def store_metadata(self, data: Data):
"""
Intended to be used before Data is stored.
:param data:
:return:
"""
# attr ---------------------------------------------------------
# TODO: avoid sending long cols blob when unneeded
cols = zlibext_pack(data.columns)
uuid_cols = uuid(cols)
sql = f'''
insert or ignore into attr values (
NULL,
?,
?
);'''
with warnings.catch_warnings():
warnings.simplefilter("ignore")
self.query(sql, [uuid_cols, cols])
# dataset ---------------------------------------------------------
# TODO: avoid sending long names when unneeded
sql = f'''
insert or ignore into dataset values (
NULL,
?,
?,
?
);'''
with warnings.catch_warnings():
warnings.simplefilter("ignore")
self.query(sql, [data.name_uuid(), data.name, uuid_cols])
# history ------------------------------------------------------
# TODO: avoid sending long hist blob when unneeded
sql = f'''
insert or ignore into hist values (
NULL,
?,
?
)'''
with warnings.catch_warnings():
warnings.simplefilter("ignore")
self.query(sql, [data.history_uuid(), data.history_dump()])
def get_data_by_name_impl(self, name, fields=None, history=None):
"""
To just recover the original dataset you can pass history=None.
Specify fields if you want to reduce traffic, otherwise all available
fields will be fetched.
ps. 1: Obviously, when getting prediction data (i.e., results),
the history which led to the predictions should be provided.
:param name:
:param fields: None=get full Data; case insensitive; e.g. 'X,y,Z'
:param history: nested tuples
:param just_check_exists:
:return:
"""
hist_uuid = uuid(zlibext_pack(history))
sql = f'''
select
X,Y,Z,P,U,V,W,Q,R,S,l,m,T,C,cols,des
from
data
left join dataset on dataset=dsid
left join attr on attr=aid
where
des=? and hist=?'''
self.query(sql, [name, hist_uuid])
row = self.get_one()
if row is None:
return None
# Recover requested matrices/vectors.
dic = {'name': name, 'history': history}
if fields is None:
flst = [k for k, v in row.items() if len(k) == 1 and v is not None]
else:
flst = fields.split(',')
for field in flst:
mid = row[field]
if mid is not None:
self.query(f'select val,w,h from mat where mid=?', [mid])
rone = self.get_one()
dic[field] = unpack_data(rone['val'], rone['w'], rone['h'])
return Data(columns=zlibext_unpack(row['cols']), **dic)
def history_dump(self):
if self._history_dump is None:
self._history_dump = zlibext_pack(self.history)
return self._history_dump