MNT Use check_scalar in AdaBoostClassifier

sklearn/ensemble/_weight_boosting.py

@@ -25,6 +25,7 @@
 
 from abc import ABCMeta, abstractmethod
 
+import numbers
 import numpy as np
 
 import warnings
@@ -36,6 +37,7 @@
 
 from ..tree import DecisionTreeClassifier, DecisionTreeRegressor
 from ..utils import check_random_state, _safe_indexing
+from ..utils import check_scalar
 from ..utils.extmath import softmax
 from ..utils.extmath import stable_cumsum
 from ..metrics import accuracy_score, r2_score
@@ -478,9 +480,27 @@ def fit(self, X, y, sample_weight=None):
         self : object
             Fitted estimator.
         """
+        check_scalar(
+            self.n_estimators,
+            "n_estimators",
+            target_type=numbers.Integral,
+            min_val=1,
+            include_boundaries="left",
+        )
+
+        check_scalar(
+            self.learning_rate,
+            "learning_rate",
+            target_type=numbers.Real,
+            min_val=0,
+            include_boundaries="neither",
+        )
+
         # Check that algorithm is supported
         if self.algorithm not in ("SAMME", "SAMME.R"):
-            raise ValueError("algorithm %s is not supported" % self.algorithm)
+            raise ValueError(
+                f"Algorithm must be 'SAMME' or 'SAMME.R'. Got {self.algorithm} instead."
+            )
 
         # Fit
         return super().fit(X, y, sample_weight)

sklearn/ensemble/tests/test_weight_boosting.py

@@ -549,6 +549,24 @@ def test_adaboostregressor_sample_weight():
     assert score_no_outlier == pytest.approx(score_with_weight)
 
 
+@pytest.mark.parametrize(
+    "params, err_type, err_msg",
+    [
+        ({"n_estimators": 0}, ValueError, "n_estimators == 0, must be >= 1"),
+        ({"learning_rate": 0}, ValueError, "learning_rate == 0, must be >= 1."),
+        (
+            {"algorithm": "unknown"},
+            ValueError,
+            "Algorithm must be 'SAMME' or 'SAMME.R'.",
+        ),
+    ],
+)
+def test_adaboost_classifier_params_validation(params, err_type, err_msg):
+    """Check the parameters validation in `AdaBoostClassifier`."""
+    with pytest.raises(err_type, match=err_msg):
+        AdaBoostClassifier(**params).fit(X, y_class)  # args are from toy sample
+
+
 @pytest.mark.parametrize("algorithm", ["SAMME", "SAMME.R"])
 def test_adaboost_consistent_predict(algorithm):
     # check that predict_proba and predict give consistent results