fork download
  1. import pandas as pd
  2.  
  3. df = pd.DataFrame({'person_id': [11,11,11],'text':['DOSE: 667 mg - TDS with food - Inject','DOSE: 667 mg - TDS with food - Tube','DOSE: 667 mg - TDS with food - PO'],'Summary':['Test','Test1','Test2']})
  4. df['text'] = df['text'].str.replace(r'\bDOSE:\s*([^-]*)-[^-]*-\s*(.*)', r'\1\2')
  5. print ( df.filter(['person_id', 'text', 'Summary']) )
Success #stdin #stdout 0.34s 60936KB
stdin
Standard input is empty
stdout
   person_id           text Summary
0         11  667 mg Inject    Test
1         11    667 mg Tube   Test1
2         11      667 mg PO   Test2