:py:mod:`n2j.trainval_data.graphs.cosmodc2_graph`
=================================================

.. py:module:: n2j.trainval_data.graphs.cosmodc2_graph

.. autoapi-nested-parse::

   Training input graph X created from the postprocessed CosmoDC2 catalog



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

Classes
~~~~~~~

.. autoapisummary::

   n2j.trainval_data.graphs.cosmodc2_graph.CosmoDC2Graph
   n2j.trainval_data.graphs.cosmodc2_graph.CosmoDC2GraphHealpix




.. py:class:: CosmoDC2Graph(in_dir, healpixes, raytracing_out_dirs, aperture_size, n_data, features, subsample_pdf_func=None, n_subsample=None, subsample_with_replacement=True, stop_mean_std_early=False, n_cores=20, num_workers=4, out_dir=None, seed=123)

   Bases: :py:obj:`torch.utils.data.dataset.ConcatDataset`

   Concatenation of multiple CosmoDC2GraphHealpix instances,
   with an added data transformation functionality


   .. py:method:: data_stats()

      Statistics of the X, Y data used for standardizing

              


   .. py:method:: data_stats_valtest()

      Statistics of the X, Y data on validation set used for
      resampling to mimic training dist.
      Mean, std computation skipped.



   .. py:method:: __getitem__(idx)



.. py:class:: CosmoDC2GraphHealpix(healpix, in_dir, raytracing_out_dir, aperture_size, n_data, features, n_cores=20, out_dir=None, debug=False)

   Bases: :py:obj:`n2j.trainval_data.graphs.base_graph.BaseGraph`

   Set of graphs representing a single healpix of the CosmoDC2 field

       

   .. py:property:: n_features


   .. py:property:: raw_dir
      :type: str


   .. py:property:: raw_file_name


   .. py:property:: raw_file_names


   .. py:property:: processed_file_fmt


   .. py:property:: processed_file_path_fmt


   .. py:property:: processed_file_names

      A list of files relative to self.processed_dir which needs to be
      found in order to skip the processing



   .. py:attribute:: columns
      :value: ['ra', 'dec', 'galaxy_id', 'redshift']

      

   .. py:method:: get_los_node()

      Properties of the sightline galaxy, with unobservable features
      (everything other than position) appropriately masked out.

      Parameters
      ----------
      ra_los : ra of sightline, in arcmin
      dec_los : dec of sightline, in arcmin



   .. py:method:: download()

      Called when `raw_file_names` aren't found

              


   .. py:method:: get_gals_iterator(healpix, columns, chunksize=100000)

      Get an iterator over the galaxy catalog defining the line-of-sight
      galaxies



   .. py:method:: get_edges(ra_dec)

      Get the edge indices from the node positions

      Parameters
      ----------
      ra_dec : `np.ndarray`
          ra and dec of nodes, of shape `[n_nodes, 2]`

      Returns
      -------
      `torch.LongTensor`
          edge indices, of shape `[2, n_edges]`



   .. py:method:: _save_graph_to_disk(i)


   .. py:method:: _get_y_class(y)


   .. py:method:: process_single(i)

      Process a single sightline indexed i

              


   .. py:method:: process()

      Process multiple sightline in parallel

              


   .. py:method:: len()


   .. py:method:: get(idx)