sequince_density.utils
======================

.. py:module:: sequince_density.utils

.. autoapi-nested-parse::

   Utility helpers shared by density implementations.



Functions
---------

.. autoapisummary::

   sequince_density.utils.validate_training_data
   sequince_density.utils.draw_seed
   sequince_density.utils.torch_random_context


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

.. py:function:: validate_training_data(samples, dims, stage = 'Raw')

   Validate training particles using their native array backend.

   :param samples: Nonempty, finite particle coordinates. Validation does not modify them.
   :type samples: array, shape (n_samples, dims)
   :param dims: Expected number of dimensions.
   :type dims: int
   :param stage: Label for the data in error messages, for example "Transformed".
   :type stage: str, default="Raw"

   :raises ValueError: If the shape is invalid or any coordinates are non-finite. Non-finite
       errors report the affected dimension indices (zero-based).


.. py:function:: draw_seed(rng)

   Consume one deterministic integer seed from an optional RNG.


.. py:function:: torch_random_context(rng = None, *, device = None)

   Temporarily seed Torch and restore its global RNG state on exit.