Merge pull request #71 from rmarkello/cammoun_hcp

[REF] Adds fs_LR_32k Cammoun 2012 atlases

Author: rmarkello

netneurotools/data/osf.json

@@ -5,35 +5,42 @@
                 "mb37e",
                 "5ce6bb4423fec40017e82c5e"
             ],
-            "md5": "c3435f2720da6a74c3d55db54ebdbfff"
+            "md5": "266c4520af768e766328fb8e6648005d"
         },
         "fsaverage": {
             "url": [
                 "mb37e",
                 "5ce6c30523fec40017e83439"
             ],
-            "md5": "478599b362a88198396fdb15ad999f9e"
+            "md5": "2a19eb4744c0ce6c243f721bd43ecff0"
         },
         "fsaverage5": {
             "url": [
                 "mb37e",
                 "5e189a1c57341903868036dd"
             ],
-            "md5": "e96a456f14fd30f26734a7dfbcbb18e0"
+            "md5": "2afb22e1887d47f1ca81c340fff7692b"
         },
         "fsaverage6": {
             "url": [
                 "mb37e",
                 "5e189a1b5734190380804072"
             ],
-            "md5": "b220fb658e1abdfdf8bdb55b26f2acf3"
+            "md5": "1df743bff13316f67bd41d13ec691c97"
         },
-        "volume": {
+        "MNI152NLin2009aSym": {
             "url": [
                 "mb37e",
-                "5ce6bb438d6e05001860abca"
+                "5e2f4bf0e71ef800301880c2"
             ],
-            "md5": "088fb64b397557dfa01901f04f4cd9d2"
+            "md5": "9da30bad22d732aa5f00a6d178d087c4"
+        },
+        "fslr32k": {
+            "url": [
+                "mb37e",
+                "5e2f4bf1e71ef80027189c56"
+            ],
+            "md5": "a5177319d5e0b8825a91d503ded1a59e"
         }
     },
     "atl-pauli2018": [

netneurotools/datasets/__init__.py

@@ -5,11 +5,13 @@
 __all__ = [
     'fetch_cammoun2012', 'fetch_pauli2018', 'fetch_fsaverage', 'fetch_conte69',
     'fetch_connectome', 'available_connectomes', 'fetch_vazquez_rodriguez2019',
-    'fetch_mirchi2018', 'make_correlated_xy', 'fetch_schaefer2018'
+    'fetch_mirchi2018', 'make_correlated_xy', 'fetch_schaefer2018',
+    'fetch_hcp_standards'
 ]
 
 from .fetchers import (fetch_cammoun2012, fetch_pauli2018, fetch_fsaverage,
                        fetch_conte69, fetch_connectome, available_connectomes,
-                       fetch_vazquez_rodriguez2019, fetch_schaefer2018)
+                       fetch_vazquez_rodriguez2019, fetch_schaefer2018,
+                       fetch_hcp_standards)
 from .generators import (make_correlated_xy)
 from .mirchi import (fetch_mirchi2018)

netneurotools/datasets/fetchers.py

@@ -5,7 +5,6 @@
 
 import itertools
 import json
-import os
 import os.path as op
 import warnings
 
@@ -17,19 +16,21 @@
 from ..utils import check_fs_subjid
 
 
-def fetch_cammoun2012(version='volume', data_dir=None, url=None, resume=True,
-                      verbose=1):
+def fetch_cammoun2012(version='MNI125NLin2009aSym', data_dir=None, url=None,
+                      resume=True, verbose=1):
     """
     Downloads files for Cammoun et al., 2012 multiscale parcellation
 
     Parameters
     ----------
-    version : {'volume', 'fsaverage', 'fsaverage5', 'fsaverage6', 'gcs'}
-        Specifies which version of the dataset to download, where 'volume' will
-        return .nii.gz atlas files defined in MNI152 space, 'fsaverageX' will
-        return .annot files defined in fsaverageX space (FreeSurfer 6.0.1), and
-        'gcs' will return FreeSurfer-style .gcs probabilistic atlas files for
-        generating new, subject-specific parcellations
+    version : str, optional
+        Specifies which version of the dataset to download, where
+        'MNI125NLin2009aSym' will return .nii.gz atlas files defined in MNI152
+        space, 'fsaverageX' will return .annot files defined in fsaverageX
+        space (FreeSurfer 6.0.1), 'fslr32k' will return .label.gii files in
+        fs_LR_32k HCP space, and 'gcs' will return FreeSurfer-style .gcs
+        probabilistic atlas files for generating new, subject-specific
+        parcellations. Default: 'MNI125NLin2009aSym'
     data_dir : str, optional
         Path to use as data directory. If not specified, will check for
         environmental variable 'NNT_DATA'; if that is not set, will use
@@ -62,8 +63,23 @@ def fetch_cammoun2012(version='volume', data_dir=None, url=None, resume=True,
     License: https://raw.githubusercontent.com/LTS5/cmp/master/COPYRIGHT
     """
 
+    if version == 'surface':
+        warnings.warn('Providing `version="surface"` is deprecated and will '
+                      'be removed in a future release. For consistent '
+                      'behavior please use `version="fsaverage"` instead.',
+                      DeprecationWarning, stacklevel=2)
+        version = 'fsaverage'
+    elif version == 'volume':
+        warnings.warn('Providing `version="volume"` is deprecated and will '
+                      'be removed in a future release. For consistent '
+                      'behavior please use `version="MNI152NLin2009aSym"` '
+                      'instead.',
+                      DeprecationWarning, stacklevel=2)
+        version = 'MNI152NLin2009aSym'
+
     versions = [
-        'volume', 'surface', 'gcs', 'fsaverage', 'fsaverage5', 'fsaverage6'
+        'gcs', 'fsaverage', 'fsaverage5', 'fsaverage6', 'fslr32k',
+        'MNI152NLin2009aSym'
     ]
     if version not in versions:
         raise ValueError('The version of Cammoun et al., 2012 parcellation '
@@ -73,13 +89,6 @@ def fetch_cammoun2012(version='volume', data_dir=None, url=None, resume=True,
     dataset_name = 'atl-cammoun2012'
     keys = ['scale033', 'scale060', 'scale125', 'scale250', 'scale500']
 
-    if version == 'surface':
-        warnings.warn('Providing `version="surface"` is deprecated and will '
-                      'be removed in a future release. For consistent '
-                      'behavior please use `version="fsaverage"` instead. ',
-                      DeprecationWarning, stacklevel=2)
-        version = 'fsaverage'
-
     data_dir = _get_data_dir(data_dir=data_dir)
     info = _get_dataset_info(dataset_name)[version]
     if url is None:
@@ -92,11 +101,17 @@ def fetch_cammoun2012(version='volume', data_dir=None, url=None, resume=True,
     }
 
     # filenames differ based on selected version of dataset
-    if version == 'volume':
+    if version == 'MNI152NLin2009aSym':
         filenames = [
             'atl-Cammoun2012_space-MNI152NLin2009aSym_res-{}_deterministic{}'
             .format(res[-3:], suff) for res in keys for suff in ['.nii.gz']
         ] + ['atl-Cammoun2012_space-MNI152NLin2009aSym_info.csv']
+    elif version == 'fslr32k':
+        filenames = [
+            'atl-Cammoun2012_space-fslr32k_res-{}_hemi-{}_deterministic{}'
+            .format(res[-3:], hemi, suff) for res in keys
+            for hemi in ['L', 'R'] for suff in ['.label.gii']
+        ]
     elif version in ('fsaverage', 'fsaverage5', 'fsaverage6'):
         filenames = [
             'atl-Cammoun2012_space-{}_res-{}_hemi-{}_deterministic{}'
@@ -111,12 +126,14 @@ def fetch_cammoun2012(version='volume', data_dir=None, url=None, resume=True,
             for hemi in ['L', 'R'] for suff in ['.gcs', '.ctab']
         ]
 
-    files = [(os.path.join(dataset_name, f), url, opts) for f in filenames]
+    files = [
+        (op.join(dataset_name, version, f), url, opts) for f in filenames
+    ]
     data = _fetch_files(data_dir, files=files, resume=resume, verbose=verbose)
 
-    if version == 'volume':
+    if version == 'MNI152NLin2009aSym':
         keys += ['info']
-    elif version in ('fsaverage', 'fsaverage5', 'fsaverage6'):
+    elif version in ('fslr32k', 'fsaverage', 'fsaverage5', 'fsaverage6'):
         data = [data[i:i + 2] for i in range(0, len(data), 2)]
     else:
         data = [data[::2][i:i + 2] for i in range(0, len(data) // 2, 2)]
@@ -313,7 +330,7 @@ def fetch_fsaverage(version='fsaverage', data_dir=None, url=None, resume=True,
 
     try:
         data_dir = check_fs_subjid(version)[1]
-        data = [os.path.join(data_dir, f) for f in filenames]
+        data = [op.join(data_dir, f) for f in filenames]
     except FileNotFoundError:
         data = _fetch_files(data_dir, resume=resume, verbose=verbose,
                             files=[(op.join(dataset_name, f), url, opts)
@@ -393,7 +410,7 @@ def fetch_connectome(dataset, data_dir=None, url=None, resume=True,
     }
 
     filenames = [
-        os.path.join(dataset, '{}.csv'.format(fn)) for fn in info['keys']
+        op.join(dataset, '{}.csv'.format(fn)) for fn in info['keys']
     ] + [op.join(dataset, 'ref.txt')]
     data = _fetch_files(data_dir, files=[(f, url, opts) for f in filenames],
                         resume=resume, verbose=verbose)
@@ -454,7 +471,7 @@ def fetch_vazquez_rodriguez2019(data_dir=None, url=None, resume=True,
     }
 
     filenames = [
-        os.path.join(dataset_name, 'rsquared_gradient.csv')
+        op.join(dataset_name, 'rsquared_gradient.csv')
     ]
     data = _fetch_files(data_dir, files=[(f, url, opts) for f in filenames],
                         resume=resume, verbose=verbose)
@@ -534,10 +551,51 @@ def fetch_schaefer2018(version='fsaverage', data_dir=None, url=None,
         .format(version, hemi, desc) for desc in keys for hemi in ['L', 'R']
     ]
 
-    files = [(os.path.join(dataset_name, version, f), url, opts)
+    files = [(op.join(dataset_name, version, f), url, opts)
              for f in filenames]
     data = _fetch_files(data_dir, files=files, resume=resume, verbose=verbose)
 
     data = [data[i:i + 2] for i in range(0, len(keys) * 2, 2)]
 
     return Bunch(**dict(zip(keys, data)))
+
+
+def fetch_hcp_standards(data_dir=None, url=None, resume=True, verbose=1):
+    """
+    Fetches HCP standard mesh atlases for converting between FreeSurfer and HCP
+
+    Parameters
+    ----------
+    data_dir : str, optional
+        Path to use as data directory. If not specified, will check for
+        environmental variable 'NNT_DATA'; if that is not set, will use
+        `~/nnt-data` instead. Default: None
+    url : str, optional
+        URL from which to download data. Default: None
+    resume : bool, optional
+        Whether to attempt to resume partial download, if possible. Default:
+        True
+    verbose : int, optional
+        Modifies verbosity of download, where higher numbers mean more updates.
+        Default: 1
+
+    Returns
+    -------
+    standards : str
+        Filepath to standard_mesh_atlases directory
+    """
+    if url is None:
+        url = 'http://brainvis.wustl.edu/workbench/standard_mesh_atlases.zip'
+    dataset_name = 'standard_mesh_atlases'
+    data_dir = _get_data_dir(data_dir=data_dir)
+    opts = {
+        'uncompress': True,
+        'move': '{}.zip'.format(dataset_name)
+    }
+    filenames = [
+        'L.sphere.32k_fs_LR.surf.gii', 'R.sphere.32k_fs_LR.surf.gii'
+    ]
+    files = [(op.join(dataset_name, f), url, opts) for f in filenames]
+    _fetch_files(data_dir, files=files, resume=resume, verbose=verbose)
+
+    return op.join(data_dir, dataset_name)

netneurotools/tests/test_datasets.py

@@ -72,10 +72,11 @@ def test_fetch_fsaverage(tmpdir, version):
 
 
 @pytest.mark.parametrize('version, expected', [
-    ('volume', [1, 1, 1, 1, 1]),
+    ('MNI152NLin2009aSym', [1, 1, 1, 1, 1]),
     ('fsaverage', [2, 2, 2, 2, 2]),
     ('fsaverage5', [2, 2, 2, 2, 2]),
     ('fsaverage6', [2, 2, 2, 2, 2]),
+    ('fslr32k', [2, 2, 2, 2, 2]),
     ('gcs', [2, 2, 2, 2, 6])
 ])
 def test_fetch_cammoun2012(tmpdir, version, expected):
@@ -139,9 +140,14 @@ def test_fetch_schaefer2018(tmpdir, version):
                for k in keys)
 
 
+def test_fetch_hcp_standards(tmpdir):
+    hcp = datasets.fetch_hcp_standards(data_dir=tmpdir, verbose=0)
+    assert os.path.isdir(hcp)
+
+
 @pytest.mark.parametrize('dset, expected', [
-    ('atl-cammoun2012', ['volume', 'fsaverage', 'fsaverage5', 'fsaverage6',
-                         'gcs']),
+    ('atl-cammoun2012', ['fsaverage', 'fsaverage5', 'fsaverage6', 'fslr32k',
+                         'MNI152NLin2009aSym', 'gcs']),
     ('tpl-conte69', ['url', 'md5']),
     ('atl-pauli2018', ['url', 'md5', 'name']),
     ('tpl-fsaverage', ['fsaverage' + f for f in ['', '3', '4', '5', '6']]),

netneurotools/tests/test_utils.py

@@ -33,7 +33,8 @@ def test_add_triu():
 ])
 def test_get_centroids(tmpdir, scale, expected):
     # fetch test dataset
-    cammoun = datasets.fetch_cammoun2012('volume', data_dir=tmpdir, verbose=0)
+    cammoun = datasets.fetch_cammoun2012('MNI152NLin2009aSym', data_dir=tmpdir,
+                                         verbose=0)
 
     ijk = utils.get_centroids(cammoun[scale])
     xyz = utils.get_centroids(cammoun[scale], image_space=True)

netneurotools/utils.py

@@ -238,7 +238,7 @@ def get_centroids(img, labels=None, image_space=False):
     from nilearn._utils import check_niimg_3d
 
     img = check_niimg_3d(img)
-    data = img.get_data()
+    data = np.asarray(img.dataobj)
 
     if labels is None:
         labels = np.trim_zeros(np.unique(data))