def compose_chain(self, data: InputData,
initial_chain: Optional[Chain],
composer_requirements: ComposerRequirements,
metrics: Optional[Callable],
optimiser_parameters=None,
is_visualise: bool = False) -> Chain:
new_chain = Chain()
if self.dummy_chain_type == DummyChainTypeEnum.hierarchical:
# (y1, y2) -> y
last_node = SecondaryNode(composer_requirements.secondary[0])
for requirement_model in composer_requirements.primary:
new_node = PrimaryNode(requirement_model)
new_chain.add_node(new_node)
last_node.nodes_from.append(new_node)
new_chain.add_node(last_node)
elif self.dummy_chain_type == DummyChainTypeEnum.flat:
# (y1) -> (y2) -> y
first_node = PrimaryNode(composer_requirements.primary[0])
new_chain.add_node(first_node)
prev_node = first_node
for requirement_model in composer_requirements.secondary:
new_node = SecondaryNode(requirement_model)
new_node.nodes_from = [prev_node]
prev_node = new_node
new_chain.add_node(new_node)
else:
raise NotImplementedError()
return new_chain
def chain_with_secondary_nodes_only():
first = SecondaryNode(model_type='logit', nodes_from=[])
second = SecondaryNode(model_type='logit', nodes_from=[first])
chain = Chain()
chain.add_node(first)
chain.add_node(second)
return chain
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_cycle():
first = PrimaryNode(model_type='logit')
second = SecondaryNode(model_type='logit', nodes_from=[first])
third = SecondaryNode(model_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(model_type='logit')
root_first = SecondaryNode(model_type='logit', nodes_from=[first])
root_second = SecondaryNode(model_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(model_type='logit')
second = SecondaryNode(model_type='logit', nodes_from=[first])
third = SecondaryNode(model_type='logit', nodes_from=[])
fourth = SecondaryNode(model_type='logit', nodes_from=[third])
chain = Chain()
for node in [first, second, third, fourth]:
chain.add_node(node)
return chain
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 valid_chain():
first = PrimaryNode(model_type='logit')
second = SecondaryNode(model_type='logit', nodes_from=[first])
third = SecondaryNode(model_type='logit', nodes_from=[second])
last = SecondaryNode(model_type='logit', nodes_from=[third])
chain = Chain()
for node in [first, second, third, last]:
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(model_type='logit')
second = PrimaryNode(model_type='lda')
third = PrimaryNode(model_type='knn')
final = SecondaryNode(model_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(model_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].cache.clear()
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 get_composite_lstm_chain():
chain = Chain()
node_trend = PrimaryNode('trend_data_model')
node_lstm_trend = SecondaryNode('lasso', nodes_from=[node_trend])
node_residual = PrimaryNode('residual_data_model')
node_ridge_residual = SecondaryNode('ridge', nodes_from=[node_residual])
node_final = SecondaryNode(
'additive_data_model',
nodes_from=[node_ridge_residual, node_lstm_trend])
chain.add_node(node_final)
return chain
def get_composite_lstm_chain():
chain = Chain()
node_trend = PrimaryNode('trend_data_model')
node_trend.labels = ["fixed"]
node_lstm_trend = SecondaryNode('linear', nodes_from=[node_trend])
node_trend.labels = ["fixed"]
node_residual = PrimaryNode('residual_data_model')
node_ridge_residual = SecondaryNode('linear', nodes_from=[node_residual])
node_final = SecondaryNode(
'additive_data_model',
nodes_from=[node_ridge_residual, node_lstm_trend])
node_final.labels = ["fixed"]
chain.add_node(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 test_cache_historical_state_using(data_setup):
train, _ = data_setup
chain = chain_first()
# chain fitted, model goes to cache
chain.fit(input_data=train)
new_node = SecondaryNode(model_type='logit')
old_node = chain.root_node.nodes_from[0]
# change child node to new one
chain.update_node(old_node=old_node,
new_node=new_node)
# cache is not actual
assert not chain.root_node.cache.actual_cached_state
# fit modified chain
chain.fit(input_data=train)
# cache is actual now
assert chain.root_node.cache.actual_cached_state
# change node back
chain.update_node(old_node=chain.root_node.nodes_from[0],
new_node=old_node)
# cache is actual without new fitting,
# because the cached model was saved after first fit
assert chain.root_node.cache.actual_cached_state
def chain_simple() -> Chain:
node_first = PrimaryNode('svc')
node_second = PrimaryNode('lda')
node_final = SecondaryNode('rf', nodes_from=[node_first, node_second])
chain = Chain(node_final)
return chain
def get_simple_chain():
first = PrimaryNode(model_type='xgboost')
second = PrimaryNode(model_type='knn')
final = SecondaryNode(model_type='logit', nodes_from=[first, second])
chain = Chain(final)
return chain
def chain_with_pca() -> Chain:
node_first = PrimaryNode('pca_data_model')
node_second = PrimaryNode('lda')
node_final = SecondaryNode('rf', nodes_from=[node_first, node_second])
chain = Chain(node_final)
return chain
def chain_with_incorrect_decomposition_structure():
first = PrimaryNode(model_type='trend_data_model')
second = PrimaryNode(model_type='residual_data_model')
final = SecondaryNode(model_type='linear', nodes_from=[first, second])
chain = Chain(final)
return chain
def chain_with_incorrect_task_type():
first = PrimaryNode(model_type='linear')
second = PrimaryNode(model_type='linear')
final = SecondaryNode(model_type='kmeans', nodes_from=[first, second])
chain = Chain(final)
return chain, Task(TaskTypesEnum.classification)
def get_comp_chain():
node_first = PrimaryNode('lstm')
node_second = PrimaryNode('rfr')
node_final = SecondaryNode('linear',
nodes_from=[node_first, node_second],
manual_preprocessing_func=EmptyStrategy)
chain = Chain(node_final)
return chain
def chain_with_incorrect_root_model():
first = PrimaryNode(model_type='logit')
second = PrimaryNode(model_type='logit')
final = SecondaryNode(model_type='direct_data_model',
nodes_from=[first, second])
chain = Chain(final)
return chain
def chain_with_primary_composition_model():
first = PrimaryNode(model_type='additive_data_model')
second = PrimaryNode(model_type='residual_data_model')
final = SecondaryNode(model_type='additive_data_model',
nodes_from=[first, second])
chain = Chain(final)
return chain
def get_decomposed_chain(model_trend='lstm', model_residual='ridge'):
chain = Chain()
node_trend = PrimaryNode('trend_data_model')
node_first_trend = SecondaryNode('lstm', nodes_from=[node_trend])
if model_trend == 'lstm':
# decrease the number of epochs to fit
node_first_trend.model.params = {'epochs': 1}
node_residual = PrimaryNode('residual_data_model')
node_model_residual = SecondaryNode(model_residual,
nodes_from=[node_residual])
node_final = SecondaryNode(
'additive_data_model',
nodes_from=[node_model_residual, node_first_trend])
chain.add_node(node_final)
return chain
def chain_fourth():
# XG
# | \
# XG KNN
# | \ | \
# QDA KNN LR LDA
# | \ | \
# RF RF KNN KNN
chain = chain_first()
new_node = SecondaryNode('qda')
for model_type in ('rf', 'rf'):
new_node.nodes_from.append(PrimaryNode(model_type))
chain.replace_node_with_parents(chain.root_node.nodes_from[0].nodes_from[1], new_node)
new_node = SecondaryNode('knn')
for model_type in ('knn', 'knn'):
new_node.nodes_from.append(PrimaryNode(model_type))
chain.replace_node_with_parents(chain.root_node.nodes_from[0].nodes_from[0], new_node)
return chain
def test_nodes_sequence_fit_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
train, _ = train_test_data_setup(data)
first = PrimaryNode(model_type='logit')
second = SecondaryNode(model_type='lda', nodes_from=[first])
third = SecondaryNode(model_type='qda', nodes_from=[first])
final = SecondaryNode(model_type='knn', nodes_from=[second, third])
train_predicted = final.fit(input_data=train)
assert final.descriptive_id == ('((/n_logit_default_params;)/'
'n_lda_default_params;;(/'
'n_logit_default_params;)/'
'n_qda_default_params;)/'
'n_knn_default_params')
assert train_predicted.predict.shape[0] == train.target.shape[0]
assert final.cache.actual_cached_state is not None
def get_regr_chain():
# Chain composition
first = PrimaryNode(model_type='xgbreg')
second = PrimaryNode(model_type='knnreg')
final = SecondaryNode(model_type='linear', nodes_from=[first, second])
chain = Chain()
chain.add_node(final)
return chain
def chain_with_self_cycle():
first = PrimaryNode(model_type='logit')
second = SecondaryNode(model_type='logit', nodes_from=[first])
second.nodes_from.append(second)
chain = Chain()
chain.add_node(first)
chain.add_node(second)
return chain
def get_class_chain():
# Chain composition
first = PrimaryNode(model_type='xgboost')
second = PrimaryNode(model_type='knn')
final = SecondaryNode(model_type='logit', nodes_from=[first, second])
chain = Chain()
chain.add_node(final)
return chain
def two_level_chain():
first = PrimaryNode(model_type='logit')
second = PrimaryNode(model_type='knn')
third = SecondaryNode(model_type='xgboost', nodes_from=[first, second])
chain = Chain()
for node in [first, second, third]:
chain.add_node(node)
return chain
def baseline_chain():
chain = Chain()
last_node = SecondaryNode(model_type='xgboost', nodes_from=[])
for requirement_model in ['knn', 'logit']:
new_node = PrimaryNode(requirement_model)
chain.add_node(new_node)
last_node.nodes_from.append(new_node)
chain.add_node(last_node)
return chain
def chain_third():
# QDA
# | \
# RF RF
chain = Chain()
new_node = SecondaryNode('qda')
for model_type in ('rf', 'rf'):
new_node.nodes_from.append(PrimaryNode(model_type))
chain.add_node(new_node)
[chain.add_node(node_from) for node_from in new_node.nodes_from]
return chain