[pymvpa] Mask in from_wizard generates no data.

[Yaroslav Halchenko]

On Wed, 10 Dec 2014, Thomas Nickson wrote:

>    My main problem is that this isn't at all consistent with how the function
>    for constructing fmri datasets works. Which way do you consider to be
>    correct? 

I thought "correct way" is when mask dimensionality (be it a boolean
array or tuple of indices) matches the dimensionality of the data
array.  That is I think how all our functions work

> I think the fmri way of handling it makes more sense. This way I
>    have to understand that the mask needs to be flattened and I need to
>    provide an array of nonzero indices. 

that is where you are loosing me ;)  why mask needs to be flattened?

> The other way does not work. No other
>    way works.A  I can't just provide a flattened boolean mask, if by that you
>    mean 1's and 0's. 

I mean dtype=bool array of True and False's.  Array of indices 1 and 0
is just that -- array of indicies ;)

> I can't provide a mask of the same shape as the original
>    data. 

that is what confuses me -- it must work.  looking back to our
correspondence -- you never showed that dtype of your mask is bool...
may be that is the catch?

> This is confusing because the original data will be automatically
>    flattened but the mask won't.

confused

> Why does that make any sense? 

dunno since it doesn't

> Surely you
>    would at least want the inputs to be consistent for the mask and the
>    original data? 

yeah

> It's neither consistent within the function itself nor is
>    it consistent between other functions that do the same thing.

hm... confused

>    The fmri data provided for the tutorial does exactly the same thing. It
>    hasn't got anything to do with the data. I can provide the code.

oy--  lets check that hypothesis of mine about dtype of your mask first

>    Anyway, I don't mean to non-constructively criticise but I found it
>    confusing and frustrating and thought it might be nice to alleviate some
>    of that.
>    #Open the main VBM data - some functions to help

>    import numpy as np
>    import nibabel as nb
>    import os
>    from functools import partial
>    from operator import mul
>    import pickle as p
>    from mvpa2.datasets.base import Dataset
>    from mvpa2.mappers.zscore import zscore
>    from mvpa2.datasets.mri import fmri_dataset

>    """4ddata is fddata and 2ddata is tddata"""

>    def getImages(imagePath):
>    A A A  """load a nifti"""
>    A A A  return nb.load(imagePath)

>    def writeDatatoImages(writePath, Data):
>    A A A  """Write a numpy array to a nifti1 image"""
>    A A A  N = nb.Nifti1Image(Data, np.eye(4))
>    A A A  N.to_filename(writePath)

>    def getImageData(imagePath):
>    A A A  """load a nifti as numpy data"""
>    A A A  return getImages(imagePath).get_data()
>    A A A 
>    def rotateShape(FDData):
>    A A A  """we need to rotate the shape of the data as other wise the time
>    dimension (here denoting the subjects) is actually last"""
>    A A A  if len(FDData.shape) == 4:
>    A A A A A A A  FDData = np.rollaxis(FDData, -1)
>    A A A  return FDData

>    def reshapeFlatten(FDData):
>    A A A  """Reshape the data and then flatten each member of the array"""
>    A A A  Data = rotateShape(FDData)
>    A A A  return Data.reshape(Data.shape[0],reduce(mul,Data.shape[1:],1))

>    #======================================Helper functions
>    above=====================================

>    DATA_LOCATION = ./pymvpa/PyMVPA/tutorial_data/data/bold.nii.gz'

>    MASK = './pymvpa/PyMVPA/tutorial_data/data/mask_brain.nii.gz'

>    #Load the metadata pickle
>    #metaData = p.load(open('VBMMeta.pkl'))

>    #get image data and reshape
>    rotatedImageData = rotateShape(getImageData(DATA_LOCATION))

>    #Get mask data
>    mask = getImageData(MASK).flatten()#.nonzero()[0]#.flatten().nonzero()[0]

just try

getImageData(MASK).astype(bool)

?

>    #mask = np.float32(mask)
>    #print type(mask)

>    #Load dataset
>    ds = Dataset.from_wizard(rotatedImageData,
>    mask=mask)#targets=metaData['diagnosesT1'], mask=mask)
>    #ds = fmri_dataset(rotatedImageData)#, targets=metaData['diagnosesT1'],
>    mask=mask)
>    #ds = fmri_dataset(DATA_LOCATION, mask=mask)#,
>    targets=metaData['diagnosesT1'], mask=mask, chunks=np.array(range(133)))

>    #zscore normalise the data
>    #zscore(ds, chunks_attr=None)
-- 
Yaroslav O. Halchenko, Ph.D.
http://neuro.debian.net http://www.pymvpa.org http://www.fail2ban.org
Research Scientist,            Psychological and Brain Sciences Dept.
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