def __init__(self):
FundHolder.__init__(self)
FundFactor.__init__(self)
FundPool.__init__(self)
FundStatic.__init__(self)
FundExposure.__init__(self)
def cal_fund_holder_risk_alpha_return_quarter(self, fund, end_date):
""" 根据季报持仓风格暴露进行收益拆分 """
beg_date = "20040101"
type_list = ['STYLE', 'COUNTRY', 'INDUSTRY']
fund_exposure = FundHolderExposureQuarter(
).get_fund_holder_exposure_quarter_daily(fund, beg_date, end_date)
barra_riskfactor_return = Barra().get_factor_return(
beg_date, end_date, type_list=type_list)
date_series = Date().get_trade_date_series(beg_date, end_date)
fund_pct = FundFactor().get_fund_factor("Repair_Nav_Pct",
fund_pool=[fund],
date_list=date_series)
fund_pct.columns = ["FundReturn"]
if fund_exposure is None:
return None
fund_riskfactor_return = barra_riskfactor_return.mul(fund_exposure)
fund_return = pd.concat([fund_pct, fund_riskfactor_return], axis=1)
fund_return = fund_return.dropna()
barra_factor_name = list(
Barra().get_factor_name(type_list=["STYLE"])["NAME_EN"].values)
fund_return["StyleReturn"] = fund_return[barra_factor_name].sum(axis=1)
barra_factor_name = list(
Barra().get_factor_name(type_list=["INDUSTRY"])["NAME_EN"].values)
fund_return["IndustryReturn"] = fund_return[barra_factor_name].sum(
axis=1)
barra_factor_name = list(
Barra().get_factor_name(type_list=["COUNTRY"])["NAME_EN"].values)
fund_return["CountryReturn"] = fund_return[barra_factor_name].sum(
axis=1)
barra_factor_name = ["StyleReturn", "IndustryReturn", "CountryReturn"]
fund_return["SumReturn"] = fund_return[barra_factor_name].sum(axis=1)
fund_return["AlphaReturn"] = fund_return["FundReturn"] - fund_return[
"SumReturn"]
data_new = fund_return.dropna()
# 合并新数据
####################################################################
out_path = os.path.join(self.data_path_exposure,
'fund_holding_risk_alpha_return_quarter')
out_file = os.path.join(
out_path, 'Fund_Holder_Risk_Alpha_Return_Quarter_' + fund + "_" +
end_date + '.csv')
print(out_file)
if os.path.exists(out_file):
data_old = pd.read_csv(out_file, index_col=[0], encoding='gbk')
data_old.index = data_old.index.map(str)
params = FactorOperate().pandas_add_row(data_old, data_new)
else:
params = data_new
params.to_csv(out_file)
return data_new
def cal_fund_regression_risk_alpha_return_index(self, fund):
# 参数
####################################################################
exposure_index = FundRegressionExposureIndex(
).get_fund_regression_exposure_index(fund)
if exposure_index is not None:
# 取得数据 指数收益率数据 和 基金涨跌幅数据
print(fund)
####################################################################
for i_index in range(len(self.index_code_list)):
index_code = self.index_code_list[i_index]
index_return = Index().get_index_factor(index_code,
attr=["PCT"])
if i_index == 0:
index_return = Index().get_index_factor(index_code,
attr=["PCT"])
index_return_all = index_return
else:
index_return_all = pd.concat(
[index_return_all, index_return], axis=1)
index_return_all.columns = self.index_code_list
if fund[len(fund) - 2:] == 'OF':
fund_return = FundFactor().get_fund_factor(
"Repair_Nav_Pct", None, [fund]) / 100.0
fund_return.columns = ["FundReturn"]
else:
fund_return = Index().get_index_factor(fund, attr=["PCT"])
fund_return.columns = ["FundReturn"]
exposure_index = exposure_index.dropna(how="all")
index_exposure_return = index_return_all.mul(exposure_index)
index_exposure_return = index_exposure_return.dropna(how="all")
data = pd.concat([fund_return, index_exposure_return], axis=1)
data = data.dropna(how="all")
data = data.loc[index_exposure_return.index, :]
data = data.dropna(subset=["FundReturn"])
data["SumReturn"] = data[self.index_code_list].sum(axis=1,
skipna=True)
data["AlphaReturn"] = data["FundReturn"] - data["SumReturn"]
data["CumFundReturn"] = (data["FundReturn"] + 1.0).cumprod() - 1.0
data["CumAlphaReturn"] = (data["AlphaReturn"] +
1.0).cumprod() - 1.0
data["CumSumReturn"] = (data["SumReturn"] + 1.0).cumprod() - 1.0
# 合并新数据
file = '%s_%s_%s.csv' % (self.file_prefix, self.folder_name, fund)
out_file = os.path.join(self.index_return_path, file)
data.to_csv(out_file)
def __init__(self,
regress_length=25,
regress_length_min=20,
stock_ratio_up=0.95,
stock_ratio_low=0.60,
turnover_daily=0.035,
index_code_list=None):
Data.__init__(self)
self.data_path = os.path.join(self.primary_data_path,
r'fund_data\fund_stock_style_ratio')
index_close = Index().get_index_cross_factor(factor_name='CLOSE')
index_pct = index_close.pct_change() * 100
fund_return = FundFactor().get_fund_factor("Repair_Nav_Pct")
self.data_return = pd.concat([index_pct, fund_return], axis=1)
self.regress_length = regress_length
self.regress_length_min = regress_length_min
self.stock_ratio_up = stock_ratio_up
self.stock_ratio_low = stock_ratio_low
self.turnover_daily = turnover_daily
if index_code_list is None:
# 需要有债券指数 来测量股债仓位
self.index_code_list = [
"885062.WI", "801853.SI", "000300.SH", "000905.SH",
"000852.SH", "399006.SZ"
]
self.index_name_list = [
'短期纯债基金', '绩优股指数', '沪深300', '中证500', '中证1000', '创业板指'
]
else:
self.index_code_list = index_code_list
def get_data(self):
""" 季度公募主动股票基金股票权重 作为指数股票权重参考标准 """
self.stock_ratio = FundFactor().get_fund_factor('Stock_Ratio').T
self.industry_citic1 = Stock().read_factor_h5(
"industry_citic1",
Stock().get_h5_path("mfc_primary"))
self.pct = Stock().read_factor_h5("Pct_chg") # 调整股票的调整日的权重
def get_data(self):
""" 季度公募主动股票基金股票权重 作为指数股票权重参考标准 """
self.stock_ratio = FundFactor().get_fund_factor('Stock_Ratio').T
self.free_mv = Stock().read_factor_h5(
"Mkt_freeshares",
Stock().get_h5_path("mfc_primary")) / 100000000.0
self.pct = Stock().read_factor_h5("Pct_chg") # 调整股票的调整日的权重
def example(self):
""" 举例 """
setup_date = '20150101'
beg_date = "20161231"
new_fund_date = beg_date
end_date = '20171130'
fund_code = '229002.OF'
excess = False
rank_pool = "股票型基金"
date_array = np.array([["2017年以来", '20170101', end_date, "20170101"],
["2016年", '20160101', '20161231', "20160101"],
["2015年", setup_date, '20151231', setup_date],
["成立以来", setup_date, end_date, setup_date]])
fund_pct = FundFactor().get_fund_factor("Repair_Nav_Pct")
bench_pct = FundFactor().get_fund_factor("Fund_Bench_Pct") * 100
print(
self.rank_fund_array2(fund_pct, bench_pct, fund_code, date_array,
rank_pool, excess))
def update_data(self, beg_date=None, end_date=None):
""" 更新计算基金暴露 所需要的数据 """
if end_date is None:
end_date = datetime.today().strftime("%Y%m%d")
if beg_date is None:
beg_date = Date().get_trade_date_offset(end_date, -60)
FundFactor().load_fund_factor("Repair_Nav_Pct", beg_date, end_date)
for index_code in self.index_code_list:
Index().load_index_factor(index_code, beg_date, end_date)
def rank_excess_fund(self, fund_pool_name, ge_index_code, my_index_code,
my_fund_code, beg_date, end_date):
"""
计算某只基金在基金池的超额收益排名
这只基金指定基准 其他默认为windqa
"""
fund_pool = FundPool().get_fund_pool_all(date="20181231",
name=fund_pool_name)
fund_pool = fund_pool[fund_pool['setupdate'] < beg_date]
fund_pool = list(fund_pool['wind_code'].values)
fund_pool.append(my_fund_code)
result = pd.DataFrame([], index=fund_pool)
data = FundFactor().get_fund_factor("Repair_Nav")
for i in range(0, len(fund_pool)):
fund_code = fund_pool[i]
if fund_code == my_fund_code:
index_code = my_index_code
else:
index_code = ge_index_code
try:
print(fund_code, index_code, beg_date, end_date)
fund = pd.DataFrame(data[fund_code])
index = Index().get_index_factor(index_code, attr=["CLOSE"])
fs = FinancialSeries(pd.DataFrame(fund), pd.DataFrame(index))
fund_return = fs.get_interval_return(beg_date, end_date)
bench_return = fs.get_interval_return_benchmark(
beg_date, end_date)
result.loc[fund_code, "基准收益"] = bench_return
result.loc[fund_code, "基金收益"] = fund_return
result.loc[fund_code, "超额收益"] = -bench_return + fund_return
except Exception as e:
print(e)
result = result.dropna()
result = result[~result.index.duplicated()]
result = result.sort_values(by=['超额收益'], ascending=False)
result['收益名次'] = range(1, len(result) + 1)
result['收益排名'] = result['收益名次'].map(
lambda x: str(x) + '/' + str(len(result)))
result['收益排名百分比'] = result['收益名次'].map(lambda x: x / len(result))
excess_return = result.loc[my_fund_code, "超额收益"]
pct = result.loc[my_fund_code, "收益排名百分比"]
rank_str = result.loc[my_fund_code, "收益排名"]
result.to_csv(
os.path.join(
self.data_path,
"超额收益_%s_%s_%s.csv" % (my_fund_code, beg_date, end_date)))
return excess_return, pct, rank_str
def split_flexible_fund_pool(self, date):
""" 分离灵活配置基金池 """
data = self.get_fund_pool_all(date=date, name="灵活配置型基金")
data.index = data['wind_code']
report_date = Date().get_last_fund_quarter_date(date)
ratio = FundFactor().get_fund_factor("Stock_Ratio", [report_date],
fund_pool=list(data['wind_code']))
ratio = ratio.T
ratio.columns = ['stock_ratio']
data = pd.concat([data, ratio], axis=1)
data['stock_ratio'] = ratio
data_60 = data[data['stock_ratio'] > 60]
add_fund = ['003501.OF', '004000.OF']
try:
d = data.loc[add_fund, :]
data_60 = data_60.append(d)
data_60 = data_60.reset_index(drop=True)
except Exception as e:
print(e)
print(add_fund, "is not in Fund Pool")
name = "灵活配置型基金_60"
print(" Split Flexible Fund Pool %s At %s" % (name, date))
file = name + '_' + date + '.csv'
out_file = os.path.join(self.data_path_pool, name, file)
data_60 = data_60.reset_index(drop=True)
data_60.to_csv(out_file)
data_30 = data[data['stock_ratio'] < 32]
name = "灵活配置型基金_30"
file = name + '_' + date + '.csv'
out_file = os.path.join(self.data_path_pool, name, file)
data_30 = data_30.reset_index(drop=True)
data_30.to_csv(out_file)
def get_etf_fund_data(self, beg_date, end_date):
""" 得到etf数据"""
print("ETF Data %s %s" % (beg_date, end_date))
exchange_share = FundFactor().get_fund_factor("Exchange_Share")
exchange_share = exchange_share.fillna(method='pad', limit=3)
unit_nav = FundFactor().get_fund_factor("Unit_Nav")
unit_nav = unit_nav.fillna(method='pad', limit=1)
exchange_share_date = pd.DataFrame(exchange_share.T[end_date])
exchange_share_date.columns = ['Share']
exchange_share_date_last = pd.DataFrame(exchange_share.T[beg_date])
exchange_share_date_last.columns = ['ShareLast']
unit_nav_date = pd.DataFrame(unit_nav.T[end_date])
unit_nav_date.columns = ['UnitNav']
fund_pool = FundPool().get_fund_pool_all(name="ETF基金", date="20181231")
fund_pool = fund_pool[[
'sec_name', 'wind_code', 'setupdate', 'bench_code', 'bench_name'
]]
fund_pool.index = fund_pool.wind_code
concat_data = pd.concat([
fund_pool, unit_nav_date, exchange_share_date,
exchange_share_date_last
],
axis=1)
concat_data = concat_data.dropna()
concat_data['MvEnd'] = concat_data['Share'] * concat_data['UnitNav']
concat_data['Inflow'] = (
concat_data['Share'] -
concat_data['ShareLast']) * concat_data['UnitNav']
concat_data['MvEnd'] /= 100000000.0
concat_data['Inflow'] /= 100000000.0
return concat_data
def cal_fund_regression_exposure_index(self, fund, beg_date, end_date, period="D"):
"""
计算一只基金每日对不同指数的暴露
"""
# 参数
####################################################################
one_index_up_limit = 1.0
one_index_low_limit = 0.0
sum_index = 1.0
beg_date = Date().change_to_str(beg_date)
end_date = Date().change_to_str(end_date)
# 取得 指数收益率数据
####################################################################
for i_index in range(len(self.index_code_list)):
index_code = self.index_code_list[i_index]
index_return = Index().get_index_factor(index_code, Nattr=["PCT"])
if i_index == 0:
index_return = Index().get_index_factor(index_code, attr=["PCT"])
index_return_all = index_return
else:
index_return_all = pd.concat([index_return_all, index_return], axis=1)
index_return_all.columns = self.index_code_list
# 取得 基金涨跌幅数据
####################################################################
if fund[len(fund)-2:] == 'OF':
fund_return = FundFactor().get_fund_factor("Repair_Nav_Pct", None, [fund]) / 100.0
else:
fund_return = Index().get_index_factor(fund, attr=["PCT"])
fund_return.columns = [fund]
# 合并数据
####################################################################
data = pd.concat([fund_return, index_return_all], axis=1)
data = data.dropna(subset=[fund])
# 回归日期
####################################################################
date_series = Date().get_trade_date_series(beg_date, end_date, period=period)
date_series = list(set(date_series) & set(data.index))
date_series.sort()
# 循环优化计算每天的暴露
####################################################################
for i_date in range(0, len(date_series)):
# 约束回归所需要的数据
#############################################################################################
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(subset=[fund])
data_periods = data_periods.T.dropna(how='all').T
data_periods = data_periods.T.fillna(data_periods.mean(axis=1)).T
data_periods = data_periods.dropna()
# 有约束的回归 可以转换为二次规划
#############################################################################################
if len(data_periods) > self.regression_period_min and (len(data_periods.columns) > 1):
# 平方和最小
#############################################################################################
y = data_periods.ix[:, 0].values
x = data_periods.ix[:, 1:].values
P = 2 * np.dot(x.T, x)
Q = -2 * np.dot(x.T, y)
# 单个指数上下限为 0
#############################################################################################
G_up = np.diag(np.ones(x.shape[1]))
G_low = - np.diag(np.ones(x.shape[1]))
G = np.row_stack((G_up, G_low))
h_up = np.row_stack(np.ones((x.shape[1], 1))) * one_index_up_limit
h_low = - np.row_stack(np.ones((x.shape[1], 1))) * one_index_low_limit
h = np.row_stack((h_up, h_low))
#############################################################################################
A = np.column_stack(np.ones((x.shape[1], 1)))
b = np.array([sum_index])
# 开始规划求解
############################################################################################
try:
P = matrix(P)
Q = matrix(Q)
G = matrix(G)
h = matrix(h)
A = matrix(A)
b = matrix(b)
result = sol.qp(P, Q, G, h, A, b)
params_add = pd.DataFrame(np.array(result['x'][0:]),
columns=[period_end_date], index=data_periods.columns[1:]).T
print("########## Fund Regression Index Exposure GF %s %s ##########" % (fund, period_end_date))
except Exception as e:
params_add = pd.DataFrame([], columns=[period_end_date], index=data_periods.columns[1:]).T
print("########## Quadratic Programming is InCorrect %s %s ##########" % (fund, period_end_date))
else:
params_add = pd.DataFrame([], columns=[period_end_date], index=data_periods.columns[1:]).T
print("########## Fund Regression Data Len is Too Small %s %s ##########" % (fund, period_end_date))
if i_date == 0:
params_new = params_add
else:
params_new = pd.concat([params_new, params_add], axis=0)
# 合并新数据 并存储数据
####################################################################
out_file = os.path.join(self.data_path, self.file_prefix + 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 = FactorOperate().pandas_add_row(params_old, params_new)
else:
params = params_new
params.to_csv(out_file)
def get_data(self):
""" 收益率数据 """
index_pct = Index().get_index_cross_factor("PCT") * 100
fund_pct = FundFactor().get_fund_factor("Repair_Nav_Pct")
self.asset_pct = pd.concat([fund_pct, index_pct], axis=1)
def cal_fund_holder_exposure_halfyear(self, fund_code, beg_date, end_date):
""" 计算单个基金的半年持仓暴露（注意计算的是非满仓暴露） """
# fund_code, beg_date, end_date = "000001.OF", "20170101", "20190101"
type_list = ['COUNTRY', 'STYLE', 'INDUSTRY']
barra_name = list(Barra().get_factor_name(type_list)['NAME_EN'].values)
out_file = os.path.join(
self.halfyear_exposure_path,
'Fund_Holder_Exposure_HalfYear_%s.csv' % fund_code)
if not os.path.exists(out_file):
beg_date = "20040101"
date_series = Date().get_normal_date_series(beg_date,
end_date,
period='S')
fund_holding = FundHolder().get_fund_stock_weight_halfyear(fund_code)
if fund_holding is not None:
date_series = list(set(date_series) & set(fund_holding.columns))
date_series.sort()
print(date_series)
else:
return None
if len(date_series) > 0:
for i_date in range(0, 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)
print("Calculate HalfYear Holder Exposure %s %s" %
(fund_code, report_date))
barra_exposure = Barra().get_factor_exposure_date(
trade_date, type_list)
fund_holding_date = FundHolder(
).get_fund_stock_weight_halfyear(fund_code)
if (barra_exposure is None) or (len(fund_holding_date) == 0):
exposure_add = pd.DataFrame([],
columns=barra_name,
index=[report_date])
else:
fund_holding_date = pd.DataFrame(fund_holding[report_date])
fund_holding_date = fund_holding_date.dropna()
fund_holding_date = fund_holding_date.sort_values(
by=[report_date], ascending=False)
fund_holding_date.columns = ["Weight"]
fund_holding_date /= 100.0
data = pd.concat([fund_holding_date, 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[
'Weight'] * data_weight[factor_name]
exp = data_weight['StockExposure'].sum()
exposure_add.ix[report_date, factor_name] = exp
country_name = Barra().get_factor_name(
["COUNTRY"])["NAME_EN"].values[0]
position = FundFactor().get_fund_factor(
"Stock_Ratio",
date_list=[report_date],
fund_pool=[fund_code])
exposure_add.ix[
report_date,
country_name] = position.values[0][0] / 100
if i_date == 0:
exposure_new = exposure_add
else:
exposure_new = pd.concat([exposure_new, exposure_add],
axis=0)
else:
exposure_new = pd.DataFrame([])
# 合并新数据
####################################################################
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 = FactorOperate().pandas_add_row(exposure_old, exposure_new)
else:
params = exposure_new
if len(params) > 0:
params = params[barra_name]
params.to_csv(out_file)
def get_data(self):
""" 季度公募主动股票基金股票权重 作为指数股票权重参考标准 """
self.stock_ratio = FundFactor().get_fund_factor('Stock_Ratio').T
self.pct = Stock().read_factor_h5("Pct_chg") # 调整股票的调整日的权重
def cal_fund_regression_risk_alpha_return_style(self, fund, beg_date,
end_date):
# 参数
####################################################################
exposure_index = FundRegressionExposureStyle(
).get_fund_regression_exposure_style(fund)
if exposure_index is not None:
# 取得数据 指数收益率数据 和 基金涨跌幅数据
####################################################################
barra_name = list(Barra().get_factor_name(['STYLE'
])['NAME_EN'].values)
barra_name.extend(
list(Barra().get_factor_name(["COUNTRY"])['NAME_EN'].values))
barra_return = Barra().get_factor_return(
None, None, type_list=["INDUSTRY", "COUNTRY", "STYLE"])
barra_return = barra_return[barra_name]
barra_return /= 100.0
if fund[len(fund) - 2:] == 'OF':
fund_return = FundFactor().get_fund_factor(
"Repair_Nav_Pct", None, [fund]) / 100.0
fund_return.columns = ["FundReturn"]
else:
fund_return = Index().get_index_factor(fund, attr=["PCT"])
fund_return.columns = ["FundReturn"]
exposure_index = exposure_index.dropna(how="all")
index_exposure_return = barra_return.mul(exposure_index)
index_exposure_return = index_exposure_return.dropna(how="all")
data = pd.concat([fund_return, index_exposure_return], axis=1)
data = data.dropna(how="all")
data = data.loc[index_exposure_return.index, :]
data = data.dropna(subset=["FundReturn"])
data["SumReturn"] = data[barra_name].sum(axis=1, skipna=True)
data["AlphaReturn"] = data["FundReturn"] - data["SumReturn"]
data = data.loc[beg_date:end_date, :]
data["CumFundReturn"] = (data["FundReturn"] + 1.0).cumprod() - 1.0
data["CumAlphaReturn"] = (data["AlphaReturn"] +
1.0).cumprod() - 1.0
data["CumSumReturn"] = (data["SumReturn"] + 1.0).cumprod() - 1.0
# 合并新数据
####################################################################
out_path = os.path.join(self.data_path_exposure,
'fund_regression_risk_alpha_return_style')
out_file = os.path.join(
out_path, 'Fund_Regression_Risk_Alpha_Style_' + 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 = FactorOperate().pandas_add_row(params_old, data)
else:
params = data
print(params)
params.to_csv(out_file)
def cal_fund_regression_risk_alpha_return_index(self, fund, beg_date,
end_date):
# 参数
####################################################################
exposure_index = FundRegressionExposureIndex(
).get_fund_regression_exposure_index(fund)
if exposure_index is not None:
# 取得数据 指数收益率数据 和 基金涨跌幅数据
####################################################################
for i_index in range(len(self.index_code_list)):
index_code = self.index_code_list[i_index]
index_return = Index().get_index_factor(index_code,
attr=["PCT"])
if i_index == 0:
index_return = Index().get_index_factor(index_code,
attr=["PCT"])
index_return_all = index_return
else:
index_return_all = pd.concat(
[index_return_all, index_return], axis=1)
index_return_all.columns = self.index_code_list
if fund[len(fund) - 2:] == 'OF':
fund_return = FundFactor().get_fund_factor(
"Repair_Nav_Pct", None, [fund]) / 100.0
fund_return.columns = ["FundReturn"]
else:
fund_return = Index().get_index_factor(fund, attr=["PCT"])
fund_return.columns = ["FundReturn"]
exposure_index = exposure_index.dropna(how="all")
index_exposure_return = index_return_all.mul(exposure_index)
index_exposure_return = index_exposure_return.dropna(how="all")
data = pd.concat([fund_return, index_exposure_return], axis=1)
data = data.dropna(how="all")
data = data.loc[index_exposure_return.index, :]
data = data.dropna(subset=["FundReturn"])
data["SumReturn"] = data[self.index_code_list].sum(axis=1,
skipna=True)
data["AlphaReturn"] = data["FundReturn"] - data["SumReturn"]
data = data.loc[beg_date:end_date, :]
data["CumFundReturn"] = (data["FundReturn"] + 1.0).cumprod() - 1.0
data["CumAlphaReturn"] = (data["AlphaReturn"] +
1.0).cumprod() - 1.0
data["CumSumReturn"] = (data["SumReturn"] + 1.0).cumprod() - 1.0
# 合并新数据
####################################################################
out_path = self.data_path
out_file = os.path.join(out_path, self.file_prefix + 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 = FactorOperate().pandas_add_row(params_old, data)
else:
params = data
print(params)
params.to_csv(out_file)
def update_data(self):
""" 更新所需要的数据 """
Date().load_trade_date_series("D")
end_date = datetime.today()
beg_date = Date().get_trade_date_offset(end_date, -60)
FundFactor().load_fund_factor_all(beg_date, end_date)
def cal_fund_holder_exposure_quarter(self, fund, beg_date, end_date):
""" 计算单个基金的季度持仓暴露 (前十大重仓暴露) """
type_list = ['STYLE', 'COUNTRY', 'INDUSTRY']
date_series = Date().get_normal_date_series(beg_date,
end_date,
period='Q')
fund_holding = FundHolder().get_fund_stock_weight_quarter(fund)
if fund_holding is not None:
date_series = list(set(date_series) & set(fund_holding.columns))
date_series.sort()
else:
return None
for i_date in range(0, 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)
print(
"########## Calculate Quarter 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_date = pd.DataFrame(fund_holding[report_date])
fund_holding_date = fund_holding_date.dropna()
fund_holding_date = fund_holding_date.sort_values(
by=[report_date], ascending=False)
fund_holding_date.columns = ["Weight"]
data = pd.concat([fund_holding_date, 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
country_name = Barra().get_factor_name(
["COUNTRY"])["NAME_EN"].values[0]
position = FundFactor().get_fund_factor(
"Stock_Ratio",
date_list=[report_date],
fund_pool=[fund])
position = position.values[0][0]
exposure_add.ix[report_date, country_name] = position / 100
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 = os.path.join(self.data_path_exposure,
'fund_holding_exposure_quarter')
out_file = os.path.join(
out_path, 'Fund_Holder_Exposure_Quarter_' + 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 = FactorOperate().pandas_add_row(exposure_old, exposure_new)
else:
params = exposure_new
params.to_csv(out_file)
def cal_fund_regression_exposure_style(self,
fund,
beg_date,
end_date,
period="D"):
# 参数
####################################################################
up_style_exposure = 1.25
up_position_exposure = 0.95
low_position_exposure = 0.75
position_sub = 0.08
beg_date = Date().change_to_str(beg_date)
end_date = Date().change_to_str(end_date)
# 取得数据 因子收益率数据 和 基金涨跌幅数据
####################################################################
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)
if fund[len(fund) - 2:] == 'OF':
fund_return = FundFactor().get_fund_factor("Repair_Nav_Pct", None,
[fund])
else:
fund_return = Index().get_index_factor(fund, attr=["PCT"]) * 100
fund_return.columns = [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)
stock_ratio = FundFactor().get_fund_factor("Stock_Ratio", None,
[fund]) / 100
date_series = list(set(date_series) & set(data.index))
date_series.sort()
# 循环回归计算每天的暴露 计算当天的暴露之时需要 前一天及之前数据
####################################################################
for i_date in range(0, len(date_series)):
# 回归所需要的数据
####################################################################
period_end_date = date_series[i_date]
period_beg_date = Date().get_trade_date_offset(
period_end_date, -self.regression_period)
data_end_date = Date().get_trade_date_offset(period_end_date, -0)
period_date_series = Date().get_trade_date_series(
period_beg_date, data_end_date)
data_periods = data.ix[period_date_series, :]
data_periods = data_periods.dropna()
# 上个季度基金仓位
#####################################################################################
quarter_date = Date().get_last_fund_quarter_date(period_end_date)
stock_ratio_fund = stock_ratio.loc[quarter_date, fund]
print(
"########## Calculate Regression Exposure %s %s %s %s %s %s ##########"
% (fund, period_beg_date, period_end_date, quarter_date,
len(data_periods), stock_ratio_fund))
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_fund - position_sub,
low_position_exposure)
if np.isnan(low_position_exposure):
low_position_exposure = 0.75
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 Exception as e:
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 = os.path.join(self.data_path_exposure,
'fund_regression_exposure_style')
out_file = os.path.join(
out_path, 'Fund_Regression_Exposure_Style_' + 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 = FactorOperate().pandas_add_row(params_old, params_new)
else:
params = params_new
print(params)
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)
def get_data(self):
""" 季度公募主动股票基金股票权重 作为指数股票权重参考标准 """
self.stock_ratio = FundFactor().get_fund_factor('Stock_Ratio').T
