p值与显著性

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')
    X = sm.add_constant(df[['educ', 'exper', 'tenure']])
    model = sm.OLS(df['wage'], X).fit()
    
    pvalues = model.pvalues.drop('const')
    
    plt.figure(figsize=(10,6))
    colors = ['green' if p < 0.05 else 'red' for p in pvalues]
    plt.bar(range(len(pvalues)), pvalues, color=colors, alpha=0.7)
    plt.axhline(y=0.05, color='k', linestyle='--', linewidth=2, label='显著性水平 0.05')
    plt.xticks(range(len(pvalues)), pvalues.index)
    plt.title('各变量p值与显著性', fontsize=14)
    plt.xlabel('变量', fontsize=12)
    plt.ylabel('p值', fontsize=12)
    plt.legend()
    plt.grid(axis='y', alpha=0.3)
    plt.tight_layout()
    plt.show()
    
    print(round(model.pvalues['educ'], 6))