MNT Deprecate SAMME.R algorithm from AdaBoostClassifier (scikit-learn#26830)

Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>

Author: StefanieSenger

benchmarks/bench_20newsgroups.py

@@ -21,7 +21,7 @@
     "extra_trees": ExtraTreesClassifier(max_features="sqrt", min_samples_split=10),
     "logistic_regression": LogisticRegression(),
     "naive_bayes": MultinomialNB(),
-    "adaboost": AdaBoostClassifier(n_estimators=10),
+    "adaboost": AdaBoostClassifier(n_estimators=10, algorithm="SAMME"),
 }
 
 

doc/conf.py

@@ -300,6 +300,9 @@
     "auto_examples/decomposition/plot_beta_divergence": (
         "auto_examples/applications/plot_topics_extraction_with_nmf_lda"
     ),
+    "auto_examples/ensemble/plot_adaboost_hastie_10_2": (
+        "auto_examples/ensemble/plot_adaboost_multiclass"
+    ),
 }
 html_context["redirects"] = redirects
 for old_link in redirects:

doc/modules/ensemble.rst

@@ -1570,15 +1570,15 @@ ever-increasing influence. Each subsequent weak learner is thereby forced to
 concentrate on the examples that are missed by the previous ones in the sequence
 [HTF]_.
 
-.. figure:: ../auto_examples/ensemble/images/sphx_glr_plot_adaboost_hastie_10_2_001.png
-   :target: ../auto_examples/ensemble/plot_adaboost_hastie_10_2.html
+.. figure:: ../auto_examples/ensemble/images/sphx_glr_plot_adaboost_multiclass_001.png
+   :target: ../auto_examples/ensemble/plot_adaboost_multiclass.html
    :align: center
    :scale: 75
 
 AdaBoost can be used both for classification and regression problems:
 
   - For multi-class classification, :class:`AdaBoostClassifier` implements
-    AdaBoost-SAMME and AdaBoost-SAMME.R [ZZRH2009]_.
+    AdaBoost.SAMME [ZZRH2009]_.
 
   - For regression, :class:`AdaBoostRegressor` implements AdaBoost.R2 [D1997]_.
 
@@ -1593,7 +1593,7 @@ learners::
     >>> from sklearn.ensemble import AdaBoostClassifier
 
     >>> X, y = load_iris(return_X_y=True)
-    >>> clf = AdaBoostClassifier(n_estimators=100)
+    >>> clf = AdaBoostClassifier(n_estimators=100, algorithm="SAMME",)
     >>> scores = cross_val_score(clf, X, y, cv=5)
     >>> scores.mean()
     0.9...
@@ -1608,12 +1608,8 @@ minimum required number of samples to consider a split ``min_samples_split``).
 
 .. topic:: Examples:
 
- * :ref:`sphx_glr_auto_examples_ensemble_plot_adaboost_hastie_10_2.py` compares the
-   classification error of a decision stump, decision tree, and a boosted
-   decision stump using AdaBoost-SAMME and AdaBoost-SAMME.R.
-
  * :ref:`sphx_glr_auto_examples_ensemble_plot_adaboost_multiclass.py` shows the performance
-   of AdaBoost-SAMME and AdaBoost-SAMME.R on a multi-class problem.
+   of AdaBoost on a multi-class problem.
 
  * :ref:`sphx_glr_auto_examples_ensemble_plot_adaboost_twoclass.py` shows the decision boundary
    and decision function values for a non-linearly separable two-class problem
@@ -1634,4 +1630,3 @@ minimum required number of samples to consider a split ``min_samples_split``).
 
  .. [HTF] T. Hastie, R. Tibshirani and J. Friedman, "Elements of
               Statistical Learning Ed. 2", Springer, 2009.
-

doc/whats_new/v1.4.rst

@@ -150,6 +150,10 @@ Changelog
   :pr:`13649` by :user:`Samuel Ronsin <samronsin>`,
   initiated by :user:`Patrick O'Reilly <pat-oreilly>`.
 
+- |API| In :class:`AdaBoostClassifier`, the `algorithm` argument `SAMME.R` was
+  deprecated and will be removed in 1.6. :pr:`26830` by :user:`Stefanie Senger
+  <StefanieSenger>`.
+
 - |Efficiency| :class:`ensemble.GradientBoostingClassifier` is faster,
   for binary and in particular for multiclass problems thanks to the private loss
   function module.

examples/classification/plot_classifier_comparison.py

@@ -66,7 +66,7 @@
         max_depth=5, n_estimators=10, max_features=1, random_state=42
     ),
     MLPClassifier(alpha=1, max_iter=1000, random_state=42),
-    AdaBoostClassifier(random_state=42),
+    AdaBoostClassifier(algorithm="SAMME", random_state=42),
     GaussianNB(),
     QuadraticDiscriminantAnalysis(),
 ]

examples/ensemble/plot_adaboost_hastie_10_2.py

@@ -71,7 +71,11 @@
     DecisionTreeClassifier(max_depth=None),
     RandomForestClassifier(n_estimators=n_estimators),
     ExtraTreesClassifier(n_estimators=n_estimators),
-    AdaBoostClassifier(DecisionTreeClassifier(max_depth=3), n_estimators=n_estimators),
+    AdaBoostClassifier(
+        DecisionTreeClassifier(max_depth=3),
+        n_estimators=n_estimators,
+        algorithm="SAMME",
+    ),
 ]
 
 for pair in ([0, 1], [0, 2], [2, 3]):