Explore new Penn CNB data structure to identify problems

explore_new_cnb.py

from glob import glob
import json

dict1={'1':'SPLLT-A','2':'SPLLT-B','3':'SPLLT-C','4':'SPLLT-D','5':'PLLT-A','6':'PLLT-B','':'_______'}

files=glob('Pr*/PHOENIX/PROTECTED/Pr*/raw/???????/surveys/*.UPENN_nda.json')

# odd number of sessions and not provided cnb_pllt_test
for file in files:
    with open(file) as f:
        data=json.load(f)
        
    id=data[0]['src_subject_id']
    # for even number of sessions, change this to len(data)%2==0
    if len(data)%2:
        print(len(data), id)
        
    dict2=[]   
    for d in data:
        dict2.append((d['interview_date'],dict1[d['cnb_pllt_test']]))
    
    for d in sorted(dict2):
        print('\t',d)
    
    print('')