industry_return.py 文件源码

def get_ind_return(data):
    '''
    ??xlsx????????????????????????????????
    :param [DataFrame] data: ?xlsx????????-????
    :return: [DataFrame] ind_ret: ??*?? ???????????
    '''
    # ??stk_ind_pair.xlsx???????????????
    stk_ind = pd.read_excel('E:\\QuantProject2\\temp_data\\stk_ind_pair.xlsx')
    # ?stk_ind?????????????????
    stk_ind.Stkcd = stk_ind.Stkcd.apply(lambda x: x[:6])
    # ?stk_ind?data??merge??????????data
    data = pd.merge(data, stk_ind, on='Stkcd')
    # ?????????
    groups = data.groupby(['Trdmnt', 'ind'])
    # ???????????????
    total_Ms = groups['Msmvttl'].sum()
    # ?????????????????????
    total_Mr=groups['total_Mr'].sum()
    # ?????????????????
    ind_ret=total_Mr/total_Ms
    # ?ind_ret???level????
    ind_ret=ind_ret.unstack()
    #?ind_ret???
    ind_ret=pd.DataFrame(scale(ind_ret),columns=ind_ret.columns)
    return ind_ret