Medical_code/HRS_P/HRS_preprocess.py

import pandas as pd


#HHID、PN



if __name__ == "__main__":
    #获取所有人的出生年月
    HHID_list = []
    PN_list = []
    BORN_YEAR_list = []
    SEX_list = []
    #1992加入人群
    with(open("/root/r_base/HRS/1992/data/health.da", "r", encoding="utf-8") )as file:
        # 逐行读取文件
        for line in file:
            HHID = line[0:6]
            PN = line[6:9]
            BORN_YEAR = line[99:104]
            SEX = line[109:110]   #1.Male 2.Female
            HHID_list.append(HHID)
            PN_list.append(PN)
            BORN_YEAR_list.append(BORN_YEAR)
            SEX_list.append(SEX)
            print(line, end='')  # end='' 用来避免多余的换行
    #93年加入
    with(open("/root/r_base/HRS/1993/data/BR21.DA", "r", encoding="utf-8") )as file:
        # 逐行读取文件
        for line in file:
            HHID = line[0:6]
            PN = line[6:9]
            BORN_YEAR = line[61:65]
            SEX = line[16:17]   #1.Male 2.Female
            HHID_list.append(HHID)
            PN_list.append(PN)
            BORN_YEAR_list.append(BORN_YEAR)
            SEX_list.append(SEX)
            print(line, end='')  # end='' 用来避免多余的换行
    #98年加入
    with(open("/root/r_base/HRS/1998/data/H98CS_R.DA", "r", encoding="utf-8") )as file:
        # 逐行读取文件
        for line in file:
            HHID = line[0:6]
            PN = line[6:9]
            BORN_YEAR = line[66:70]
            SEX = line[70:71]   #1.Male 2.Female
            HHID_list.append(HHID)
            PN_list.append(PN)
            BORN_YEAR_list.append(BORN_YEAR)
            SEX_list.append(SEX)
            print(line, end='')  # end='' 用来避免多余的换行
    #04年加入
    with(open("/root/r_base/HRS/2004/data/H04PR_R.da", "r", encoding="utf-8") )as file:
        # 逐行读取文件
        for line in file:
            HHID = line[0:6]
            PN = line[6:9]
            BORN_YEAR = line[25:29]
            SEX = line[20:21]   #1.Male 2.Female
            HHID_list.append(HHID)
            PN_list.append(PN)
            BORN_YEAR_list.append(BORN_YEAR)
            SEX_list.append(SEX)
            print(line, end='')  # end='' 用来避免多余的换行
    data = {
        "HHID":HHID_list,
        "PN":PN_list,
        "BORN_YEAR":BORN_YEAR_list,
        "SEX":SEX_list
    }
    result = pd.DataFrame(data)
    print(result.info())
    #进行去重处理
    result.drop_duplicates(subset=["HHID","PN"], keep="last", inplace=True)
    print(result.info())