import pandas as pd, re junk = """Shot - Wounded/Injured, Shot - Dead (murder, accidental, suicide), Suicide - Attempt, Murder/Suicide, Attempted Murder/Suicide (one variable unsuccessful), Institution/Group/Business, Mass Murder (4+ deceased victims excluding the subject/suspect/perpetrator , one location), Mass Shooting (4+ victims injured or killed excluding the subject/suspect""" rx = re.compile(r'\([^()]+\)|,(\s+)') data = [x for nugget in rx.split(junk) if nugget for x in [nugget.strip()] if x] df = pd.DataFrame({'incident_characteristics': data}) print(df)