artlib.hierarchical.SMART
=========================

.. py:module:: artlib.hierarchical.SMART

.. autoapi-nested-parse::

   SMART :cite:`bartfai1994hierarchical`.



Classes
-------

.. autoapisummary::

   artlib.hierarchical.SMART.SMART


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

.. py:class:: SMART(base_ART_class: Type, rho_values: Union[list[float], numpy.ndarray], base_params: dict, **kwargs)

   Bases: :py:obj:`artlib.hierarchical.DeepARTMAP.DeepARTMAP`


   SMART for Hierachical Clustering.

   This module implements SMART as first published in: :cite:`bartfai1994hierarchical`

   .. # Bartfai, G. (1994).
   .. # Hierarchical clustering with ART neural networks.
   .. # In Proc. IEEE International Conference on Neural Networks (ICNN)
   .. # (pp. 940–944). volume 2.
   .. # doi:10.1109/ICNN.1994.374307.

   SMART accepts an uninstantiated :class:`~artlib.common.BaseART.BaseART` class and
   hierarchically clusters data in a divisive fashion by using a set of vigilance
   values that monotonically increase in their restrictiveness. SMART is a special
   case of :class:`~artlib.hierarchical.DeepARTMAP.DeepARTMAP`, which forms the
   backbone of this class, where all channels receive the same data.



   .. py:attribute:: rho_values


   .. py:method:: prepare_data(X: Union[numpy.ndarray, list[numpy.ndarray]], y: Optional[numpy.ndarray] = None) -> Union[numpy.ndarray, Tuple[list[numpy.ndarray], Optional[numpy.ndarray]]]

      Prepare data for clustering.

      :param X: The dataset to prepare.
      :type X: np.ndarray

      :returns: Prepared data.
      :rtype: np.ndarray



   .. py:method:: restore_data(X: Union[numpy.ndarray, list[numpy.ndarray]], y: Optional[numpy.ndarray] = None) -> Union[numpy.ndarray, Tuple[list[numpy.ndarray], Optional[numpy.ndarray]]]

      Restore data to its original form before preparation.

      :param X: The dataset to restore.
      :type X: np.ndarray

      :returns: Restored data.
      :rtype: np.ndarray



   .. py:method:: fit(X: numpy.ndarray, y: Optional[numpy.ndarray] = None, max_iter=1, match_tracking: Literal['MT+', 'MT-', 'MT0', 'MT1', 'MT~'] = 'MT+', epsilon: float = 0.0)

      Fit the SMART model to the data.

      :param X: The dataset to fit the model on.
      :type X: np.ndarray
      :param y: Not used, present for compatibility.
      :type y: np.ndarray, optional
      :param max_iter: The number of iterations to run the model on the data.
      :type max_iter: int, optional
      :param match_tracking: The match reset method to use when adjusting vigilance.
      :type match_tracking: {"MT+", "MT-", "MT0", "MT1", "MT~"}, optional
      :param epsilon: A small value to adjust vigilance during match tracking.
      :type epsilon: float, optional

      :returns: Fitted SMART model.
      :rtype: SMART



   .. py:method:: partial_fit(X: numpy.ndarray, y: Optional[numpy.ndarray] = None, match_tracking: Literal['MT+', 'MT-', 'MT0', 'MT1', 'MT~'] = 'MT+', epsilon: float = 0.0)

      Partial fit the SMART model to the data.

      :param X: The dataset to partially fit the model on.
      :type X: np.ndarray
      :param y: Not used, present for compatibility.
      :type y: np.ndarray, optional
      :param match_tracking: The match reset method to use when adjusting vigilance.
      :type match_tracking: {"MT+", "MT-", "MT0", "MT1", "MT~"}, optional
      :param epsilon: A small value to adjust vigilance during match tracking.
      :type epsilon: float, optional

      :returns: Partially fitted SMART model.
      :rtype: SMART



   .. py:method:: plot_cluster_bounds(ax: matplotlib.axes.Axes, colors: artlib.common.utils.IndexableOrKeyable, linewidth: int = 1)

      Visualize the cluster boundaries.

      :param ax: The matplotlib axes on which to plot the cluster boundaries.
      :type ax: Axes
      :param colors: The colors to use for each cluster.
      :type colors: IndexableOrKeyable
      :param linewidth: The width of the boundary lines.
      :type linewidth: int, optional

      :rtype: None



   .. py:method:: visualize(X: numpy.ndarray, y: numpy.ndarray, ax: Optional[matplotlib.axes.Axes] = None, marker_size: int = 10, linewidth: int = 1, colors: Optional[artlib.common.utils.IndexableOrKeyable] = None)

      Visualize the clustering of the data with cluster boundaries.

      :param X: The dataset to visualize.
      :type X: np.ndarray
      :param y: The cluster labels for the data points.
      :type y: np.ndarray
      :param ax: The matplotlib axes on which to plot the visualization.
      :type ax: Axes, optional
      :param marker_size: The size of the data points in the plot.
      :type marker_size: int, optional
      :param linewidth: The width of the cluster boundary lines.
      :type linewidth: int, optional
      :param colors: The colors to use for each cluster.
      :type colors: IndexableOrKeyable, optional

      :rtype: None