房价多元回归（含散点图）

def solve():
    import pandas as pd
    import statsmodels.api as sm
    import matplotlib.pyplot as plt
    import numpy as np
    
    df = pd.read_csv('https://liangdaima.com/static/data/wooldridge/hprice1.csv')
    
    plt.figure(figsize=(10,6))
    plt.scatter(df['sqrft'], df['price'], alpha=0.5, color='steelblue')
    
    X = sm.add_constant(df[['sqrft', 'bdrms']])
    model = sm.OLS(df['price'], X).fit()
    
    x_line = np.linspace(df['sqrft'].min(), df['sqrft'].max(), 100)
    y_line = model.params['const'] + model.params['sqrft'] * x_line + model.params['bdrms'] * df['bdrms'].mean()
    plt.plot(x_line, y_line, 'r-', linewidth=2, label='回归线')
    
    plt.title('房价与房屋面积关系', fontsize=14)
    plt.xlabel('房屋面积（平方英尺）', fontsize=12)
    plt.ylabel('房价（美元）', fontsize=12)
    plt.legend()
    plt.grid(alpha=0.3)
    plt.tight_layout()
    plt.show()
    
    print(round(model.params['sqrft'], 4))