def test_max_depth(self):
model_list = [(Lasso, {}), (Ridge, {}), (RandomForestRegressor, {})]
max_depth = 2
addition = 0.25
epochs = 20
data = Dataset(datasets.load_boston().data,
datasets.load_boston().target)
context, pipeline_data = LocalExecutor(data, epochs) << (
Pipeline() >> ModelSpace(model_list) >> FormulaFeatureGenerator(
['+', '-', '*', '/'], max_depth=max_depth, addition=addition)
>> Validate(test_size=0.33, metrics=mean_squared_error) >>
ChooseBest(1) >> FeatureSelector(30))
depths = [feature["depth"] for feature in pipeline_data.dataset.meta]
preprocessing = Preprocessing()
final_data = preprocessing.reproduce(
pipeline_data.dataset,
Dataset(datasets.load_boston().data,
datasets.load_boston().target))
self.assertEqual(pipeline_data.dataset.data.shape, final_data.shape)
self.assertTrue((final_data == pipeline_data.dataset.data).all())
self.assertLessEqual(max(depths), max_depth + addition * epochs)
def test_correlated_feature_generator(self):
model_list = [(RandomForestRegressor, {}),
(GradientBoostingRegressor, {}), (SVR, {}),
(XGBRegressor, {})]
n_features_to_select = random.randint(5, 30)
data = Dataset(datasets.load_boston().data,
datasets.load_boston().target)
context, pipeline_data = LocalExecutor(data, 5) << (
Pipeline() >> PipelineStep(
'model space', ModelSpace(model_list), initializer=True) >>
FormulaFeatureGenerator(['+', '-', '*', '/'], limit=10) >>
Validate(test_size=0.1, metrics=mean_absolute_error) >> ChooseBest(
1, by_largest_score=False) >>
RecursiveFeatureSelector(n_features_to_select=n_features_to_select)
>> CorrelatedFeatureSelector(max_correlation=0.9))
preprocessing = Preprocessing()
final_data = preprocessing.reproduce(
pipeline_data.dataset,
Dataset(datasets.load_boston().data,
datasets.load_boston().target))
self.assertEqual(pipeline_data.dataset.data.shape, final_data.shape)
self.assertTrue((final_data == pipeline_data.dataset.data).all())
def test_pipeline_hyperopt(self):
x, y = make_classification(n_samples=100,
n_features=40,
n_informative=2,
n_redundant=10,
flip_y=0.05)
model_list = [(RandomForestClassifier, random_forest_hp_space()),
(GradientBoostingClassifier, grad_boosting_hp_space()),
(SVC, svc_kernel_hp_space('rbf')),
(KNeighborsClassifier, knn_hp_space()),
(XGBClassifier, xgboost_hp_space())]
data = Dataset(x, y)
context, pipeline_data = LocalExecutor(data, 2) << (
Pipeline() >> PipelineStep(
'model space', ModelSpace(model_list),
initializer=True) >> FormulaFeatureGenerator(['+', '-', '*'])
>> Hyperopt(Validate(test_size=0.1, metrics=roc_auc_score),
max_evals=2) >> ChooseBest(1) >> FeatureSelector(10))
print('0' * 30)
for result in pipeline_data.return_val:
print(result.model, result.score)
print(pipeline_data.dataset.data.shape)
print('0' * 30)
def test_RFS(self):
x, y = make_classification(n_samples=100,
n_features=40,
n_informative=2,
n_redundant=10,
flip_y=0.05)
model_list = [(RandomForestClassifier, {}),
(GradientBoostingClassifier, {}), (SVC, {}),
(KNeighborsClassifier, {}), (XGBClassifier, {})]
n_features_to_select = random.randint(5, 30)
data = Dataset(x, y)
context, pipeline_data = LocalExecutor(
data, 2) << (Pipeline() >> PipelineStep(
'model space', ModelSpace(model_list), initializer=True) >>
FormulaFeatureGenerator(['+', '-', '*', '/']) >>
Validate(test_size=0.1, metrics=roc_auc_score) >>
ChooseBest(1) >> RecursiveFeatureSelector(
n_features_to_select=n_features_to_select))
preprocessing = Preprocessing()
final_data = preprocessing.reproduce(pipeline_data.dataset,
Dataset(x, y))
self.assertEqual(pipeline_data.dataset.data.shape, final_data.shape)
self.assertTrue((final_data == pipeline_data.dataset.data).all())
def test_voting_feature_selector(self):
x, y = make_regression(
n_samples=100,
n_features=40,
n_informative=2,
)
model_list = [(RandomForestRegressor, {}),
(GradientBoostingRegressor, {}), (SVR, {}),
(XGBRegressor, {})]
data = Dataset(x, y)
result_mult = []
result_div = []
context, pipeline_data = LocalExecutor(data, 10) << (
Pipeline() >> PipelineStep(
'model space', ModelSpace(model_list), initializer=True) >>
FormulaFeatureGenerator(['+', '-', '*', '/']) >> Validate(
test_size=0.1, metrics=mean_absolute_error) >> ChooseBest(
4, by_largest_score=False) >> VotingFeatureSelector(
feature_to_select=10, reverse_score=True))
preprocessing = Preprocessing()
final_data = preprocessing.reproduce(pipeline_data.dataset,
Dataset(x, y))
self.assertEqual(pipeline_data.dataset.data.shape, final_data.shape)
self.assertTrue((final_data == pipeline_data.dataset.data).all())
print('0' * 30)
for result in pipeline_data.return_val:
print(result.model, result.score)
print(pipeline_data.dataset.data.shape)
print('0' * 30)
def test_xgboost(self):
max_evals = 2
x, y = make_classification()
dataset = Dataset(x, y)
result = LocalExecutor(dataset) << (Pipeline() >> ModelSpace([
(XGBClassifier, xgboost_hp_space())
]) >> Hyperopt(CV('roc_auc'), max_evals=max_evals))
result = result[1].return_val[0]
self.assertIsInstance(result, HyperparameterSearchResult)
self.assertEqual(len(result.history), max_evals)
def test_hyperopt(self):
max_evals = 2
x, y = make_classification()
dataset = Dataset(x, y)
result = LocalExecutor(dataset) << (Pipeline() >> ModelSpace([
(RandomForestClassifier, random_forest_hp_space())
]) >> Hyperopt(CV('roc_auc'), max_evals=max_evals))
result = result[1].return_val[0]
self.assertIsInstance(result.history, hyperopt.base.Trials)
self.assertEqual(len(result.history), max_evals)
def test_step_space_regression_model(self):
model_list = [
(Lasso, {}),
(Ridge, {}),
(KernelRidge, {}),
]
data = Dataset(datasets.load_boston().data,
datasets.load_boston().target)
LocalExecutor(data) << (
Pipeline() >> ModelSpace(model_list) >> Validate(
test_size=0.33, metrics=mean_absolute_error) >> ChooseBest(3))
def test_model_space(self):
model_list_1 = [
(LogisticRegression, {}),
(RandomForestClassifier, {}),
(GradientBoostingClassifier, {}),
(SVC, {}),
(KNeighborsClassifier, {}),
]
context = PipelineContext()
model_space = ModelSpace(model_list_1)
model_space('data', context)
self.assertListEqual(model_list_1, context.model_space)
def test_forest(self):
model_list = [
#(RandomForestRegressor, random_forest_hp_space('mae')),
(RandomForestClassifier, random_forest_hp_space())
]
data = Dataset(datasets.load_iris().data, datasets.load_iris().target)
context, pipeline_data = LocalExecutor(data, 1) << (
Pipeline() >> PipelineStep('model space', ModelSpace(model_list))
>> PipelineStep(
'H',
Hyperopt(Validate(test_size=0.33, metrics=mean_absolute_error),
max_evals=2)))
def test_step_cv(self):
model_list = [
(LogisticRegression, {}),
(RandomForestClassifier, {
'n_estimators': 100
}),
(GradientBoostingClassifier, {}),
(SVC, {}),
(KNeighborsClassifier, {}),
]
data = Dataset(datasets.load_iris().data, datasets.load_iris().target)
LocalExecutor(data) << (Pipeline() >> ModelSpace(model_list) >>
CV('accuracy') >> ChooseBest(3))
def test_recovering_dataset_FFG(self):
model_list = [(Lasso, {}), (Ridge, {}), (RandomForestRegressor, {})]
data = Dataset(datasets.load_boston().data,
datasets.load_boston().target)
context, pipeline_data = LocalExecutor(
data, 10) << (Pipeline() >> ModelSpace(model_list) >>
FormulaFeatureGenerator(['+', '-', '*']) >> Validate(
test_size=0.33, metrics=mean_squared_error) >>
ChooseBest(1) >> FeatureSelector(30))
preprocessing = Preprocessing()
final_data = preprocessing.reproduce(
pipeline_data.dataset,
Dataset(datasets.load_boston().data,
datasets.load_boston().target))
self.assertEqual(pipeline_data.dataset.data.shape, final_data.shape)
self.assertTrue((final_data == pipeline_data.dataset.data).all())
def test_poly_gen(self):
model_list = [
(Lasso, {}),
#(Ridge, {}),
(RandomForestRegressor, {})
]
X, y = datasets.make_regression(n_features=5)
data = Dataset(X, y)
context, pipeline_data = LocalExecutor(
data, 10) << (Pipeline() >> ModelSpace(model_list) >>
PolynomialFeatureGenerator(max_degree=3) >> Validate(
test_size=0.33, metrics=mean_squared_error) >>
ChooseBest(1) >> FeatureSelector(10))
preprocessing = Preprocessing()
final_data = preprocessing.reproduce(pipeline_data.dataset,
Dataset(X, y))
self.assertEqual(pipeline_data.dataset.data.shape, final_data.shape)
self.assertTrue((final_data == pipeline_data.dataset.data).all())
def test_all_step(self):
model_list = [
#(Lasso, {}),
#(Ridge, {}),
#(KernelRidge, {}),
(RandomForestRegressor, {}),
(XGBRegressor, {})
]
data = Dataset(datasets.load_boston().data,
datasets.load_boston().target)
context, pipeline_data = LocalExecutor(data, 10) << (
Pipeline() >> ModelSpace(model_list) >> FormulaFeatureGenerator([
'+', '-', '*'
]) >> Validate(test_size=0.33, metrics=mean_squared_error) >>
ChooseBest(1, by_largest_score=False) >> FeatureSelector(20))
print('0' * 30)
for result in pipeline_data.return_val:
print(result.model, result.score)
print(pipeline_data.dataset.data.shape)
print('0' * 30)