Medical_code/CHARLS_P/CHARLS_exit.py

import pandas as pd
import pyreadstat

if __name__ == "__main__":
    #读取CHARLS数据
    CHARLS_data = pd.read_csv("CHARLS_data_pollutants_mete.csv")
    CHARLS_data.to_csv("CHARLS_data_pollutants_exit.csv",index=False)
    CHARLS_data = pd.read_csv("CHARLS_data_pollutants_exit.csv")
    
    #增加一列死亡状态
    #0：未死亡
    #1：死亡 
    #读取2013年的死亡数据
    exit, meta = pyreadstat.read_dta("/root/r_base/CHARLS/CHARLS2013/Exit_Interview.dta")
    exit['ID'] = pd.to_numeric(exit['ID'], errors='coerce').astype('Int64')
    exit["exit_year"] = exit["exb001_1"]
    CHARLS_data = pd.merge(CHARLS_data, exit[['ID', "exit_year"]], on = "ID", how="left")

    #读取2020年的死亡数据
    exit, meta = pyreadstat.read_dta("/root/r_base/CHARLS/CHARLS2020/Exit_Module.dta")
    exit['ID'] = pd.to_numeric(exit['ID'], errors='coerce').astype('Int64')
    exit["exit_year"] = exit["exb001_1"]
    CHARLS_data = pd.merge(CHARLS_data, exit[['ID', "exit_year"]], on = "ID", how="left")
    CHARLS_data.to_csv("CHARLS_data_pollutants_exit.csv",index=False)