Source Code for Module mvpa.measures.pls

 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   
10  __docformat__ = 'restructuredtext' 
11   
12  import numpy as N 
13   
14  from mvpa.measures.base import FeaturewiseDatasetMeasure 
15   
16  if __debug__: 
17      from mvpa.base import debug 
18   
19   
20 -class PLS(FeaturewiseDatasetMeasure): 
21 -    def __init__(self, num_permutations=200, num_bootstraps=100, **kwargs): 
22          # init base classes first 
23          FeaturewiseDatasetMeasure.__init__(self, **kwargs) 
24   
25          # save the args for the analysis 
26          self.num_permutations = num_permutations 
27          self.num_bootstraps = num_bootstraps 
28           
29 -    def _calc_pls(self,mat,labels): 
30          # take mean within condition(label) and concat to make a 
31          # condition by features matrix 
32          X = [] 
33          for ul in N.unique(labels): 
34              X.append(mat[labels==ul].mean(axis=0)) 
35          X = N.asarray(X) 
36           
37          # center each condition by subtracting the grand mean 
38          X -= X.mean(axis=1)[:,N.newaxis].repeat(X.shape[1],axis=1) 
39           
40          # run SVD (checking to transpose if necessary) 
41          U,s,Vh = N.linalg.svd(X, full_matrices=0) 
42   
43          # run procrust to reorder if necessary 
44   
45 -    def _procrust(): 
46          pass 
47   
48 -    def _call(self,dataset): 
49           
50          #  
51          pass 
52   
53 -class TaskPLS(PLS): 
54      pass 
55