medcat.config_transformers_ner

Module Contents

Classes

General	The general part of the Transformers NER config
ConfigTransformersNER	The transformer NER config

class medcat.config_transformers_ner.General

Bases: medcat.config.MixingConfig, medcat.config.BaseModel

The general part of the Transformers NER config

class Config

extra

validate_assignment = True

name: str = 'deid'

model_name: str = 'roberta-base'

Can be path also

seed: int = 13

description: str = 'No description'

Should provide a basic description of this MetaCAT model

pipe_batch_size_in_chars: int = 20000000

How many characters are piped at once into the meta_cat class

ner_aggregation_strategy: str = 'simple'

Agg strategy for HF pipeline for NER

chunking_overlap_window: medcat.config.Optional[int] = 5

Size of the overlap window used for chunking

test_size: float = 0.2

last_train_on: medcat.config.Optional[int]

verbose_metrics: bool = False

class medcat.config_transformers_ner.ConfigTransformersNER

Bases: medcat.config.MixingConfig, medcat.config.BaseModel

The transformer NER config

class Config

extra

validate_assignment = True

general: General