def fetch_model(self,
ref_date=None,
model_type=None,
model_version=None,
is_primary=True,
model_id=None) -> pd.DataFrame:
from alphamind.model.composer import DataMeta
conditions = []
if ref_date:
conditions.append(Models.trade_date == ref_date)
if model_id:
conditions.append(Models.model_id == model_id)
if model_type:
conditions.append(Models.model_type == model_type)
if model_version:
conditions.append(Models.model_version == model_version)
conditions.append(Models.is_primary == is_primary)
query = select([Models]).where(and_(*conditions))
model_df = pd.read_sql(query, self.engine)
for i, data in enumerate(zip(model_df.model_desc, model_df.data_meta)):
model_desc, data_desc = data
model_df.loc[i, 'model'] = load_model(model_desc)
model_df.loc[i, 'data_meta'] = DataMeta.load(data_desc)
del model_df['model_desc']
return model_df
def fetch_model(self,
ref_date=None,
model_type=None,
model_version=None,
is_primary=True,
model_id=None) -> pd.DataFrame:
conditions = []
if ref_date:
conditions.append(Models.trade_date == ref_date)
if model_id:
conditions.append(Models.model_id == model_id)
if model_type:
conditions.append(Models.model_type == model_type)
if model_version:
conditions.append(Models.model_version == model_version)
conditions.append(Models.is_primary == is_primary)
query = select([Models]).where(and_(*conditions))
model_df = pd.read_sql(query, self.engine)
for i, model_desc in enumerate(model_df.model_desc):
model_df.loc[i, 'model'] = load_model(model_desc)
del model_df['model_desc']
return model_df
def test_const_linear_model_persistence(self):
weights = dict(c=3., b=2., a=1.)
model = ConstLinearModel(features=['a', 'b', 'c'], weights=weights)
desc = model.save()
new_model = load_model(desc)
self.assertEqual(model.features, new_model.features)
np.testing.assert_array_almost_equal(model.weights, new_model.weights)
def test_linear_regression_persistence(self):
model = LinearRegression(['a', 'b', 'c'], fit_intercept=False)
model.fit(self.train_x, self.train_y)
desc = model.save()
new_model = load_model(desc)
calculated_y = new_model.predict(self.predict_x)
expected_y = model.predict(self.predict_x)
np.testing.assert_array_almost_equal(calculated_y, expected_y)
np.testing.assert_array_almost_equal(new_model.weights, model.weights)
def test_load_model(self):
model = LinearRegression(['a', 'b', 'c'])
model.fit(self.trained_x, self.trained_y)
model_desc = model.save()
new_model = load_model(model_desc)
np.testing.assert_array_almost_equal(model.predict(self.predict_x),
new_model.predict(self.predict_x))
self.assertEqual(model.features, new_model.features)
self.assertEqual(model.trained_time, new_model.trained_time)
def test_xgb_regress_persistence(self):
model = XGBRegressor(features=self.features)
model.fit(self.x, self.y)
desc = model.save()
new_model = load_model(desc)
self.assertEqual(model.features, new_model.features)
np.testing.assert_array_almost_equal(model.predict(self.sample_x),
new_model.predict(self.sample_x))
np.testing.assert_array_almost_equal(model.importances,
new_model.importances)
def test_xgb_classify_persistence(self):
model = XGBClassifier(features=self.features)
y = np.where(self.y > 0, 1, 0)
model.fit(self.x, y)
desc = model.save()
new_model = load_model(desc)
self.assertEqual(model.features, new_model.features)
np.testing.assert_array_almost_equal(model.predict(self.sample_x),
new_model.predict(self.sample_x))
np.testing.assert_array_almost_equal(model.importances,
new_model.importances)
def test_xgb_trainer_persistence(self):
model = XGBTrainer(features=self.features,
objective='binary:logistic',
booster='gbtree',
tree_method='hist',
n_estimators=200)
y = np.where(self.y > 0, 1, 0)
model.fit(self.x, y)
desc = model.save()
new_model = load_model(desc)
self.assertEqual(model.features, new_model.features)
np.testing.assert_array_almost_equal(model.predict(self.sample_x),
new_model.predict(self.sample_x))
np.testing.assert_array_almost_equal(model.importances,
new_model.importances)
def load(cls, comp_desc):
alpha_model = load_model(comp_desc['alpha_model'])
data_meta = DataMeta.load(comp_desc['data_meta'])
return cls(alpha_model, data_meta)
