noether.data.datasets.cfd.shapenet_car.dataset
==============================================

.. py:module:: noether.data.datasets.cfd.shapenet_car.dataset


Attributes
----------

.. autoapisummary::

   noether.data.datasets.cfd.shapenet_car.dataset.logger
   noether.data.datasets.cfd.shapenet_car.dataset.NUM_PARAM_FOLDERS
   noether.data.datasets.cfd.shapenet_car.dataset.PREPROCESSED_FOLDER_NAME
   noether.data.datasets.cfd.shapenet_car.dataset.TEST_PARAM_INDEX
   noether.data.datasets.cfd.shapenet_car.dataset.SUPPORTED_SPLITS


Classes
-------

.. autoapisummary::

   noether.data.datasets.cfd.shapenet_car.dataset.ShapeNetCarDataset


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

.. py:data:: logger

.. py:data:: NUM_PARAM_FOLDERS
   :value: 9


.. py:data:: PREPROCESSED_FOLDER_NAME
   :value: 'preprocessed'


.. py:data:: TEST_PARAM_INDEX
   :value: 0


.. py:data:: SUPPORTED_SPLITS

.. py:class:: ShapeNetCarDataset(dataset_config)

   Bases: :py:obj:`noether.data.datasets.cfd.dataset.AeroDataset`


   Dataset implementation for ShapeNet Car CFD simulations.

   This dataset provides access to:
   - Surface properties: positions, pressure, normals
   - Volume properties: positions, velocity, normals, signed distance field (SDF)

   The dataset is split by parameter configurations:
   - Test: param0 (100 samples)
   - Validation: no validation split defined
   - Train: param1-8 (789 samples)

   Download link to the raw dataset: http://www.nobuyuki-umetani.com/publication/mlcfd_data.zip

   Expected directory structure:
       root/
           preprocessed/
               param0/
                   <simulation_id>/
                       surface_points.pt
                       surface_pressure.pt
                       surface_normals.pt
                       volume_velocity.pt
                       volume_points.pt
                       volume_sdf.pt
                       volume_normals.pt
               param1/
                   ...
               ...
               param8/

   :param dataset_config: Configuration object containing root path, split, and scaling parameters

   .. attribute:: split

      One of 'train', 'test', or 'valid'

   .. attribute:: source_root

      Path to preprocessed data directory

   .. attribute:: uris

      List of paths to individual simulation samples

   Initialize the ShapeNet Car dataset.

   :param dataset_config: Configuration for the dataset.

   :raises TypeError: If dataset_config is not ShapeNetDatasetConfig
   :raises ValueError: If configuration is invalid or split is unknown
   :raises FileNotFoundError: If data directory does not exist


   .. py:attribute:: split


   .. py:attribute:: source_root
      :type:  pathlib.Path


   .. py:property:: get_dataset_splits
      :type: noether.core.schemas.dataset.DatasetSplitIDs



   .. py:method:: sample_info(idx)

      Get information about a sample such as its local path, run name, etc.