def load_fund_factor(self, factor_name, beg_date, end_date):
beg_date = Date().change_to_str(beg_date)
end_date = Date().change_to_str(end_date)
new_data = FinDb().load_raw_data_filter_period(factor_name, beg_date,
end_date)
fund_info_data = FundStatic().get_fund_info()
val_name = Parameter().get_load_findb_val_name(factor_name)
new_data = pd.merge(new_data, fund_info_data, on="证券内码", how='inner')
new_data = pd.DataFrame(
new_data[val_name].values,
index=[list(new_data['基金代码'].values),
list(new_data['日期'].values)])
new_data = new_data.sort_index()
new_data = new_data[~new_data.index.duplicated()]
new_data = new_data.unstack()
new_data.columns = new_data.columns.droplevel(level=0)
new_data = new_data.T
new_data = new_data.dropna(how='all')
new_data.index = new_data.index.map(str)
out_file = Parameter().get_read_file(factor_name)
if os.path.exists(out_file):
data = pd.read_csv(out_file, encoding='gbk', index_col=[0])
data.index = data.index.map(str)
data = pandas_add_row(data, new_data)
else:
print(" File No Exist ", factor_name)
data = new_data
data = data.dropna(how='all')
data.to_csv(out_file)
def GetAllFundAllDateFactorAlphaFile(in_path, out_path, factor_name_list,
date_series):
# params
####################################################################################
# in_path = 'E:\\3_Data\\4_fund_data\\7_fund_select_stock\\StockAlpha\\'
# out_path = 'E:\\3_Data\\4_fund_data\\7_fund_select_stock\\FundSelectStockAlpha\\'
#
# factor_name_list = ["TotalMarketValue", "BP", "IncomeYOYDaily", "ROETTMDaily", "Industry"]
#
# beg_date = "20170530"
# end_date = "20180630"
# date_series = Date().get_normal_date_series(beg_date, end_date, "S")
if not os.path.exists(out_path):
os.makedirs(out_path)
# read data
####################################################################################
fund_holding_all = Fund().get_fund_holding_all()
# cal alpha
####################################################################################
for i_factor in range(len(factor_name_list)):
factor_name = factor_name_list[i_factor]
stock_alpha = GetStockAlphaAtFactorFile(in_path, factor_name)
for i_date in range(len(date_series)):
report_date = date_series[i_date]
fund_holding_date = fund_holding_all[fund_holding_all['Date'] ==
report_date]
alpha_date = GetAllFundAlphaOnFactorFile(stock_alpha,
fund_holding_date,
factor_name, report_date)
if i_date == 0:
new_data = alpha_date
else:
new_data = pd.concat([new_data, alpha_date], axis=1)
new_data = new_data.T.dropna(how="all")
filename = os.path.join(out_path,
'FundSelectStockAlpha_' + factor_name + '.csv')
if os.path.exists(filename):
old_data = pd.read_csv(filename, index_col=[0], encoding='gbk')
old_data.index = old_data.index.map(str)
result = pandas_add_row(old_data, new_data)
else:
result = new_data
result.to_csv(filename)
def stock_ratio_10(beg_date, end_date):
factor_name = "Stock_Ratio_10"
fund_holder = Fund().get_fund_holding_all()
quarter_date = Date().get_last_fund_quarter_date(end_date)
position_all = Fund().get_fund_factor("Stock_Ratio", date_list=[quarter_date], fund_pool=None).T
position_all.columns = ['Stock_Weight']
position_all = position_all[position_all['Stock_Weight'] > 65]
code_list = list(position_all.index)
date_list = Date().get_normal_date_series(beg_date=beg_date, end_date=end_date, period="Q")
code_list.sort()
date_list.sort()
new_data = pd.DataFrame([], index=code_list, columns=date_list)
for i_date in range(len(date_list)):
for i_fund in range(len(code_list)):
fund_code = code_list[i_fund]
date = date_list[i_date]
holder = fund_holder[fund_holder.FundCode == fund_code]
holder = holder[holder.Date == date]
holder = holder.sort_values(by=['Weight'], ascending=False)
holder = holder.reset_index(drop=True)
if len(holder) >= 10:
holder = holder.ix[0:10, :]
new_data.ix[fund_code, date] = holder.Weight.sum()
print("计算 %s 在 %s 的前10大重仓股票为 %s" % (fund_code, date, holder.Weight.sum()))
out_file = Parameter().get_read_file(factor_name)
if os.path.exists(out_file):
data = pd.read_csv(out_file, encoding='gbk', index_col=[0])
data.index = data.index.map(str)
data = pandas_add_row(data, new_data)
else:
print(" File No Exist ", factor_name)
data = new_data
data.to_csv(out_file)
def cal_index_exposure_period(self, index_code="000300.SH",
beg_date="20031231", end_date=datetime.today().strftime("%Y%m%d"),
period="D"):
date_series_daily = Date().get_trade_date_series(beg_date, end_date, period=period)
for i_date in range(len(date_series_daily)):
date = date_series_daily[i_date]
res = self.cal_index_exposure_date(index_code, date)
if i_date == 0:
new_data = res
else:
new_data = pd.concat([new_data, res], axis=0)
out_file = os.path.join(self.path, "Index_Barra_Exposure_" + index_code + '.csv')
if os.path.exists(out_file):
data = pd.read_csv(out_file, encoding='gbk', index_col=[0])
data.index = data.index.map(str)
data = pandas_add_row(data, new_data)
else:
data = new_data
data.to_csv(out_file)
def GetAllStockAllDateAlpha(path, factor_name_list, date_series):
####################################################################################
# path = 'E:\\3_Data\\4_fund_data\\7_fund_select_stock\\FundSelectStockAlpha\\'
# factor_name_list = ["TotalMarketValue", "BP", "IncomeYOYDaily", "ROETTMDaily"]
# beg_date = "20170530"
# end_date = "20180630"
# date_series = Date().get_normal_date_series(beg_date, end_date, "S")
# params
####################################################################################
code_list = Stock().get_all_stock_code_now()
if not os.path.exists(path):
os.makedirs(path)
# read data
####################################################################################
industry = Stock().get_factor_h5("industry_citic1", None, "primary_mfc")
price = Stock().get_factor_h5("PriceCloseAdjust", None, 'alpha_dfc')
# cal fund alpha all date all fund all factor
####################################################################################
for i_factor in range(len(factor_name_list)):
factor_name = factor_name_list[i_factor]
factor = Stock().get_factor_h5(factor_name, None, "alpha_dfc")
new_data = pd.DataFrame([], index=code_list, columns=date_series)
for i_date in range(len(date_series)):
report_date = date_series[i_date]
for i_stock in range(len(code_list)):
code = code_list[i_stock]
alpha = GetStockAlphaAtFactor(factor, price, code, report_date)
new_data.ix[code, report_date] = alpha
print(code, report_date, factor_name, alpha)
new_data = new_data.T.dropna(how="all")
filename = os.path.join(path, 'StockAlpha_' + factor_name + '.csv')
if os.path.exists(filename):
old_data = pd.read_csv(filename, index_col=[0], encoding='gbk')
old_data.index = old_data.index.map(str)
result = pandas_add_row(old_data, new_data)
else:
result = new_data
result.to_csv(filename)
# cal fund alpha all date all fund on industry
####################################################################################
factor_name = "Industry"
new_data = pd.DataFrame([], index=code_list, columns=date_series)
for i_date in range(len(date_series)):
report_date = date_series[i_date]
for i_stock in range(len(code_list)):
code = code_list[i_stock]
alpha = GetStockAlphaAtIndustry(industry, price, code, report_date)
new_data.ix[code, report_date] = alpha
print(code, report_date, factor_name, alpha)
new_data = new_data.T.dropna(how="all")
filename = os.path.join(path, 'StockAlpha_' + factor_name + '.csv')
if os.path.exists(filename):
old_data = pd.read_csv(filename, index_col=[0], encoding='gbk')
old_data.index = old_data.index.map(str)
result = pandas_add_row(old_data, new_data)
else:
result = new_data
result.to_csv(filename)
# GetAllStockAllDateAlpha(path, factor_name_list, date_series)
code_list = Stock().get_all_stock_code_now()
if not os.path.exists(path):
os.makedirs(path)
# read data
####################################################################################
industry = Stock().get_factor_h5("industry_citic2", None, "primary_mfc")
price = Stock().get_factor_h5("PriceCloseAdjust", None, 'alpha_dfc')
factor_name = "Industry2"
new_data = pd.DataFrame([], index=code_list, columns=date_series)
for i_date in range(len(date_series)):
report_date = date_series[i_date]
for i_stock in range(len(code_list)):
code = code_list[i_stock]
alpha = GetStockAlphaAtIndustry(industry, price, code, report_date)
new_data.ix[code, report_date] = alpha
print(code, report_date, factor_name, alpha)
new_data = new_data.T.dropna(how="all")
filename = os.path.join(path, 'StockAlpha_' + factor_name + '.csv')
if os.path.exists(filename):
old_data = pd.read_csv(filename, index_col=[0], encoding='gbk')
old_data.index = old_data.index.map(str)
result = pandas_add_row(old_data, new_data)
else:
result = new_data
result.to_csv(filename)
def cal_fund_holder_exposure(self, fund, beg_date, end_date):
# 每半年计算一次
type_list = ['STYLE', 'COUNTRY', 'INDUSTRY']
date_series = Date().get_normal_date_series(beg_date,
end_date,
period='S')
for i_date in range(len(date_series)):
date = date_series[i_date]
report_date = Date().get_normal_date_month_end_day(date)
trade_date = Date().get_trade_date_month_end_day(date)
barra_name = list(
Barra().get_factor_name(type_list)['NAME_EN'].values)
barra_exposure = Barra().get_factor_exposure_date(
trade_date, type_list)
fund_holding = FundHolder().get_fund_holding_report_date_fund(
fund, report_date)
print("########## Calculate Holder Exposure %s %s ##########" %
(fund, report_date))
if (barra_exposure is None) or (fund_holding is None):
exposure_add = pd.DataFrame([],
columns=barra_name,
index=[report_date])
else:
fund_holding = fund_holding['Weight']
data = pd.concat([fund_holding, barra_exposure], axis=1)
data = data.dropna()
if (len(data) == 0) or (data is None):
exposure_add = pd.DataFrame([],
columns=barra_name,
index=[report_date])
else:
exposure_add = pd.DataFrame([],
columns=barra_name,
index=[report_date])
for i_factor in range(len(barra_name)):
factor_name = barra_name[i_factor]
data_weight = data[['Weight', factor_name]]
data_weight['StockExposure'] = data['Weight'] * data[
factor_name]
exposure_add.ix[report_date,
factor_name] = data_weight[
'StockExposure'].sum() / 100.0
if i_date == 0:
exposure_new = exposure_add
else:
exposure_new = pd.concat([exposure_new, exposure_add], axis=0)
# 合并新数据
####################################################################
out_path = Parameter().get_read_file(self.holder_exposure_name)
out_file = os.path.join(out_path,
'Fund_Holder_Exposure_' + fund + '.csv')
if os.path.exists(out_file):
exposure_old = pd.read_csv(out_file, index_col=[0], encoding='gbk')
exposure_old.index = exposure_old.index.map(str)
params = pandas_add_row(exposure_old, exposure_new)
else:
params = exposure_new
params.to_csv(out_file)
def cal_fund_regression_exposure(self,
fund,
beg_date,
end_date,
period="M"):
# 参数
####################################################################
up_style_exposure = 1.5
up_position_exposure = 0.95
low_position_exposure = 0.75
position_sub = 0.10
beg_date = Date().change_to_str(beg_date)
end_date = Date().change_to_str(end_date)
# 取得数据
####################################################################
type_list = ['STYLE', 'COUNTRY']
barra_name = list(Barra().get_factor_name(type_list)['NAME_EN'].values)
barra_return = Barra().get_factor_return(None, None, type_list)
date_series = Date().get_trade_date_series(beg_date,
end_date,
period=period)
fund_return = FundFactor().get_fund_factor("Repair_Nav_Pct", None,
[fund])
data = pd.concat([fund_return, barra_return], axis=1)
data = data.dropna()
print(" Fund Code Total Len %s " % len(data))
factor_number = len(barra_name)
# 循环回归计算每天的暴露
####################################################################
for i_date in range(0, len(date_series)):
period_end_date = date_series[i_date]
period_beg_date = Date().get_trade_date_offset(
period_end_date, -self.regression_period)
period_date_series = Date().get_trade_date_series(
period_beg_date, period_end_date)
data_periods = data.ix[period_date_series, :]
data_periods = data_periods.dropna()
quarter_date = Date().get_last_fund_quarter_date(period_end_date)
stock_ratio = (FundFactor().get_fund_factor(
"Stock_Ratio", [quarter_date], [fund]) / 100).values[0][0]
print(
"########## Calculate Regression Exposure %s %s %s %s %s %s ##########"
% (fund, period_beg_date, period_end_date, quarter_date,
len(data_periods), stock_ratio))
if len(data_periods) > self.regression_period_min:
y = data_periods.ix[:, 0].values
x = data_periods.ix[:, 1:].values
x_add = sm.add_constant(x)
low_position_exposure = max(stock_ratio - position_sub,
low_position_exposure)
print(low_position_exposure)
P = 2 * np.dot(x_add.T, x_add)
Q = -2 * np.dot(x_add.T, y)
G_up = np.diag(np.ones(factor_number + 1))
G_low = -np.diag(np.ones(factor_number + 1))
G = np.row_stack((G_up, G_low))
h_up = np.row_stack((np.ones(
(factor_number, 1)) * up_style_exposure,
np.array([up_position_exposure])))
h_low = np.row_stack((np.ones(
(factor_number, 1)) * up_style_exposure,
np.array([-low_position_exposure])))
h = np.row_stack((h_up, h_low))
P = matrix(P)
Q = matrix(Q)
G = matrix(G)
h = matrix(h)
try:
result = sol.qp(P, Q, G, h)
params_add = pd.DataFrame(np.array(result['x'][1:]),
columns=[period_end_date],
index=barra_name).T
print(params_add)
except:
params_add = pd.DataFrame([],
columns=[period_end_date],
index=barra_name).T
print(params_add)
else:
params_add = pd.DataFrame([],
columns=[period_end_date],
index=barra_name).T
print(params_add)
if i_date == 0:
params_new = params_add
else:
params_new = pd.concat([params_new, params_add], axis=0)
# 合并新数据
####################################################################
out_path = Parameter().get_read_file(self.regression_exposure_name)
out_file = os.path.join(out_path,
'Fund_Regression_Exposure_' + fund + '.csv')
if os.path.exists(out_file):
params_old = pd.read_csv(out_file, index_col=[0], encoding='gbk')
params_old.index = params_old.index.map(str)
params = pandas_add_row(params_old, params_new)
else:
params = params_new
print(params)
params.to_csv(out_file)