info/tutorials/intro/exploring-with-almirah.md

Exploring the CALM Brain Resource with almirah

Load the dataset

from almirah import Dataset

Dataset.options()

[<Dataset name: 'calm-brain'>]

ds = Dataset(name="calm-brain")
ds.components

[<Layout root: '/path/to/data'>,
 <Layout root: '/path/to/genome'>,
 <Database url: 'request:calm-brain@https://www.calm-brain.ncbs.res.in/db-request/'>]

Quering layouts

lay = ds.components[0]
print(lay)
len(lay.files)

<Layout root: '/path/to/data'>

42652

from almirah import Tag

tags = Tag.options()
len(tags)

1589

tags_names_possible = {tag.name for tag in tags}
tags_names_possible

{'acquisition',
 'datatype',
 'direction',
 'extension',
 'run',
 'sample',
 'session',
 'space',
 'subject',
 'suffix',
 'task'}

Tag.options(name="datatype")

[<Tag datatype: 'anat'>,
 <Tag datatype: 'dwi'>,
 <Tag datatype: 'eeg'>,
 <Tag datatype: 'eyetrack'>,
 <Tag datatype: 'fmap'>,
 <Tag datatype: 'func'>,
 <Tag datatype: 'genome'>,
 <Tag datatype: 'nirs'>]

files = lay.query(datatype="eeg")
len(files)

15821

file = files[0]
file.rel_path

'sub-D0828/ses-101/eeg/sub-D0828_ses-101_task-auditoryPCP_run-01_events.json'

file.tags

{'datatype': 'eeg', 'extension': '.json', 'run': '01', 'session': '101', 'subject': 'D0828', 'suffix': 'events', 'task': 'auditoryPCP'}

Querying databases

db = ds.components[2]
db

<Database url: 'request:calm-brain@https://www.calm-brain.ncbs.res.in/db-request/'>

db.connect("username", "password")
df = db.query(table="presenting_disorders")
df[["subject", "session", "addiction"]].head()

	subject	session	addiction
0	D0019	101	0
1	D0019	111	0
2	D0020	101	0
3	D0020	111	<NA>
4	D0021	101	0

Generating summaries

anat_subject_tags = ds.query(returns="subject", datatype="anat")
anat_subjects = {subject for t in anat_subject_tags for subject in t}
len(anat_subjects)

699

eyetrack_subject_tags = ds.query(returns="subject", datatype="eyetrack")
eyetrack_subjects = {subject for t in eyetrack_subject_tags for subject in t}
len(eyetrack_subjects)

1075    

df = db.query(table="subjects")
len(df)

2276

df = db.query(table="modified_kuppuswamy_socioeconomic_scale")
len(df)

1444