dicee.evaluator
===============

.. py:module:: dicee.evaluator


Classes
-------

.. autoapisummary::

   dicee.evaluator.Evaluator


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

.. py:class:: Evaluator(args, is_continual_training=None)

    Evaluator class to evaluate KGE models in various downstream tasks

    Arguments
   ----------
   executor: Executor class instance


   .. py:attribute:: re_vocab
      :value: None



   .. py:attribute:: er_vocab
      :value: None



   .. py:attribute:: ee_vocab
      :value: None



   .. py:attribute:: func_triple_to_bpe_representation
      :value: None



   .. py:attribute:: is_continual_training
      :value: None



   .. py:attribute:: num_entities
      :value: None



   .. py:attribute:: num_relations
      :value: None



   .. py:attribute:: args


   .. py:attribute:: report


   .. py:attribute:: during_training
      :value: False



   .. py:method:: vocab_preparation(dataset) -> None

      A function to wait future objects for the attributes of executor


      :rtype: None



   .. py:method:: eval(dataset: dicee.knowledge_graph.KG, trained_model, form_of_labelling, during_training=False) -> None


   .. py:method:: eval_rank_of_head_and_tail_entity(*, train_set, valid_set=None, test_set=None, trained_model)


   .. py:method:: eval_rank_of_head_and_tail_byte_pair_encoded_entity(*, train_set=None, valid_set=None, test_set=None, ordered_bpe_entities, trained_model)


   .. py:method:: eval_with_byte(*, raw_train_set, raw_valid_set=None, raw_test_set=None, trained_model, form_of_labelling) -> None

      Evaluate model after reciprocal triples are added



   .. py:method:: eval_with_bpe_vs_all(*, raw_train_set, raw_valid_set=None, raw_test_set=None, trained_model, form_of_labelling) -> None

      Evaluate model after reciprocal triples are added



   .. py:method:: eval_with_vs_all(*, train_set, valid_set=None, test_set=None, trained_model, form_of_labelling) -> None

      Evaluate model after reciprocal triples are added



   .. py:method:: evaluate_lp_k_vs_all(model, triple_idx, info=None, form_of_labelling=None)

      Filtered link prediction evaluation.
      :param model:
      :param triple_idx: test triples
      :param info:
      :param form_of_labelling:
      :return:



   .. py:method:: evaluate_lp_with_byte(model, triples: List[List[str]], info=None)


   .. py:method:: evaluate_lp_bpe_k_vs_all(model, triples: List[List[str]], info=None, form_of_labelling=None)

      :param model:
      :param triples:
      :type triples: List of lists
      :param info:
      :param form_of_labelling:



   .. py:method:: evaluate_lp(model, triple_idx, info: str)


   .. py:method:: dummy_eval(trained_model, form_of_labelling: str)


   .. py:method:: eval_with_data(dataset, trained_model, triple_idx: numpy.ndarray, form_of_labelling: str)