mmgp.dimensionality_reduction
=============================

.. py:module:: mmgp.dimensionality_reduction


Attributes
----------

.. autoapisummary::

   mmgp.dimensionality_reduction.available_dimensionality_reduction_algos


Classes
-------

.. autoapisummary::

   mmgp.dimensionality_reduction.DimensionalityReductor


Functions
---------

.. autoapisummary::

   mmgp.dimensionality_reduction.truncated_SVD_sym_lower


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

.. py:data:: available_dimensionality_reduction_algos
   :value: ['SnapshotPOD']


   List of available dimensionality reduction algorithms

.. py:class:: DimensionalityReductor(algo: str, options: dict, common_morphed_mesh: Muscat.Containers.Mesh, input_or_output: str)

   Bases: :py:obj:`object`


   The DimensionalityReductor class is designed to perform dimensionality reduction
   on a set of data using different algorithms.

   Initializes an instance of the DimensionalityReductor class.

   :param algo: The name of the dimensionality reduction algorithm to use.
   :type algo: str
   :param options (dict[str: Union[int, str]]): A dictionary of options and settings for the algorithm with fields 'number_of_modes' and 'correlation_type'.
   :param common_morphed_mesh: The mesh containing the data for dimensionality reduction.
   :type common_morphed_mesh: Mesh
   :param input_or_output: Specifies whether the data should be reduced based on input or output.
   :type input_or_output: str

   :raises AssertionError: If the specified algorithm is not supported.

   .. rubric:: Example

   .. code-block:: python

       from mmgp.dimensionality_reduction import DimensionalityReductor
       options = { 'number_of_modes': 8, 'correlation_type': 'mass_matrix' }
       dim_reductor = Regressor('SnapshotPOD', options)


   .. py:attribute:: algo
      :type:  str


   .. py:attribute:: options
      :type:  dict


   .. py:attribute:: common_morphed_mesh
      :type:  Muscat.Containers.Mesh


   .. py:attribute:: input_or_output
      :type:  str


   .. py:attribute:: training_data
      :type:  dict
      :value: None



   .. py:method:: fit_transform(snapshots: numpy.ndarray) -> numpy.ndarray

      Fits and transforms the dimensionality reduction model to the data.

      :param snapshots: The input data snapshots to be reduced.
      :type snapshots: np.ndarray

      :returns: The reduced data in the form of generalized coordinates.
      :rtype: np.ndarray



   .. py:method:: transform(snapshots: numpy.ndarray) -> numpy.ndarray

      Apply dimensionality reduction to a set of data 'snapshots'

      :param snapshots: The input data snapshots that needs to be transformed
      :type snapshots: np.ndarray

      :returns: The transformed data or dataset resulting from the dimensionality reduction operation.
      :rtype: np.ndarray



   .. py:method:: inverse_transform(reduced_dimension_representation: numpy.ndarray) -> numpy.ndarray

      Reverse the dimensionality reduction transformation applied to a reduced-dimensional representation of data.

      :param reduced_dimension_representation: The reduced-dimensional representation of the data
      :type reduced_dimension_representation: np.ndarray

      :returns: The reconstructed data resulting from the inverse transformation.
      :rtype: np.ndarray



.. py:function:: truncated_SVD_sym_lower(matrix: scipy.sparse.csr, epsilon: float = None, nb_modes: int = None) -> Tuple[numpy.ndarray, numpy.ndarray]

   Computes a truncated singular value decomposition of a symetric definite
   matrix in scipy.sparse.csr format. Only the lower triangular part needs
   to be defined

   :param matrix: the input matrix
   :type matrix: scipy.sparse.csr
   :param epsilon: the truncation tolerence, determining the number of keps eigenvalues
   :type epsilon: float
   :param nb_modes: the number of keps eigenvalues
   :type nb_modes: int

   :returns: * *np.ndarray* -- kept eigenvalues, of size (numberOfEigenvalues)
             * *np.ndarray* -- kept eigenvectors, of size (numberOfEigenvalues, numberOfSnapshots)