一种解决高版本python无法加载sklearn内置的波士顿房价数据的方法

  本人用的是python3.11，在机器学习项目实战时，无法通过传统的方式加载sklearn内置的波士顿房价数据。

原代码如下：

# 导入必要的库
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

# 加载波士顿房屋数据集
boston = load_boston()

# 数据准备
X = boston.data
y = boston.target

# 将数据集划分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 创建线性回归模型实例
model = LinearRegression()

# 模型训练
model.fit(X_train, y_train)

# 模型预测
y_pred = model.predict(X_test)

# 计算均方误差
mse = np.mean((y_pred - y_test) ** 2)
print("均方误差：", mse)

# 结果可视化
plt.scatter(y_test, y_pred)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=2)
plt.xlabel('actual_price')
plt.ylabel('predict_price')
plt.title('liner')
plt.show()

运行这个代码会出现错误：

Traceback (most recent call last):
  File "\line_regression.py", line 5, in <module>
    from sklearn.datasets import load_boston
  File "sklearn\datasets\__init__.py", line 157, in __getattr__
    raise ImportError(msg)
ImportError: 
`load_boston` has been removed from scikit-learn since version 1.2.
该错误说明高版本不再适用传统形式加载这个数据集。

对加载波士顿房屋数据集模块进行修改，修改代码如下：

# 导入必要的库
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
#from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

# 加载波士顿房屋数据集
data_url = "http://lib.stat.cmu.edu/datasets/boston"
raw_df = pd.read_csv(data_url, sep="\s+", skiprows=22, header=None)
data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
target = raw_df.values[1::2, 2]

# 数据准备
X = data
y = target

# 将数据集划分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 创建线性回归模型实例
model = LinearRegression()

# 模型训练
model.fit(X_train, y_train)

# 模型预测
y_pred = model.predict(X_test)

# 计算均方误差
mse = np.mean((y_pred - y_test) ** 2)
print("均方误差：", mse)

# 结果可视化
plt.scatter(y_test, y_pred)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=2)
plt.xlabel('actual_price')
plt.ylabel('predict_price')
plt.title('liner')
plt.show()