def test_chain_hierarchy_fit_correct(data_setup):
data = data_setup
train, _ = train_test_data_setup(data)
first = NodeGenerator.primary_node(model_type=ModelTypesIdsEnum.logit)
second = NodeGenerator.secondary_node(model_type=ModelTypesIdsEnum.logit,
nodes_from=[first])
third = NodeGenerator.secondary_node(model_type=ModelTypesIdsEnum.logit,
nodes_from=[first])
final = NodeGenerator.secondary_node(model_type=ModelTypesIdsEnum.logit,
nodes_from=[second, third])
chain = Chain()
for node in [first, second, third, final]:
chain.add_node(node)
train_predicted = chain.fit(input_data=train, use_cache=False)
assert chain.root_node.descriptive_id == (
'((/n_ModelTypesIdsEnum.logit_defaultparams;)/'
'n_ModelTypesIdsEnum.logit_defaultparams;;(/'
'n_ModelTypesIdsEnum.logit_defaultparams;)/'
'n_ModelTypesIdsEnum.logit_defaultparams;)/'
'n_ModelTypesIdsEnum.logit_defaultparams')
assert chain.length == 4
assert chain.depth == 3
assert train_predicted.predict.shape == train.target.shape
def chain_tuning(nodes_to_tune: str,
chain: Chain,
train_data: InputData,
test_data: InputData,
local_iter: int,
tuner_iter_num: int = 50) -> (float, list):
several_iter_scores_test = []
if nodes_to_tune == 'primary':
print('primary_node_tuning')
chain_tune_strategy = chain.fine_tune_primary_nodes
elif nodes_to_tune == 'root':
print('root_node_tuning')
chain_tune_strategy = chain.fine_tune_all_nodes
else:
raise ValueError(
f'Invalid type of nodes. Nodes must be primary or root')
for iteration in range(local_iter):
print(f'current local iteration {iteration}')
# Chain tuning
chain_tune_strategy(train_data, iterations=tuner_iter_num)
# After tuning prediction
chain.fit(train_data)
after_tuning_predicted = chain.predict(test_data)
# Metrics
aft_tun_roc_auc = roc_auc(y_true=test_data.target,
y_score=after_tuning_predicted.predict)
several_iter_scores_test.append(aft_tun_roc_auc)
return float(np.mean(several_iter_scores_test)), several_iter_scores_test
def get_rmse_value(chain: Chain, train_data: InputData, test_data: InputData) -> (float, float):
train_pred = chain.predict(input_data=train_data)
test_pred = chain.predict(input_data=test_data)
rmse_value_test = mse(y_true=test_data.target, y_pred=test_pred.predict, squared=False)
rmse_value_train = mse(y_true=train_data.target, y_pred=train_pred.predict, squared=False)
return rmse_value_train, rmse_value_test
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 = NodeGenerator.secondary_node(
composer_requirements.secondary[0])
for requirement_model in composer_requirements.primary:
new_node = NodeGenerator.primary_node(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 = NodeGenerator.primary_node(
composer_requirements.primary[0])
new_chain.add_node(first_node)
prev_node = first_node
for requirement_model in composer_requirements.secondary:
new_node = NodeGenerator.secondary_node(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 metric_for_nodes(self, metric_function, train_data: InputData,
test_data: InputData, is_chain_shared: bool,
chain: Chain) -> float:
validate(chain)
if is_chain_shared:
chain = SharedChain(base_chain=chain,
shared_cache=self.shared_cache)
chain.fit(input_data=train_data)
return metric_function(chain, test_data)
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 get_roc_auc_value(chain: Chain, train_data: InputData,
test_data: InputData) -> (float, float):
train_pred = chain.predict(input_data=train_data)
test_pred = chain.predict(input_data=test_data)
roc_auc_value_test = roc_auc(y_true=test_data.target,
y_score=test_pred.predict)
roc_auc_value_train = roc_auc(y_true=train_data.target,
y_score=train_pred.predict)
return roc_auc_value_train, roc_auc_value_test
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 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_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 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 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
def chain_third():
# QDA
# | \
# RF RF
chain = Chain()
new_node = NodeGenerator.secondary_node(ModelTypesIdsEnum.qda)
for model_type in (ModelTypesIdsEnum.rf, ModelTypesIdsEnum.rf):
new_node.nodes_from.append(NodeGenerator.primary_node(model_type))
chain.add_node(new_node)
[chain.add_node(node_from) for node_from in new_node.nodes_from]
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 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 chain_with_multiple_roots():
first = NodeGenerator.primary_node(model_type=ModelTypesIdsEnum.logit)
root_first = NodeGenerator.secondary_node(
model_type=ModelTypesIdsEnum.logit, nodes_from=[first])
root_second = NodeGenerator.secondary_node(
model_type=ModelTypesIdsEnum.logit, nodes_from=[first])
chain = Chain()
for node in [first, root_first, root_second]:
chain.add_node(node)
return chain
def chain_with_cycle():
first = NodeGenerator.primary_node(model_type=ModelTypesIdsEnum.logit)
second = NodeGenerator.secondary_node(model_type=ModelTypesIdsEnum.logit,
nodes_from=[first])
third = NodeGenerator.secondary_node(model_type=ModelTypesIdsEnum.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 compose_chain() -> Chain:
chain = Chain()
node_first = PrimaryNode('svc')
node_second = PrimaryNode('lda')
node_third = SecondaryNode('rf')
node_third.nodes_from.append(node_first)
node_third.nodes_from.append(node_second)
chain.add_node(node_third)
return chain
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 default_valid_chain():
first = NodeGenerator.primary_node(model_type=ModelTypesIdsEnum.logit)
second = NodeGenerator.secondary_node(model_type=ModelTypesIdsEnum.logit,
nodes_from=[first])
third = NodeGenerator.secondary_node(model_type=ModelTypesIdsEnum.logit,
nodes_from=[first])
final = NodeGenerator.secondary_node(model_type=ModelTypesIdsEnum.logit,
nodes_from=[second, third])
chain = Chain()
for node in [first, second, third, final]:
chain.add_node(node)
return chain
def chain_with_isolated_nodes():
first = NodeGenerator.primary_node(model_type=ModelTypesIdsEnum.logit)
second = NodeGenerator.secondary_node(model_type=ModelTypesIdsEnum.logit,
nodes_from=[first])
third = NodeGenerator.secondary_node(model_type=ModelTypesIdsEnum.logit,
nodes_from=[second])
isolated = NodeGenerator.secondary_node(model_type=ModelTypesIdsEnum.logit,
nodes_from=[])
chain = Chain()
for node in [first, second, third, isolated]:
chain.add_node(node)
return chain
def test_regression_chain_with_datamodel_fit_correct():
data = get_synthetic_regression_data()
train_data, test_data = train_test_data_setup(data)
node_data = PrimaryNode('direct_data_model')
node_first = PrimaryNode('ridge')
node_second = SecondaryNode('lasso')
node_second.nodes_from = [node_first, node_data]
chain = Chain(node_second)
chain.fit(train_data)
results = chain.predict(test_data)
assert results.predict.shape == test_data.target.shape
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 metric_for_nodes(self, metric_function, train_data: InputData,
test_data: InputData, is_chain_shared: bool,
chain: Chain) -> float:
try:
validate(chain)
if is_chain_shared:
chain = SharedChain(base_chain=chain,
shared_cache=self.shared_cache)
chain.fit(input_data=train_data)
return metric_function(chain, test_data)
except Exception as ex:
print(
f'Error in chain assessment during composition: {ex}. Continue.'
)
return max_int_value
def calculate_validation_metric(chain: Chain, dataset_to_validate: InputData) -> float:
# the execution of the obtained composite models
predicted = chain.predict(dataset_to_validate)
# the quality assessment for the simulation results
roc_auc_value = roc_auc(y_true=dataset_to_validate.target,
y_score=predicted.predict)
return roc_auc_value
def apply_model_to_data(model: Chain, data_path: str):
df, file_path = create_multi_clf_examples_from_excel(data_path,
return_df=True)
dataset_to_apply = InputData.from_csv(file_path, with_target=False)
evo_predicted = model.predict(dataset_to_apply)
df['forecast'] = probs_to_labels(evo_predicted.predict)
return df
def get_value(cls, chain: Chain, reference_data: InputData) -> float:
metric = cls.default_value
try:
results = chain.predict(reference_data)
metric = cls.metric(reference_data, results)
except Exception as ex:
print(f'Metric evaluation error: {ex}')
return metric
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 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
