import pandas as pd

df = pd.DataFrame(
    {
        "Customerkeycode": [
            "B01:B14:110083",
            "B02:B15:110084"
        ]
    }
)

df['PlanningCustomerSuperGroupCode'] = df['Customerkeycode'].apply(lambda x: x.split(":")[0])
df['DPGCode'] = df['Customerkeycode'].apply(lambda x: x.split(":")[1])
df['APGCode'] = df['Customerkeycode'].apply(lambda x: x.split(":")[2])

df_rep = df.drop("Customerkeycode", axis = 1)

print(df_rep)

   PlanningCustomerSuperGroupCode DPGCode APGCode
0                            B01     B14  110083
1                            B02     B15  110084

按“：”拆分为3列，列名称为[“计划客户超级组代码”、“DPGCode”、“APGCode”]

import pyspark.sql.functions as F

df.withColumn('PlanningCustomerSuperGroupCode', F.split(F.col('Customerkeycode'), ':')[0]) \
    .withColumn('DPGCode', F.split(F.col('Customerkeycode'), ':')[1]) \
    .withColumn('APGCode', F.split(F.col('Customerkeycode'), ':')[2]) \
    .drop('Customerkeycode') \
    .show()