回归问题 #

import lightgbm as lgb
import numpy as np
import pandas as pd
from sklearn.datasets import load_diabetes
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
import matplotlib.pyplot as plt

data = load_diabetes()
X = pd.DataFrame(data.data, columns=data.feature_names)
y = data.target

print(f"数据形状: {X.shape}")
print(f"目标值范围: [{y.min():.2f}, {y.max():.2f}]")
print(f"目标值均值: {y.mean():.2f}")

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

train_data = lgb.Dataset(X_train, label=y_train)
valid_data = lgb.Dataset(X_test, label=y_test, reference=train_data)

params = {
    'objective': 'regression',
    'metric': ['rmse', 'mae'],
    'num_leaves': 31,
    'learning_rate': 0.05,
    'verbose': -1
}

model = lgb.train(
    params,
    train_data,
    num_boost_round=1000,
    valid_sets=[valid_data],
    callbacks=[
        lgb.log_evaluation(100),
        lgb.early_stopping(50)
    ]
)

y_pred = model.predict(X_test, num_iteration=model.best_iteration)

rmse = np.sqrt(mean_squared_error(y_test, y_pred))
mae = mean_absolute_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

print(f"\nRMSE: {rmse:.4f}")
print(f"MAE: {mae:.4f}")
print(f"R²: {r2:.4f}")

fig, axes = plt.subplots(1, 2, figsize=(14, 5))

axes[0].scatter(y_test, y_pred, alpha=0.5)
axes[0].plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'r--', lw=2)
axes[0].set_xlabel('真实值')
axes[0].set_ylabel('预测值')
axes[0].set_title('预测结果')

residuals = y_test - y_pred
axes[1].hist(residuals, bins=30, edgecolor='black')
axes[1].set_xlabel('残差')
axes[1].set_ylabel('频数')
axes[1].set_title('残差分布')

plt.tight_layout()
plt.show()