seqgra.evaluator.gradientbased.gradientbasedevaluator module¶

Gradient-based Feature Importance Evaluators

class GradientBasedEvaluator(evaluator_id: str, evaluator_name: str, learner: seqgra.learner.learner.Learner, output_dir: str, importance_threshold: Optional[float] = None, silent: bool = False)[source]¶

Bases: seqgra.evaluator.evaluator.FeatureImportanceEvaluator

Abstract base class for gradient-based feature importance evaluators

Only supports PyTorch models.

evaluate_model(set_name: str = 'test', subset_idx: Optional[List[int]] = None, subset_n: Optional[int] = None, subset_labels: Optional[List[str]] = None, subset_n_per_label: bool = True, subset_shuffle: bool = True, subset_threshold: Optional[float] = None, suppress_plots: bool = False) → Any¶

abstract explain(x, y)[source]¶

get_layer(key_list)[source]¶

select_examples(set_name: str = 'test', labels: Optional[Set[str]] = None, threshold: Optional[float] = None) → seqgra.schema.AnnotatedExampleSet ¶

Returns all correctly classified examples that exceed the threshold.

for the specified labels and set that exceed the threshold.

Parameters: TODO –
Returns: TODO

select_n_examples(set_name: str = 'test', n: Optional[int] = None, labels: Optional[Set[str]] = None, n_per_label: bool = True, shuffle: bool = True, threshold: Optional[float] = None) → seqgra.schema.AnnotatedExampleSet ¶