:py:mod:`medcat.config_transformers_ner`
========================================

.. py:module:: medcat.config_transformers_ner


Module Contents
---------------

Classes
~~~~~~~

.. autoapisummary::

   medcat.config_transformers_ner.General
   medcat.config_transformers_ner.ConfigTransformersNER




.. py:class:: General


   Bases: :py:obj:`medcat.config.MixingConfig`, :py:obj:`medcat.config.BaseModel`

   The general part of the Transformers NER config

   .. py:class:: Config


      .. py:attribute:: extra

         

      .. py:attribute:: validate_assignment
         :value: True

         


   .. py:attribute:: name
      :type: str
      :value: 'deid'

      

   .. py:attribute:: model_name
      :type: str
      :value: 'roberta-base'

      Can be path also

   .. py:attribute:: seed
      :type: int
      :value: 13

      

   .. py:attribute:: description
      :type: str
      :value: 'No description'

      Should provide a basic description of this MetaCAT model

   .. py:attribute:: pipe_batch_size_in_chars
      :type: int
      :value: 20000000

      How many characters are piped at once into the meta_cat class

   .. py:attribute:: ner_aggregation_strategy
      :type: str
      :value: 'simple'

      Agg strategy for HF pipeline for NER

   .. py:attribute:: chunking_overlap_window
      :type: medcat.config.Optional[int]
      :value: 5

      Size of the overlap window used for chunking

   .. py:attribute:: test_size
      :type: float
      :value: 0.2

      

   .. py:attribute:: last_train_on
      :type: medcat.config.Optional[int]

      

   .. py:attribute:: verbose_metrics
      :type: bool
      :value: False

      


.. py:class:: ConfigTransformersNER


   Bases: :py:obj:`medcat.config.MixingConfig`, :py:obj:`medcat.config.BaseModel`

   The transformer NER config

   .. py:class:: Config


      .. py:attribute:: extra

         

      .. py:attribute:: validate_assignment
         :value: True

         


   .. py:attribute:: general
      :type: General