:py:mod:`deeprvat.data.rare`
============================

.. py:module:: deeprvat.data.rare

.. autodoc2-docstring:: deeprvat.data.rare
   :allowtitles:

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

Classes
~~~~~~~

.. list-table::
   :class: autosummary longtable
   :align: left

   * - :py:obj:`PaddedAnnotations <deeprvat.data.rare.PaddedAnnotations>`
     - .. autodoc2-docstring:: deeprvat.data.rare.PaddedAnnotations
          :summary:
   * - :py:obj:`SparseGenotype <deeprvat.data.rare.SparseGenotype>`
     - .. autodoc2-docstring:: deeprvat.data.rare.SparseGenotype
          :summary:

Data
~~~~

.. list-table::
   :class: autosummary longtable
   :align: left

   * - :py:obj:`logger <deeprvat.data.rare.logger>`
     - .. autodoc2-docstring:: deeprvat.data.rare.logger
          :summary:

API
~~~

.. py:data:: logger
   :canonical: deeprvat.data.rare.logger
   :value: 'getLogger(...)'

   .. autodoc2-docstring:: deeprvat.data.rare.logger

.. py:class:: PaddedAnnotations(base_dataset, annotations: typing.List[str], thresholds: typing.Dict[str, str] = None, gene_file: typing.Optional[str] = None, genes_to_keep: typing.Optional[typing.Set[str]] = None, pad_value: typing.Union[float, int, str] = 0.0, verbose: bool = False, low_memory: bool = False, skip_embedding: bool = False)
   :canonical: deeprvat.data.rare.PaddedAnnotations

   .. autodoc2-docstring:: deeprvat.data.rare.PaddedAnnotations

   .. rubric:: Initialization

   .. autodoc2-docstring:: deeprvat.data.rare.PaddedAnnotations.__init__

   .. py:method:: embed(idx: int, variant_ids: numpy.ndarray, genotype: numpy.ndarray) -> typing.List[typing.List[torch.Tensor]]
      :canonical: deeprvat.data.rare.PaddedAnnotations.embed

      .. autodoc2-docstring:: deeprvat.data.rare.PaddedAnnotations.embed

   .. py:method:: collate_fn(batch: typing.List[typing.List[typing.List[numpy.ndarray]]], device: torch.device = torch.device('cpu')) -> torch.Tensor
      :canonical: deeprvat.data.rare.PaddedAnnotations.collate_fn

      .. autodoc2-docstring:: deeprvat.data.rare.PaddedAnnotations.collate_fn

   .. py:method:: setup_annotations(rare_variant_ids: pandas.Series, thresholds: typing.Optional[typing.Dict[str, str]], gene_file: typing.Optional[str], genes_to_keep: typing.Optional[typing.Set[str]] = None)
      :canonical: deeprvat.data.rare.PaddedAnnotations.setup_annotations

      .. autodoc2-docstring:: deeprvat.data.rare.PaddedAnnotations.setup_annotations

   .. py:method:: apply_thresholds(thresholds: typing.Optional[typing.Dict[str, str]])
      :canonical: deeprvat.data.rare.PaddedAnnotations.apply_thresholds

      .. autodoc2-docstring:: deeprvat.data.rare.PaddedAnnotations.apply_thresholds

   .. py:method:: remap_group_ids()
      :canonical: deeprvat.data.rare.PaddedAnnotations.remap_group_ids

      .. autodoc2-docstring:: deeprvat.data.rare.PaddedAnnotations.remap_group_ids

   .. py:method:: setup_metadata()
      :canonical: deeprvat.data.rare.PaddedAnnotations.setup_metadata

      .. autodoc2-docstring:: deeprvat.data.rare.PaddedAnnotations.setup_metadata

   .. py:method:: get_metadata() -> typing.Dict[str, numpy.ndarray]
      :canonical: deeprvat.data.rare.PaddedAnnotations.get_metadata

      .. autodoc2-docstring:: deeprvat.data.rare.PaddedAnnotations.get_metadata

.. py:class:: SparseGenotype(base_dataset, annotations: typing.List[str], thresholds: typing.Dict[str, str] = None, gene_file: typing.Optional[str] = None, genes_to_keep: typing.Optional[typing.Set[str]] = None, verbose: bool = False, low_memory: bool = False)
   :canonical: deeprvat.data.rare.SparseGenotype

   .. autodoc2-docstring:: deeprvat.data.rare.SparseGenotype

   .. rubric:: Initialization

   .. autodoc2-docstring:: deeprvat.data.rare.SparseGenotype.__init__

   .. py:method:: embed(idx: int, variant_ids: numpy.ndarray, genotype: numpy.ndarray) -> scipy.sparse.coo_matrix
      :canonical: deeprvat.data.rare.SparseGenotype.embed

      .. autodoc2-docstring:: deeprvat.data.rare.SparseGenotype.embed

   .. py:method:: collate_fn(batch: typing.List[scipy.sparse.coo_matrix]) -> scipy.sparse.coo_matrix
      :canonical: deeprvat.data.rare.SparseGenotype.collate_fn

      .. autodoc2-docstring:: deeprvat.data.rare.SparseGenotype.collate_fn

   .. py:method:: setup_annotations(rare_variant_ids: pandas.Series, thresholds: typing.Optional[typing.Dict[str, str]], gene_file: typing.Optional[str], genes_to_keep: typing.Optional[typing.Set[str]] = None)
      :canonical: deeprvat.data.rare.SparseGenotype.setup_annotations

      .. autodoc2-docstring:: deeprvat.data.rare.SparseGenotype.setup_annotations

   .. py:method:: apply_thresholds(thresholds: typing.Optional[typing.Dict[str, str]])
      :canonical: deeprvat.data.rare.SparseGenotype.apply_thresholds

      .. autodoc2-docstring:: deeprvat.data.rare.SparseGenotype.apply_thresholds

   .. py:method:: remap_group_ids()
      :canonical: deeprvat.data.rare.SparseGenotype.remap_group_ids

      .. autodoc2-docstring:: deeprvat.data.rare.SparseGenotype.remap_group_ids

   .. py:method:: setup_metadata()
      :canonical: deeprvat.data.rare.SparseGenotype.setup_metadata

      .. autodoc2-docstring:: deeprvat.data.rare.SparseGenotype.setup_metadata

   .. py:method:: get_metadata() -> typing.Dict[str, numpy.ndarray]
      :canonical: deeprvat.data.rare.SparseGenotype.get_metadata

      .. autodoc2-docstring:: deeprvat.data.rare.SparseGenotype.get_metadata