:py:mod:`medcat.utils.relation_extraction.base_component`
=========================================================

.. py:module:: medcat.utils.relation_extraction.base_component


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

Classes
~~~~~~~

.. autoapisummary::

   medcat.utils.relation_extraction.base_component.BaseComponent_RelationExtraction




Attributes
~~~~~~~~~~

.. autoapisummary::

   medcat.utils.relation_extraction.base_component.logger


.. py:data:: logger

   

.. py:class:: BaseComponent_RelationExtraction(tokenizer = BaseTokenizerWrapper_RelationExtraction(), model = None, model_config = None, config = ConfigRelCAT(), task = 'train', init_model = False)


   .. py:attribute:: name
      :value: 'base_component_rel'

      

   .. py:method:: __init__(tokenizer = BaseTokenizerWrapper_RelationExtraction(), model = None, model_config = None, config = ConfigRelCAT(), task = 'train', init_model = False)

      Component that holds the model and everything for RelCAT.

      :param tokenizer: The base tokenizer for RelCAT.
      :type tokenizer: BaseTokenizerWrapper_RelationExtraction
      :param model: The model wrapper.
      :type model: BaseModel_RelationExtraction
      :param model_config: The model-specific config.
      :type model_config: BaseConfig_RelationExtraction
      :param config: The RelCAT config.
      :type config: ConfigRelCAT
      :param task: The task - used for checkpointing.
      :type task: str
      :param init_model: Loads default BERT base model, tokenizer, model config. Defaults to False.
      :type init_model: bool


   .. py:method:: save(save_path)

      Saves model and its dependencies to specified save_path folder.
          The CDB is obviously not saved, it is however necessary to save the tokenizer used.

      :param save_path: folder path in which to save the model & deps.
      :type save_path: str


   .. py:method:: load(pretrained_model_name_or_path = './')
      :classmethod:

      :param pretrained_model_name_or_path: Path to RelCAT model. Defaults to "./".
      :type pretrained_model_name_or_path: str

      :Returns: **BaseComponent_RelationExtraction** -- component.