nessie.detectors.knn_entropy

Module Contents

Classes

KnnEntropy	Based on
KnnErrorDetector	Based on
KnnFlagger	Based on

class nessie.detectors.knn_entropy.KnnEntropy(k: float = 10)

Bases: KnnErrorDetector

Based on

Not a cute stroke: Analysis of Rule- and Neural Network-based Information Extraction Systems for Brain Radiology Reports Andreas Grivas, Beatrice Alex, Claire Grover, Richard Tobin, William Whiteley In: Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis

error_detector_kind(self) → nessie.detectors.error_detector.DetectorKind

class nessie.detectors.knn_entropy.KnnErrorDetector(k: float = 10)

Bases: nessie.detectors.error_detector.Detector, abc.ABC

Based on

Not a cute stroke: Analysis of Rule- and Neural Network-based Information Extraction Systems for Brain Radiology Reports Andreas Grivas, Beatrice Alex, Claire Grover, Richard Tobin, William Whiteley In: Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis

score(self, labels: nessie.types.StringArray, embedded_instances: nessie.types.FloatArray2D, **kwargs) → numpy.typing.NDArray[float]

Finds neighbours of each instance in the embedding space, computes a distribution over labels based on their distance, the resulting score is the entropy over this distribution.

Parameters

• labels – a (num_samples, ) numpy array

• embedded_instances – 2d numpy array of shape (num_items, encoding_dim)

Returns

a (num_samples, ) numpy array containing the scores for each instance

class nessie.detectors.knn_entropy.KnnFlagger(k: float = 10)

Bases: KnnErrorDetector

Based on

Not a cute stroke: Analysis of Rule- and Neural Network-based Information Extraction Systems for Brain Radiology Reports Andreas Grivas, Beatrice Alex, Claire Grover, Richard Tobin, William Whiteley In: Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis

error_detector_kind(self) → nessie.detectors.error_detector.DetectorKind