import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score

# 設(shè)置字體，解決中文顯示問(wèn)題
plt.rcParams['font.sans-serif'] = ['SimHei']  # 使用黑體字體顯示中文
plt.rcParams['axes.unicode_minus'] = False  # 解決坐標(biāo)軸負(fù)號(hào)顯示問(wèn)題

# 加載加州房?jī)r(jià)數(shù)據(jù)集
california = fetch_california_housing()
data = pd.DataFrame(california.data, columns=california.feature_names)
data['MedHouseVal'] = california.target
data

# 選擇特征 'MedInc' 進(jìn)行建模
X = data[['MedInc', 'HouseAge', 'AveRooms', 'AveOccup']]
y = data['MedHouseVal']

# 分割數(shù)據(jù)為訓(xùn)練集和測(cè)試集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 初始化線性回歸模型
model = LinearRegression()

# 訓(xùn)練模型
model.fit(X_train, y_train)

# 使用測(cè)試集進(jìn)行預(yù)測(cè)
y_pred = model.predict(X_test)

# 評(píng)估模型表現(xiàn)
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

print(f"均方誤差（MSE）: {mse}")
print(f"決定系數(shù)（R^2）: {r2}")

# 可視化預(yù)測(cè)值與實(shí)際值的比較
plt.figure(figsize=(10, 6))
plt.scatter(y_test, y_pred, alpha=0.5, label="預(yù)測(cè)值 vs 實(shí)際值")
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'r--', lw=2, label="理想的直線 $y = x$")
plt.xlabel("實(shí)際房?jī)r(jià)")
plt.ylabel("預(yù)測(cè)房?jī)r(jià)")
plt.title("實(shí)際房?jī)r(jià) vs 預(yù)測(cè)房?jī)r(jià)")
plt.legend()
plt.show()