46ae0787a570a8c7ec79c6d46cb66145f129c284,autosklearn/ensembles/ensemble_selection.py,EnsembleSelection,_fast,#EnsembleSelection#Any#Any#,55

Before Change

                    (1. / float(s + 1)) * pred,
                    out=fant_ensemble_prediction
                )
                scores[j] = self.metric._optimum - calculate_score(
                    solution=labels,
                    prediction=fant_ensemble_prediction,
                    task_type=self.task_type,
                    metric=self.metric,
                    all_scoring_functions=False)

            all_best = np.argwhere(scores == np.nanmin(scores)).flatten()
            best = self.random_state.choice(all_best)
            ensemble.append(predictions[best])

After Change

                // when all_scoring_functions=False, we know it will be a float
                calculated_score = cast(
                    float,
                    calculate_score(
                        solution=labels,
                        prediction=fant_ensemble_prediction,
                        task_type=self.task_type,
                        metric=self.metric,
                        all_scoring_functions=False
                    )
                )
                scores[j] = self.metric._optimum - calculated_score

            all_best = np.argwhere(scores == np.nanmin(scores)).flatten()
            best = self.random_state.choice(all_best)

Instances