def test_ts_forecasting_lagged_data_operation():
train_input, predict_input, y_test = get_time_series()
node_lagged = PrimaryNode('lagged')
node_ridge = SecondaryNode('ridge', nodes_from=[node_lagged])
chain = Chain(node_ridge)
chain.fit_from_scratch(train_input)
predicted_output = chain.predict(predict_input)
predicted = np.ravel(predicted_output.predict)
assert len(predicted) == len(np.ravel(y_test))
def test_ts_forecasting_smoothing_data_operation():
train_input, predict_input, y_test = get_time_series()
for smoothing_operation in ['smoothing', 'gaussian_filter']:
node_smoothing = PrimaryNode(smoothing_operation)
node_lagged = SecondaryNode('lagged', nodes_from=[node_smoothing])
node_ridge = SecondaryNode('ridge', nodes_from=[node_lagged])
chain = Chain(node_ridge)
chain.fit_from_scratch(train_input)
predicted_output = chain.predict(predict_input)
predicted = np.ravel(predicted_output.predict)
assert len(predicted) == len(np.ravel(y_test))
def test_classification_data_operations():
train_input, predict_input, y_test = get_small_classification_dataset()
for data_operation in [
'kernel_pca', 'pca', 'scaling', 'normalization', 'poly_features',
'rfe_lin_class', 'rfe_non_lin_class'
]:
node_data_operation = PrimaryNode(data_operation)
node_final = SecondaryNode('logit', nodes_from=[node_data_operation])
chain = Chain(node_final)
# Fit and predict for chain
chain.fit_from_scratch(train_input)
predicted_output = chain.predict(predict_input)
predicted = predicted_output.predict
assert len(predicted) == len(y_test)
def test_data_merge_in_chain():
""" Test check is the chain can correctly work with dynamic changes in
tables during the fit process
"""
# ridge
# / \ (merge operation)
# | ransac_lin_reg (remove several lines in table)
# \ /
# scaling
node_scaling = PrimaryNode('scaling')
node_lin_ransac = SecondaryNode('ransac_lin_reg', nodes_from=[node_scaling])
node_final = SecondaryNode('ridge', nodes_from=[node_lin_ransac, node_scaling])
chain = Chain(node_final)
features_options = {'informative': 2, 'bias': 2.0}
x_train, y_train, x_test, y_test = get_regression_dataset(features_options=features_options,
samples_amount=100,
features_amount=5)
# Define regression task
task = Task(TaskTypesEnum.regression)
# Prepare data to train the model
train_input = InputData(idx=np.arange(0, len(x_train)),
features=x_train,
target=y_train,
task=task,
data_type=DataTypesEnum.table)
# Fit and predict
chain.fit_from_scratch(train_input)
prediction = chain.predict(train_input)
print(prediction)
assert prediction is not None
def synthetic_benchmark_dataset(samples_amount: int,
features_amount: int,
classes_amount: int = 2,
features_options: Dict = DEFAULT_OPTIONS,
fitted_chain: Chain = None) -> InputData:
"""
Generates a binary classification benchmark dataset that was obtained using
the (TODO: add. reference) proposed fitting schema.
:param samples_amount: Total amount of samples in the resulted dataset.
:param features_amount: Total amount of features per sample.
:param classes_amount: The amount of classes in the dataset.
:param features_options: features options in key-value suitable for classification_dataset.
:param fitted_chain: Chain with separately fitted models.
If None then 3-level balanced tree were fitted and taken as a default.
:return: Benchmark dataset that is ready to be used by Chain.
"""
if fitted_chain is None:
fitted_chain = _default_chain(samples_amount=samples_amount,
features_amount=features_amount,
classes_amount=classes_amount)
if classes_amount != 2:
raise NotImplementedError(
'Only binary classification tasks are supported')
features, target = classification_dataset(
samples_amount=samples_amount,
features_amount=features_amount,
classes_amount=classes_amount,
features_options=features_options)
target = np.expand_dims(target, axis=1)
task = Task(TaskTypesEnum.classification)
samples_idxs = np.arange(0, samples_amount)
train = InputData(idx=samples_idxs,
features=features,
target=target,
task=task,
data_type=DataTypesEnum.table)
synth_target = fitted_chain.predict(input_data=train).predict
synth_labels = _to_labels(synth_target)
data_synth_train = InputData(idx=np.arange(0, samples_amount),
features=features,
target=synth_labels,
task=task,
data_type=DataTypesEnum.table)
# TODO: fix preproc issues
fitted_chain.fit_from_scratch(input_data=data_synth_train)
features, target = classification_dataset(
samples_amount=samples_amount,
features_amount=features_amount,
classes_amount=classes_amount,
features_options=features_options)
target = np.expand_dims(target, axis=1)
test = InputData(idx=samples_idxs,
features=features,
target=target,
data_type=DataTypesEnum.table,
task=task)
synth_target = fitted_chain.predict(input_data=test).predict
synth_labels = _to_labels(synth_target)
data_synth_final = InputData(idx=samples_idxs,
features=features,
data_type=DataTypesEnum.table,
target=synth_labels,
task=task)
return data_synth_final
