seqgra.evaluator.gradientbased.nonlinearintegratedgradientevaluator module

Non-linear Integrated Gradient Evaluator

class NonlinearIntegratedGradientEvaluator(learner: seqgra.learner.learner.Learner, output_dir: str, importance_threshold: Optional[float] = None, data=None, k=5, reference=None, path_generator=None, silent: bool = False)

Bases: seqgra.evaluator.gradientbased.abstractgradientevaluator.AbstractGradientEvaluator

Non-linear integrated gradient evaluator for PyTorch models

static dijkstra(u, v, distances, indices)

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

explain(x, y)

get_layer(key_list)

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

static sequence_path(args, data, k)

distances = [[1,40],[1,35],[40,3],[35,1],[4,1]] indices = [[1,2],[0,3],[0,4],[1,4],[2,3]] nddist = np.array([np.array(xi) for xi in distances]) ndinds = np.array([np.array(xi) for xi in indices]) sp = shortest_path(0,4, nddist, ndinds) print(sp)

#unit tests change numbers to test path # 0-1-3 # | # 2 # | # 4

static shortest_path(start, end, distances, indices)