事件研究法Python代码

 # 事件研究法

    
 import pandas as pd 
    
 import tushare as ts 
    
 import matplotlib.pyplot as plt 
    
 from sklearn.linear_model import LinearRegression 
    
  
    
 # 线性回归 
    
 import csv import numpy as np 
    
 import math 
    
 plt.rcParams['font.sans-serif'] = ['SimHei'] # 中文 
    
 plt.rcParams['axes.unicode_minus'] = False 
    
 pro = ts.pro_api('个人 tushare 端口代码') 
    
 plt.style.use('fivethirtyeight') 
    
  
    
 # 市场收益率 
    
 Rm df = pro.index_daily(ts_code='市场代码', start_date='20100101', end_date='20220101') df_index = df[['trade_date', 'pct_chg']].copy() 
    
 df_index['trade_date'] = pd.to_datetime(df_index['trade_date']) 
    
 df_index = df_index.sort_values("trade_date")
    
 df_index = df_index.reset_index().drop("index", axis=1) 
    
 df_index['pct_chg'] = df_index['pct_chg'] / 100 
    
  
    
 # 企业收益率 
    
 Ri ts_code = '企业代码' d2 = pro.index_daily(ts_code=ts_code, start_date='20100101', end_date='20220101') 
    
 d0 = d2[['trade_date', 'pct_chg']].copy() 
    
 d0.columns = ['trade_date', 'return'] 
    
 d0['trade_date'] = pd.to_datetime(d0['trade_date']) 
    
 d0 = d0.sort_values("trade_date") 
    
 d0 = d0.reset_index().drop("index", axis=1) 
    
 d0['return'] = d0['return'] / 100
    
  
    
 # 合并 Ri 和 Rm 
    
 df_final = d0.merge(df_index, on='trade_date', how='left') 
    
 df_final.to_excel("整理数据.xlsx") 
    
  
    
 # 计算预期收益率
    
 def get_OLS(X, y, pre_X):
    
     linear_m = LinearRegression().fit(X, y)
    
     r_2 = linear_m.score(X, y)  # 值越接近1拟合优度越好
    
     pre_y = linear_m.predict(X)
    
     Residual = sum((y - pre_y) ** 2)
    
     L_xx = len(X) * np.var(X)
    
     sigma = np.sqrt(Residual / (len(X) - 2))
    
     t = linear_m.coef_ * np.sqrt(L_xx) / sigma
    
     t = round(float(t), 4)
    
  
    
     print(f"构建模型，拟合优度为{round(r_2 * 100, 2)}%")
    
     print(f"Ri = {round(linear_m.intercept_, 3)} + {round(linear_m.coef_[0], 3)}Rm + e")
    
  
    
     if 1.65 <= abs(t) < 1.96:
    
     print(f'回归模型的t值为{t}，回归系数在10%的置信水平下显著')
    
     elif 1.96 <= abs(t) < 2.58:
    
     print(f'回归模型的t值为{t}，回归系数在5%的置信水平下显著')
    
     elif abs(t) >= 2.58:
    
     print(f'回归模型的t值为{t}，回归系数在1%的置信水平下显著')
    
     else:
    
     print(f'回归模型的t值为{t}，回归系数不显著')
    
  
    
     return linear_m.predict(pre_X)
    
  
    
 # 计算AR,CAR
    
 def get_data(event):
    
     print("事件日为: ", event)
    
     q, h = df_final[df_final['trade_date'] == event].index[0] - 15, df_final[df_final['trade_date'] == event].index[0] + 15  # 事件窗口[-15,15]
    
     target = df_final.loc[q:h].copy()
    
     estimate = df_final.loc[q - 195:q - 6].copy()  # 估计窗口[-210,-21]
    
     X = estimate[['pct_chg']]  # 估计期市场回报率
    
     y = estimate['return']  # 估计期企业回报率
    
     predict_X = target[['pct_chg']]  # 窗口期市场回报率
    
     target['E(Rt)'] = get_OLS(X, y, predict_X)  # 企业预期收益率
    
     target['ARt'] = target['return'] - target['E(Rt)']  # 企业异常收益率
    
     target['CARt'] = target['ARt'].cumsum()  # 累计异常收益率 = 异常收益率在窗口期的求和
    
     return target
    
  
    
  
    
 # 绘制图像
    
 def main(e):
    
     a = get_data(e)
    
     a.to_excel('data.xls',index=False)
    
     AR = a['ARt']
    
     CAR = a['CARt']
    
     theta1 = np.mean(AR)/math.sqrt(np.var(AR))
    
     theta2 = np.mean(CAR)/math.sqrt(np.var(CAR))
    
     print('theta1:',theta1)
    
     print('theta2:',theta2)
    
     a.set_index('trade_date')[['ARt', 'CARt']].plot()
    
  
    
  
    
 # 结果
    
 events = ['事件发生日期 00:00:00']
    
 for e in events:
    
     main(e)
    
  
    
 plt.title('企业名称')
    
 plt.savefig('.\企业名称.jpg', bbox_inches='tight')