def test_pipeline_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])
pipeline = Pipeline()
for node in [first, second, third, final]:
pipeline.add_node(node)
pipeline.unfit()
train_predicted = pipeline.fit(input_data=train)
assert pipeline.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 pipeline.length == 4
assert pipeline.depth == 3
assert train_predicted.predict.shape[0] == train.target.shape[0]
assert final.fitted_operation is not None
def test_pipeline_unfit(data_fixture, request):
data = request.getfixturevalue(data_fixture)
pipeline = Pipeline(PrimaryNode('logit'))
pipeline.fit(data)
assert pipeline.is_fitted
pipeline.unfit()
assert not pipeline.is_fitted
assert not pipeline.root_node.fitted_operation
with pytest.raises(ValueError) as exc:
assert pipeline.predict(data)
def composer_metric(self, metrics, train_data: Union[InputData,
MultiModalData],
test_data: Union[InputData, MultiModalData],
pipeline: Pipeline) -> Optional[Tuple[Any]]:
try:
validate(pipeline)
pipeline.log = self.log
if type(metrics) is not list:
metrics = [metrics]
if self.cache is not None:
# TODO improve cache
pipeline.fit_from_cache(self.cache)
if not pipeline.is_fitted:
self.log.debug(
f'Pipeline {pipeline.root_node.descriptive_id} fit started'
)
pipeline.fit(input_data=train_data,
time_constraint=self.composer_requirements.
max_pipeline_fit_time)
try:
self.cache.save_pipeline(pipeline)
except Exception as ex:
self.log.info(f'Cache can not be saved: {ex}. Continue.')
evaluated_metrics = ()
for metric in metrics:
if callable(metric):
metric_func = metric
else:
metric_func = MetricsRepository().metric_by_id(metric)
evaluated_metrics = evaluated_metrics + (metric_func(
pipeline, reference_data=test_data), )
self.log.debug(
f'Pipeline {pipeline.root_node.descriptive_id} with metrics: {list(evaluated_metrics)}'
)
# enforce memory cleaning
pipeline.unfit()
gc.collect()
except Exception as ex:
self.log.info(f'Pipeline assessment warning: {ex}. Continue.')
evaluated_metrics = None
return evaluated_metrics
