Python Pandas 比较列

Question

我需要帮助来将 csv 列中的数据与另一个 csv 进行比较。获取正确地址

num_lines = sum(1 for line in open('example.csv')) # 计算行数

for row in range(num_line - 1):
    df1 = pd.read_csv("example.csv", na_values=['NA'])  # read csv addresses list that need to be fixed
    df2 = pd.read_csv("CTT.csv", na_values=['NA'])      # read csv with correct addresses 

    if cp7 == True:

将列与另一个 csv 文件进行比较

        if cp7 == 1:

cp7 只匹配一个地址

            File = open('Norm.csv', 'w')
            Norm = csv.writer(File)
            Norm = [column for column in Norm]
            File.close()
        else:

所有 cp7 可能性

            File = open('PNorm.csv', 'w')
            PNorm = csv.writer(File)
            PNorm = [column for column in PNorm]
            File.close()

    elif cp4 == True:

所有 cp4 可能性

将列与另一个 csv 文件进行比较

        File = open('PNorm.csv', 'w')
        PNorm = csv.writer(File)
        PNorm = [column for column in PNorm]
        File.close()
    else:
        pass

    if localidade == True:

所有本地化可能性

阅读本地化

        File = open('PNorm.csv', 'w')
        PNorm = csv.writer(File)
        PNorm = [column for column in PNorm]
        File.close()

    else:
        pass

    if tipovia == True 

        # compare column with another csv file

        if tipovia == 1:

TipoVia 只匹配一个地址

            File = open('Norm.csv', 'w')
            Norm = csv.writer(File)
            Norm = [column for column in Norm]
            File.close()
        else:

所有 cp7 可能性

            File = open('PNorm.csv', 'w')
            PNorm = csv.writer(File)
            PNorm = [column for column in PNorm]
            File.close()
    else:
        pass

    if nomerua_numpolicia == True

将列与另一个 csv 文件进行比较

        if nomerua_numpolicia == 1:

NomeRua_NumPolicia 只匹配一个地址

            File = open('Norm.csv', 'w')
            Norm = csv.writer(File)
            Norm = [column for column in Norm]
            File.close()
        else:

所有 cp7 可能性

            File = open('PNorm.csv', 'w')
            PNorm = csv.writer(File)
            PNorm = [column for column in PNorm]
            File.close()
    else:
        pass

Answer 1

解决方法：

if df1.reset_index(drop=True)["CP4"] == df2.reset_index(drop=True)["CP4"] and
df1.reset_index(drop=True)["CP3"] == df2.reset_index(drop=True)["CP3"]

Python Pandas 比较列

Python Pandas Compare column

python

csv

multiple-columns

pandas