Medical_code/HRS_P/HRS_preprocess.py

import pandas as pd

def get_smoked():
    #获取所有人的出生年月
    HHID_list = []
    PN_list = []
    SMOKED_list = []
    #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())
    result.to_csv("/root/r_base/HRS/result_born_sex.csv", encoding="utf-8", index=False)

if __name__ == "__main__":
    # result_born_sex = pd.read_csv("/root/r_base/HRS/result_born_sex.csv", encoding="utf-8")
    #2006数据
    year = "20"
    wave = "06"
    # 获取06年之前加入人员的信息
    with(open("/root/r_base/HRS/2006/data/H06PR_R.da", "r", encoding="utf-8") )as file:
        HHID_list = []
        PN_list = []
        BORN_YEAR_list = []
        SEX_list = []
        MARITAL_STATUS_list = []
        EDUCATION_list = []
        # 逐行读取文件
        for line in file:
            HHID = line[0:6]
            PN = line[6:9]
            BORN_YEAR = line[25:29]
            # 1.Male 
            # 2.Female
            SEX = line[20:21]   
            # 0.  UNKNOWN
            # 1.  MARRIED
            # 2.  MARRIED SP ABSENT (IN INSTITUTION)
            # 3.  MARRIED SP ABSENT (NOT IN INSTITUTION)
            # 4.  DIVORCED/SEPARATED
            # 5.  WIDOWED
            # 6.  NEVER MARRIED
            MARITAL_STATUS = line[106:107]
            # 0 For no formal education 
            # 1-11 .....Grades 
            # 12 .......High school 
            # 13-15 ....Some college
            # 16 .......College grad
            # 17 .......Post college (17+ years)
            # 97 .......Other
            EDUCATION = line[585:587]
            HHID_list.append(HHID)
            PN_list.append(PN)
            BORN_YEAR_list.append(BORN_YEAR)
            SEX_list.append(SEX)
            MARITAL_STATUS_list.append(MARITAL_STATUS)
            EDUCATION_list.append(EDUCATION)
            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,
            "MARITAL_STATUS":MARITAL_STATUS_list,
            "EDUCATION":EDUCATION_list
        }
        data["WAVE"] = 2006
        result = pd.DataFrame(data)
    # 将06年新加入的人员合并入数据
    with(open("/root/r_base/HRS/2006/data/H06C_R.da", "r", encoding="utf-8") )as file:
        HHID_list = []
        PN_list = []
        DRINK_list = []
        # 逐行读取文件
        for line in file:
            HHID = line[0:6]
            PN = line[6:9]
            #饮酒
            #      1.  YES
            #      3.  [VOL] NEVER HAVE USED ALCOHOL
            #      5.  NO
            #      8.  DK (Don't Know); NA (Not Ascertained)
            #      9.  RF (Refused)
            #  Blank.  INAP (Inapplicable); Partial Interview
            DRINK = line[207:208]

            HHID_list.append(HHID)
            PN_list.append(PN)
            DRINK_list.append(DRINK)
            print(line, end='')  # end='' 用来避免多余的换行
        data = {
            "HHID":HHID_list,
            "PN":PN_list,
            "EDUCATION":EDUCATION_list
        }
        result = pd.DataFrame(data)
        print(result.info())