def get_risk_data(self, date):
if date in self._riskdata_cache:
return self._riskdata_cache[date]
root = self.riskmodel_root + "/" + date.strftime("%Y%m%d")
if not os.path.exists(root):
return None
factor_exp = load_dataset(root + "/" + self.factor_exp_path,
index_col=[0])
factor_cov = load_dataset(root + "/" + self.factor_cov_path,
index_col=[0])
specific_risk = load_dataset(root + "/" + self.specific_risk_path,
index_col=[0])
if not factor_exp.index.equals(specific_risk.index):
# NOTE: for stocks missing specific_risk, we always assume it have the highest volatility
specific_risk = specific_risk.reindex(
factor_exp.index, fill_value=specific_risk.max())
universe = factor_exp.index.tolist()
blacklist = []
if os.path.exists(root + "/" + self.blacklist_path):
blacklist = load_dataset(root + "/" +
self.blacklist_path).index.tolist()
self._riskdata_cache[
date] = factor_exp.values, factor_cov.values, specific_risk.values, universe, blacklist
return self._riskdata_cache[date]
def _maybe_load_raw_data(self):
if self._data is not None:
return
self._data = pd.concat(
{fields_group: load_dataset(path_or_obj) for fields_group, path_or_obj in self.config.items()},
axis=1,
join=self.join,
)
self._data.sort_index(inplace=True)
def _maybe_load_raw_data(self):
if self._data is not None:
return
if isinstance(self._config, dict):
self._data = pd.concat(
{
fields_group: load_dataset(path_or_obj)
for fields_group, path_or_obj in self._config.items()
},
axis=1,
join=self.join,
)
self._data.sort_index(inplace=True)
elif isinstance(self._config, (str, Path)):
with Path(self._config).open("rb") as f:
self._data = pickle.load(f)
elif isinstance(self._config, pd.DataFrame):
self._data = self._config
