:py:mod:`medcat.linking.vector_context_model`
=============================================

.. py:module:: medcat.linking.vector_context_model


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

Classes
~~~~~~~

.. autoapisummary::

   medcat.linking.vector_context_model.ContextModel




Attributes
~~~~~~~~~~

.. autoapisummary::

   medcat.linking.vector_context_model.logger


.. py:data:: logger

   

.. py:class:: ContextModel(cdb, vocab, config)


   Bases: :py:obj:`object`

   Used to learn embeddings for concepts and calculate similarities in new documents.

   :param cdb: The Context Database
   :type cdb: CDB
   :param vocab: The vocabulary
   :type vocab: Vocab
   :param config: The config to be used
   :type config: Config

   .. py:method:: __init__(cdb, vocab, config)


   .. py:method:: get_context_tokens(entity, doc, size)

      Get context tokens for an entity, this will skip anything that
      is marked as skip in token._.to_skip

      :param entity: The entity to look for.
      :type entity: Span
      :param doc: The document look in.
      :type doc: Doc
      :param size: The size of the entity.
      :type size: int

      :Returns: **Tuple** -- The tokens on the left, centre, and right.


   .. py:method:: get_context_vectors(entity, doc, cui=None)

      Given an entity and the document it will return the context representation for the
      given entity.

      :param entity: The entity to look for.
      :type entity: Span
      :param doc: The document to look in.
      :type doc: Doc
      :param cui: The CUI.
      :type cui: Any

      :Returns: **Dict** -- The context vector.


   .. py:method:: similarity(cui, entity, doc)

      Calculate the similarity between the learnt context for this CUI and the context
      in the given `doc`.

      :param cui: The CUI.
      :type cui: str
      :param entity: The entity to look for.
      :type entity: Span
      :param doc: The document to look in.
      :type doc: Doc

      :Returns: **float** -- The similarity.


   .. py:method:: _similarity(cui, vectors)

      Calculate similarity once we have vectors and a cui.

      :param cui: The CUI.
      :type cui: str
      :param vectors: The vectors.
      :type vectors: Dict

      :Returns: **float** -- The similarity.


   .. py:method:: disambiguate(cuis, entity, name, doc)


   .. py:method:: train(cui, entity, doc, negative = False, names = [])

      Update the context representation for this CUI, given it's correct location (entity)
      in a document (doc).

      :param cui: The CUI to train.
      :type cui: str
      :param entity: The entity we're at.
      :type entity: Span
      :param doc: The document within which we're working.
      :type doc: Doc
      :param negative: Whether or not the example is negative. Defaults to False.
      :type negative: bool
      :param names: Optionally used to update the `status` of a name-cui pair in the CDB.
      :type names: List[str]/Dict


   .. py:method:: train_using_negative_sampling(cui)