如何避免交叉验证中的数据泄露？

from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import KFold
import numpy as np
X = np.random.randn(1000, 20)
y = np.random.randint(0, 2, 1000)
cv_scores = []
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
kf = KFold(n_splits=5)
for train_idx, val_idx in kf.split(X_scaled):
    X_train, X_val = X_scaled[train_idx], X_scaled[val_idx]
    y_train, y_val = y[train_idx], y[val_idx]
    model = LogisticRegression()
    model.fit(X_train, y_train_fold)
    fold_score = accuracy_score(y_val_fold, y_pred)
    cv_scores.append(fold_score)
print(f"交叉验证平均准确度: {np.mean(cv_scores):.4f}")

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import cross_val_score

# Correct approach: scaling inside each fold
pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('classifier', LogisticRegression())
])
# Preprocessing happens inside each fold
scores = cross_val_score(pipeline, X, y, cv=5)
print(f"Cross-validation scores: {scores}")
print(f"Mean CV score: {scores.mean():.3f}")

import numpy as np
import pandas as pd
from sklearn.model_selection import StratifiedKFold
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

# 示例数据集
np.random.seed(42)
X = np.random.randn(100, 5)  # 100个样本，每个样本5个特征
y = np.random.choice([0, 1], size=100, p=[0.7, 0.3])  # 目标变量，类别分布不均（70% 类别0，30% 类别1）

# 创建 StratifiedKFold 实例，n_splits=5 表示5折交叉验证
skf = StratifiedKFold(n_splits=5)

# 用于存储每一折的评估结果
accuracy_scores = []

# 循环每一折
for train_index, test_index in skf.split(X, y):
    # 划分训练集和测试集
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index]

    # 初始化并训练模型
    model = LogisticRegression(solver='liblinear')
    model.fit(X_train, y_train)

    # 进行预测
    y_pred = model.predict(X_test)

    # 计算准确率
    accuracy = accuracy_score(y_test, y_pred)
    accuracy_scores.append(accuracy)

# 输出平均准确率
print(f"Average Accuracy: {np.mean(accuracy_scores):.4f}")

import numpy as np
import pandas as pd
from sklearn.model_selection import TimeSeriesSplit
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# 示例时间序列数据
np.random.seed(42)
dates = pd.date_range(start='2020-01-01', periods=100, freq='D')
data = pd.DataFrame({
    'date': dates,
    'target': np.random.randn(100),
    'feature': np.random.randn(100)
})

# 目标变量和特征
X = data[['feature']].values  # 特征
y = data['target'].values     # 目标变量

# 使用 TimeSeriesSplit 进行时间序列交叉验证
tscv = TimeSeriesSplit(n_splits=5)

# 用于存储每一折的评估结果
mse_scores = []

# 循环每一折
for train_index, test_index in tscv.split(X):
    # 划分训练集和验证集
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index]

    # 初始化并训练模型
    model = LinearRegression()
    model.fit(X_train, y_train)

    # 进行预测
    y_pred = model.predict(X_test)

    # 计算均方误差（MSE）
    mse = mean_squared_error(y_test, y_pred)
    mse_scores.append(mse)

# 输出平均MSE
print(f"Average MSE: {np.mean(mse_scores):.4f}")