scikit-learn · jeremiedbb · May 7, 2024 · May 7, 2024 · May 7, 2024
diff --git a/sklearn/metrics/_classification.py b/sklearn/metrics/_classification.py
@@ -3277,10 +3277,10 @@ def d2_log_loss_score(y_true, y_pred, *, sample_weight=None, labels=None):
    :math:`D^2` score function, fraction of log loss explained.

    Best possible score is 1.0 and it can be negative (because the model can be
-    arbitrarily worse). A model that always uses the empirical mean of `y_true` as
-    constant prediction, disregarding the input features, gets a D^2 score of 0.0.
+    arbitrarily worse). A model that always predicts the per-class proportions
+    of `y_true`, disregarding the input features, gets a D^2 score of 0.0.

-    Read more in the :ref:`User Guide <d2_score>`.
+    Read more in the :ref:`User Guide <d2_score_classification>`.

    .. versionadded:: 1.5


diff --git a/sklearn/metrics/tests/test_classification.py b/sklearn/metrics/tests/test_classification.py
@@ -3048,7 +3048,8 @@ def test_d2_log_loss_score():


 def test_d2_log_loss_score_raises():
-    """Test that d2_log_loss raises error on invalid input."""
+    """Test that d2_log_loss_score raises the appropriate errors on
+    invalid inputs."""
    y_true = [0, 1, 2]
    y_pred = [[0.2, 0.8], [0.5, 0.5], [0.4, 0.6]]
    err = "contain different number of classes"