Pushing the docs to dev/ for branch: main, commit 02b04cb3ecfc5fce1f627281c312753f3b4b8494

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -2,8 +2,7 @@
 =========================================
 Advanced Plotting With Partial Dependence
 =========================================
-The :func:`~sklearn.inspection.plot_partial_dependence` function returns a
-:class:`~sklearn.inspection.PartialDependenceDisplay` object that can be used
+The :class:`~sklearn.inspection.PartialDependenceDisplay` object can be used
 for plotting without needing to recalculate the partial dependence. In this
 example, we show how to plot partial dependence plots and how to quickly
 customize the plot with the visualization API.

dev/_downloads/1bba2567637a1618250bc13e249eb0d7/plot_partial_dependence_visualization_api.py

@@ -137,7 +137,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.ensemble import RandomForestRegressor\nfrom sklearn.datasets import fetch_california_housing\nfrom sklearn.inspection import plot_partial_dependence\n\nX, y = fetch_california_housing(return_X_y=True, as_frame=True)\nfeatures = [\"MedInc\", \"AveOccup\", \"HouseAge\", \"AveRooms\"]\nest = RandomForestRegressor(n_estimators=10)\nest.fit(X, y)\ndisplay = plot_partial_dependence(\n    est,\n    X,\n    features,\n    kind=\"individual\",\n    subsample=50,\n    n_jobs=3,\n    grid_resolution=20,\n    random_state=0,\n)\ndisplay.figure_.suptitle(\n    \"Partial dependence of house value on non-___location features\\n\"\n    \"for the California housing dataset, with BayesianRidge\"\n)\ndisplay.figure_.subplots_adjust(hspace=0.3)"
+        "from sklearn.ensemble import RandomForestRegressor\nfrom sklearn.datasets import fetch_california_housing\n\n# from sklearn.inspection import plot_partial_dependence\nfrom sklearn.inspection import PartialDependenceDisplay\n\nX, y = fetch_california_housing(return_X_y=True, as_frame=True)\nfeatures = [\"MedInc\", \"AveOccup\", \"HouseAge\", \"AveRooms\"]\nest = RandomForestRegressor(n_estimators=10)\nest.fit(X, y)\n\n# plot_partial_dependence has been removed in version 1.2. From 1.2, use\n# PartialDependenceDisplay instead.\n# display = plot_partial_dependence(\ndisplay = PartialDependenceDisplay.from_estimator(\n    est,\n    X,\n    features,\n    kind=\"individual\",\n    subsample=50,\n    n_jobs=3,\n    grid_resolution=20,\n    random_state=0,\n)\ndisplay.figure_.suptitle(\n    \"Partial dependence of house value on non-___location features\\n\"\n    \"for the California housing dataset, with BayesianRidge\"\n)\ndisplay.figure_.subplots_adjust(hspace=0.3)"
       ]
     },
     {

dev/_downloads/2e6d841155147c9fbce4ea3837b924b9/plot_release_highlights_0_24_0.ipynb

@@ -126,7 +126,9 @@
 import numpy as np
 from matplotlib import pyplot as plt
 from sklearn.model_selection import train_test_split
-from sklearn.inspection import plot_partial_dependence
+
+# from sklearn.inspection import plot_partial_dependence
+from sklearn.inspection import PartialDependenceDisplay
 from sklearn.ensemble import HistGradientBoostingRegressor
 
 n_samples = 500
@@ -138,14 +140,18 @@
 gbdt_no_cst = HistGradientBoostingRegressor().fit(X, y)
 gbdt_cst = HistGradientBoostingRegressor(monotonic_cst=[1, 0]).fit(X, y)
 
-disp = plot_partial_dependence(
+# plot_partial_dependence has been removed in version 1.2. From 1.2, use
+# PartialDependenceDisplay instead.
+# disp = plot_partial_dependence(
+disp = PartialDependenceDisplay.from_estimator(
     gbdt_no_cst,
     X,
     features=[0],
     feature_names=["feature 0"],
     line_kw={"linewidth": 4, "label": "unconstrained", "color": "tab:blue"},
 )
-plot_partial_dependence(
+# plot_partial_dependence(
+PartialDependenceDisplay.from_estimator(
     gbdt_cst,
     X,
     features=[0],

dev/_downloads/4f07b03421908788913e044918d8ed1e/plot_release_highlights_0_23_0.py

@@ -36,7 +36,10 @@
 
 from sklearn.model_selection import train_test_split
 from sklearn.svm import SVC
-from sklearn.metrics import plot_roc_curve
+
+# from sklearn.metrics import plot_roc_curve
+from sklearn.metrics import RocCurveDisplay
+
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.datasets import make_classification
 import matplotlib.pyplot as plt
@@ -49,8 +52,11 @@
 rfc = RandomForestClassifier(random_state=42)
 rfc.fit(X_train, y_train)
 
-svc_disp = plot_roc_curve(svc, X_test, y_test)
-rfc_disp = plot_roc_curve(rfc, X_test, y_test, ax=svc_disp.ax_)
+# plot_roc_curve has been removed in version 1.2. From 1.2, use RocCurveDisplay instead.
+# svc_disp = plot_roc_curve(svc, X_test, y_test)
+# rfc_disp = plot_roc_curve(rfc, X_test, y_test, ax=svc_disp.ax_)
+svc_disp = RocCurveDisplay.from_estimator(svc, X_test, y_test)
+rfc_disp = RocCurveDisplay.from_estimator(rfc, X_test, y_test, ax=svc_disp.ax_)
 rfc_disp.figure_.suptitle("ROC curve comparison")
 
 plt.show()

dev/_downloads/50040ae12dd16e7d2e79135d7793c17e/plot_release_highlights_0_22_0.py

@@ -41,7 +41,7 @@
 print()
 
 # Parameters
-sdg_params = dict(alpha=1e-5, penalty="l2", loss="log")
+sdg_params = dict(alpha=1e-5, penalty="l2", loss="log_loss")
 vectorizer_params = dict(ngram_range=(1, 2), min_df=5, max_df=0.8)
 
 # Supervised Pipeline
@@ -66,7 +66,7 @@
         ("vect", CountVectorizer(**vectorizer_params)),
         ("tfidf", TfidfTransformer()),
         # LabelSpreading does not support dense matrices
-        ("todense", FunctionTransformer(lambda x: x.todense())),
+        ("toarray", FunctionTransformer(lambda x: x.toarray())),
         ("clf", LabelSpreading()),
     ]
 )

dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -87,7 +87,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nfrom matplotlib import pyplot as plt\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.inspection import plot_partial_dependence\nfrom sklearn.ensemble import HistGradientBoostingRegressor\n\nn_samples = 500\nrng = np.random.RandomState(0)\nX = rng.randn(n_samples, 2)\nnoise = rng.normal(loc=0.0, scale=0.01, size=n_samples)\ny = 5 * X[:, 0] + np.sin(10 * np.pi * X[:, 0]) - noise\n\ngbdt_no_cst = HistGradientBoostingRegressor().fit(X, y)\ngbdt_cst = HistGradientBoostingRegressor(monotonic_cst=[1, 0]).fit(X, y)\n\ndisp = plot_partial_dependence(\n    gbdt_no_cst,\n    X,\n    features=[0],\n    feature_names=[\"feature 0\"],\n    line_kw={\"linewidth\": 4, \"label\": \"unconstrained\", \"color\": \"tab:blue\"},\n)\nplot_partial_dependence(\n    gbdt_cst,\n    X,\n    features=[0],\n    line_kw={\"linewidth\": 4, \"label\": \"constrained\", \"color\": \"tab:orange\"},\n    ax=disp.axes_,\n)\ndisp.axes_[0, 0].plot(\n    X[:, 0], y, \"o\", alpha=0.5, zorder=-1, label=\"samples\", color=\"tab:green\"\n)\ndisp.axes_[0, 0].set_ylim(-3, 3)\ndisp.axes_[0, 0].set_xlim(-1, 1)\nplt.legend()\nplt.show()"
+        "import numpy as np\nfrom matplotlib import pyplot as plt\nfrom sklearn.model_selection import train_test_split\n\n# from sklearn.inspection import plot_partial_dependence\nfrom sklearn.inspection import PartialDependenceDisplay\nfrom sklearn.ensemble import HistGradientBoostingRegressor\n\nn_samples = 500\nrng = np.random.RandomState(0)\nX = rng.randn(n_samples, 2)\nnoise = rng.normal(loc=0.0, scale=0.01, size=n_samples)\ny = 5 * X[:, 0] + np.sin(10 * np.pi * X[:, 0]) - noise\n\ngbdt_no_cst = HistGradientBoostingRegressor().fit(X, y)\ngbdt_cst = HistGradientBoostingRegressor(monotonic_cst=[1, 0]).fit(X, y)\n\n# plot_partial_dependence has been removed in version 1.2. From 1.2, use\n# PartialDependenceDisplay instead.\n# disp = plot_partial_dependence(\ndisp = PartialDependenceDisplay.from_estimator(\n    gbdt_no_cst,\n    X,\n    features=[0],\n    feature_names=[\"feature 0\"],\n    line_kw={\"linewidth\": 4, \"label\": \"unconstrained\", \"color\": \"tab:blue\"},\n)\n# plot_partial_dependence(\nPartialDependenceDisplay.from_estimator(\n    gbdt_cst,\n    X,\n    features=[0],\n    line_kw={\"linewidth\": 4, \"label\": \"constrained\", \"color\": \"tab:orange\"},\n    ax=disp.axes_,\n)\ndisp.axes_[0, 0].plot(\n    X[:, 0], y, \"o\", alpha=0.5, zorder=-1, label=\"samples\", color=\"tab:green\"\n)\ndisp.axes_[0, 0].set_ylim(-3, 3)\ndisp.axes_[0, 0].set_xlim(-1, 1)\nplt.legend()\nplt.show()"
       ]
     },
     {

dev/_downloads/7f9c06d88a8d544a3815452dacaa0548/plot_semi_supervised_newsgroups.py

@@ -196,13 +196,19 @@
 
 from sklearn.ensemble import RandomForestRegressor
 from sklearn.datasets import fetch_california_housing
-from sklearn.inspection import plot_partial_dependence
+
+# from sklearn.inspection import plot_partial_dependence
+from sklearn.inspection import PartialDependenceDisplay
 
 X, y = fetch_california_housing(return_X_y=True, as_frame=True)
 features = ["MedInc", "AveOccup", "HouseAge", "AveRooms"]
 est = RandomForestRegressor(n_estimators=10)
 est.fit(X, y)
-display = plot_partial_dependence(
+
+# plot_partial_dependence has been removed in version 1.2. From 1.2, use
+# PartialDependenceDisplay instead.
+# display = plot_partial_dependence(
+display = PartialDependenceDisplay.from_estimator(
     est,
     X,
     features,

dev/_downloads/923fcad5e07de1ce7dc8dcbd7327c178/plot_release_highlights_0_23_0.ipynb

@@ -33,7 +33,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.model_selection import train_test_split\nfrom sklearn.svm import SVC\nfrom sklearn.metrics import plot_roc_curve\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.datasets import make_classification\nimport matplotlib.pyplot as plt\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\nsvc_disp = plot_roc_curve(svc, X_test, y_test)\nrfc_disp = plot_roc_curve(rfc, X_test, y_test, ax=svc_disp.ax_)\nrfc_disp.figure_.suptitle(\"ROC curve comparison\")\n\nplt.show()"
+        "from sklearn.model_selection import train_test_split\nfrom sklearn.svm import SVC\n\n# from sklearn.metrics import plot_roc_curve\nfrom sklearn.metrics import RocCurveDisplay\n\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.datasets import make_classification\nimport matplotlib.pyplot as plt\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()"
       ]
     },
     {