[pymvpa] Dataset with multidimensional feature vector per voxel

[Ulrike Kuhl]

(The mail with the dataset attached is still waiting for moderator approval since it extends the limit of 240 KB.)

The code producing the error:

##############################
# set up DS as we worked out before:
DS_noisy = setup_ds ( sub_list, param_list, data_path )

# define a partitioner 
npart = ChainNode([
  NFoldPartitioner(len(DS_noisy.sa['targets'].unique),
                         attr='chunks'),
  Sifter([('partitions', 2),
                ('targets',
                 { 'uvalues': DS_noisy.sa['targets'].unique,
                   'balanced': True})
                ]),
  Balancer(attr='targets',count=10,limit='partitions',apply_selection=False)
  ], space='partitions')

clf_noisy = LinearCSVMC()
cvte_noisy = CrossValidation(clf_noisy, npart,errorfx=lambda p, t: np.mean(p == t),enable_ca=['stats'],postproc=mean_sample())

sl  = Searchlight(
   cvte_noisy,
   IndexQueryEngine(   # so we look for neighbors in both space and across modality_index
       voxel_indices=Sphere(3),    # that is pretty much what sphere_searchlight(radius=3) does
       modality_index=Sphere(len(param_list))), # 1cover all parameter values!
   postproc=mean_sample(),
   enable_ca=['stats'],
   roi_ids=np.where(DS_noisy.fa.modality_index == 0)[0] # restrict it to search for "modality_index" neighbors only when we are looking at modality_index==0
)

res_noisy = sl(DS_noisy)
##############################


The last line returns the IndexError.

DS_noisy.summary() returns:

Dataset: 7x3472 at float32, <sa: chunks,subject,targets>, <fa: modality,modality_index,voxel_indices>, <a: imghdr,mapper>
stats: mean=0.516962 std=0.298723 var=0.0892352 min=9.75631e-06 max=1.78471

Counts of targets in each chunk:
  chunks\targets  0   1
                 --- ---
        0         1   0
        1         1   0
        2         1   0
        3         1   0
        4         0   1
        5         0   1
        6         0   1

Summary for targets across chunks
  targets  mean  std  min max #chunks
    0     0.571 0.495  0   1     4
    1     0.429 0.495  0   1     3

Summary for chunks across targets
  chunks mean std min max #targets
    0     0.5 0.5  0   1      1
    1     0.5 0.5  0   1      1
    2     0.5 0.5  0   1      1
    3     0.5 0.5  0   1      1
    4     0.5 0.5  0   1      1
    5     0.5 0.5  0   1      1
    6     0.5 0.5  0   1      1
Sequence statistics for 7 entries from set [0, 1]
Counter-balance table for orders up to 2:
Targets/Order O1    |  O2    |
      0:       3 1  |   2 2  |
      1:       0 2  |   0 1  |
Correlations: min=-0.75 max=0.42 mean=-0.17 sum(abs)=2.7



----- Original Message -----
From: "Yaroslav Halchenko" <debian at onerussian.com>
To: "pkg-exppsy-pymvpa" <pkg-exppsy-pymvpa at lists.alioth.debian.org>
Sent: Tuesday, 24 November, 2015 21:10:52
Subject: Re: [pymvpa] Dataset with multidimensional feature vector per voxel

On Tue, 24 Nov 2015, Ulrike Kuhl wrote:
> I was able to reproduce the error when using a mask (1736 voxels) on my toy data:

could you share the code snippet and this toy dataset (h5save it)?

> Traceback (most recent call last):
>   File "DummyMvpa_noisy.py", line 322, in <module>
>     res_noisy = sl(DS_noisy)
>   File "/usr/lib/python2.7/dist-packages/mvpa2/base/learner.py", line 259, in __call__
>     return super(Learner, self).__call__(ds)
>   File "/usr/lib/python2.7/dist-packages/mvpa2/base/node.py", line 121, in __call__
>     result = self._call(ds)
>   File "/usr/lib/python2.7/dist-packages/mvpa2/measures/searchlight.py", line 143, in _call
>     results = self._sl_call(dataset, roi_ids, nproc)
>   File "/usr/lib/python2.7/dist-packages/mvpa2/measures/searchlight.py", line 371, in _sl_call
>     results=self.__handle_all_results(p_results))
>   File "/usr/lib/python2.7/dist-packages/mvpa2/measures/searchlight.py", line 207, in _concat_results
>     results = sum(results, [])
>   File "/usr/lib/python2.7/dist-packages/mvpa2/measures/searchlight.py", line 527, in __handle_all_results
>     for r in results:
>   File "/usr/lib/pymodules/python2.7/pprocess.py", line 764, in next
>     self.store()
>   File "/usr/lib/pymodules/python2.7/pprocess.py", line 400, in store
>     self.store_data(channel)
>   File "/usr/lib/pymodules/python2.7/pprocess.py", line 747, in store_data
>     data = channel.receive()
>   File "/usr/lib/pymodules/python2.7/pprocess.py", line 135, in receive
>     obj = self._receive()
>   File "/usr/lib/pymodules/python2.7/pprocess.py", line 121, in _receive
>     raise obj
> IndexError: index 1736 out of bounds 0<=index<1736


> Why does the searchlight run out of the mask?

not sure yet

-- 
Yaroslav O. Halchenko
Center for Open Neuroscience     http://centerforopenneuroscience.org
Dartmouth College, 419 Moore Hall, Hinman Box 6207, Hanover, NH 03755
Phone: +1 (603) 646-9834                       Fax: +1 (603) 646-1419
WWW:   http://www.linkedin.com/in/yarik        

_______________________________________________
Pkg-ExpPsy-PyMVPA mailing list
Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org
http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa
-- 
Max Planck Institute for Human Cognitive and Brain Sciences 
Department of Neuropsychology (A219) 
Stephanstraße 1a 
04103 Leipzig 

Phone: +49 (0) 341 9940 2625 
Mail: kuhl at cbs.mpg.de 
Internet: http://www.cbs.mpg.de/staff/kuhl-12160