简单回归-工资与教育（含绘图）

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/wage1.csv')
    
    plt.figure(figsize=(10,6))
    plt.scatter(df['educ'], df['wage'], alpha=0.5, color='steelblue')
    
    X = sm.add_constant(df['educ'])
    model = sm.OLS(df['wage'], X).fit()
    
    x_line = np.linspace(df['educ'].min(), df['educ'].max(), 100)
    y_line = model.params['const'] + model.params['educ'] * x_line
    plt.plot(x_line, y_line, 'r-', linewidth=2, label=f'回归线')
    
    plt.title('工资与教育年限回归', fontsize=14)
    plt.xlabel('教育年限', fontsize=12)
    plt.ylabel('小时工资', fontsize=12)
    plt.legend()
    plt.grid(alpha=0.3)
    plt.tight_layout()
    plt.show()
    
    print(round(model.params['educ'], 4))