[pandas] csv 파일 로드 및 encode / decode

pandas를 이용하여 csv 파일을 로드하여, 특정 열을 처리하고 다시 Dataframe으로 합치는 작업을 해보았습니다.

 

# This is a sample Python script.

# Press Shift+F10 to execute it or replace it with your code.
# Press Double Shift to search everywhere for classes, files, tool windows, actions, and settings.
import base64
import csv
import pandas as pd

def print_hi(name):
    # Use a breakpoint in the code line below to debug your script.
    print(f'Hi, {name}')  # Press Ctrl+F8 to toggle the breakpoint.


# Press the green button in the gutter to run the script.
if __name__ == '__main__':

    #words = str("¸íÁøÃÊÅëÇб¸¿ª")
    #print(words.encode('iso-8859-1').decode('cp949'))
    #print_hi('PyCharm')

    #data = pd.read_csv("c:/upload/middle_shape_2022.csv", sep=',')
    #data = pd.read_csv("c:/upload/elementary_shape_2022.csv", sep=',')
    #data = pd.read_csv("c:/upload/highschool_nostandard_shape_2022.csv", sep=',')
    data = pd.read_csv("c:/upload/highschool_standard_shape_2022.csv", sep=',')


    ls1 = []
    for row in data.index:
        row_ls1 = data['HAKGUDO_NM'][row] #여기
        row_ls1_decode = str(row_ls1).encode('iso-8859-1').decode('cp949')
        print(row_ls1_decode)
        ls1.append(row_ls1_decode)


    ls2 = []
    for row2 in data.index:
        row_ls2 = data['EDU_UP_NM'][row2] #여기
        row_ls2_decode = str(row_ls2).encode('iso-8859-1').decode('cp949')
        print(row_ls2_decode)
        ls2.append(row_ls2_decode)

    ls3 = []
    for row3 in data.index:
        row_ls3 = data['EDU_NM'][row3] #여기
        row_ls3_decode = str(row_ls3).encode('iso-8859-1').decode('cp949')
        print(row_ls3_decode)
        ls3.append(row_ls3_decode)


    df1 = pd.DataFrame(ls1, columns = ['HAKGUDO_NM']) #여기
    df2 = pd.DataFrame(ls2, columns=['EDU_UP_NM'])  # 여기
    df3 = pd.DataFrame(ls3, columns=['EDU_NM'])  # 여기

    #print(pd.concat([data['the_geom'],data['shp_srs'],data['OBJECTID'],data['HAKGUDO_ID'],df1,data['SD_CD'],data['SGG_CD'],data['EDU_UP_CD'],df2,data['EDU_CD'],df3,data['CRE_DT'],data['UPD_DT'],data['BASE_DT']], axis=1))

    final_df = pd.concat([    data['the_geom']
                             ,data['shp_srs']
                             ,data['OBJECTID']
                             ,data['HAKGUDO_ID']
                             ,df1
                             ,data['HAKGUDO_GB']
                             ,data['SD_CD']
                             #,data['SGG_CD']
                             ,data['EDU_UP_CD']
                             ,df2
                             ,data['EDU_CD']
                             ,df3
                             ,data['CRE_DT']
                             ,data['UPD_DT']
                             ,data['BASE_DT']], axis=1)
    #final_df.to_csv('c:/upload/middle_shape_2022_final.csv', sep=',', index=False)
    #final_df.to_csv('c:/upload/elementary_shape_2022_final.csv', sep=',', index=False)
    #final_df.to_csv('c:/upload/highschool_nostandard_shape_2022_final.csv', sep=',', index=False)
    final_df.to_csv('c:/upload/highschool_standard_shape_2022_final.csv', sep=',', index=False)



# See PyCharm help at https://www.jetbrains.com/help/pycharm/