双分组分析以及famamacbeth回归_股票_双分组分析；famamacbeth回归_

# _*_coding:utf-8_*_ # 开发团队：阿悦科技 # 开发人员：Administrator # 开发时间：2020/11/1718:56 # 文件名称：双分组分析.py # 开发工具：PyCharm import pandas as pd import numpy as np import math import datetime import statsmodels.api as sm import matplotlib.pyplot as plt from scipy import linalg import scipy # 第一部分，进行数据的预处理 def loadMainTrdData(): df = pd.read_csv('TRD_Mnth.csv') df['Trdmnt'] = pd.to_datetime(df.Trdmnt) df1 = pd.read_excel('Norisk_Rate.xlsx') # 读入数据 df = df.drop([0, 1]) # 删除第0行和第1行 df = df[['Stkcd', 'Trdmnt', 'Mretnd', 'Msmvosd']] df1 = df1[['Trdmnt','rf']] # 保留四个变量和两个变量 df['Stkcd'] = [str(x).zfill(6) for x in df.Stkcd] # 将股票代码以6位字符串的形式展现 df['isNormal'] = [x[0] in ['0', '3', '6'] for x in df.Stkcd] # 以0，3，6开头的股票代码才是正确的 df = df[df.isNormal] # 将股票代码正确的筛选出来 df = df.drop(['isNormal'], axis=1) # 将布尔型变量normal删掉，删除一列 df = pd.merge(df, df1, on=['Trdmnt'], how='left') # 个股匹配无风险利率（月度） df['Ret_Excess'] = df['Mretnd'] - df['rf'] # 得到超额收益率Ret_Excess df_pivot = df.pivot(index='Trdmnt', columns='Stkcd', values='Ret_Excess') # 转换dataframe的形式，index为时间，columns为股票代码，value为超额收益 df_pivot = df_pivot.shift(-1) # 时间上滞后一期得到滞后超额收益率 df_pivot = df_pivot.unstack().reset_index().rename(columns={0: 'F1_Ret'}) # 列索引变成行索引，将新的收益列命名为'F1_Ret' df = pd.merge(df, df_pivot, on=['Stkcd', 'Trdmnt'], how='left') # 将滞后超额收益率与原列表拼接 df = df[df.Trdmnt >= '2005-01'] # 取2005年1月之后的数据 df['F1_Ret'].fillna(0,inplace=True) # 将该列缺失值部分补充为0 return df df = loadMainTrdData() df_pivot = df.pivot(index='Trdmnt', columns='Stkcd', values='Mretnd') df_pivot = df_pivot.sort_index() df1=df_pivot.shift(1) #将已经滞后的收益率归正 df_pivot = df1.unstack().reset_index().rename(columns = {0: 'CumPastRet1'}) df = pd.merge(df, df_pivot, on = ['Stkcd', 'Trdmnt'], how='left') #计算1个月的累积收益率 df_pivot = df.pivot(index='Trdmnt', columns='Stkcd', values='Mretnd') df_pivot = df_pivot.sort_index() df1=df_pivot.shift(1) df_pivot = df1.rolling(window=3, min_periods=1).apply(lambda x: (1 + x).prod() - 1, raw=False) #rolling函数滚动累乘 df_pivot = df_pivot.unstack().reset_index().rename(columns = {0: 'CumPastRet3'}) df = pd.merge(df, df_pivot, on = ['Stkcd', 'Trdmnt'], how='left') #计算3个月的累计收益率 df_pivot = df.pivot(index='Trdmnt', columns='Stkcd', values='Mretnd') df_pivot = df_pivot.sort_index() df1=df_pivot.shift(1) df_pivot = df_pivot.rolling(window=6, min_periods=1).apply(lambda x: (1 + x).prod() - 1, raw=False) df_pivot = df_pivot.unstack().reset_index().rename(columns = {0: 'CumPastRet6'}) df = pd.merge(df, df_pivot, on = ['Stkcd', 'Trdmnt'], how='left') #计算6个月的累积收益率 df_pivot = df.pivot(index='Trdmnt', columns='Stkcd', values='Mretnd') df_pivot = df_pivot.sort_index() df1=df_pivot.shift(1) df_pivot = df_pivot.rolling(window=12, min_periods=1).apply(lambda x: (1 + x).prod() - 1, raw=False) df_pivot = df_pivot.unstack().reset_index().rename(columns = {0: 'CumPastRet12'}) df = pd.merge(df, df_pivot, on = ['Stkcd', 'Trdmnt'], how='left') #计算12个月的累积收益率 df['CumPastRet2-12']=(1+df['CumPastRet12'])/(1+df['CumPastRet1'])-1 #计算2-12个月的累积收益率 #依赖双分组函数 def cpt_vw_ret(group, avg_name, weight_name): d = group[avg_name] w = group[weight_name] try: return (d * w).sum() / w.sum() except ZeroDivisionError: return np.nan def get_stock_groups(data, sortname, groups_num): df = data.copy() labels = ['G0' + str(i) for i in range(1, groups_num + 1)] groups = pd.DataFrame(pd.qcut(df[sortname], groups_num, labels=labels).astype(str)).rename(columns={sortname: 'Group'}) groups.index.name = 'ID' return groups def dependent_double_sort(data, sortname1, sortname2,TimeName, groups_num1,groups_num2, weighted): df = data.copy() PortTag1 = df.groupby([TimeName]).apply(get_stock_groups, sortname1, groups_num1).reset_index().set_index('ID') df = pd.merge(df, PortTag1['Group'], left_index=True, right_index=True) df.rename(columns={'Group': 'G1'}, inplace=True) #按照sortname1进行单分组 PortTag2 = df.groupby([TimeName,'G1']).apply(get_stock_groups, sortname2, groups_num2).reset_index().set_index('ID') df = pd.merge(df, PortTag2['Group'], left_index=True, right_index=True) df.rename(columns={'Group': 'G2'}, inplace=True) #按照sortname2进行依赖双分组 df['Group'] = df['G1'] + df['G2'] df['Weight'] = df[weighted] / df.groupby([TimeName, 'Group'])[weighted].transform('sum') #按双分组分组后用市值作为每组权重 ret_name = 'F1_Ret' vwret = df.groupby([TimeName, 'Group']).apply(cpt_vw_ret, ret_name, 'Weight').to_frame().reset_index().rename(columns={0: 'Ret'}) vwret = vwret.set_index(TimeName) ewret = df.groupby([TimeName, 'Group'])[ret_name].mean().to_frame().reset_index().rename(columns={ret_name: 'Ret'}) ewret = ewret.set_index(TimeName) return vwret, ewret #3个月的市值累积收益率依赖双分组 df_temp3 = df[['Trdmnt', 'Stkcd', 'Msmvosd', 'CumPastRet3', 'F1_Ret']].dropna() vwret3, ewret3 = dependent_double_sort(df_temp3, 'Msmvosd','CumPastRet3', 'Trdmnt', 5, 5,'Msmvosd') # 3个月的双分组收益匹配FF3因子 FF3 = pd.read_csv('fivefactor_monthly.csv') FF3.index = [str(x)[:4] + '-' + str(x)[4:7] for x in FF3.trdmn] vwret3 = vwret3.reset_index().pivot(index='Trdmnt', columns='Group', values='Ret') vwret3 = vwret3.shift(1).dropna() vwret = pd.merge(vwret3, FF3[['mkt_rf', 'smb', 'hml']], left_index=True, right_index=True) #以G01G01为例计算回归 Y = vwret['G01G01'] X = vwret[['mkt_rf', 'smb', 'hml']] X = X.assign(const=1) results = sm.OLS(Y, X).fit(cov_type='HAC', cov_kwds={'maxlags': 2}, use_correction=True, use_t=True) print(results.summary()) # Fama-MacBeth 回归 # 对每一个时间t做OLS回归 def getOLS(group, x1, x2, x3, x4, y): x1 = group[x1] x2 = group[x2] x3 = group[x3] x4 = group[x4] x = np.column_stack((x1, x2, x3, x4)) X = sm.add_constant(x) y = group[y] res = sm.OLS(y, X).fit() return res.params # 将未来一个月的超额收益率,交易量（对数）,市值,过去 3 个月的累积收益率,收益率提取 df1 = pd.read_csv('TRD_Mnth1.csv') # print(df1) df2=df1[['Stkcd','Trdmnt','Mnshrtrd']] # print(M) df2['Stkcd'] = [str(x).zfill(6) for x in df2.Stkcd] df2['Trdmnt']=pd.to_datetime(df2.Trdmnt) df = pd.merge(df, df2, on = ['Stkcd', 'Trdmnt'], how='left') # print(df) df3=df[['Stkcd','Trdmnt','Mnshrtrd','Msmvosd','CumPastRet3','F1_Ret','Mretnd']] df3['Mnshrtrd']=df3['Mnshrtrd'].apply(np.log) #解释变量为交易量（对数） # print(df3) df3_pivot = df3.pivot(index='Trdmnt', columns='Stkcd', values='Mretnd') df3_pivot = df3_pivot.sort_index() df3_pivot = df3_pivot.rolling(window=12, min_periods=10).std() #定义波动率为过去12个月的收益率的标准差，要求至少有10个观测 df3_pivot = df3_pivot.unstack().reset_index().rename(columns = {0: 'Std'}) # print(df3_pivot) df3 = pd.merge(df3, df3_pivot, on = ['Stkcd', 'Trdmnt'], how='left') df3=df3.dropna() res = df3.groupby(['Trdmnt']).apply(getOLS,['Mnshrtrd'],['CumPastRet3'],['Std'],['Msmvosd'] ,'F1_Ret') print(res) def NWttest_1var(Y, L): ''' Newey and West T检验 Y:ser