Medical_code/CHARLS_P/CHARLS_PM.py

import pandas as pd
from glob import glob
import os

def pollutant_handle(path):
    years = [2011, 2013,2015, 2018, 2020]
    #读取污染物数据
    pollutants_data = pd.read_csv("pollution/result_pm10_1km_p.csv")
    for year in years:
        CHARLS_data = pd.read_csv(path)
        print(CHARLS_data.info())
        #开始筛选出year的数据
        CHARLS_data_year = CHARLS_data[CHARLS_data['wave']==year]
        #两个表合并
        table_merge = pd.merge(CHARLS_data_year, pollutants_data, on=['province', 'city'], how='left')
        if str(year) in table_merge.columns:
            #更新CHARLS表
            CHARLS_data.loc[CHARLS_data['wave']==year, 'cur_year_PM10'] = table_merge[str(year)].values
        if str(year - 1) in table_merge.columns:
            CHARLS_data.loc[CHARLS_data['wave']==year, 'last_year_PM10'] = table_merge[str(year-1)].values
        if str(year - 2) in table_merge.columns:
            CHARLS_data.loc[CHARLS_data['wave']==year, 'before_last_PM10'] = table_merge[str(year-2)].values
        CHARLS_data.to_csv(path ,index=False)
        print(year)

def aba_handle(path_data):
    years = [2011, 2013,2015, 2018, 2020]
    for year in years:
        CHARLS_data = pd.read_csv(path_data)
        path = "aba627/result/"
        #读取污染物组分
        cur_year_file_name = path+str(year)+"_PM25_and_species_p.csv"
        last_year_file_name = path+str(year-1)+"_PM25_and_species_p.csv"
        before_last_file_name = path+str(year-2)+"_PM25_and_species_p.csv"
        cur_pollutants_data = pd.read_csv(cur_year_file_name)
        last_year_pollutants_data = pd.read_csv(last_year_file_name)
        before_last_pollutants_data = pd.read_csv(before_last_file_name)
        #开始筛选出year的数据
        CHARLS_data_year = CHARLS_data[CHARLS_data['wave']==year]
        #和当年的污染物组分文件合并
        cur_table_merge = pd.merge(CHARLS_data_year, cur_pollutants_data, on=['province', 'city'], how='left')
        CHARLS_data.loc[CHARLS_data['wave']==year, 'cur_year_SO4'] = cur_table_merge["SO4"].values
        CHARLS_data.loc[CHARLS_data['wave']==year, 'cur_year_NO3'] = cur_table_merge["NO3"].values
        CHARLS_data.loc[CHARLS_data['wave']==year, 'cur_year_NH4'] = cur_table_merge["NH4"].values
        CHARLS_data.loc[CHARLS_data['wave']==year, 'cur_year_OM'] = cur_table_merge["OM"].values
        CHARLS_data.loc[CHARLS_data['wave']==year, 'cur_year_BC'] = cur_table_merge["BC"].values
        #和上一年的污染物组分文件合并
        last_table_merge = pd.merge(CHARLS_data_year, last_year_pollutants_data, on=['province', 'city'], how='left')
        CHARLS_data.loc[CHARLS_data['wave']==year, 'last_year_SO4'] = last_table_merge["SO4"].values
        CHARLS_data.loc[CHARLS_data['wave']==year, 'last_year_NO3'] = last_table_merge["NO3"].values
        CHARLS_data.loc[CHARLS_data['wave']==year, 'last_year_NH4'] = last_table_merge["NH4"].values
        CHARLS_data.loc[CHARLS_data['wave']==year, 'last_year_OM'] = last_table_merge["OM"].values
        CHARLS_data.loc[CHARLS_data['wave']==year, 'last_year_BC'] = last_table_merge["BC"].values
        #和上上年的污染物组分文件合并
        before_last_table_merge = pd.merge(CHARLS_data_year, before_last_pollutants_data, on=['province', 'city'], how='left')
        CHARLS_data.loc[CHARLS_data['wave']==year, 'before_last_SO4'] = before_last_table_merge["SO4"].values
        CHARLS_data.loc[CHARLS_data['wave']==year, 'before_last_NO3'] = before_last_table_merge["NO3"].values
        CHARLS_data.loc[CHARLS_data['wave']==year, 'before_last_NH4'] = before_last_table_merge["NH4"].values
        CHARLS_data.loc[CHARLS_data['wave']==year, 'before_last_OM'] = before_last_table_merge["OM"].values
        CHARLS_data.loc[CHARLS_data['wave']==year, 'before_last_BC'] = before_last_table_merge["BC"].values
        #更新CHARLS表
        CHARLS_data.to_csv("CHARLS_data_pollutants.csv",index=False)
        print(year)

if __name__ == "__main__":
    #读取CHARLS数据
    path = "CHARLS_data_pollutants.csv"
    # CHARLS_data = pd.read_csv("CHARLS/result_all_new.csv")
    # print(CHARLS_data.info())
    # CHARLS_data.to_csv("CHARLS_data_pollutants.csv",index=False)
    
    #处理污染物
    # pollutant_handle(path)
    #处理PM2.5组分
    aba_handle(path)