def load_weight_china_index_date(self, date):
"""
利用自由流通市值作为指数权重
"""
date = Date().change_to_str(date)
date_1y = Date().get_normal_date_offset(date, -180)
data = Stock().get_free_market_value_date(date)
ipo_data = Stock().get_ipo_date()
data = pd.concat([data, ipo_data], axis=1)
data = data[data['IPO_DATE'] <= date_1y]
data = data[data['DELIST_DATE'] >= date]
code = "China_Index_Benchmark"
data = data.dropna()
free_mv_sum = data['Free_Market_Value'].sum()
weight = pd.DataFrame(data['Free_Market_Value'].values / free_mv_sum, index=data.index, columns=['WEIGHT'])
weight.index.name = "CODE"
out_sub_path = os.path.join(self.load_out_path_weight, code)
if not os.path.exists(out_sub_path):
os.makedirs(out_sub_path)
out_file = os.path.join(out_sub_path, date + '.csv')
weight.to_csv(out_file)
def cal_factor_exposure(self, beg_date, end_date):
""" 计算因子暴露 """
# params
long_term = 40
short_term = int(long_term * 0.5)
min_term = int(long_term * 0.8)
# read data
trade_amount = Stock().read_factor_h5("TradeAmount").T
trade_amount = trade_amount.dropna(how='all')
# calculate data daily
date_series = Date().get_trade_date_series(beg_date, end_date)
date_series = list(set(trade_amount.index) & set(date_series))
date_series.sort()
res = pd.DataFrame([])
for i in range(0, len(date_series)):
current_date = date_series[i]
data_beg_date = Date().get_trade_date_offset(
current_date, -(long_term - 1))
amount_before = trade_amount.loc[data_beg_date:current_date, :]
amount_before = amount_before.fillna(0.0)
if len(amount_before) >= min_term:
print('Calculating factor %s at date %s' %
(self.raw_factor_name, current_date))
zero_number = amount_before.applymap(
lambda x: 1.0 if x == 0.0 else 0.0).sum()
code_filter_list = (
zero_number[zero_number < short_term]).index
amount_pre = trade_amount.loc[data_beg_date:current_date,
code_filter_list]
amount_pre_cv = -amount_pre.std() / amount_pre.mean()
amount_pre_cv = pd.DataFrame(amount_pre_cv)
amount_pre_cv.columns = [current_date]
else:
print('Calculating factor %s at date %s is null' %
(self.raw_factor_name, current_date))
amount_pre_cv = pd.DataFrame([],
columns=[current_date],
index=trade_amount.columns)
res = pd.concat([res, amount_pre_cv], axis=1)
res = res.T.dropna(how='all').T
self.save_alpha_factor_exposure(res, self.raw_factor_name)
def cal_factor_exposure(self, beg_date, end_date):
""" 计算因子暴露 """
# params
long_term = 120
short_term = int(long_term * 0.5)
# read data
trade_amount = Stock().read_factor_h5("TradeAmount").T / 100000000
trade_amount = trade_amount.dropna(how='all')
# calculate data daily
date_series = Date().get_trade_date_series(beg_date, end_date)
date_series = list(set(trade_amount.index) & set(date_series))
date_series.sort()
res = pd.DataFrame([])
for i in range(0, len(date_series)):
current_date = date_series[i]
data_beg_date = Date().get_trade_date_offset(current_date, -(long_term - 1))
amount_before = trade_amount.loc[data_beg_date:current_date, :]
amount_before = amount_before.fillna(0.0)
if len(amount_before) == long_term:
print('Calculating factor %s at date %s' % (self.raw_factor_name, current_date))
zero_number = amount_before.applymap(lambda x: 1.0 if x == 0.0 else 0.0).sum()
code_filter_list = (zero_number[zero_number < short_term]).index
amount_before = trade_amount.loc[data_beg_date:current_date, code_filter_list]
amount_log = amount_before.applymap(lambda x: np.nan if x == 0 else -np.log(x))
weight = np.array(list(range(1, long_term + 1)))
weight_amount = np.dot(amount_log.T.values, weight)
weight_amount = pd.DataFrame(weight_amount, index=amount_log.columns, columns=[current_date])
else:
print('Calculating factor %s at date %s is null' % (self.raw_factor_name, current_date))
weight_amount = pd.DataFrame([], columns=[current_date], index=trade_amount.columns)
res = pd.concat([res, weight_amount], axis=1)
res = res.T.dropna(how='all').T
self.save_alpha_factor_exposure(res, self.raw_factor_name)
