def test_tabular_preprocess(self):
dataset_properties = {
'numerical_columns': list(range(15)),
'categorical_columns': [],
'task_type': 'tabular_classification'
}
X = dict(
X_train=np.random.random((10, 15)),
y_train=np.random.random(10),
train_indices=[0, 1, 2, 3, 4, 5],
val_indices=[6, 7, 8, 9],
is_small_preprocess=True,
numerical_columns=list(range(15)),
categorical_columns=[],
num_features=15,
num_classes=2,
categories=[],
# Training configuration
job_id='test',
device='cpu',
budget_type='epochs',
epochs=10,
torch_num_threads=1,
early_stopping=20,
dataset_properties=dataset_properties,
split_id=0,
backend=self.backend,
)
pipeline = TabularClassificationPipeline(
dataset_properties=dataset_properties)
# Remove the trainer
pipeline.steps.pop()
pipeline = pipeline.fit(X)
X = pipeline.transform(X)
self.assertNotIn('preprocess_transforms', X.keys())
def test_pipeline_transform(self, fit_dictionary_tabular):
"""
In the context of autopytorch, transform expands a fit dictionary with
components that where previously fit. We can use this as a nice way to make sure
that fit properly work.
This code is added in light of components not properly added to the fit dicitonary
"""
pipeline = TabularClassificationPipeline(
dataset_properties=fit_dictionary_tabular['dataset_properties'])
cs = pipeline.get_hyperparameter_search_space()
config = cs.sample_configuration()
pipeline.set_hyperparameters(config)
with unittest.mock.patch.object(pipeline.named_steps['trainer'].choice, 'train_epoch') \
as patch_train:
patch_train.return_value = 1, {}
# We do not want to make the same early preprocessing operation to the fit dictionary
pipeline.fit(fit_dictionary_tabular.copy())
transformed_fit_dictionary_tabular = pipeline.transform(
fit_dictionary_tabular)
# First, we do not lose anyone! (We use a fancy subset containment check)
assert fit_dictionary_tabular.items(
) <= transformed_fit_dictionary_tabular.items()
# Then the pipeline should have added the following keys
expected_keys = {
'imputer', 'encoder', 'scaler', 'tabular_transformer',
'preprocess_transforms', 'network', 'optimizer', 'lr_scheduler',
'train_data_loader', 'val_data_loader', 'run_summary'
}
assert expected_keys.issubset(
set(transformed_fit_dictionary_tabular.keys()))
# Then we need to have transformations being created.
assert len(
get_preprocess_transforms(transformed_fit_dictionary_tabular)) > 0
# We expect the transformations to be in the pipeline at anytime for inference
assert 'preprocess_transforms' in transformed_fit_dictionary_tabular.keys(
)
def test_tabular_no_preprocess(self):
dataset_properties = {
'numerical_columns': list(range(15)),
'categorical_columns': [],
'task_type': TASK_TYPES_TO_STRING[TABULAR_CLASSIFICATION],
'output_type': OUTPUT_TYPES_TO_STRING[MULTICLASS],
'is_small_preprocess': False,
'input_shape': (15, ),
'output_shape': 2,
'categories': [],
'issparse': False
}
X = dict(
X_train=np.random.random((10, 15)),
y_train=np.random.random(10),
train_indices=[0, 1, 2, 3, 4, 5],
val_indices=[6, 7, 8, 9],
dataset_properties=dataset_properties,
# Training configuration
num_run=16,
device='cpu',
budget_type='epochs',
epochs=10,
torch_num_threads=1,
early_stopping=20,
split_id=0,
backend=self.backend,
)
pipeline = TabularClassificationPipeline(
dataset_properties=dataset_properties)
# Remove the trainer
pipeline.steps.pop()
pipeline = pipeline.fit(X)
X = pipeline.transform(X)
self.assertIn('preprocess_transforms', X.keys())
self.assertIsInstance(X['preprocess_transforms'], list)
self.assertIsInstance(X['preprocess_transforms'][-1].preprocessor,
BaseEstimator)