def test_pipeline_step(self):
pipeline = Pipeline() >> PipelineStep('a', lambda x, context: PipelineData(x.dataset + 1)) \
>> PipelineStep('b', lambda x, context: PipelineData(x.dataset + 2))
executor = LocalExecutor()
context, data = executor.run(pipeline, 0)
self.assertEqual(data.dataset, 3)
def test_random_choice_combinator(self):
for _ in range(0, 10):
data = Dataset(np.zeros((2, 2)), np.zeros((2, 2)))
result = LocalExecutor() << (Pipeline() >> RandomChoice([
PipelineStep('a', lambda x, context: 'a'),
PipelineStep('b', lambda x, context: 'b')
]))
print(result)
self.assertIn(result[1], ['a', 'b'])
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_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_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_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_pipeline(self):
df = pd.DataFrame([[1, 2], [3, 4]])
X = Dataset(df, None)
poly = PolynomialGenerator(interaction_only=True, degree=4)
context, pipe_output = LocalExecutor(X) << (
Pipeline() >> PipelineStep('generate_features', poly))
self.assertEqual(pipe_output.dataset.data.shape, (2, 4))
def test_initializer(self):
func = lambda x, context: context.epoch
result = LocalExecutor(epochs=10) << (
Pipeline() >> PipelineStep('a', func, initializer=True))
self.assertEqual(result[1], 0)