自定义数据集使用scikit-learn中的包实现线性回归方法对其进行拟合
python
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, r2_score
# 生成示例数据：y = 3 * X + 4 + 噪声
np.random.seed(42)
X = 2 * np.random.rand(100, 1) # 100个样本，1个特征
y = 3 * X + 4 + np.random.randn(100, 1) # 线性关系 + 随机噪声
# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# 创建线性回归模型并拟合
model = LinearRegression()
model.fit(X_train, y_train)
# 在测试集上进行预测
y_pred = model.predict(X_test)
# 评估模型
mse = mean_squared_error(y_test, y_pred)
print(f"Mean Squared Error: {mse}")
r2 = r2_score(y_test, y_pred)
print(f"R²: {r2}")
# 可视化结果
plt.scatter(X_train, y_train, color='blue', label='Training data')
plt.scatter(X_test, y_test, color='green', label='Test data')
plt.plot(X_test, y_pred, color='red', label='Regression line')
plt.xlabel('X')
plt.ylabel('y')
plt.legend()
plt.show()