Format REDCap data for REDCap cloud

format_for_rcloud.py

#!/usr/bin/env python

import sys
import pandas as pd

df=pd.read_csv(sys.argv[1],dtype=str)
df1=df.copy()

df1.rename(columns={'chric_record_id':'participant_id'},inplace=True)
df1["redcap_system_data_format_version"]=1
df1["redcap_subject_screening_number"]=df1['participant_id']
df1['redcap_study']=[ s[:2] for s in df1['participant_id'].values ]


df1.drop(['redcap_data_access_group','redcap_survey_identifier'],inplace=True,axis=1)

reindex=["redcap_system_data_format_version","participant_id","redcap_subject_screening_number","redcap_study","redcap_event_name"]+list(df1.columns[2:-3])
df1=df1[reindex]

df1.to_csv(sys.argv[2], index=False)