简单回归-ROE与薪酬

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/ceosal1.csv')
    
    plt.figure(figsize=(10,6))
    plt.scatter(df['roe'], df['salary'], alpha=0.5, color='steelblue')
    
    X = sm.add_constant(df['roe'])
    model = sm.OLS(df['salary'], X).fit()
    
    x_line = np.linspace(df['roe'].min(), df['roe'].max(), 100)
    y_line = model.params['const'] + model.params['roe'] * x_line
    plt.plot(x_line, y_line, 'r-', linewidth=2, label='回归线')
    
    plt.title('CEO薪酬与净资产收益率回归', fontsize=14)
    plt.xlabel('净资产收益率ROE (%)', fontsize=12)
    plt.ylabel('薪酬 (千美元)', fontsize=12)
    plt.legend()
    plt.grid(alpha=0.3)
    plt.tight_layout()
    plt.show()
    
    print(round(model.params['roe'], 2))