\n        else \"labels\"\n    )\n    tick_labels_dict = {tick_labels_parameter_name: X.columns[perm_sorted_idx]}\n    ax.boxplot(result.importances[perm_sorted_idx].T, vert=False, **tick_labels_dict)\n    ax.axvline(x=0, color=\"k\", linestyle=\"--\")\n    return ax"
       ]
     },
     {

Diff for: dev/_downloads/4941b506cc56c9cec00d40992e2a4207/plot_permutation_importance_multicollinear.ipynb

@@ -34,6 +34,7 @@
 # `plot_confusion_matrix`. Read more about this new API in the
 # :ref:`User Guide <visualizations>`.
 
+import matplotlib
 import matplotlib.pyplot as plt
 
 from sklearn.datasets import make_classification
@@ -43,6 +44,7 @@
 from sklearn.metrics import RocCurveDisplay
 from sklearn.model_selection import train_test_split
 from sklearn.svm import SVC
+from sklearn.utils.fixes import parse_version
 
 X, y = make_classification(random_state=0)
 X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
@@ -117,9 +119,18 @@
 
 fig, ax = plt.subplots()
 sorted_idx = result.importances_mean.argsort()
-ax.boxplot(
-    result.importances[sorted_idx].T, vert=False, labels=feature_names[sorted_idx]
+
+# `labels` argument in boxplot is deprecated in matplotlib 3.9 and has been
+# renamed to `tick_labels`. The following code handles this, but as a
+# scikit-learn user you probably can write simpler code by using `labels=...`
+# (matplotlib < 3.9) or `tick_labels=...` (matplotlib >= 3.9).
+tick_labels_parameter_name = (
+    "tick_labels"
+    if parse_version(matplotlib.__version__) >= parse_version("3.9")
+    else "labels"
 )
+tick_labels_dict = {tick_labels_parameter_name: feature_names[sorted_idx]}
+ax.boxplot(result.importances[sorted_idx].T, vert=False, **tick_labels_dict)
 ax.set_title("Permutation Importance of each feature")
 ax.set_ylabel("Features")
 fig.tight_layout()

Diff for: dev/_downloads/50040ae12dd16e7d2e79135d7793c17e/plot_release_highlights_0_22_0.py

@@ -26,18 +26,27 @@
 # ------------------------------------------------------
 #
 # First, we define a function to ease the plotting:
+import matplotlib
+
 from sklearn.inspection import permutation_importance
+from sklearn.utils.fixes import parse_version
 
 
 def plot_permutation_importance(clf, X, y, ax):
     result = permutation_importance(clf, X, y, n_repeats=10, random_state=42, n_jobs=2)
     perm_sorted_idx = result.importances_mean.argsort()
 
-    ax.boxplot(
-        result.importances[perm_sorted_idx].T,
-        vert=False,
-        labels=X.columns[perm_sorted_idx],
+    # `labels` argument in boxplot is deprecated in matplotlib 3.9 and has been
+    # renamed to `tick_labels`. The following code handles this, but as a
+    # scikit-learn user you probably can write simpler code by using `labels=...`
+    # (matplotlib < 3.9) or `tick_labels=...` (matplotlib >= 3.9).
+    tick_labels_parameter_name = (
+        "tick_labels"
+        if parse_version(matplotlib.__version__) >= parse_version("3.9")
+        else "labels"
     )
+    tick_labels_dict = {tick_labels_parameter_name: X.columns[perm_sorted_idx]}
+    ax.boxplot(result.importances[perm_sorted_idx].T, vert=False, **tick_labels_dict)
     ax.axvline(x=0, color="k", linestyle="--")
     return ax
 

Diff for: dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.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 import datasets, ensemble\nfrom sklearn.inspection import permutation_importance\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.model_selection import train_test_split"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn import datasets, ensemble\nfrom sklearn.inspection import permutation_importance\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.utils.fixes import parse_version"
       ]
     },
     {
@@ -105,7 +105,7 @@
       },
       "outputs": [],
       "source": [
-        "feature_importance = reg.feature_importances_\nsorted_idx = np.argsort(feature_importance)\npos = np.arange(sorted_idx.shape[0]) + 0.5\nfig = plt.figure(figsize=(12, 6))\nplt.subplot(1, 2, 1)\nplt.barh(pos, feature_importance[sorted_idx], align=\"center\")\nplt.yticks(pos, np.array(diabetes.feature_names)[sorted_idx])\nplt.title(\"Feature Importance (MDI)\")\n\nresult = permutation_importance(\n    reg, X_test, y_test, n_repeats=10, random_state=42, n_jobs=2\n)\nsorted_idx = result.importances_mean.argsort()\nplt.subplot(1, 2, 2)\nplt.boxplot(\n    result.importances[sorted_idx].T,\n    vert=False,\n    labels=np.array(diabetes.feature_names)[sorted_idx],\n)\nplt.title(\"Permutation Importance (test set)\")\nfig.tight_layout()\nplt.show()"
+        "feature_importance = reg.feature_importances_\nsorted_idx = np.argsort(feature_importance)\npos = np.arange(sorted_idx.shape[0]) + 0.5\nfig = plt.figure(figsize=(12, 6))\nplt.subplot(1, 2, 1)\nplt.barh(pos, feature_importance[sorted_idx], align=\"center\")\nplt.yticks(pos, np.array(diabetes.feature_names)[sorted_idx])\nplt.title(\"Feature Importance (MDI)\")\n\nresult = permutation_importance(\n    reg, X_test, y_test, n_repeats=10, random_state=42, n_jobs=2\n)\nsorted_idx = result.importances_mean.argsort()\nplt.subplot(1, 2, 2)\n\n# `labels` argument in boxplot is deprecated in matplotlib 3.9 and has been\n# renamed to `tick_labels`. The following code handles this, but as a\n# scikit-learn user you probably can write simpler code by using `labels=...`\n# (matplotlib < 3.9) or `tick_labels=...` (matplotlib >= 3.9).\ntick_labels_parameter_name = (\n    \"tick_labels\"\n    if parse_version(matplotlib.__version__) >= parse_version(\"3.9\")\n    else \"labels\"\n)\ntick_labels_dict = {\n    tick_labels_parameter_name: np.array(diabetes.feature_names)[sorted_idx]\n}\nplt.boxplot(result.importances[sorted_idx].T, vert=False, **tick_labels_dict)\nplt.title(\"Permutation Importance (test set)\")\nfig.tight_layout()\nplt.show()"
       ]
     }
   ],

Diff for: dev/_downloads/756be88c4ccd4c7bba02ab13f0d3258a/plot_permutation_importance_multicollinear.py

@@ -22,7 +22,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\n\nfrom sklearn.datasets import make_classification\nfrom sklearn.ensemble import RandomForestClassifier\n\n# from sklearn.metrics import plot_roc_curve\nfrom sklearn.metrics import RocCurveDisplay\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.svm import SVC\n\nX, y = make_classification(random_state=0)\nX_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)\n\nsvc = SVC(random_state=42)\nsvc.fit(X_train, y_train)\nrfc = RandomForestClassifier(random_state=42)\nrfc.fit(X_train, y_train)\n\n# plot_roc_curve has been removed in version 1.2. From 1.2, use RocCurveDisplay instead.\n# svc_disp = plot_roc_curve(svc, X_test, y_test)\n# rfc_disp = plot_roc_curve(rfc, X_test, y_test, ax=svc_disp.ax_)\nsvc_disp = RocCurveDisplay.from_estimator(svc, X_test, y_test)\nrfc_disp = RocCurveDisplay.from_estimator(rfc, X_test, y_test, ax=svc_disp.ax_)\nrfc_disp.figure_.suptitle(\"ROC curve comparison\")\n\nplt.show()"
+        "import matplotlib\nimport matplotlib.pyplot as plt\n\nfrom sklearn.datasets import make_classification\nfrom sklearn.ensemble import RandomForestClassifier\n\n# from sklearn.metrics import plot_roc_curve\nfrom sklearn.metrics import RocCurveDisplay\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.svm import SVC\nfrom sklearn.utils.fixes import parse_version\n\nX, y = make_classification(random_state=0)\nX_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)\n\nsvc = SVC(random_state=42)\nsvc.fit(X_train, y_train)\nrfc = RandomForestClassifier(random_state=42)\nrfc.fit(X_train, y_train)\n\n# plot_roc_curve has been removed in version 1.2. From 1.2, use RocCurveDisplay instead.\n# svc_disp = plot_roc_curve(svc, X_test, y_test)\n# rfc_disp = plot_roc_curve(rfc, X_test, y_test, ax=svc_disp.ax_)\nsvc_disp = RocCurveDisplay.from_estimator(svc, X_test, y_test)\nrfc_disp = RocCurveDisplay.from_estimator(rfc, X_test, y_test, ax=svc_disp.ax_)\nrfc_disp.figure_.suptitle(\"ROC curve comparison\")\n\nplt.show()"
       ]
     },
     {
@@ -58,7 +58,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\nimport numpy as np\n\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()"
+        "import matplotlib.pyplot as plt\nimport numpy as np\n\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()\n\n# `labels` argument in boxplot is deprecated in matplotlib 3.9 and has been\n# renamed to `tick_labels`. The following code handles this, but as a\n# scikit-learn user you probably can write simpler code by using `labels=...`\n# (matplotlib < 3.9) or `tick_labels=...` (matplotlib >= 3.9).\ntick_labels_parameter_name = (\n    \"tick_labels\"\n    if parse_version(matplotlib.__version__) >= parse_version(\"3.9\")\n    else \"labels\"\n)\ntick_labels_dict = {tick_labels_parameter_name: feature_names[sorted_idx]}\nax.boxplot(result.importances[sorted_idx].T, vert=False, **tick_labels_dict)\nax.set_title(\"Permutation Importance of each feature\")\nax.set_ylabel(\"Features\")\nfig.tight_layout()\nplt.show()"
       ]
     },
     {

Diff for: dev/_downloads/c536eb92f539255e80e2b3ef5200e7a1/plot_gradient_boosting_regression.ipynb

@@ -21,13 +21,15 @@
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause
 
+import matplotlib
 import matplotlib.pyplot as plt
 import numpy as np
 
 from sklearn import datasets, ensemble
 from sklearn.inspection import permutation_importance
 from sklearn.metrics import mean_squared_error
 from sklearn.model_selection import train_test_split
+from sklearn.utils.fixes import parse_version
 
 # %%
 # Load the data
@@ -145,11 +147,20 @@
 )
 sorted_idx = result.importances_mean.argsort()
 plt.subplot(1, 2, 2)
-plt.boxplot(
-    result.importances[sorted_idx].T,
-    vert=False,
-    labels=np.array(diabetes.feature_names)[sorted_idx],
+
+# `labels` argument in boxplot is deprecated in matplotlib 3.9 and has been
+# renamed to `tick_labels`. The following code handles this, but as a
+# scikit-learn user you probably can write simpler code by using `labels=...`
+# (matplotlib < 3.9) or `tick_labels=...` (matplotlib >= 3.9).
+tick_labels_parameter_name = (
+    "tick_labels"
+    if parse_version(matplotlib.__version__) >= parse_version("3.9")
+    else "labels"
 )
+tick_labels_dict = {
+    tick_labels_parameter_name: np.array(diabetes.feature_names)[sorted_idx]
+}
+plt.boxplot(result.importances[sorted_idx].T, vert=False, **tick_labels_dict)
 plt.title("Permutation Importance (test set)")
 fig.tight_layout()
 plt.show()