[MRG] Conversion of somato data to BIDS (#6414)

* adjust freq tut

* adjust dics exp

* adjust global field power exp

* temporarily change hash and url for somato

* make more use of subj variable

* use v2 of somato bids set

* ignore long lines due to links in rst

* fix typo

* add somato url from MNE osf repo

* fix sphinx rst links

* update examples for new formatting, no new data yet

* update to most recent somato data

* update

* fix path

* fix rst link

* subj --> subject

doc/manual/datasets_index.rst

@@ -104,6 +104,7 @@ The recordings were made using the BCI2000 system. To load a subject, do::
 
     * :ref:`ex-decoding-csp-eeg`
 
+.. _somato-dataset:
 
 Somatosensory
 =============

examples/inverse/plot_dics_source_power.py

@@ -8,8 +8,7 @@
 Compute a Dynamic Imaging of Coherent Sources (DICS) [1]_ filter from
 single-trial activity to estimate source power across a frequency band. This
 example demonstrates how to source localize the event-related synchronization
-(ERS) of beta band activity in the "somato" dataset.
-
+(ERS) of beta band activity in this dataset: :ref:`somato-dataset`
 
 References
 ----------
@@ -19,8 +18,11 @@
 # Author: Marijn van Vliet <w.m.vanvliet@gmail.com>
 #         Roman Goj <roman.goj@gmail.com>
 #         Denis Engemann <denis.engemann@gmail.com>
+#         Stefan Appelhoff <stefan.appelhoff@mailbox.org>
 #
 # License: BSD (3-clause)
+import os.path as op
+
 import numpy as np
 import mne
 from mne.datasets import somato
@@ -32,9 +34,10 @@
 ###############################################################################
 # Reading the raw data and creating epochs:
 data_path = somato.data_path()
-raw_fname = data_path + '/MEG/somato/sef_raw_sss.fif'
-fname_fwd = data_path + '/MEG/somato/somato-meg-oct-6-fwd.fif'
-subjects_dir = data_path + '/subjects'
+subject = '01'
+task = 'somato'
+raw_fname = op.join(data_path, 'sub-{}'.format(subject), 'meg',
+                    'sub-{}_task-{}_meg.fif'.format(subject, task))
 
 raw = mne.io.read_raw_fif(raw_fname)
 
@@ -46,7 +49,11 @@
 epochs = mne.Epochs(raw, events, event_id=1, tmin=-1.5, tmax=2, picks=picks,
                     preload=True)
 
-# Read forward operator
+# Read forward operator and point to freesurfer subject directory
+fname_fwd = op.join(data_path, 'derivatives', 'sub-{}'.format(subject),
+                    'sub-{}_task-{}-fwd.fif'.format(subject, task))
+subjects_dir = op.join(data_path, 'derivatives', 'freesurfer', 'subjects')
+
 fwd = mne.read_forward_solution(fname_fwd)
 
 ###############################################################################
@@ -79,4 +86,4 @@
 stc = beta_source_power / baseline_source_power
 message = 'DICS source power in the 12-30 Hz frequency band'
 brain = stc.plot(hemi='both', views='par', subjects_dir=subjects_dir,
-                 time_label=message)
+                 subject=subject, time_label=message)

examples/time_frequency/plot_time_frequency_global_field_power.py

@@ -27,6 +27,8 @@
 importantly, the clear-cut comparability of the spectral decomposition (the
 same type of filter is used across all bands).
 
+We will use this dataset: :ref:`somato-dataset`
+
 References
 ----------
 
@@ -38,10 +40,12 @@
        vol. 108, 328-342, NeuroImage.
 .. [3] Efron B. and Hastie T. Computer Age Statistical Inference (2016).
        Cambrdige University Press, Chapter 11.2.
-"""
+"""  # noqa: E501
 # Authors: Denis A. Engemann <denis.engemann@gmail.com>
+#          Stefan Appelhoff <stefan.appelhoff@mailbox.org>
 #
 # License: BSD (3-clause)
+import os.path as op
 
 import numpy as np
 import matplotlib.pyplot as plt
@@ -54,7 +58,10 @@
 ###############################################################################
 # Set parameters
 data_path = somato.data_path()
-raw_fname = data_path + '/MEG/somato/sef_raw_sss.fif'
+subject = '01'
+task = 'somato'
+raw_fname = op.join(data_path, 'sub-{}'.format(subject), 'meg',
+                    'sub-{}_task-{}_meg.fif'.format(subject, task))
 
 # let's explore some frequency bands
 iter_freqs = [

mne/datasets/utils.py

@@ -2,6 +2,7 @@
 #          Martin Luessi <mluessi@nmr.mgh.harvard.edu>
 #          Eric Larson <larson.eric.d@gmail.com>
 #          Denis Egnemann <denis.engemann@gmail.com>
+#          Stefan Appelhoff <stefan.appelhoff@mailbox.org>
 # License: BSD Style.
 
 from collections import OrderedDict
@@ -237,10 +238,10 @@ def _data_path(path=None, force_update=False, update_path=True, download=True,
     # To update the testing or misc dataset, push commits, then make a new
     # release on GitHub. Then update the "releases" variable:
     releases = dict(testing='0.67', misc='0.3')
-    # And also update the "hashes['testing']" variable below.
+    # And also update the "md5_hashes['testing']" variable below.
 
     # To update any other dataset, update the data archive itself (upload
-    # an updated version) and update the hash.
+    # an updated version) and update the md5 hash.
 
     # try to match url->archive_name->folder_name
     urls = dict(  # the URLs to use
@@ -254,8 +255,8 @@ def _data_path(path=None, force_update=False, update_path=True, download=True,
              'datasets/foo.tgz',
         misc='https://codeload.github.com/mne-tools/mne-misc-data/'
              'tar.gz/%s' % releases['misc'],
-        sample="https://osf.io/86qa2/download?version=4",
-        somato='https://osf.io/tp4sg/download?version=2',
+        sample='https://osf.io/86qa2/download?version=4',
+        somato='https://osf.io/tp4sg/download?version=5',
         spm='https://osf.io/je4s8/download?version=2',
         testing='https://codeload.github.com/mne-tools/mne-testing-data/'
                 'tar.gz/%s' % releases['testing'],
@@ -306,7 +307,7 @@ def _data_path(path=None, force_update=False, update_path=True, download=True,
         fieldtrip_cmc='MNE-fieldtrip_cmc-data',
         phantom_4dbti='MNE-phantom-4DBTi',
     )
-    hashes = dict(
+    md5_hashes = dict(
         brainstorm=dict(
             bst_auditory='fa371a889a5688258896bfa29dd1700b',
             bst_phantom_ctf='80819cb7f5b92d1a5289db3fb6acb33c',
@@ -316,7 +317,7 @@ def _data_path(path=None, force_update=False, update_path=True, download=True,
         fake='3194e9f7b46039bb050a74f3e1ae9908',
         misc='d822a720ef94302467cb6ad1d320b669',
         sample='fc2d5b9eb0a144b1d6ba84dc3b983602',
-        somato='77a7601948c9e38d2da52446e2eab10f',
+        somato='f08f17924e23c57a751b3bed4a05fe02',
         spm='9f43f67150e3b694b523a21eb929ea75',
         testing='9bc5543854737f32d426629b31ea85d7',
         multimodal='26ec847ae9ab80f58f204d09e2c08367',
@@ -328,9 +329,9 @@ def _data_path(path=None, force_update=False, update_path=True, download=True,
         fieldtrip_cmc='6f9fd6520f9a66e20994423808d2528c',
         phantom_4dbti='f1d96f81d46480d0cc52a7ba4f125367'
     )
-    assert set(hashes.keys()) == set(urls.keys())
+    assert set(md5_hashes.keys()) == set(urls.keys())
     url = urls[name]
-    hash_ = hashes[name]
+    hash_ = md5_hashes[name]
     folder_orig = folder_origs.get(name, None)
     if name == 'brainstorm':
         assert archive_name is not None

tutorials/time-freq/plot_sensors_time_frequency.py

@@ -8,10 +8,14 @@
 The objective is to show you how to explore the spectral content
 of your data (frequency and time-frequency). Here we'll work on Epochs.
 
-We will use the somatosensory dataset that contains so-called
-event related synchronizations (ERS) / desynchronizations (ERD) in
-the beta band.
-"""
+We will use this dataset: :ref:`somato-dataset`. It contains so-called event
+related synchronizations (ERS) / desynchronizations (ERD) in the beta band.
+"""  # noqa: E501
+# Authors: Alexandre Gramfort <alexandre.gramfort@telecom-paristech.fr>
+#          Stefan Appelhoff <stefan.appelhoff@mailbox.org>
+#
+# License: BSD (3-clause)
+import os.path as op
 
 import numpy as np
 import matplotlib.pyplot as plt
@@ -23,7 +27,10 @@
 ###############################################################################
 # Set parameters
 data_path = somato.data_path()
-raw_fname = data_path + '/MEG/somato/sef_raw_sss.fif'
+subject = '01'
+task = 'somato'
+raw_fname = op.join(data_path, 'sub-{}'.format(subject), 'meg',
+                    'sub-{}_task-{}_meg.fif'.format(subject, task))
 
 # Setup for reading the raw data
 raw = mne.io.read_raw_fif(raw_fname)