phylovelo.embedding
===================

.. py:module:: phylovelo.embedding


Classes
-------

.. autoapisummary::

   phylovelo.embedding.VelocityEmbedding


Functions
---------

.. autoapisummary::

   phylovelo.embedding.paired_correlation_rows
   phylovelo.embedding._as_float_array
   phylovelo.embedding.velocity_embedding


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

.. py:function:: paired_correlation_rows(A: numpy.array, B: numpy.array) -> numpy.array

   Calculate paired correlation

   Args:
       A: numpy.array
       B: numpy.array

   Return:
       numpy.array


.. py:function:: _as_float_array(x)

.. py:class:: VelocityEmbedding(count, xdr, v)

   .. py:attribute:: count


   .. py:attribute:: xdr


   .. py:attribute:: kNN
      :value: None



   .. py:attribute:: v


   .. py:attribute:: d


   .. py:attribute:: _d_mean


   .. py:attribute:: _d_centered


   .. py:attribute:: _d_norm


   .. py:attribute:: _d_nonzero


   .. py:attribute:: _d_nonzero_values


   .. py:attribute:: _neighbor_indices
      :value: None



   .. py:attribute:: neighs_log


   .. py:method:: rho(x)


   .. py:method:: get_neighbors(kNN)


   .. py:method:: _get_neighbor_indices()


   .. py:method:: _auto_chunk_size(n_neighs, n_genes, chunk_size=None)


   .. py:method:: _transition_probabilities(diff_vecs)


   .. py:method:: _project_neighbor_block(start, stop, neighs)


   .. py:method:: project_all(chunk_size=None, store_transition=False)


   .. py:method:: transit_mat1(i)


   .. py:method:: transit_mat(n_process=0)


   .. py:method:: project(i)


.. py:function:: velocity_embedding(sd: scData, target: str = 'count', n_neigh: int = None, chunk_size: int = None)

   Project velocity into embedding

   Args:
       sd:
           scData
       target: 
           count or x_normed
       n_neigh: 
           kNN pooling. Default: Ncells//3
       chunk_size:
           Number of cells per vectorized block. Default estimates a memory-safe size.