def test_objective_error_score_nan() -> None:
X, y = make_blobs(n_samples=10)
est = SGDClassifier(max_iter=5, tol=1e-03)
param_dist = {} # type: ignore
optuna_search = integration.OptunaSearchCV(
est,
param_dist,
cv=3,
enable_pruning=True,
max_iter=5,
error_score=np.nan,
random_state=0,
return_train_score=True,
)
with pytest.raises(ValueError, match="y cannot be None"):
optuna_search.fit(X)
def test_objective_error_score_invalid() -> None:
X, y = make_blobs(n_samples=10)
est = SGDClassifier(max_iter=5, tol=1e-03)
param_dist = {} # type: ignore
optuna_search = integration.OptunaSearchCV(
est,
param_dist,
cv=3,
enable_pruning=True,
max_iter=5,
error_score="invalid error score",
random_state=0,
return_train_score=True,
)
with pytest.raises(ValueError,
match="error_score must be 'raise' or numeric."):
optuna_search.fit(X)
def test_optuna_search_invalid_param_dist() -> None:
X, y = make_blobs(n_samples=10)
est = KernelDensity()
param_dist = [
"kernel",
distributions.CategoricalDistribution(("gaussian", "linear"))
]
with pytest.raises(TypeError,
match="param_distributions must be a dictionary."):
integration.OptunaSearchCV(
est,
param_dist, # type: ignore
cv=3,
error_score="raise",
random_state=0,
return_train_score=True,
)
def test_optuna_search_invalid_param_dist():
# type: () -> None
X, y = make_blobs(n_samples=10)
est = KernelDensity()
param_dist = [
'kernel',
distributions.CategoricalDistribution(('gaussian', 'linear'))
]
optuna_search = integration.OptunaSearchCV(
est,
param_dist, # type: ignore
cv=3,
error_score='raise',
random_state=0,
return_train_score=True)
with pytest.raises(ValueError,
match='param_distributions must be a dictionary.'):
optuna_search.fit(X)
def test_optuna_search_properties() -> None:
X, y = make_blobs(n_samples=10)
est = LogisticRegression(tol=1e-03)
param_dist = {"C": distributions.LogUniformDistribution(1e-04, 1e03)}
optuna_search = integration.OptunaSearchCV(
est, param_dist, cv=3, error_score="raise", random_state=0, return_train_score=True
)
optuna_search.fit(X, y)
optuna_search.set_user_attr("dataset", "blobs")
assert optuna_search._estimator_type == "classifier"
assert type(optuna_search.best_index_) == int
assert type(optuna_search.best_params_) == dict
assert optuna_search.best_score_ is not None
assert optuna_search.best_trial_ is not None
assert np.allclose(optuna_search.classes_, np.array([0, 1, 2]))
assert optuna_search.n_trials_ == 10
assert optuna_search.user_attrs_ == {"dataset": "blobs"}
assert type(optuna_search.predict_log_proba(X)) == np.ndarray
assert type(optuna_search.predict_proba(X)) == np.ndarray
def test_optuna_search(enable_pruning):
# type: (bool) -> None
X, y = make_blobs(n_samples=10)
est = SGDClassifier(max_iter=5, tol=1e-03)
param_dist = {'alpha': distributions.LogUniformDistribution(1e-04, 1e+03)}
optuna_search = integration.OptunaSearchCV(est,
param_dist,
cv=3,
enable_pruning=enable_pruning,
error_score='raise',
max_iter=5,
random_state=0,
return_train_score=True)
with pytest.raises(NotFittedError):
optuna_search._check_is_fitted()
optuna_search.fit(X, y)
optuna_search.trials_dataframe()
optuna_search.decision_function(X)
optuna_search.predict(X)
optuna_search.score(X, y)