jupyter数据预处理代码

以下是一个简单的 Jupyter Notebook 数据预处理代码示例：

import pandas as pd
import numpy as np

# 读取数据
data = pd.read_csv('data.csv')

# 处理缺失值
data = data.dropna()  # 删除包含缺失值的行
data = data.reset_index(drop=True)  # 重置索引

# 处理异常值
data = data[data['age'] > 0]  # 删除年龄小于等于0的行

# 处理重复值
data = data.drop_duplicates()

# 特征缩放
data['age'] = (data['age'] - data['age'].mean()) / data['age'].std()

# 特征编码
data = pd.get_dummies(data, columns=['gender'])

# 特征选择
features = ['age', 'gender_Male']
X = data[features]

# 目标变量
y = data['income']

# 数据集拆分
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)