def test_sklearn_real_data(tmp_dir):
tuner = kt.SklearnTuner(
oracle=kt.oracles.BayesianOptimization(objective=kt.Objective(
"score", "max"),
max_trials=10),
hypermodel=build_model,
scoring=metrics.make_scorer(metrics.accuracy_score),
cv=model_selection.StratifiedKFold(5),
directory=tmp_dir,
)
x, y = datasets.load_iris(return_X_y=True)
x_train, x_test, y_train, y_test = model_selection.train_test_split(
x, y, test_size=0.2)
tuner.search(x_train, y_train)
best_models = tuner.get_best_models(10)
best_model = best_models[0]
worst_model = best_models[9]
best_model_score = best_model.score(x_test, y_test)
worst_model_score = worst_model.score(x_test, y_test)
assert best_model_score > 0.8
assert best_model_score >= worst_model_score
def test_sklearn_cv_with_groups(tmp_dir):
tuner = kt.SklearnTuner(
oracle=kt.oracles.BayesianOptimization(objective=kt.Objective(
"score", "max"),
max_trials=10),
hypermodel=build_model,
cv=model_selection.GroupKFold(5),
directory=tmp_dir,
)
x = np.random.uniform(size=(50, 10))
y = np.random.randint(0, 2, size=(50, ))
groups = np.random.randint(0, 5, size=(50, ))
tuner.search(x, y, groups=groups)
assert len(tuner.oracle.trials) == 10
best_trial = tuner.oracle.get_best_trials()[0]
assert best_trial.status == "COMPLETED"
assert best_trial.score is not None
assert best_trial.best_step == 0
assert best_trial.metrics.exists("score")
# Make sure best model can be reloaded.
best_model = tuner.get_best_models()[0]
best_model.score(x, y)
def test_sklearn_pipeline(tmp_dir):
tuner = kt.SklearnTuner(
oracle=kt.oracles.BayesianOptimization(objective=kt.Objective(
"score", "max"),
max_trials=10),
hypermodel=build_pipeline,
directory=tmp_dir,
)
x = np.random.uniform(size=(50, 10))
y = np.random.randint(0, 2, size=(50, ))
sample_weight = np.random.uniform(0.1, 1, size=(50, ))
tuner.search(x, y, sample_weight=sample_weight)
assert len(tuner.oracle.trials) == 10
best_trial = tuner.oracle.get_best_trials()[0]
assert best_trial.status == "COMPLETED"
assert best_trial.score is not None
assert best_trial.best_step == 0
assert best_trial.metrics.exists("score")
# Make sure best pipeline can be reloaded.
best_pipeline = tuner.get_best_models()[0]
best_pipeline.score(x, y)
def test_sklearn_additional_metrics(tmp_dir):
tuner = kt.SklearnTuner(
oracle=kt.oracles.BayesianOptimization(objective=kt.Objective(
"score", "max"),
max_trials=10),
hypermodel=build_model,
metrics=[metrics.balanced_accuracy_score, metrics.recall_score],
directory=tmp_dir,
)
x = np.random.uniform(size=(50, 10))
y = np.random.randint(0, 2, size=(50, ))
tuner.search(x, y)
assert len(tuner.oracle.trials) == 10
best_trial = tuner.oracle.get_best_trials()[0]
assert best_trial.status == "COMPLETED"
assert best_trial.score is not None
assert best_trial.best_step == 0
assert best_trial.metrics.exists("score")
assert best_trial.metrics.exists("balanced_accuracy_score")
assert best_trial.metrics.exists("recall_score")
# Make sure best model can be reloaded.
best_model = tuner.get_best_models()[0]
best_model.score(x, y)
def test_sklearn_custom_scoring_and_cv(tmp_dir):
tuner = kt.SklearnTuner(
oracle=kt.oracles.BayesianOptimization(objective=kt.Objective(
"score", "max"),
max_trials=10),
hypermodel=build_model,
scoring=metrics.make_scorer(metrics.balanced_accuracy_score),
cv=model_selection.StratifiedKFold(5),
directory=tmp_dir,
)
x = np.random.uniform(size=(50, 10))
y = np.random.randint(0, 2, size=(50, ))
tuner.search(x, y)
assert len(tuner.oracle.trials) == 10
best_trial = tuner.oracle.get_best_trials()[0]
assert best_trial.status == "COMPLETED"
assert best_trial.score is not None
assert best_trial.best_step == 0
assert best_trial.metrics.exists("score")
# Make sure best model can be reloaded.
best_model = tuner.get_best_models()[0]
best_model.score(x, y)
def test_sklearn_tuner_with_df(tmp_dir):
tuner = kt.SklearnTuner(
oracle=kt.oracles.BayesianOptimization(objective=kt.Objective(
"score", "max"),
max_trials=10),
hypermodel=build_model,
directory=tmp_dir,
)
x = pd.DataFrame(np.random.uniform(size=(50, 10)))
y = pd.DataFrame(np.random.randint(0, 2, size=(50, )))
tuner.search(x, y)
assert len(tuner.oracle.trials) == 10
def test_sklearn_not_install_error(tmp_dir):
sklearn_module = kt.tuners.sklearn_tuner.sklearn
kt.tuners.sklearn_tuner.sklearn = None
with pytest.raises(ImportError, match="Please install sklearn"):
kt.SklearnTuner(
oracle=kt.oracles.BayesianOptimization(objective=kt.Objective(
"score", "max"),
max_trials=10),
hypermodel=build_model,
directory=tmp_dir,
)
kt.tuners.sklearn_tuner.sklearn = sklearn_module