ValueError在Scikit中查找最佳超参数时使用GridSearchCV学习LogisticRegression

import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# 假设 X 和 y 是你的数据和目标变量
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 标准化特征
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# 检查是否有 NaN 或无穷大值
assert not np.isnan(X_train).any() and not np.isinf(X_train).any()
assert not np.isnan(X_test).any() and not np.isinf(X_test).any()

from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV

# 定义参数网格
param_grid = {
    'C': [0.001, 0.01, 0.1, 1, 10, 100],  # 正则化强度的倒数
    'penalty': ['l1', 'l2'],  # 正则化类型
    'solver': ['liblinear']  # 优化算法
}

# 创建 Logistic Regression 实例
log_reg = LogisticRegression(max_iter=1000)

# 创建 GridSearchCV 实例
grid_search = GridSearchCV(log_reg, param_grid, cv=5)

# 拟合模型
grid_search.fit(X_train, y_train)

from sklearn.decomposition import PCA

# 应用 PCA
pca = PCA(n_components=0.95)  # 保留95%的方差
X_train_pca = pca.fit_transform(X_train)
X_test_pca = pca.transform(X_test)

# 使用 PCA 后的数据重新进行 GridSearchCV
grid_search.fit(X_train_pca, y_train)