def test_const_linear_model(self):
features = ['c', 'b', 'a']
weights = dict(c=3., b=2., a=1.)
model = ConstLinearModel(features=features,
weights=weights)
calculated_y = model.predict(self.predict_x)
expected_y = self.predict_x[features] @ np.array([weights[f] for f in features])
np.testing.assert_array_almost_equal(calculated_y, expected_y)
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_const_linear_model(self):
weights = np.array([1., 2., 3.])
model = ConstLinearModel(features=['a', 'b', 'c'],
weights=weights)
calculated_y = model.predict(self.predict_x)
expected_y = self.predict_x @ weights
np.testing.assert_array_almost_equal(calculated_y, expected_y)
def test_const_linear_model_persistence(self):
weights = np.array([1., 2., 3.])
model = ConstLinearModel(features=['a', 'b', 'c'],
weights=weights)
desc = model.save()
new_model = ConstLinearModel.load(desc)
self.assertEqual(model.features, new_model.features)
np.testing.assert_array_almost_equal(model.weights, new_model.weights)
def test_const_linear_model_score(self):
model = LinearRegression(['a', 'b', 'c'], fit_intercept=False)
model.fit(self.train_x, self.train_y)
expected_score = model.score(self.train_x, self.train_y)
const_model = ConstLinearModel(features=['a', 'b', 'c'],
weights=dict(zip(model.features, model.weights)))
calculated_score = const_model.score(self.train_x, self.train_y)
self.assertAlmostEqual(expected_score, calculated_score)
def load_model(model_desc: dict) -> ModelBase:
model_name = model_desc['model_name']
model_name_parts = set(model_name.split('.'))
if 'ConstLinearModel' in model_name_parts:
return ConstLinearModel.load(model_desc)
elif 'LinearRegression' in model_name_parts:
return LinearRegression.load(model_desc)
elif 'LassoRegression' in model_name_parts:
return LassoRegression.load(model_desc)
elif 'LogisticRegression' in model_name_parts:
return LogisticRegression.load(model_desc)
elif 'RandomForestRegressor' in model_name_parts:
return RandomForestRegressor.load(model_desc)
elif 'RandomForestClassifier' in model_name_parts:
return RandomForestClassifier.load(model_desc)
elif 'XGBRegressor' in model_name_parts:
return XGBRegressor.load(model_desc)
elif 'XGBClassifier' in model_name_parts:
return XGBClassifier.load(model_desc)
elif 'XGBTrainer' in model_name_parts:
return XGBTrainer.load(model_desc)
elif 'NvSVR' in model_name_parts:
return NvSVRModel.load(model_desc)
else:
raise ValueError('{0} is not currently supported in model loader.'.format(model_name))
def load_model(model_desc: dict) -> ModelBase:
model_name = model_desc['model_name']
model_name_parts = set(model_name.split('.'))
if 'ConstLinearModel' in model_name_parts:
return ConstLinearModel.load(model_desc)
elif 'LinearRegression' in model_name_parts:
return LinearRegression.load(model_desc)
else:
raise ValueError(
'{0} is not currently supported in model loader.'.format(
model_name))
def test_simple_model_features(self):
model = ConstLinearModel(features=['c', 'b', 'a'])
self.assertListEqual(['a', 'b', 'c'], model.features)
@classmethod
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)
if __name__ == '__main__':
import numpy as np
from alphamind.data.standardize import standardize
from alphamind.data.winsorize import winsorize_normal
from alphamind.data.engines.sqlengine import industry_styles
from alphamind.model.linearmodel import ConstLinearModel
data_source = "postgres+psycopg2://postgres:we083826@localhost/alpha"
alpha_model = ConstLinearModel(['EPS'], np.array([1.]))
alpha_factors = ['EPS']
freq = '1w'
universe = Universe('zz500', ['zz500'])
batch = 4
neutralized_risk = ['SIZE'] + industry_styles
risk_model = 'short'
pre_process = [winsorize_normal, standardize]
pos_process = [winsorize_normal, standardize]
data_meta = DataMeta(freq,
universe,
batch,
neutralized_risk,
risk_model,
pre_process,