mapie.conformity_scores
.NaiveConformityScore¶
- class mapie.conformity_scores.NaiveConformityScore[source]¶
Naive classification non-conformity score method that is based on the cumulative sum of probabilities until the 1-alpha threshold.
- Attributes
- classes: Optional[ArrayLike]
Names of the classes.
- random_state: Optional[Union[int, RandomState]]
Pseudo random number generator state.
- quantiles_: ArrayLike of shape (n_alpha)
The quantiles estimated from
get_sets
method.
- get_conformity_score_quantiles(conformity_scores: ndarray[Any, dtype[_ScalarType_co]], alpha_np: ndarray[Any, dtype[_ScalarType_co]], estimator: EnsembleClassifier, **kwargs) ndarray[Any, dtype[_ScalarType_co]] [source]¶
Get the quantiles of the conformity scores for each uncertainty level.
- get_conformity_scores(y: ndarray[Any, dtype[_ScalarType_co]], y_pred: ndarray[Any, dtype[_ScalarType_co]], **kwargs) ndarray[Any, dtype[_ScalarType_co]] [source]¶
Get the conformity score.
- Parameters
- y: NDArray of shape (n_samples,)
Observed target values.
- y_pred: NDArray of shape (n_samples,)
Predicted target values.
- Returns
- NDArray of shape (n_samples,)
Conformity scores.
- get_prediction_sets(y_pred_proba: ndarray[Any, dtype[_ScalarType_co]], conformity_scores: ndarray[Any, dtype[_ScalarType_co]], alpha_np: ndarray[Any, dtype[_ScalarType_co]], estimator: EnsembleClassifier, **kwargs) ndarray[Any, dtype[_ScalarType_co]] [source]¶
Generate prediction sets based on the probability predictions, the conformity scores and the uncertainty level.