first commit

.circleci/config.yml

@@ -0,0 +1,18 @@
+version: 2 # use CircleCI 2.0
+jobs: # A basic unit of work in a run
+  build: # runs not using Workflows must have a `build` job as entry point 
+    docker: # run the steps with Docker
+      # CircleCI Python images available at: https://hub.docker.com/r/circleci/python/
+      - image: circleci/python:3.6.4
+    working_directory: /tmp/src/rename_fmriprep
+    steps:
+      - checkout
+      - run:
+        name: Install requirements
+        command: |
+          pip install pytest==4.5.*
+          pip install -r requirements.txt
+      - run:
+        name: Test command
+        command: |
+          pytest -vv

.gitignore

@@ -0,0 +1,77 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+*.c
+
+# Distribution / packaging
+.Python
+env/
+# build/ # commented due to some strangeness with Docker/circle setup
+develop-eggs/
+dist/
+build/lib*
+build/temp*
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+.hypothesis/
+.pytest_cache
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+docs/examples/notebooks
+docs/api
+
+# PyBuilder
+target/
+
+# Ipython Notebook
+.ipynb_checkpoints
+
+auth/
+secrets.py
+local_settings.py
+
+*.swp
+
+# Text Editors
+.vscode

rename_old_fmriprep/conform_fmriprep.py

@@ -0,0 +1,154 @@
+#!/usr/bin/env python3
+"""
+rename fmriprep (< v1.2.0) files to be in conformance with the
+bids derivatives release candidate
+"""
+from argparse import ArgumentParser
+import json
+import os
+import re
+from shutil import copyfile
+
+from bids.layout.writing import build_path
+
+
+# templates for matching the old fmriprep files
+BIDS_NAME = (
+    r'^(.*\/)?'
+    r'sub-(?P<subject>[a-zA-Z0-9]+)'
+    r'(_ses-(?P<session>[a-zA-Z0-9]+))?'
+    r'(_task-(?P<task>[a-zA-Z0-9]+))?'
+    r'(_acq-(?P<acq>[a-zA-Z0-9]+))?'
+    r'(_rec-(?P<rec>[a-zA-Z0-9]+))?'
+    r'(_run-(?P<run>[a-zA-Z0-9]+))?')
+
+DERIV_NAME = (
+    r'_(?P<suffix>[a-zA-Z0-9]+)'
+    r'(_space-(?P<space>[a-zA-Z0-9]+))?'
+    r'(_class-(?P<class>[a-zA-Z0-9]+))?'
+    r'(_target-(?P<target>[a-zA-Z0-9]+))?'
+    r'(_variant-(?P<variant>[a-zA-Z0-9]+))?'
+    r'_(?P<desc>[a-zA-Z0-9]+)'
+    r'\.(?P<ext>(?!svg).*)')
+
+# regular expression to match old fmriprep
+DERIV_REGEX = re.compile(r''.join([BIDS_NAME, DERIV_NAME]))
+
+# template to build the "correct" derivative file
+PATH_PATTERN = (
+    'sub-{subject}'
+    '[_ses-{session}]'
+    '[_task-{task}]'
+    '[_acq-{acq}]'
+    '[_rec-{rec}]'
+    '[_run-{run}]'
+    '[_from-{fspace}]'
+    '[_to-{tspace}]'
+    '[_mode-{mode}]'
+    '[_hemi-{hemi}]'
+    '[_space-{space}]'
+    '[_label-{label}]'
+    '[_desc-{desc}]'
+    '_{suffix}'
+    '.{ext}')
+
+
+def rename_fmriprep_files(fmriprep_dir, renamed_dir, dset_desc):
+    # copy the dataset_description file over first
+    os.makedirs(renamed_dir, exist_ok=True)
+    copyfile(dset_desc, os.path.join(renamed_dir, os.path.basename(dset_desc)))
+
+    # collect the mapping from old file names to new file names
+    rename_files = {}
+    for root, _, files in os.walk(fmriprep_dir):
+        for file in files:
+            match = re.search(DERIV_REGEX, file)
+            if match is not None:
+                file_dict = match.groupdict()
+                # change brainmask to desc-brain_mask
+                if file_dict.get('desc') == 'brainmask':
+                    file_dict['desc'] = 'brain'
+                    file_dict['suffix'] = 'mask'
+                # variant is now desc
+                if file_dict.get('variant'):
+                    file_dict['desc'] = file_dict.pop('variant')
+                # different formats of transformation files
+                if file_dict.get('space') and file_dict.get('target'):
+                    file_dict['fspace'] = file_dict.pop('space')
+                    file_dict['tspace'] = file_dict.pop('target')
+                    file_dict['mode'] = 'image'
+                    file_dict['suffix'] = 'xfm'
+                    del file_dict['desc']
+                if file_dict.get('target'):
+                    file_dict['fspace'] = file_dict.pop('suffix')
+                    file_dict['tspace'] = file_dict.pop('target')
+                    file_dict['mode'] = 'image'
+                    file_dict['suffix'] = 'xfm'
+                    del file_dict['desc']
+                # segmentations
+                if file_dict.get('class'):
+                    file_dict['label'] = file_dict.pop('class')
+                    file_dict['suffix'] = 'probseg'
+                    del file_dict['desc']
+                if file_dict.get('desc') == 'dtissue':
+                    file_dict['suffix'] = 'dseg'
+                    del file_dict['desc']
+                # freesurfer hemisphere files
+                if file_dict['ext'].startswith('L') or file_dict['ext'].startswith('R'):
+                    file_dict['hemi'] = file_dict['ext'][0]
+                    file_dict['ext'] = file_dict['ext'][2:]
+                    file_dict['suffix'] = file_dict.pop('desc')
+                # aroma files
+                if file_dict.get('desc') == 'MELODICmix':
+                    file_dict['desc'] = 'MELODIC'
+                    file_dict['suffix'] = 'mixing'
+                if file_dict.get('desc') == 'AROMAnoiseICs':
+                    file_dict['suffix'] = file_dict['desc']
+                    del file_dict['desc']
+                # confounds file change
+                if file_dict.get('desc') == 'confounds':
+                    file_dict['suffix'] = 'regressors'
+
+                # write the file to the new directory
+                new_file = build_path(file_dict, PATH_PATTERN)
+                new_root = root.replace(fmriprep_dir, renamed_dir)
+                new_path = os.path.join(new_root, new_file)
+                old_path = os.path.join(root, file)
+                rename_files[old_path] = new_path
+                os.makedirs(new_root, exist_ok=True)
+                copyfile(old_path, new_path)
+
+    # write out log for how files were renamed
+    data_transfer_log = os.path.join(renamed_dir, "logs", "data_transfer.json")
+    os.makedirs(os.path.dirname(data_transfer_log), exist_ok=True)
+    with open(data_transfer_log, 'w') as fp:
+        json.dump(rename_files, fp)
+
+    return data_transfer_log
+
+
+def main():
+    # set up a parser to read arguments
+    parser = ArgumentParser(description='conform_fmriprep: rename old fmriprep (< v1.2.0) files')
+    requiredNamed = parser.add_argument_group('required named arguments')
+    requiredNamed.add_argument('-i', '--input-dir', dest='fmriprep_dir',
+                               action='store', required=True,
+                               help='the root folder of a fmriprep derivatives '
+                               'dataset (sub-XXXXX folders should be found at the '
+                               'top level in this folder).')
+    requiredNamed.add_argument('-o', '--output-dir', dest='renamed_dir',
+                               action='store', required=True,
+                               help='the root folder to place the renamed fmriprep outputs')
+    requiredNamed.add_argument('-d', '--dataset-description', dest='dset_desc',
+                               action='store', required=True,
+                               help='the required dataset description file to be placed '
+                               'at the root folder of fmriprep')
+
+    opts = parser.parse_args()
+
+    # rename the files
+    rename_fmriprep_files(opts.fmriprep_dir, opts.renamed_dir, opts.dset_desc)
+
+
+if __name__ == '__main__':
+    main()

rename_old_fmriprep/tests/data/dataset_description.json

@@ -0,0 +1 @@
+{"Name": "fmriprep", "BIDSVersion": "1.0.0", "PipelineDescription": {"Name": "fmriprep"}}

rename_old_fmriprep/tests/data_transfer.json

@@ -0,0 +1 @@
+{"./tests/data/sub-01/anat/sub-01_T1w_brainmask.nii.gz": "./tst_out/sub-01/anat/sub-01_desc-brain_mask.nii.gz", "./tests/data/sub-01/anat/sub-01_T1w_class-CSF_probtissue.nii.gz": "./tst_out/sub-01/anat/sub-01_label-CSF_probseg.nii.gz", "./tests/data/sub-01/anat/sub-01_T1w_class-GM_probtissue.nii.gz": "./tst_out/sub-01/anat/sub-01_label-GM_probseg.nii.gz", "./tests/data/sub-01/anat/sub-01_T1w_class-WM_probtissue.nii.gz": "./tst_out/sub-01/anat/sub-01_label-WM_probseg.nii.gz", "./tests/data/sub-01/anat/sub-01_T1w_dtissue.nii.gz": "./tst_out/sub-01/anat/sub-01_dseg.nii.gz", "./tests/data/sub-01/anat/sub-01_T1w_inflated.L.surf.gii": "./tst_out/sub-01/anat/sub-01_hemi-L_inflated.surf.gii", "./tests/data/sub-01/anat/sub-01_T1w_inflated.R.surf.gii": "./tst_out/sub-01/anat/sub-01_hemi-R_inflated.surf.gii", "./tests/data/sub-01/anat/sub-01_T1w_midthickness.L.surf.gii": "./tst_out/sub-01/anat/sub-01_hemi-L_midthickness.surf.gii", "./tests/data/sub-01/anat/sub-01_T1w_midthickness.R.surf.gii": "./tst_out/sub-01/anat/sub-01_hemi-R_midthickness.surf.gii", "./tests/data/sub-01/anat/sub-01_T1w_pial.L.surf.gii": "./tst_out/sub-01/anat/sub-01_hemi-L_pial.surf.gii", "./tests/data/sub-01/anat/sub-01_T1w_pial.R.surf.gii": "./tst_out/sub-01/anat/sub-01_hemi-R_pial.surf.gii", "./tests/data/sub-01/anat/sub-01_T1w_preproc.nii.gz": "./tst_out/sub-01/anat/sub-01_desc-preproc_T1w.nii.gz", "./tests/data/sub-01/anat/sub-01_T1w_smoothwm.L.surf.gii": "./tst_out/sub-01/anat/sub-01_hemi-L_smoothwm.surf.gii", "./tests/data/sub-01/anat/sub-01_T1w_smoothwm.R.surf.gii": "./tst_out/sub-01/anat/sub-01_hemi-R_smoothwm.surf.gii", "./tests/data/sub-01/anat/sub-01_T1w_space-MNI152NLin2009cAsym_brainmask.nii.gz": "./tst_out/sub-01/anat/sub-01_space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz", "./tests/data/sub-01/anat/sub-01_T1w_space-MNI152NLin2009cAsym_class-CSF_probtissue.nii.gz": "./tst_out/sub-01/anat/sub-01_space-MNI152NLin2009cAsym_label-CSF_probseg.nii.gz", "./tests/data/sub-01/anat/sub-01_T1w_space-MNI152NLin2009cAsym_class-GM_probtissue.nii.gz": "./tst_out/sub-01/anat/sub-01_space-MNI152NLin2009cAsym_label-GM_probseg.nii.gz", "./tests/data/sub-01/anat/sub-01_T1w_space-MNI152NLin2009cAsym_class-WM_probtissue.nii.gz": "./tst_out/sub-01/anat/sub-01_space-MNI152NLin2009cAsym_label-WM_probseg.nii.gz", "./tests/data/sub-01/anat/sub-01_T1w_space-MNI152NLin2009cAsym_dtissue.nii.gz": "./tst_out/sub-01/anat/sub-01_space-MNI152NLin2009cAsym_dseg.nii.gz", "./tests/data/sub-01/anat/sub-01_T1w_space-MNI152NLin2009cAsym_preproc.nii.gz": "./tst_out/sub-01/anat/sub-01_space-MNI152NLin2009cAsym_desc-preproc_T1w.nii.gz", "./tests/data/sub-01/anat/sub-01_T1w_space-MNI152NLin2009cAsym_target-T1w_warp.h5": "./tst_out/sub-01/anat/sub-01_from-MNI152NLin2009cAsym_to-T1w_mode-image_xfm.h5", "./tests/data/sub-01/anat/sub-01_T1w_target-fsnative_affine.txt": "./tst_out/sub-01/anat/sub-01_from-T1w_to-fsnative_mode-image_xfm.txt", "./tests/data/sub-01/anat/sub-01_T1w_target-MNI152NLin2009cAsym_warp.h5": "./tst_out/sub-01/anat/sub-01_from-T1w_to-MNI152NLin2009cAsym_mode-image_xfm.h5", "./tests/data/sub-01/ses-post/anat/sub-01_ses-post_T1w_space-orig_target-T1w_affine.txt": "./tst_out/sub-01/ses-post/anat/sub-01_ses-post_from-orig_to-T1w_mode-image_xfm.txt", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-flanker_bold_AROMAnoiseICs.csv": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-flanker_AROMAnoiseICs.csv", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-flanker_bold_confounds.tsv": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-flanker_desc-confounds_regressors.tsv", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-flanker_bold_MELODICmix.tsv": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-flanker_desc-MELODIC_mixing.tsv", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-flanker_bold_space-MNI152NLin2009cAsym_brainmask.nii.gz": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-flanker_space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-flanker_bold_space-MNI152NLin2009cAsym_preproc.nii.gz": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-flanker_space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-flanker_bold_space-MNI152NLin2009cAsym_variant-AROMAnonaggr_preproc.nii.gz": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-flanker_space-MNI152NLin2009cAsym_desc-AROMAnonaggr_bold.nii.gz", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-flanker_bold_space-MNI152NLin2009cAsym_variant-smoothAROMAnonaggr_preproc.nii.gz": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-flanker_space-MNI152NLin2009cAsym_desc-smoothAROMAnonaggr_bold.nii.gz", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-rest_bold_AROMAnoiseICs.csv": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-rest_AROMAnoiseICs.csv", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-rest_bold_confounds.tsv": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-rest_desc-confounds_regressors.tsv", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-rest_bold_MELODICmix.tsv": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-rest_desc-MELODIC_mixing.tsv", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-rest_bold_space-MNI152NLin2009cAsym_brainmask.nii.gz": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-rest_space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-rest_bold_space-MNI152NLin2009cAsym_preproc.nii.gz": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-rest_space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-rest_bold_space-MNI152NLin2009cAsym_variant-AROMAnonaggr_preproc.nii.gz": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-rest_space-MNI152NLin2009cAsym_desc-AROMAnonaggr_bold.nii.gz", "./tests/data/sub-01/ses-post/func/sub-01_ses-post_task-rest_bold_space-MNI152NLin2009cAsym_variant-smoothAROMAnonaggr_preproc.nii.gz": "./tst_out/sub-01/ses-post/func/sub-01_ses-post_task-rest_space-MNI152NLin2009cAsym_desc-smoothAROMAnonaggr_bold.nii.gz", "./tests/data/sub-01/ses-pre/anat/sub-01_ses-pre_T1w_space-orig_target-T1w_affine.txt": "./tst_out/sub-01/ses-pre/anat/sub-01_ses-pre_from-orig_to-T1w_mode-image_xfm.txt", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_bold_AROMAnoiseICs.csv": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_AROMAnoiseICs.csv", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_bold_confounds.tsv": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_desc-confounds_regressors.tsv", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_bold_MELODICmix.tsv": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_desc-MELODIC_mixing.tsv", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_bold_space-MNI152NLin2009cAsym_brainmask.nii.gz": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_bold_space-MNI152NLin2009cAsym_preproc.nii.gz": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_bold_space-MNI152NLin2009cAsym_variant-AROMAnonaggr_preproc.nii.gz": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_space-MNI152NLin2009cAsym_desc-AROMAnonaggr_bold.nii.gz", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_bold_space-MNI152NLin2009cAsym_variant-smoothAROMAnonaggr_preproc.nii.gz": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-flanker_space-MNI152NLin2009cAsym_desc-smoothAROMAnonaggr_bold.nii.gz", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_bold_AROMAnoiseICs.csv": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_AROMAnoiseICs.csv", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_bold_confounds.tsv": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_desc-confounds_regressors.tsv", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_bold_MELODICmix.tsv": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_desc-MELODIC_mixing.tsv", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_bold_space-MNI152NLin2009cAsym_brainmask.nii.gz": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_bold_space-MNI152NLin2009cAsym_preproc.nii.gz": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_bold_space-MNI152NLin2009cAsym_variant-AROMAnonaggr_preproc.nii.gz": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_space-MNI152NLin2009cAsym_desc-AROMAnonaggr_bold.nii.gz", "./tests/data/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_bold_space-MNI152NLin2009cAsym_variant-smoothAROMAnonaggr_preproc.nii.gz": "./tst_out/sub-01/ses-pre/func/sub-01_ses-pre_task-rest_space-MNI152NLin2009cAsym_desc-smoothAROMAnonaggr_bold.nii.gz"}

rename_old_fmriprep/tests/test_conform_fmriprep.py

@@ -0,0 +1,25 @@
+import os
+import json
+from ..conform_fmriprep import rename_fmriprep_files
+
+
+def test_rename_fmriprep_files(tmp_path):
+    cwd = os.path.dirname(os.path.realpath(__file__))
+    fmriprep_dir = os.path.join(cwd, 'data')
+    renamed_dir = tmp_path
+    dset_desc = os.path.join(fmriprep_dir, "dataset_description.json")
+    # reference output
+    with open(os.path.join(cwd, 'data_transfer.json'), 'r') as js:
+        ground_truth_tmp = json.load(js)
+    ground_truth = {os.path.basename(old): os.path.basename(new)
+                    for old, new in ground_truth_tmp.items()}
+    tst_truth_file = rename_fmriprep_files(fmriprep_dir, str(renamed_dir), dset_desc)
+
+    with open(tst_truth_file, 'r') as js2:
+        tst_truth_tmp = json.load(js2)
+
+    tst_truth = {os.path.basename(old): os.path.basename(new)
+                 for old, new in tst_truth_tmp.items()}
+    # get basenames for each key-value
+
+    assert ground_truth == tst_truth

requirements.txt

@@ -0,0 +1 @@
+pybids>=0.9.*