Extract questions and anwers from healthtap dataset

healthtap_extraction.py

import ast
import pandas as pd

data = pd.read_csv('path_to_healthtap_file.csv')
all_questions = []
all_answers = []
for question, answer_format in zip(data.question, data.answers):
    try:
        if answer_format != "[]":
            all_answers.append(ast.literal_eval(answer_format)[0]["answer"])
            all_questions.append(question)
    except:
        continue