def _optimize_periodmomentum_weight(cls, calc_date):
"""
优化计算日内各时段动量因子载荷的权重
Parameters:
--------
:param calc_date: datetime-like, str
计算日期
:return: pd.Series
--------
日内各时段动量因子载荷的优化权重向量
0. date, 日期, datetimelike
1. w0, 隔夜时段动量因子权重
2. w1, 第1小时动量因子权重
3. w2, 第2小时动量因子权重
4. w3, 第3小时动量因子权重
5. w4, 第4小时动量因子权重
"""
calc_date = Utils.to_date(calc_date)
# 读取过去60个月日内各时段动量因子IC时间序列值
ic_filepath = os.path.join(SETTINGS.FACTOR_DB_PATH, alphafactor_ct.INTRADAYMOMENTUM_CT['factor_ic_file'])
df_ic = pd.read_csv(ic_filepath, header=0, parse_dates=[0])
df_ic = df_ic[df_ic['date'] <= calc_date].iloc[-60:]
# 计算IC的均值和协方差矩阵
df_ic.drop(columns='date', inplace=True)
ic_mean = np.mat(df_ic.mean(axis=0)).reshape((df_ic.shape[1], 1))
ic_cov = np.mat(df_ic.cov())
# 计算日内时段因子的最优权重
optimal_weights = ic_cov.I * ic_mean
optimal_weights /= optimal_weights.sum()
optimal_weights = np.array(optimal_weights).flatten().tolist()
optimal_weights.insert(0, calc_date)
optimal_weights = pd.Series(optimal_weights, index=['date', 'w0', 'w1', 'w2', 'w3', 'w4'])
# 保存最优权重
weight_filepath = os.path.join(SETTINGS.FACTOR_DB_PATH, alphafactor_ct.INTRADAYMOMENTUM_CT['optimal_weight_file'])
Utils.save_timeseries_data(optimal_weights, weight_filepath, save_type='a', columns=['date', 'w0', 'w1', 'w2', 'w3', 'w4'])
def _calc_periodmomentum_ic(cls, calc_date, date_interval_type='month'):
"""
计算日内各时段动量因子的Rank IC值向量
Parameters:
--------
:param calc_date: datetime-like, str
计算日期, e.g: YYYY-MM-DD, YYYYMMDD
:param date_interval_type: str
个股收益率计算的时间长度, 'month'=月度收益, 'day'=日收益
:return: pd.Series
--------
IC值向量
0. date, 日期
1. IC0, 隔夜时段动量因子IC
2. IC1, 第1小时动量因子IC
3. IC2, 第2小时动量因子IC
4. IC3, 第3小时动量因子IC
5. IC4, 第4小时动量因子IC
"""
# 读取日内各时段动量因子载荷数据
df_period_mom = cls._get_factor_loading(cls._db_file, Utils.datetimelike_to_str(calc_date, dash=False),
factor_name='periodmomentum', factor_type='raw', drop_na=True)
if df_period_mom.empty:
return None
if date_interval_type == 'month':
# 读取个股下个月的月度收益率数据
ret_start, ret_end = Utils.next_month(calc_date)
elif date_interval_type == 'day':
ret_start = ret_end = Utils.get_trading_days(start=calc_date, ndays=2)[1]
df_period_mom['ret'] = np.nan
for idx, factorloading_data in df_period_mom.iterrows():
fret = Utils.calc_interval_ret(factorloading_data['id'], start=ret_start, end=ret_end)
if fret is not None:
df_period_mom.loc[idx, 'ret'] = fret
df_period_mom.dropna(inplace=True)
# 计算Rank IC值
df_period_mom.drop(columns=['date', 'id', 'm_normal'], inplace=True)
df_spearman_corr = df_period_mom.corr(method='spearman')
rank_IC = df_spearman_corr.loc['ret', ['m0', 'm1', 'm2', 'm3', 'm4']]
rank_IC['date'] = calc_date
# 保存Rank IC值
ic_filepath = os.path.join(SETTINGS.FACTOR_DB_PATH, alphafactor_ct.INTRADAYMOMENTUM_CT['factor_ic_file'])
Utils.save_timeseries_data(rank_IC, ic_filepath, save_type='a', columns=['date', 'm0', 'm1', 'm2', 'm3', 'm4'])
return rank_IC
def _save_mvpfp_performance(performance_data, factor_name, performance_type,
save_type):
"""
保存最小波动纯因子组合的绩效数据
Parameters:
--------
:param performance_data: pd.DataFrame
绩效数据(包含日度时间序列数据, 月度时间序列数据, summary data)
:param factor_name: str
alpha因子名称, e.g: SmartMoney
:param performance_type: str
绩效数据类型, 'daily'=日度时间序列数据, 'monthly'=月度时间序列数据, 'summary'=汇总数据
:param save_type: str
保存类型, 'a'=新增, 'w'=覆盖
:return:
"""
if not isinstance(performance_data, pd.DataFrame):
raise TypeError("绩效数据必须为pd.DataFrame类型.")
if performance_data.empty:
logging.info('绩效数据为空, 未保存.')
return
if performance_type == 'daily':
performance_filepath = os.path.join(
SETTINGS.FACTOR_DB_PATH,
eval('alphafactor_ct.' + factor_name.upper() + '_CT')['db_file'],
'performance/performance_daily.csv')
elif performance_type == 'monthly':
performance_filepath = os.path.join(
SETTINGS.FACTOR_DB_PATH,
eval('alphafactor_ct.' + factor_name.upper() + '_CT')['db_file'],
'performance/performance_monthly.csv')
elif performance_type == 'summary':
if not isinstance(performance_data, pd.Series):
raise TypeError("‘summary’类型的绩效数据类型应该为pd.Series.")
performance_filepath = os.path.join(
SETTINGS.FACTOR_DB_PATH,
eval('alphafactor_ct.' + factor_name.upper() + '_CT')['db_file'],
'performance/performance_{}.csv'.format(performance_data['type']))
else:
raise ValueError(
"绩效数据类型有误, 应为'daily'=日度绩效时间序列数据, 'monthly'=月度绩效时间序列数据, 'summary'=绩效汇总数据."
)
if save_type == 'a':
if performance_type == 'daily':
if os.path.isfile(performance_filepath):
df_performance_data = pd.read_csv(performance_filepath,
parse_dates=[0],
header=0)
df_performance_data = df_performance_data[
df_performance_data['date'] <= performance_data.loc[
0, 'date']]
if not df_performance_data.empty:
performance_data['nav'] *= df_performance_data.loc[0,
'nav']
performance_data['accu_ret'] = performance_data['nav'] - 1
Utils.save_timeseries_data(performance_data,
performance_filepath, 'a')
elif performance_type in ['monthly', 'summary']:
Utils.save_timeseries_data(performance_data, performance_filepath,
'a')
else:
raise ValueError(
"绩效数据类型有误, 应为'daily'=日度绩效时间序列数据, 'monthly'=月度绩效时间序列数据, 'summary'=绩效汇总数据."
)
elif save_type == 'w':
Utils.save_timeseries_data(performance_data, performance_filepath, 'w')
else:
raise ValueError("保存类型有误, 应为'a'=新增, 'w'=覆盖.")
