def handle_fit_transform(self, data_container: DataContainer, context: ExecutionContext) -> (
'ReversiblePreprocessingWrapper', DataContainer):
"""
According to the idiom of `(1, 2, reversed(1))`, we do this, in order:
- `1`. Fit Transform preprocessing step
- `2`. Fit Transform postprocessing step
- `reversed(1)`. Inverse transform preprocessing step
:param data_container: data container to transform
:type data_container: DataContainer
:param context: execution context
:type context: ExecutionContext
:return: (self, data_container)
:rtype: (ReversiblePreprocessingWrapper, DataContainer)
"""
self["preprocessing_step"], data_container = self["preprocessing_step"].handle_fit_transform(data_container,
context.push(self[
"preprocessing_step"]))
self["postprocessing_step"], data_container = self["postprocessing_step"].handle_fit_transform(data_container,
context.push(
self[
"postprocessing_step"]))
data_container = self["preprocessing_step"].handle_inverse_transform(data_container,
context.push(self["preprocessing_step"]))
current_ids = self.hash(data_container)
data_container.set_current_ids(current_ids)
return self, data_container
def _transform_data_container(self, data_container: DataContainer,
context: ExecutionContext) -> DataContainer:
"""
According to the idiom of `(1, 2, reversed(1))`, we do this, in order:
- `1`. Transform preprocessing step
- `2`. Transform postprocessing step
- `reversed(1)`. Inverse transform preprocessing step
:param data_container: data container to transform
:param context: execution context
:return: data_container
"""
data_container = self["preprocessing_step"].handle_transform(
data_container, context.push(self["preprocessing_step"]))
data_container = self["postprocessing_step"].handle_transform(
data_container, context.push(self["postprocessing_step"]))
data_container = self["preprocessing_step"].handle_inverse_transform(
data_container, context.push(self["preprocessing_step"]))
current_ids = self.hash(data_container)
data_container.set_current_ids(current_ids)
return data_container
def handle_fit_transform(self, data_container: DataContainer,
context: ExecutionContext):
"""
Change the shape of the data container.
and/or
Apply any side effects based on the data container
And/or
Change the execution flow of the pipeline
"""
current_ids = self.hash(data_container)
data_container.set_current_ids(current_ids)
return self, data_container
def _create_expanded_data_container(
self, data_container: DataContainer) -> ExpandedDataContainer:
"""
Create expanded data container.
:param data_container: data container to expand
:type data_container: DataContainer
:return: expanded data container
:rtype: ExpandedDataContainer
"""
current_ids = self.hash(data_container)
data_container.set_current_ids(current_ids)
expanded_data_container = ExpandedDataContainer.create_from(
data_container)
return expanded_data_container
def handle_fit(self, data_container: DataContainer, context: ExecutionContext) -> 'ReversiblePreprocessingWrapper':
"""
Handle fit by fitting preprocessing step, and postprocessing step.
:param data_container: data container to fit on
:type data_container: DataContainer
:param context: execution context
:type context: ExecutionContext
:return: self, data_container
:rtype: (ReversiblePreprocessingWrapper, DataContainer)
"""
self["preprocessing_step"], data_container = \
self["preprocessing_step"].handle_fit_transform(data_container, context.push(self["preprocessing_step"]))
self["postprocessing_step"] = \
self["postprocessing_step"].handle_fit(data_container, context.push(self["postprocessing_step"]))
current_ids = self.hash(data_container)
data_container.set_current_ids(current_ids)
return self
def handle_transform(self, data_containers,
context: ExecutionContext) -> DataContainer:
"""
Handle transform.
:param data_containers: the data container to join
:param context: execution context
:return: transformed data container
"""
data_inputs = self.transform(
[dc.data_inputs for dc in data_containers])
data_container = DataContainer(
current_ids=data_containers[-1].current_ids,
data_inputs=data_inputs,
expected_outputs=data_containers[-1].expected_outputs)
data_container.set_data_inputs(data_inputs)
current_ids = self.hash(data_container)
data_container.set_current_ids(current_ids)
return data_container
