Merge remote-tracking branch 'upstream/main' into from_pred

DeaMariaLeon · Feb 14, 2025 · 3996689 · 3996689
2 parents 0a13cd0 + 2b97ac5
commit 3996689
Show file tree

Hide file tree

Showing 14 changed files with 72 additions and 51 deletions.
diff --git a/.github/workflows/cuda-label-remover.yml b/.github/workflows/cuda-label-remover.yml
@@ -16,7 +16,7 @@ jobs:
   label-remover:
     if: contains(github.event.pull_request.labels.*.name, 'CUDA CI')
     name: Remove "CUDA CI" Label
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     steps:
       - uses: actions-ecosystem/action-remove-labels@v1
         with:

diff --git a/.github/workflows/labeler-title-regex.yml b/.github/workflows/labeler-title-regex.yml
@@ -13,7 +13,7 @@ permissions:
 jobs:
 
   labeler:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     steps:
     - uses: actions/checkout@v4
     - uses: actions/setup-python@v5

diff --git a/azure-pipelines.yml b/azure-pipelines.yml
@@ -11,7 +11,7 @@ jobs:
 - job: git_commit
   displayName: Get Git Commit
   pool:
-    vmImage: ubuntu-20.04
+    vmImage: ubuntu-24.04
   steps:
     - bash: python build_tools/azure/get_commit_message.py
       name: commit
@@ -27,7 +27,7 @@ jobs:
     )
   displayName: Linting
   pool:
-    vmImage: ubuntu-20.04
+    vmImage: ubuntu-24.04
   steps:
     - task: UsePythonVersion@0
       inputs:
@@ -49,7 +49,7 @@ jobs:
 - template: build_tools/azure/posix.yml
   parameters:
     name: Linux_Nightly
-    vmImage: ubuntu-20.04
+    vmImage: ubuntu-22.04
     dependsOn: [git_commit, linting]
     condition: |
       and(
@@ -94,11 +94,11 @@ jobs:
     vmImage: ubuntu-22.04
   variables:
     # Need to match Python version and Emscripten version for the correct
-    # Pyodide version. For example, for Pyodide version 0.25.1, see
-    # https://github.com/pyodide/pyodide/blob/0.25.1/Makefile.envs
-    PYODIDE_VERSION: '0.26.0'
+    # Pyodide version. For example, for Pyodide version 0.27.2, see
+    # https://github.com/pyodide/pyodide/blob/0.27.2/Makefile.envs
+    PYODIDE_VERSION: '0.27.2'
     EMSCRIPTEN_VERSION: '3.1.58'
-    PYTHON_VERSION: '3.12.1'
+    PYTHON_VERSION: '3.12.7'
 
   dependsOn: [git_commit, linting]
   condition: |
@@ -126,7 +126,7 @@ jobs:
 - template: build_tools/azure/posix.yml
   parameters:
     name: Linux_Runs
-    vmImage: ubuntu-20.04
+    vmImage: ubuntu-22.04
     dependsOn: [git_commit]
     condition: |
       and(
@@ -232,7 +232,7 @@ jobs:
 - template: build_tools/azure/posix-docker.yml
   parameters:
     name: Linux_Docker
-    vmImage: ubuntu-20.04
+    vmImage: ubuntu-24.04
     dependsOn: [linting, git_commit, Ubuntu_Jammy_Jellyfish]
     # Runs when dependencies succeeded or skipped
     condition: |

diff --git a/bench_num_threads.parquet b/bench_num_threads.parquet
diff --git a/build_tools/circle/doc_linux-64_conda.lock b/build_tools/circle/doc_linux-64_conda.lock
diff --git a/doc/common_pitfalls.rst b/doc/common_pitfalls.rst
@@ -549,10 +549,10 @@ When we evaluate a randomized estimator performance by cross-validation, we
 want to make sure that the estimator can yield accurate predictions for new
 data, but we also want to make sure that the estimator is robust w.r.t. its
 random initialization. For example, we would like the random weights
-initialization of a :class:`~sklearn.linear_model.SGDClassifier` to be
+initialization of an :class:`~sklearn.linear_model.SGDClassifier` to be
 consistently good across all folds: otherwise, when we train that estimator
 on new data, we might get unlucky and the random initialization may lead to
-bad performance. Similarly, we want a random forest to be robust w.r.t the
+bad performance. Similarly, we want a random forest to be robust w.r.t. the
 set of randomly selected features that each tree will be using.
 
 For these reasons, it is preferable to evaluate the cross-validation

diff --git a/doc/modules/ensemble.rst b/doc/modules/ensemble.rst
@@ -1642,6 +1642,10 @@ computationally expensive.
     ...       .format(multi_layer_regressor.score(X_test, y_test)))
     R2 score: 0.53
 
+.. rubric:: Examples
+
+* :ref:`sphx_glr_auto_examples_ensemble_plot_stack_predictors.py`
+
 .. rubric:: References
 
 .. [W1992] Wolpert, David H. "Stacked generalization." Neural networks 5.2

diff --git a/examples/applications/plot_face_recognition.py b/examples/applications/plot_face_recognition.py
@@ -4,10 +4,8 @@
 ===================================================
 
 The dataset used in this example is a preprocessed excerpt of the
-"Labeled Faces in the Wild", aka LFW_:
-http://vis-www.cs.umass.edu/lfw/lfw-funneled.tgz (233MB)
-
-.. _LFW: http://vis-www.cs.umass.edu/lfw/
+"Labeled Faces in the Wild", aka LFW:
+https://www.kaggle.com/datasets/jessicali9530/lfw-dataset
 
 """
 

diff --git a/examples/inspection/plot_partial_dependence.py b/examples/inspection/plot_partial_dependence.py
@@ -365,8 +365,11 @@
 # However, it is worth noting that we are creating potential meaningless
 # synthetic samples if features are correlated.
 #
+# .. _ice-vs-pdp:
+#
 # ICE vs. PDP
 # ~~~~~~~~~~~
+#
 # PDP is an average of the marginal effects of the features. We are averaging the
 # response of all samples of the provided set. Thus, some effects could be hidden. In
 # this regard, it is possible to plot each individual response. This representation is

diff --git a/sklearn/datasets/descr/lfw.rst b/sklearn/datasets/descr/lfw.rst
@@ -4,9 +4,9 @@ The Labeled Faces in the Wild face recognition dataset
 ------------------------------------------------------
 
 This dataset is a collection of JPEG pictures of famous people collected
-over the internet, all details are available on the official website:
+over the internet, and the details are available on the Kaggle website:
 
-http://vis-www.cs.umass.edu/lfw/
+https://www.kaggle.com/datasets/jessicali9530/lfw-dataset
 
 Each picture is centered on a single face. The typical task is called
 Face Verification: given a pair of two pictures, a binary classifier
@@ -114,7 +114,7 @@ Features            real, between 0 and 255
 
 * `Labeled Faces in the Wild: A Database for Studying Face Recognition
   in Unconstrained Environments.
-  <http://vis-www.cs.umass.edu/lfw/lfw.pdf>`_
+  <https://people.cs.umass.edu/~elm/papers/lfw.pdf>`_
   Gary B. Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller.
   University of Massachusetts, Amherst, Technical Report 07-49, October, 2007.
 

diff --git a/sklearn/ensemble/_gb.py b/sklearn/ensemble/_gb.py
@@ -1152,6 +1152,10 @@ class GradientBoostingClassifier(ClassifierMixin, BaseGradientBoosting):
         There is a trade-off between learning_rate and n_estimators.
         Values must be in the range `[0.0, inf)`.
 
+        For an example of the effects of this parameter and its interaction with
+        ``subsample``, see
+        :ref:`sphx_glr_auto_examples_ensemble_plot_gradient_boosting_regularization.py`.
+
     n_estimators : int, default=100
         The number of boosting stages to perform. Gradient boosting
         is fairly robust to over-fitting so a large number usually

diff --git a/sklearn/ensemble/_hist_gradient_boosting/gradient_boosting.py b/sklearn/ensemble/_hist_gradient_boosting/gradient_boosting.py
@@ -1512,7 +1512,8 @@ class HistGradientBoostingRegressor(RegressorMixin, BaseHistGradientBoosting):
         converted to floating point numbers. This means that categorical values
         of 1.0 and 1 are treated as the same category.
 
-        Read more in the :ref:`User Guide <categorical_support_gbdt>`.
+        Read more in the :ref:`User Guide <categorical_support_gbdt>` and
+        :ref:`sphx_glr_auto_examples_ensemble_plot_gradient_boosting_categorical.py`.
 
         .. versionadded:: 0.24
 
@@ -1562,6 +1563,8 @@ class HistGradientBoostingRegressor(RegressorMixin, BaseHistGradientBoosting):
         and specifies that each branch of a tree will either only split
         on features 0 and 1 or only split on features 2, 3 and 4.
 
+        See :ref:`this example<ice-vs-pdp>` on how to use `interaction_cst`.
+
         .. versionadded:: 1.2
 
     warm_start : bool, default=False
@@ -1907,8 +1910,8 @@ class HistGradientBoostingClassifier(ClassifierMixin, BaseHistGradientBoosting):
         .. versionchanged:: 1.4
            Added `"from_dtype"` option.
 
-        .. versionchanged::1.6
-           The default will changed from `None` to `"from_dtype"`.
+        .. versionchanged:: 1.6
+           The default value changed from `None` to `"from_dtype"`.
 
     monotonic_cst : array-like of int of shape (n_features) or dict, default=None
         Monotonic constraint to enforce on each feature are specified using the
@@ -1949,6 +1952,8 @@ class HistGradientBoostingClassifier(ClassifierMixin, BaseHistGradientBoosting):
         and specifies that each branch of a tree will either only split
         on features 0 and 1 or only split on features 2, 3 and 4.
 
+        See :ref:`this example<ice-vs-pdp>` on how to use `interaction_cst`.
+
         .. versionadded:: 1.2
 
     warm_start : bool, default=False

diff --git a/sklearn/inspection/_partial_dependence.py b/sklearn/inspection/_partial_dependence.py
@@ -385,7 +385,9 @@ def partial_dependence(
     the average response of an estimator for each possible value of the
     feature.
 
-    Read more in the :ref:`User Guide <partial_dependence>`.
+    Read more in
+    :ref:`sphx_glr_auto_examples_inspection_plot_partial_dependence.py`
+    and the :ref:`User Guide <partial_dependence>`.
 
     .. warning::
 

diff --git a/sklearn/inspection/_plot/partial_dependence.py b/sklearn/inspection/_plot/partial_dependence.py
@@ -284,7 +284,9 @@ def from_estimator(
         marks on the x-axes for one-way plots, and on both axes for two-way
         plots.
 
-        Read more in the :ref:`User Guide <partial_dependence>`.
+        Read more in
+        :ref:`sphx_glr_auto_examples_inspection_plot_partial_dependence.py`
+        and the :ref:`User Guide <partial_dependence>`.
 
         .. note::