:py:mod:`helper_classes`
========================

.. py:module:: helper_classes


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

Classes
~~~~~~~

.. autoapisummary::

   helper_classes.DatasetTriple
   helper_classes.HeadAndRelationBatchLoader
   helper_classes.Reproduce




Attributes
~~~~~~~~~~

.. autoapisummary::

   helper_classes.seed


.. py:data:: seed
   :value: 1

   

.. py:class:: DatasetTriple(data)


   Bases: :py:obj:`torch.utils.data.Dataset`

   An abstract class representing a :class:`Dataset`.

   All datasets that represent a map from keys to data samples should subclass
   it. All subclasses should overwrite :meth:`__getitem__`, supporting fetching a
   data sample for a given key. Subclasses could also optionally overwrite
   :meth:`__len__`, which is expected to return the size of the dataset by many
   :class:`~torch.utils.data.Sampler` implementations and the default options
   of :class:`~torch.utils.data.DataLoader`.

   .. note::
     :class:`~torch.utils.data.DataLoader` by default constructs a index
     sampler that yields integral indices.  To make it work with a map-style
     dataset with non-integral indices/keys, a custom sampler must be provided.

   .. py:method:: __len__()


   .. py:method:: __getitem__(idx)



.. py:class:: HeadAndRelationBatchLoader(er_vocab, num_e)


   Bases: :py:obj:`torch.utils.data.Dataset`

   An abstract class representing a :class:`Dataset`.

   All datasets that represent a map from keys to data samples should subclass
   it. All subclasses should overwrite :meth:`__getitem__`, supporting fetching a
   data sample for a given key. Subclasses could also optionally overwrite
   :meth:`__len__`, which is expected to return the size of the dataset by many
   :class:`~torch.utils.data.Sampler` implementations and the default options
   of :class:`~torch.utils.data.DataLoader`.

   .. note::
     :class:`~torch.utils.data.DataLoader` by default constructs a index
     sampler that yields integral indices.  To make it work with a map-style
     dataset with non-integral indices/keys, a custom sampler must be provided.

   .. py:method:: __len__()


   .. py:method:: __getitem__(idx)



.. py:class:: Reproduce


   .. py:method:: get_er_vocab(data)
      :staticmethod:


   .. py:method:: get_head_tail_vocab(data)
      :staticmethod:


   .. py:method:: get_data_idxs(data)


   .. py:method:: get_batch_1_to_N(er_vocab, er_vocab_pairs, idx)


   .. py:method:: evaluate_link_prediction(model, data, per_rel_flag_=True)


   .. py:method:: reproduce(model_path, data_path, model_name, per_rel_flag_=False, tail_pred_constraint=False, out_of_vocab_flag=False)


   .. py:method:: get_embeddings(model_path, data_path, model_name, per_rel_flag_=False, tail_pred_constraint=False, out_of_vocab_flag=False)


   .. py:method:: load_model(model_path, model_name)


   .. py:method:: reproduce_ensemble(model, data_path, per_rel_flag_=False, tail_pred_constraint=False, out_of_vocab_flag=False)

      per_rel_flag_ reports link prediction results per relations.
      flag_of_removal  -> removes triples from testing split containing entities that did not occur during training
      at testing time.

      lp_based_on_head_and_tail_entity_rankings-> computes rank of missing entities based on head and tail entity.