def __init__(
self,
steps: NamedTupleList,
pipeline_runner: BasePipelineRunner = BlockPipelineRunner(),
):
BaseStep.__init__(self)
TruncableSteps.__init__(self, steps)
self.pipeline_runner: BasePipelineRunner = pipeline_runner
def __init__(self,
phase_to_callable: Dict[ExecutionPhase, BaseTransformer],
default: OptionalType[BaseTransformer] = None):
phase, steps = zip(*phase_to_callable.items())
if default:
steps.append(default)
TruncableSteps.__init__(self, steps_as_tuple=steps)
self.phase_to_step_index = {p: i for i, p in enumerate(phase)}
self.default = default
def __init__(self,
steps_as_tuple: NamedTupleList,
joiner: NonFittableMixin = NumpyConcatenateInnerFeatures(),
n_jobs: int = None,
backend: str = "threading"):
"""
Create a feature union.
:param steps_as_tuple: the NamedTupleList of steps to process in parallel and to join.
:param joiner: What will be used to join the features. For example, ``NumpyConcatenateInnerFeatures()``.
:param n_jobs: The number of jobs for the parallelized ``joblib.Parallel`` loop in fit and in transform.
:param backend: The type of parallelization to do with ``joblib.Parallel``. Possible values: "loky", "multiprocessing", "threading", "dask" if you use dask, and more.
"""
TruncableSteps.__init__(self, steps_as_tuple)
self.joiner = joiner
self.n_jobs = n_jobs
self.backend = backend
def __init__(self,
steps_as_tuple: NamedTupleList,
joiner: BaseTransformer = None,
n_jobs: int = None,
backend: str = "threading",
cache_folder_when_no_handle: str = None):
"""
Create a feature union.
:param steps_as_tuple: the NamedTupleList of steps to process in parallel and to join.
:param joiner: What will be used to join the features. ``NumpyConcatenateInnerFeatures()`` is used by default.
:param n_jobs: The number of jobs for the parallelized ``joblib.Parallel`` loop in fit and in transform.
:param backend: The type of parallelization to do with ``joblib.Parallel``. Possible values: "loky", "multiprocessing", "threading", "dask" if you use dask, and more.
"""
if joiner is None:
joiner = NumpyConcatenateInnerFeatures()
steps_as_tuple.append(('joiner', joiner))
TruncableSteps.__init__(self, steps_as_tuple)
ForceHandleOnlyMixin.__init__(self,
cache_folder=cache_folder_when_no_handle)
self.n_jobs = n_jobs
self.backend = backend
def join_transform(self, step: TruncableSteps, data_container: DataContainer,
context: ExecutionContext) -> ZipDataContainer:
context = context.push(step)
data_container_batches = data_container.minibatches(
batch_size=self.batch_size,
keep_incomplete_batch=self.keep_incomplete_batch,
default_value_data_inputs=self.default_value_data_inputs,
default_value_expected_outputs=self.default_value_expected_outputs
)
output_data_container = []
for data_container_batch in data_container_batches:
output_data_container.append(step._transform_data_container(data_container_batch, context))
return ZipDataContainer.create_from(*output_data_container)
def __init__(self, steps: NamedTupleList):
TruncableSteps.__init__(self, steps_as_tuple=steps)
def __init__(self, preprocessing_step, postprocessing_step):
ForceMustHandleMixin.__init__(self)
TruncableSteps.__init__(self, [
("preprocessing_step", preprocessing_step),
("postprocessing_step", postprocessing_step)
])
def __init__(self, preprocessing_step, postprocessing_step):
TruncableSteps.__init__(self,
[("preprocessing_step", preprocessing_step),
("postprocessing_step", postprocessing_step)])
HandleOnlyMixin.__init__(self)
def __init__(self):
TruncableSteps.__init__(self,
hyperparams=HYPERPARAMETERS,
hyperparams_space=HYPERPARAMETERS_SPACE,
steps_as_tuple=(SomeStepWithHyperparams(),
SomeStepWithHyperparams()))
def __init__(self, steps: NamedTupleList):
BaseStep.__init__(self)
TruncableSteps.__init__(self, steps)