pre-refactor.py

def fetch_spm_auditory(data_dir=None, data_name='spm_auditory',
                       subject_id="sub001", verbose=1):
    """Function to fetch SPM auditory single-subject data.
    Parameters
    ----------
    data_dir: string
        Path of the data directory. Used to force data storage in a specified
        location. If the data is already present there, then will simply
        glob it.
    Returns
    -------
    data: sklearn.datasets.base.Bunch
        Dictionary-like object, the interest attributes are:
        - 'func': string list. Paths to functional images
        - 'anat': string list. Path to anat image
    References
    ----------
    :download:
        http://www.fil.ion.ucl.ac.uk/spm/data/auditory/
    """
    data_dir = _get_dataset_dir(data_name, data_dir=data_dir,
                                verbose=verbose)
    subject_dir = os.path.join(data_dir, subject_id)

    def _glob_spm_auditory_data():
        """glob data from subject_dir.
        """

        if not os.path.exists(subject_dir):
            return None

        subject_data = {}
        for file_name in SPM_AUDITORY_DATA_FILES:
            file_path = os.path.join(subject_dir, file_name)
            if os.path.exists(file_path):
                subject_data[file_name] = file_path
            else:
                print("%s missing from filelist!" % file_name)
                return None

        _subject_data = {}
        _subject_data["func"] = sorted(
            [subject_data[x] for x in subject_data.keys()
             if re.match("^fM00223_0\d\d\.img$", os.path.basename(x))])

        # volumes for this dataset of shape (64, 64, 64, 1); let's fix this
        for x in _subject_data["func"]:
            vol = nib.load(x)
            if len(vol.shape) == 4:
                vol = nib.Nifti1Image(vol.get_data()[:, :, :, 0],
                                      vol.affine)
                nib.save(vol, x)

        _subject_data["anat"] = [subject_data[x] for x in subject_data.keys()
                                 if re.match("^sM00223_002\.img$",
                                             os.path.basename(x))][0]

        # ... same thing for anat
        vol = nib.load(_subject_data["anat"])
        if len(vol.shape) == 4:
            vol = nib.Nifti1Image(vol.get_data()[:, :, :, 0],
                                  vol.affine)
            nib.save(vol, _subject_data["anat"])

        return Bunch(**_subject_data)

    # maybe data_dir already contains the data ?
    data = _glob_spm_auditory_data()
    if data is not None:
        return data

    # No. Download the data
    print("Data absent, downloading...")
    url = ("http://www.fil.ion.ucl.ac.uk/spm/download/data/MoAEpilot/"
           "MoAEpilot.zip")
    archive_path = os.path.join(subject_dir, os.path.basename(url))
    _fetch_file(url, subject_dir)
    try:
        _uncompress_file(archive_path)
    except:
        print("Archive corrupted, trying to download it again.")
        return fetch_spm_auditory(data_dir=data_dir, data_name="",
                                  subject_id=subject_id)

    return _glob_spm_auditory_data()