@@ -587,12 +587,12 @@ def explained_variance_score(y_true, y_pred, *,
587587@_deprecate_positional_args
588588def r2_score (y_true , y_pred , * , sample_weight = None ,
589589 multioutput = "uniform_average" ):
590- """R^2 (coefficient of determination) regression score function.
590+ """:math:` R^2` (coefficient of determination) regression score function.
591591
592592 Best possible score is 1.0 and it can be negative (because the
593593 model can be arbitrarily worse). A constant model that always
594594 predicts the expected value of y, disregarding the input features,
595- would get a R^2 score of 0.0.
595+ would get a :math:` R^2` score of 0.0.
596596
597597 Read more in the :ref:`User Guide <r2_score>`.
598598
@@ -630,15 +630,15 @@ def r2_score(y_true, y_pred, *, sample_weight=None,
630630 Returns
631631 -------
632632 z : float or ndarray of floats
633- The R^2 score or ndarray of scores if 'multioutput' is
633+ The :math:` R^2` score or ndarray of scores if 'multioutput' is
634634 'raw_values'.
635635
636636 Notes
637637 -----
638638 This is not a symmetric function.
639639
640- Unlike most other scores, R^2 score may be negative (it need not actually
641- be the square of a quantity R).
640+ Unlike most other scores, :math:` R^2` score may be negative (it need not
641+ actually be the square of a quantity R).
642642
643643 This metric is not well-defined for single samples and will return a NaN
644644 value if n_samples is less than two.
0 commit comments