Source Code for Module mvpa.mappers.pca

 1  # emacs: -*- mode: python; py-indent-offset: 4; indent-tabs-mode: nil -*- 
 2  # vi: set ft=python sts=4 ts=4 sw=4 et: 
 3  ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ## 
 4  # 
 5  #   See COPYING file distributed along with the PyMVPA package for the 
 6  #   copyright and license terms. 
 7  # 
 8  ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ## 
 9  """Data mapper""" 
10   
11  __docformat__ = 'restructuredtext' 
12   
13  import numpy as N 
14   
15  from mvpa.base import warning 
16  from mvpa.base.dochelpers import enhancedDocString 
17  from mvpa.mappers.base import ProjectionMapper 
18   
19  import mvpa.base.externals as externals 
20  if externals.exists('mdp', raiseException=True): 
21      from mdp.nodes import NIPALSNode 
22   
23   
24 -class PCAMapper(ProjectionMapper): 
25      """Mapper to project data onto PCA components estimated from some dataset. 
26   
27      After the mapper has been instantiated, it has to be train first. The PCA 
28      mapper only handles 2D data matrices. 
29      """ 
30 -    def __init__(self, transpose=False, **kwargs): 
31          ProjectionMapper.__init__(self, **kwargs) 
32   
33          self._var = None 
34   
35   
36      __doc__ = enhancedDocString('PCAMapper', locals(), ProjectionMapper) 
37   
38   
39 -    def _train(self, dataset): 
40          """Determine the projection matrix onto the components from 
41          a 2D samples x feature data matrix. 
42          """ 
43          samples = dataset.samples 
44          dtype = samples.dtype 
45          if str(dtype).startswith('uint') \ 
46                 or str(dtype).startswith('int'): 
47                  warning("PCA: input data is in integers. " + \ 
48                          "MDP's NIPALSNode operates only on floats, thus "+\ 
49                          "coercing to double") 
50                  dtype = N.double 
51                  samples = samples.astype(N.double) 
52   
53          node = NIPALSNode(dtype=dtype) 
54          node.train(samples) 
55          self._proj = N.asmatrix(node.get_projmatrix()) 
56          self._recon = N.asmatrix(node.get_recmatrix()) 
57   
58          # store variance per PCA component 
59          self._var = node.d 
60   
61   
62      var = property(fget=lambda self: self._var, doc='Variances per component') 
63