def test_chain_hierarchy_fit_correct(data_setup):
data = data_setup
train, _ = train_test_data_setup(data)
first = PrimaryNode(operation_type='logit')
second = SecondaryNode(operation_type='logit', nodes_from=[first])
third = SecondaryNode(operation_type='logit', nodes_from=[first])
final = SecondaryNode(operation_type='logit', nodes_from=[second, third])
chain = Chain()
for node in [first, second, third, final]:
chain.add_node(node)
chain.unfit()
train_predicted = chain.fit(input_data=train)
assert chain.root_node.descriptive_id == ('((/n_logit_default_params;)/'
'n_logit_default_params;;(/'
'n_logit_default_params;)/'
'n_logit_default_params;)/'
'n_logit_default_params')
assert chain.length == 4
assert chain.depth == 3
assert train_predicted.predict.shape[0] == train.target.shape[0]
assert final.fitted_operation is not None
def run_chain_from_automl(train_file_path: str,
test_file_path: str,
max_run_time: timedelta = timedelta(minutes=10)):
""" Function run chain with Auto ML models in nodes
:param train_file_path: path to the csv file with data for train
:param test_file_path: path to the csv file with data for validation
:param max_run_time: maximum running time for customization of the "tpot" model
:return roc_auc_value: ROC AUC metric for chain
"""
train_data = InputData.from_csv(train_file_path)
test_data = InputData.from_csv(test_file_path)
testing_target = test_data.target
chain = Chain()
node_scaling = PrimaryNode('scaling')
node_tpot = PrimaryNode('tpot')
node_tpot.operation.params = {'max_run_time_sec': max_run_time.seconds}
node_lda = SecondaryNode('lda', nodes_from=[node_scaling])
node_rf = SecondaryNode('rf', nodes_from=[node_tpot, node_lda])
chain.add_node(node_rf)
chain.fit(train_data)
results = chain.predict(test_data)
roc_auc_value = roc_auc(y_true=testing_target, y_score=results.predict)
print(roc_auc_value)
return roc_auc_value
def get_chain():
node_scaling = PrimaryNode('scaling')
node_ransac = SecondaryNode('ransac_lin_reg', nodes_from=[node_scaling])
node_ridge = SecondaryNode('lasso', nodes_from=[node_ransac])
chain = Chain(node_ridge)
return chain
def get_nodes():
first_node = PrimaryNode('knn')
second_node = PrimaryNode('knn')
third_node = SecondaryNode('lda', nodes_from=[first_node, second_node])
root = SecondaryNode('logit', nodes_from=[third_node])
return [root, third_node, first_node, second_node]
def get_composite_chain(composite_flag: bool = True) -> Chain:
node_first = PrimaryNode('cnn')
node_first.custom_params = {
'image_shape': (28, 28, 1),
'architecture': 'deep',
'num_classes': 10,
'epochs': 15,
'batch_size': 128
}
node_second = PrimaryNode('cnn')
node_second.custom_params = {
'image_shape': (28, 28, 1),
'architecture_type': 'simplified',
'num_classes': 10,
'epochs': 10,
'batch_size': 128
}
node_final = SecondaryNode('rf', nodes_from=[node_first, node_second])
if not composite_flag:
node_final = SecondaryNode('rf', nodes_from=[node_first])
chain = Chain(node_final)
return chain
def run_chain_from_automl(train_file_path: str, test_file_path: str,
max_run_time: timedelta = timedelta(minutes=10)):
train_data = InputData.from_csv(train_file_path)
test_data = InputData.from_csv(test_file_path)
testing_target = test_data.target
chain = Chain()
node_tpot = PrimaryNode('tpot')
node_tpot.model.params = {'max_run_time_sec': max_run_time.seconds}
node_lda = PrimaryNode('lda')
node_rf = SecondaryNode('rf')
node_rf.nodes_from = [node_tpot, node_lda]
chain.add_node(node_rf)
chain.fit(train_data)
results = chain.predict(test_data)
roc_auc_value = roc_auc(y_true=testing_target,
y_score=results.predict)
print(roc_auc_value)
return roc_auc_value
def generate_chain() -> Chain:
node_scaling = PrimaryNode('scaling')
node_first = SecondaryNode('kmeans', nodes_from=[node_scaling])
node_second = SecondaryNode('kmeans', nodes_from=[node_scaling])
node_root = SecondaryNode('logit', nodes_from=[node_first, node_second])
chain = Chain(node_root)
return chain
def ts_chain_with_incorrect_data_flow():
"""
Connection lagged -> lagged is incorrect
Connection ridge -> ar is incorrect also
lagged - lagged - ridge \
ar -> final forecast
lagged - ridge /
"""
# First level
node_lagged = PrimaryNode('lagged')
# Second level
node_lagged_1 = SecondaryNode('lagged', nodes_from=[node_lagged])
node_lagged_2 = PrimaryNode('lagged')
# Third level
node_ridge_1 = SecondaryNode('ridge', nodes_from=[node_lagged_1])
node_ridge_2 = SecondaryNode('ridge', nodes_from=[node_lagged_2])
# Fourth level - root node
node_final = SecondaryNode('ar', nodes_from=[node_ridge_1, node_ridge_2])
chain = Chain(node_final)
return chain
def get_complex_chain():
"""
Chain looking like this
smoothing - lagged - ridge \
\
ridge -> final forecast
/
lagged - ridge /
"""
# First level
node_smoothing = PrimaryNode('smoothing')
# Second level
node_lagged_1 = SecondaryNode('lagged', nodes_from=[node_smoothing])
node_lagged_2 = PrimaryNode('lagged')
# Third level
node_ridge_1 = SecondaryNode('ridge', nodes_from=[node_lagged_1])
node_ridge_2 = SecondaryNode('ridge', nodes_from=[node_lagged_2])
# Fourth level - root node
node_final = SecondaryNode('ridge',
nodes_from=[node_ridge_1, node_ridge_2])
chain = Chain(node_final)
return chain
def get_knn_class_chain(k_neighbors):
""" Function return chain with K-nn classification model in it """
node_scaling = PrimaryNode('scaling')
node_final = SecondaryNode('knn', nodes_from=[node_scaling])
node_final.custom_params = {'n_neighbors': k_neighbors}
chain = Chain(node_final)
return chain
def generate_chain() -> Chain:
node_scaling = PrimaryNode('scaling')
node_lasso = SecondaryNode('lasso', nodes_from=[node_scaling])
node_ridge = SecondaryNode('ridge', nodes_from=[node_scaling])
node_root = SecondaryNode('linear', nodes_from=[node_lasso, node_ridge])
chain = Chain(node_root)
return chain
def run_tpot_vs_fedot_example(train_file_path: str, test_file_path: str):
train_data = InputData.from_csv(train_file_path)
test_data = InputData.from_csv(test_file_path)
training_features = train_data.features
testing_features = test_data.features
training_target = train_data.target
testing_target = test_data.target
# Average CV score on the training set was: 0.93755
exported_pipeline = make_pipeline(
StackingEstimator(estimator=BernoulliNB()), RandomForestClassifier())
# Fix random state for all the steps in exported pipeline
set_param_recursive(exported_pipeline.steps, 'random_state', 1)
exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict_proba(testing_features)[:, 1]
roc_auc_value = roc_auc(y_true=testing_target, y_score=results)
print(f'ROC AUC for TPOT: {roc_auc_value}')
node_scaling = PrimaryNode('scaling')
node_bernb = SecondaryNode('bernb', nodes_from=[node_scaling])
node_rf = SecondaryNode('rf', nodes_from=[node_bernb, node_scaling])
chain = Chain(node_rf)
chain.fit(train_data)
results = chain.predict(test_data)
roc_auc_value = roc_auc(y_true=testing_target, y_score=results.predict)
print(f'ROC AUC for FEDOT: {roc_auc_value}')
return roc_auc_value
def chain_with_secondary_nodes_only():
first = SecondaryNode(operation_type='logit', nodes_from=[])
second = SecondaryNode(operation_type='logit', nodes_from=[first])
chain = Chain()
chain.add_node(first)
chain.add_node(second)
return chain
def chain_with_only_data_operations():
first = PrimaryNode(operation_type='one_hot_encoding')
second = SecondaryNode(operation_type='scaling', nodes_from=[first])
final = SecondaryNode(operation_type='ransac_lin_reg', nodes_from=[second])
chain = Chain(final)
return chain
def get_complex_regr_chain():
node_scaling = PrimaryNode(operation_type='scaling')
node_ridge = SecondaryNode('ridge', nodes_from=[node_scaling])
node_linear = SecondaryNode('linear', nodes_from=[node_scaling])
final = SecondaryNode('xgbreg', nodes_from=[node_ridge, node_linear])
chain = Chain(final)
return chain
def test_ordered_subnodes_hierarchy():
first_node = PrimaryNode('knn')
second_node = PrimaryNode('knn')
third_node = SecondaryNode('lda', nodes_from=[first_node, second_node])
root = SecondaryNode('logit', nodes_from=[third_node])
ordered_nodes = root.ordered_subnodes_hierarchy()
assert len(ordered_nodes) == 4
def test_distance_to_primary_level():
first_node = PrimaryNode('knn')
second_node = PrimaryNode('knn')
third_node = SecondaryNode('lda', nodes_from=[first_node, second_node])
root = SecondaryNode('logit', nodes_from=[third_node])
distance = root.distance_to_primary_level
assert distance == 2
def default_valid_chain():
first = PrimaryNode(model_type='logit')
second = SecondaryNode(model_type='logit', nodes_from=[first])
third = SecondaryNode(model_type='logit', nodes_from=[first])
final = SecondaryNode(model_type='logit', nodes_from=[second, third])
chain = Chain(final)
return chain
def chain_with_pca() -> Chain:
node_scaling = PrimaryNode('scaling')
node_pca = SecondaryNode('pca', nodes_from=[node_scaling])
node_lda = SecondaryNode('lda', nodes_from=[node_scaling])
node_final = SecondaryNode('rf', nodes_from=[node_pca, node_lda])
chain = Chain(node_final)
return chain
def chain_simple() -> Chain:
node_scaling = PrimaryNode('scaling')
node_svc = SecondaryNode('svc', nodes_from=[node_scaling])
node_lda = SecondaryNode('lda', nodes_from=[node_scaling])
node_final = SecondaryNode('rf', nodes_from=[node_svc, node_lda])
chain = Chain(node_final)
return chain
def chain_with_cycle():
first = PrimaryNode(operation_type='logit')
second = SecondaryNode(operation_type='logit', nodes_from=[first])
third = SecondaryNode(operation_type='logit', nodes_from=[second, first])
second.nodes_from.append(third)
chain = Chain()
for node in [first, second, third]:
chain.add_node(node)
return chain
def chain_with_multiple_roots():
first = PrimaryNode(operation_type='logit')
root_first = SecondaryNode(operation_type='logit', nodes_from=[first])
root_second = SecondaryNode(operation_type='logit', nodes_from=[first])
chain = Chain()
for node in [first, root_first, root_second]:
chain.add_node(node)
return chain
def chain_with_isolated_components():
first = PrimaryNode(operation_type='logit')
second = SecondaryNode(operation_type='logit', nodes_from=[first])
third = SecondaryNode(operation_type='logit', nodes_from=[])
fourth = SecondaryNode(operation_type='logit', nodes_from=[third])
chain = Chain()
for node in [first, second, third, fourth]:
chain.add_node(node)
return chain
def test_secondary_nodes_is_invariant_to_inputs_order(data_setup):
data = data_setup
train, test = train_test_data_setup(data)
first = PrimaryNode(operation_type='logit')
second = PrimaryNode(operation_type='lda')
third = PrimaryNode(operation_type='knn')
final = SecondaryNode(operation_type='xgboost',
nodes_from=[first, second, third])
chain = Chain()
for node in [first, second, third, final]:
chain.add_node(node)
first = deepcopy(first)
second = deepcopy(second)
third = deepcopy(third)
final_shuffled = SecondaryNode(operation_type='xgboost',
nodes_from=[third, first, second])
chain_shuffled = Chain()
# change order of nodes in list
for node in [final_shuffled, third, first, second]:
chain_shuffled.add_node(node)
train_predicted = chain.fit(input_data=train)
train_predicted_shuffled = chain_shuffled.fit(input_data=train)
# train results should be invariant
assert chain.root_node.descriptive_id == chain_shuffled.root_node.descriptive_id
assert np.equal(train_predicted.predict,
train_predicted_shuffled.predict).all()
test_predicted = chain.predict(input_data=test)
test_predicted_shuffled = chain_shuffled.predict(input_data=test)
# predict results should be invariant
assert np.equal(test_predicted.predict,
test_predicted_shuffled.predict).all()
# change parents order for the nodes fitted chain
nodes_for_change = chain.nodes[3].nodes_from
chain.nodes[3].nodes_from = [
nodes_for_change[2], nodes_for_change[0], nodes_for_change[1]
]
chain.nodes[3].unfit()
chain.fit(train)
test_predicted_re_shuffled = chain.predict(input_data=test)
# predict results should be invariant
assert np.equal(test_predicted.predict,
test_predicted_re_shuffled.predict).all()
def chain_with_isolated_nodes():
first = PrimaryNode(model_type='logit')
second = SecondaryNode(model_type='logit', nodes_from=[first])
third = SecondaryNode(model_type='logit', nodes_from=[second])
isolated = SecondaryNode(model_type='logit', nodes_from=[])
chain = Chain()
for node in [first, second, third, isolated]:
chain.add_node(node)
return chain
def get_composite_multiscale_chain():
chain = Chain()
node_trend = PrimaryNode('trend_data_model')
node_lstm_trend = SecondaryNode('ridge', nodes_from=[node_trend])
node_residual = PrimaryNode('residual_data_model')
node_ridge_residual = SecondaryNode('ridge', nodes_from=[node_residual])
node_final = SecondaryNode(
'linear', nodes_from=[node_ridge_residual, node_lstm_trend])
chain.add_node(node_final)
return chain
def valid_chain():
first = PrimaryNode(operation_type='logit')
second = SecondaryNode(operation_type='logit', nodes_from=[first])
third = SecondaryNode(operation_type='logit', nodes_from=[second])
last = SecondaryNode(operation_type='logit', nodes_from=[third])
chain = Chain()
for node in [first, second, third, last]:
chain.add_node(node)
return chain
def test_delete_node_with_redirection():
first = PrimaryNode(operation_type='logit')
second = PrimaryNode(operation_type='lda')
third = SecondaryNode(operation_type='knn', nodes_from=[first, second])
final = SecondaryNode(operation_type='xgboost', nodes_from=[third])
chain = Chain()
chain.add_node(final)
chain.delete_node(third)
assert len(chain.nodes) == 3
assert first in chain.root_node.nodes_from
def test_update_node_in_chain_raise_exception():
first = PrimaryNode(operation_type='logit')
final = SecondaryNode(operation_type='xgboost', nodes_from=[first])
chain = Chain()
chain.add_node(final)
replacing_node = SecondaryNode('logit')
with pytest.raises(ValueError) as exc:
chain.update_node(old_node=first, new_node=replacing_node)
assert str(exc.value) == "Can't update PrimaryNode with SecondaryNode"
def create_classification_chain_with_preprocessing():
node_scaling = PrimaryNode('scaling')
node_rfe = PrimaryNode('rfe_lin_class')
xgb_node = SecondaryNode('xgboost', nodes_from=[node_scaling])
logit_node = SecondaryNode('logit', nodes_from=[node_rfe])
knn_root = SecondaryNode('knn', nodes_from=[xgb_node, logit_node])
chain = Chain(knn_root)
return chain