feat: add learning_rate to AdaBoost classifier and regressor. (#251)

Closes #167.

Adds learning_rate parameter to AdaBoost classifier and regressor.

<!-- Please provide a summary of changes in this pull request, ensuring
all changes are explained. -->

---------

Co-authored-by: Lars Reimann <mail@larsreimann.com>

src/safeds/ml/classical/classification/_ada_boost.py

@@ -13,12 +13,22 @@
 
 
 class AdaBoost(Classifier):
-    """Ada Boost classification."""
+    """Ada Boost classification.
 
-    def __init__(self) -> None:
+    Parameters
+    ----------
+    learning_rate : float
+        Weight applied to each classifier at each boosting iteration.
+        A higher learning rate increases the contribution of each classifier.
+    """
+
+    def __init__(self, learning_rate: float = 1.0) -> None:
         self._wrapped_classifier: sk_AdaBoostClassifier | None = None
         self._feature_names: list[str] | None = None
         self._target_name: str | None = None
+        if learning_rate <= 0:
+            raise ValueError("learning_rate must be positive.")
+        self._learning_rate = learning_rate
 
     def fit(self, training_set: TaggedTable) -> AdaBoost:
         """
@@ -41,10 +51,10 @@ def fit(self, training_set: TaggedTable) -> AdaBoost:
         LearningError
             If the training data contains invalid values or if the training failed.
         """
-        wrapped_classifier = sk_AdaBoostClassifier()
+        wrapped_classifier = sk_AdaBoostClassifier(learning_rate=self._learning_rate)
         fit(wrapped_classifier, training_set)
 
-        result = AdaBoost()
+        result = AdaBoost(learning_rate=self._learning_rate)
         result._wrapped_classifier = wrapped_classifier
         result._feature_names = training_set.features.column_names
         result._target_name = training_set.target.name

src/safeds/ml/classical/regression/_ada_boost.py

@@ -13,12 +13,22 @@
 
 
 class AdaBoost(Regressor):
-    """Ada Boost regression."""
+    """Ada Boost regression.
 
-    def __init__(self) -> None:
+    Parameters
+    ----------
+    learning_rate : float
+        Weight applied to each regressor at each boosting iteration.
+        A higher learning rate increases the contribution of each regressor.
+    """
+
+    def __init__(self, learning_rate: float = 1.0) -> None:
         self._wrapped_regressor: sk_AdaBoostRegressor | None = None
         self._feature_names: list[str] | None = None
         self._target_name: str | None = None
+        if learning_rate <= 0:
+            raise ValueError("learning_rate must be positive.")
+        self.learning_rate = learning_rate
 
     def fit(self, training_set: TaggedTable) -> AdaBoost:
         """
@@ -41,10 +51,10 @@ def fit(self, training_set: TaggedTable) -> AdaBoost:
         LearningError
             If the training data contains invalid values or if the training failed.
         """
-        wrapped_regressor = sk_AdaBoostRegressor()
+        wrapped_regressor = sk_AdaBoostRegressor(learning_rate=self.learning_rate)
         fit(wrapped_regressor, training_set)
 
-        result = AdaBoost()
+        result = AdaBoost(learning_rate=self.learning_rate)
         result._wrapped_regressor = wrapped_regressor
         result._feature_names = training_set.features.column_names
         result._target_name = training_set.target.name

tests/safeds/ml/classical/classification/test_ada_boost.py

@@ -0,0 +1,17 @@
+import pytest
+from safeds.data.tabular.containers import Table
+from safeds.ml.classical.classification import AdaBoost
+
+
+def test_should_throw_value_error_if_learning_rate_is_non_positive() -> None:
+    with pytest.raises(ValueError, match="learning_rate must be positive."):
+        AdaBoost(learning_rate=-1)
+
+
+def test_should_give_learning_rate_to_sklearn() -> None:
+    training_set = Table.from_dict({"col1": [1, 2, 3, 4], "col2": [1, 2, 3, 4]})
+    tagged_table = training_set.tag_columns("col1")
+
+    regressor = AdaBoost(learning_rate=2).fit(tagged_table)
+    assert regressor._wrapped_classifier is not None
+    assert regressor._wrapped_classifier.learning_rate == regressor._learning_rate

tests/safeds/ml/classical/regression/test_ada_boost.py

@@ -0,0 +1,17 @@
+import pytest
+from safeds.data.tabular.containers import Table
+from safeds.ml.classical.regression import AdaBoost
+
+
+def test_should_throw_value_error_if_learning_rate_is_non_positive() -> None:
+    with pytest.raises(ValueError, match="learning_rate must be positive."):
+        AdaBoost(learning_rate=-1)
+
+
+def test_should_give_learning_rate_to_sklearn() -> None:
+    training_set = Table.from_dict({"col1": [1, 2, 3, 4], "col2": [1, 2, 3, 4]})
+    tagged_table = training_set.tag_columns("col1")
+
+    regressor = AdaBoost(learning_rate=2).fit(tagged_table)
+    assert regressor._wrapped_regressor is not None
+    assert regressor._wrapped_regressor.learning_rate == regressor.learning_rate