AFQ.recognition.clustering
==========================

.. py:module:: AFQ.recognition.clustering


Functions
---------

.. autoapisummary::

   AFQ.recognition.clustering._compute_mean_euclidean_matrix
   AFQ.recognition.clustering._distance_to_similarity
   AFQ.recognition.clustering._rectangular_similarity_matrix
   AFQ.recognition.clustering.spectral_atlas_label
   AFQ.recognition.clustering.subcluster_by_atlas


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

.. py:function:: _compute_mean_euclidean_matrix(group_n, group_m)

.. py:function:: _distance_to_similarity(distance, sigmasq)

.. py:function:: _rectangular_similarity_matrix(fgarray_sub, fgarray_atlas, sigma)

.. py:function:: spectral_atlas_label(sub_fgarray, atlas_fgarray, atlas_data=None, sigma_multiplier=1.0, cluster_indices=None)

   
   Use an existing atlas to label a new streamlines.


   :Parameters:

       **sub_fgarray** : ndarray
           Resampled fiber group to be labeled.

       **atlas_fgarray** : ndarray
           Resampled atlas to use for labelling.

       **atlas_data** : dict, optional
           Precomputed atlas data formatted as a dictionary of arrays and floats.
           See `afd.read_org800_templates` as a reference.

       **sigma_multiplier** : float, optional
           Multiplier for the sigma value used in computing the similarity
           matrix. Default is 1.0.

       **cluster_indices** : list of int, optional
           If provided, only these cluster indices from the atlas will be used
           for labeling. Default is None, which uses all clusters.

   :Returns:

       tuple of (ndarray, ndarray)
           Cluster indices for all the fibers and their embedding













   ..
       !! processed by numpydoc !!

.. py:function:: subcluster_by_atlas(sub_trk, mapping, dwi_ref, cluster_indices, atlas_data=None, n_points=20, batch_size=int(50000.0))

   
   Use an existing atlas to label a new set of streamlines, and return the
   cluster indices for each streamline.


   :Parameters:

       **sub_trk** : StatefulTractogram
           streamlines to be labeled.

       **mapping** : DIPY or pyAFQ mapping
           Mapping to use to move streamlines.

       **dwi_ref** : Nifti1Image
           Image defining reference for where the atlas streamlines move to.

       **cluster_indices** : list of int
           Cluster indices from the atlas to use for labeling.

       **atlas_data** : dict, optional
           Precomputed atlas data formatted as a dictionary of arrays and floats.
           See `afd.read_org800_templates` as a reference.

       **n_points** : int, optional
           Number of points to resample streamlines to for labeling. Default is 20.

       **batch_size** : int, optional
           Number of streamlines to process in a batch. Default is 50,000.














   ..
       !! processed by numpydoc !!