def __init__(
self,
pipeline: Union[BaseStep, NamedTupleList],
validation_size: int = None,
batch_size: int = None,
batch_metrics: Dict[str, Callable] = None,
shuffle_in_each_epoch_at_train: bool = True,
seed: int = None,
n_epochs: int = 1,
epochs_metrics: Dict[str, Callable] = None,
scoring_function: Callable = None,
cache_folder: str = None,
print_epoch_metrics=False,
print_batch_metrics=False
):
"""
:param pipeline: pipeline to wrap with an epoch repeater, a validation split wrapper, and a mini batch sequential pipeline
:param validation_size: ratio for validation size between 0 and 1
:param batch_size: batch size for the mini batch sequential pipeline
:param batch_metrics: metrics to calculate for each processed mini batch
:param shuffle_in_each_epoch_at_train:
:param seed: random seed for the data shuffling that can be done at each epoch when the param shuffle_in_each_epoch_at_train is True
:param n_epochs: number of epochs
:param epochs_metrics: metrics to calculate for each epoch
:param scoring_function: scoring function with two arguments (y_true, y_pred)
:param cache_folder: cache folder to be used inside the pipeline
:param print_epoch_metrics: whether or not to print epoch metrics
:param print_batch_metrics: whether or not to print batch metrics
"""
if epochs_metrics is None:
epochs_metrics = {}
if batch_metrics is None:
batch_metrics = {}
self.final_scoring_metric = scoring_function
self.epochs_metrics = epochs_metrics
self.n_epochs = n_epochs
self.shuffle_in_each_epoch_at_train = shuffle_in_each_epoch_at_train
self.batch_size = batch_size
self.batch_metrics = batch_metrics
self.validation_size = validation_size
self.print_batch_metrics = print_batch_metrics
self.print_epoch_metrics = print_epoch_metrics
wrapped = pipeline
wrapped = self._create_mini_batch_pipeline(wrapped)
if shuffle_in_each_epoch_at_train:
wrapped = TrainShuffled(wrapped=wrapped, seed=seed)
wrapped = self._create_validation_split(wrapped)
wrapped = self._create_epoch_repeater(wrapped)
BaseStep.__init__(self)
MetaStepMixin.__init__(self, wrapped)
EvaluableStepMixin.__init__(self)
ForceHandleMixin.__init__(self, cache_folder)
def __init__(self, wrapped=None, scoring_function=r2_score, joiner=NumpyConcatenateOuterBatch(),
cache_folder_when_no_handle=None,
split_data_container_during_fit=True, predict_after_fit=True):
BaseValidation.__init__(self, wrapped=wrapped, scoring_function=scoring_function)
ForceHandleOnlyMixin.__init__(self, cache_folder=cache_folder_when_no_handle)
EvaluableStepMixin.__init__(self)
self.split_data_container_during_fit = split_data_container_during_fit
self.predict_after_fit = predict_after_fit
self.joiner = joiner
def __init__(self,
scoring_function=r2_score,
joiner=NumpyConcatenateOuterBatch(),
cache_folder_when_no_handle=None):
BaseValidation.__init__(self, scoring_function)
ForceHandleOnlyMixin.__init__(self,
cache_folder=cache_folder_when_no_handle)
EvaluableStepMixin.__init__(self)
self.joiner = joiner
def __init__(self,
wrapped: BaseStep = None,
test_size: float = 0.2,
scoring_function=r2_score,
run_validation_split_in_test_mode=True,
metrics_already_enabled=True,
cache_folder_when_no_handle=None):
"""
:param wrapped: wrapped step
:param test_size: ratio for test size between 0 and 1
:param scoring_function: scoring function with two arguments (y_true, y_pred)
"""
BaseStep.__init__(self)
MetaStepMixin.__init__(self, wrapped)
ForceHandleOnlyMixin.__init__(self, cache_folder_when_no_handle)
EvaluableStepMixin.__init__(self)
self.run_validation_split_in_test_mode = run_validation_split_in_test_mode
self.test_size = test_size
self.scoring_function = scoring_function
self.metrics_enabled = metrics_already_enabled