Rename methods to be Pareto set methods

autosklearn/automl.py

@@ -1651,9 +1651,9 @@ def _load_best_individual_model(self):
         )
         return ensemble
 
-    def _load_pareto_front(self) -> Sequence[VotingClassifier | VotingRegressor]:
+    def _load_pareto_set(self) -> Sequence[VotingClassifier | VotingRegressor]:
         if len(self._metrics) <= 1:
-            raise ValueError("Pareto front is only available for two or more metrics.")
+            raise ValueError("Pareto set is only available for two or more metrics.")
 
         if self._ensemble_class is not None:
             self.ensemble_ = self._backend.load_ensemble(self._seed)
@@ -1664,22 +1664,22 @@ def _load_pareto_front(self) -> Sequence[VotingClassifier | VotingRegressor]:
         if not self.ensemble_:
 
             raise ValueError(
-                "Pareto front can only be accessed if an ensemble is available."
+                "Pareto set can only be accessed if an ensemble is available."
             )
 
         if isinstance(self.ensemble_, AbstractMultiObjectiveEnsemble):
-            pareto_front = self.ensemble_.get_pareto_front()
+            pareto_set = self.ensemble_.get_pareto_set()
         else:
             self._logger.warning(
-                "Pareto front not available for single objective ensemble "
-                "method. The Pareto front will only include the single ensemble "
+                "Pareto set not available for single objective ensemble "
+                "method. The Pareto set will only include the single ensemble "
                 "constructed by %s",
                 type(self.ensemble_),
             )
-            pareto_front = [self.ensemble_]
+            pareto_set = [self.ensemble_]
 
         ensembles = []
-        for ensemble in pareto_front:
+        for ensemble in pareto_set:
             identifiers = ensemble.get_selected_model_identifiers()
             weights = {
                 identifier: weight

autosklearn/ensembles/abstract_ensemble.py

@@ -140,5 +140,5 @@ def get_validation_performance(self) -> float:
 
 
 class AbstractMultiObjectiveEnsemble(AbstractEnsemble):
-    def get_pareto_front(self) -> Sequence[AbstractEnsemble]:
+    def get_pareto_set(self) -> Sequence[AbstractEnsemble]:
         pass

autosklearn/estimators.py

@@ -1322,8 +1322,8 @@ def get_configuration_space(
             else self.automl_.configuration_space
         )
 
-    def get_pareto_front(self) -> Sequence[VotingClassifier | VotingRegressor]:
-        return self.automl_._load_pareto_front()
+    def get_pareto_set(self) -> Sequence[VotingClassifier | VotingRegressor]:
+        return self.automl_._load_pareto_set()
 
 
 class AutoSklearnClassifier(AutoSklearnEstimator, ClassifierMixin):

examples/40_advanced/example_multi_objective.py

@@ -9,7 +9,7 @@
 in the `scikit-learn docs <https://scikit-learn.org/stable/auto_examples/model_selection/plot_precision_recall.html>`_.
 
 Auto-sklearn uses `SMAC3's implementation of ParEGO <https://automl.github.io/SMAC3/main/details/multi_objective.html>`_.
-Multi-objective ensembling and proper access to the full Pareto front will be added in the near
+Multi-objective ensembling and proper access to the full Pareto set will be added in the near
 future.
 """
 from pprint import pprint
@@ -71,10 +71,10 @@
 pprint(automl.cv_results_)
 
 ############################################################################
-# Visualize the Pareto front
+# Visualize the Pareto set
 # ==========================
 plot_values = []
-pareto_front = automl.get_pareto_front()
+pareto_front = automl.get_pareto_set()
 for ensemble in pareto_front:
     predictions = ensemble.predict(X_test)
     precision = sklearn.metrics.precision_score(y_test, predictions)
@@ -86,5 +86,5 @@
     ax.scatter(precision, recall, c="blue")
 ax.set_xlabel("Precision")
 ax.set_ylabel("Recall")
-ax.set_title("Pareto front")
+ax.set_title("Pareto set")
 plt.show()

test/test_automl/test_post_fit.py

@@ -90,7 +90,7 @@ def test__load_pareto_front(automl: AutoML) -> None:
     assert automl.predict_proba(X).shape == (1, 3)
     assert automl.predict(X).shape == (1,)
 
-    pareto_front = automl._load_pareto_front()
+    pareto_front = automl._load_pareto_set()
     assert len(pareto_front) == 1
     for ensemble in pareto_front:
         assert isinstance(ensemble, (VotingClassifier, VotingRegressor))