dataframe 更改某列某值_pyspark如何修改Dataframe中一列的值

12345678_0001

import pandas as pd

df = pd.read_csv('xxx.csv', header=0, encoding='utf-8')

age_interval = [(lower, upper) for lower, upper in zip(range(0, 96, 5), range(5, 101, 5))]def age_partition(age):

    """ 将年龄分类 """

    for lower, upper in age_interval:        if age is None:            return "None"

        elif lower <= age <= upper:            return f"({lower}, {upper})"df['new_col'] = df.age.apply(age_partition)