def test_weighted_prox_functions(data, thresholder):
x, x_dot = data
if x.ndim == 1:
x = x.reshape(-1, 1)
thresholds = np.ones((1, 1))
else:
thresholds = np.ones((x_dot.shape[1], x.shape[1]))
model = ConstrainedSR3(thresholder=thresholder, thresholds=thresholds)
model.fit(x, x_dot)
check_is_fitted(model)
def test_target_format_constraints(data_linear_combination, target_value):
x, x_dot = data_linear_combination
constraint_rhs = target_value * np.ones(2)
constraint_lhs = np.zeros((2, x.shape[1] * x_dot.shape[1]))
# Should force corresponding entries of coef_ to be target_value
constraint_lhs[0, 1] = 1
constraint_lhs[1, 4] = 1
model = ConstrainedSR3(constraint_lhs=constraint_lhs, constraint_rhs=constraint_rhs)
model.fit(x, x_dot)
np.testing.assert_allclose(model.coef_[:, 1], target_value)
def test_linear_constraints(data_lorenz):
x, t = data_lorenz
library = PolynomialLibrary().fit(x)
constraint_rhs = np.ones(2)
constraint_lhs = np.zeros((2, x.shape[1] * library.n_output_features_))
target_1, target_2 = 1, 3
constraint_lhs[0, 3] = target_1
constraint_lhs[1, library.n_output_features_] = target_2
optimizer = ConstrainedSR3(constraint_lhs=constraint_lhs,
constraint_rhs=constraint_rhs)
model = SINDy(feature_library=library, optimizer=optimizer).fit(x, t)
coeffs = model.coefficients()
np.testing.assert_allclose(np.array([coeffs[0, 3], coeffs[1, 0]]),
np.array([1 / target_1, 1 / target_2]))
def test_row_format_constraints(data_linear_combination, target_value):
# Solution is x_dot = x.dot(np.array([[1, 1, 0], [0, 1, 1]]))
x, x_dot = data_linear_combination
constraint_rhs = target_value * np.ones(2)
constraint_lhs = np.zeros((2, x.shape[1] * x_dot.shape[1]))
# Should force corresponding entries of coef_ to be target_value
constraint_lhs[0, 0] = 1
constraint_lhs[1, 3] = 1
model = ConstrainedSR3(
constraint_lhs=constraint_lhs,
constraint_rhs=constraint_rhs,
constraint_order="feature",
)
model.fit(x, x_dot)
np.testing.assert_allclose(
np.array([model.coef_[0, 0], model.coef_[1, 1]]), target_value
)
def test_constrained_sr3_prox_functions(data_derivative_1d, thresholder):
x, x_dot = data_derivative_1d
x = x.reshape(-1, 1)
model = ConstrainedSR3(thresholder=thresholder)
model.fit(x, x_dot)
check_is_fitted(model)
)
def test_supports_multiple_targets(cls, support):
assert supports_multiple_targets(cls()) == support
@pytest.fixture(params=["data_derivative_1d", "data_derivative_2d"])
def data(request):
return request.getfixturevalue(request.param)
@pytest.mark.parametrize(
"optimizer",
[
STLSQ(),
SR3(),
ConstrainedSR3(),
TrappingSR3(),
Lasso(fit_intercept=False),
ElasticNet(fit_intercept=False),
DummyLinearModel(),
],
)
def test_fit(data, optimizer):
x, x_dot = data
if len(x.shape) == 1:
x = x.reshape(-1, 1)
opt = SINDyOptimizer(optimizer, unbias=False)
opt.fit(x, x_dot)
check_is_fitted(opt)
assert opt.complexity >= 0
np.testing.assert_almost_equal(model.score(x, t=dt),
model_t_default.score(x))
np.testing.assert_almost_equal(model.differentiate(x, t=dt),
model_t_default.differentiate(x))
@pytest.mark.parametrize(
"data",
[pytest.lazy_fixture("data_1d"),
pytest.lazy_fixture("data_lorenz")])
@pytest.mark.parametrize(
"optimizer",
[
STLSQ(),
SR3(),
ConstrainedSR3(),
Lasso(fit_intercept=False),
ElasticNet(fit_intercept=False),
],
)
def test_predict(data, optimizer):
x, t = data
model = SINDy(optimizer=optimizer)
model.fit(x, t)
x_dot = model.predict(x)
assert x.shape == x_dot.shape
@pytest.mark.parametrize(
"data",
)
def test_supports_multiple_targets(cls, support):
assert supports_multiple_targets(cls()) == support
@pytest.fixture(params=["data_derivative_1d", "data_derivative_2d"])
def data(request):
return request.getfixturevalue(request.param)
@pytest.mark.parametrize(
"optimizer",
[
STLSQ(),
SR3(),
ConstrainedSR3(),
Lasso(fit_intercept=False),
ElasticNet(fit_intercept=False),
DummyLinearModel(),
],
)
def test_fit(data, optimizer):
x, x_dot = data
if len(x.shape) == 1:
x = x.reshape(-1, 1)
opt = SINDyOptimizer(optimizer, unbias=False)
opt.fit(x, x_dot)
check_is_fitted(opt)
assert opt.complexity >= 0
if len(x_dot.shape) > 1: