lasdi.latent_dynamics.sindy
===========================

.. py:module:: lasdi.latent_dynamics.sindy


Classes
-------

.. autoapisummary::

   lasdi.latent_dynamics.sindy.SINDy


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

.. py:class:: SINDy(dim, nt, config)

   Bases: :py:obj:`lasdi.latent_dynamics.LatentDynamics`


   .. py:attribute:: fd_type
      :value: ''



   .. py:attribute:: fd
      :value: None



   .. py:attribute:: fd_oper
      :value: None



   .. py:attribute:: ncoefs


   .. py:attribute:: coef_norm_order
      :value: 1



   .. py:attribute:: MSE


   .. py:method:: calibrate(Z, dt, compute_loss=True, numpy=False)

      loop over all train cases, if Z dimension is 3



   .. py:method:: compute_time_derivative(Z, Dt)

      Builds the SINDy dataset, assuming only linear terms in the SINDy dataset. The time derivatives are computed through
      finite difference.

      Z is the encoder output (2D tensor), with shape [time_dim, space_dim]
      Dt is the size of timestep (assumed to be a uniform scalar)

      The output dZdt is a 2D tensor with the same shape of Z.




   .. py:method:: simulate(coefs, z0, t_grid)

      Integrates each system of ODEs corresponding to each training points, given the initial condition Z0 = encoder(U0)




   .. py:method:: export()