kazu.steps.ner.spacy_ner

Classes

SpacyNerStep

A simple spacy NER implementation.

class kazu.steps.ner.spacy_ner.SpacyNerStep

Bases: Step

A simple spacy NER implementation.

Runs a spacy pipeline over document sections, expecting the resulting spacy doc to have a populated doc.ents field.

__call__(doc)

Process documents and respond with processed and failed documents.

Note that many steps will be decorated by document_iterating_step() or document_batch_step() which will modify the ‘original’ __call__ function signature to match the expected signature for a step, as the decorators handle the exception/failed documents logic for you.

Parameters:

• docs

• self (Self)

• doc (Document)

Returns:

The first element is all the provided docs (now modified by the processing), the second is the docs that failed to (fully) process correctly.

Return type:

tuple[list[Document], list[Document]]

__init__(path, add_sentence_spans=True)

Parameters:

• path (str) – path to the spacy pipeline to use.

• add_sentence_spans (bool) – If True, add sentence spans to the section.