python实现简单的数据预处理

import pandas as pd
import numpy as np

def pre_1():
    # 读取数据
    df = pd.read_csv("/home/hadoop/下载/cs-training.csv")

    # 去除重复值
    df.duplicated()
    df.drop_duplicates()

    # 查看各字段缺失率
    df.info()
    # 缺失值按均值填充
    for col in list(df.columns[df.isnull().sum() > 0]):
        mean_val = df[col].mean()
        df[col].fillna(mean_val, inplace=True)

    # 删除不分析的列
    columns = ["RevolvingUtilizationOfUnsecuredLines"]
    df.drop(columns, axis=1, inplace=True)

    # 保存到本地
    df.to_csv("/home/hadoop/下载/data.csv")