def set_hyperparams(self, hyperparams: HyperparameterSamples) -> BaseStep:
MetaStepMixin.set_hyperparams(self, hyperparams)
self.steps = [
s.set_hyperparams(self.wrapped.get_hyperparams())
for s in self.steps
]
return self
def set_hyperparams(self, hyperparams: HyperparameterSamples) -> BaseStep:
MetaStepMixin.set_hyperparams(self, hyperparams)
self.steps_as_tuple = [
(name, step.set_hyperparams(self.wrapped.get_hyperparams()))
for name, step in self
]
return self
def __init__(self,
scoring_function=r2_score,
joiner=NumpyConcatenateOuterBatch()):
MetaStepMixin.__init__(self)
BaseStep.__init__(self)
self.scoring_function = scoring_function
self.joiner = joiner
def __init__(self, wrapped: BaseStep, copy_op=copy.deepcopy):
BaseStep.__init__(self)
MetaStepMixin.__init__(self, wrapped)
self.set_step(wrapped)
self.steps: List[BaseStep] = []
self.copy_op = copy_op
def __init__(self, wrapped, epochs, fit_only=False, repeat_in_test_mode=False, cache_folder_when_no_handle=None):
BaseStep.__init__(self)
MetaStepMixin.__init__(self, wrapped)
ForceHandleOnlyMixin.__init__(self, cache_folder=cache_folder_when_no_handle)
self.repeat_in_test_mode = repeat_in_test_mode
self.fit_only = fit_only
self.epochs = epochs
def __init__(self, wrapped: BaseStep, copy_op=copy.deepcopy):
# TODO: set params on wrapped.
# TODO: use MetaStep*s*Mixin (plural) and review.
BaseStep.__init__(self)
MetaStepMixin.__init__(self)
self.set_step(wrapped)
self.steps: List[BaseStep] = []
self.copy_op = copy_op
def __init__(self,
wrapped,
from_data_inputs=False,
cache_folder_when_no_handle=None):
BaseStep.__init__(self)
MetaStepMixin.__init__(self, wrapped)
ForceHandleOnlyMixin.__init__(self, cache_folder_when_no_handle)
self.from_data_inputs = from_data_inputs
def set_hyperparams_space(
self, hyperparams_space: HyperparameterSpace) -> 'BaseStep':
MetaStepMixin.set_hyperparams_space(self, hyperparams_space)
self.steps = [
s.set_hyperparams_space(self.wrapped.get_hyperparams_space())
for s in self.steps
]
return self
def __init__(self, columns_selection, n_dimension=3):
BaseStep.__init__(self)
col_selector = ColumnSelector2D(columns_selection=columns_selection)
for _ in range(min(0, n_dimension - 2)):
col_selector = ForEachDataInput(col_selector)
MetaStepMixin.__init__(self, col_selector)
self.n_dimension = n_dimension
def set_hyperparams_space(
self, hyperparams_space: HyperparameterSpace) -> 'BaseStep':
MetaStepMixin.set_hyperparams_space(self, hyperparams_space)
self.steps_as_tuple = [
(name,
step.set_hyperparams_space(self.wrapped.get_hyperparams_space()))
for name, step in self
]
return self
def __init__(self,
hyperparameter_optimizer: BaseHyperparameterOptimizer,
higher_score_is_better=True,
cache_folder_when_no_handle=None):
BaseStep.__init__(self)
MetaStepMixin.__init__(self, None)
ForceHandleOnlyMixin.__init__(self, cache_folder_when_no_handle)
self.higher_score_is_better = higher_score_is_better
self.hyperparameter_optimizer = hyperparameter_optimizer
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):
"""
Wrap a scikit-learn MetaEstimatorMixin for usage in Neuraxle.
This class is similar to the SKLearnWrapper class of Neuraxle that can wrap a scikit-learn BaseEstimator.
:param wrapped: a scikit-learn object of type "MetaEstimatorMixin".
"""
MetaStepMixin.__init__(self)
BaseStep.__init__(self)
self.wrapped_sklearn_metaestimator = wrapped # TODO: use self.set_step of the MetaStepMixin instead?
def __init__(self,
wrapped,
epochs,
fit_only=False,
repeat_in_test_mode=False):
BaseStep.__init__(self)
MetaStepMixin.__init__(self, wrapped)
self.repeat_in_test_mode = repeat_in_test_mode
self.fit_only = fit_only
self.epochs = epochs
def __init__(self, wrapped: BaseStep, then_unflatten: bool = True):
BaseStep.__init__(self)
MetaStepMixin.__init__(self, wrapped)
ResumableStepMixin.__init__(self)
ForceHandleMixin.__init__(self)
self.then_unflatten = then_unflatten
self.len_di = []
self.len_eo = []
def __init__(self,
wrapped: BaseStep,
is_train_only=True,
cache_folder_when_no_handle=None):
BaseStep.__init__(self)
MetaStepMixin.__init__(self, wrapped)
ForceHandleOnlyMixin.__init__(self,
cache_folder=cache_folder_when_no_handle)
self.is_train_only = is_train_only
def __init__(self,
wrapped: BaseStep,
copy_op=copy.deepcopy,
cache_folder_when_no_handle=None):
BaseStep.__init__(self)
MetaStepMixin.__init__(self, wrapped)
ForceHandleOnlyMixin.__init__(self, cache_folder_when_no_handle)
self.set_step(wrapped)
self.steps: List[BaseStep] = []
self.copy_op = copy_op
def __init__(self, wrapped=None, scoring_function: Callable = r2_score):
"""
Base class For validation wrappers.
It has a scoring function to calculate the score for the validation split.
:param scoring_function: scoring function with two arguments (y_true, y_pred)
:type scoring_function: Callable
"""
BaseStep.__init__(self)
MetaStepMixin.__init__(self, wrapped)
self.scoring_function = scoring_function
def __init__(self,
wrapped: BaseStep,
copy_op=copy.deepcopy,
cache_folder_when_no_handle=None):
BaseStep.__init__(self)
MetaStepMixin.__init__(self, wrapped)
ForceHandleOnlyMixin.__init__(self, cache_folder_when_no_handle)
self.savers.append(TruncableJoblibStepSaver())
self.set_step(wrapped)
self.steps_as_tuple: List[NamedTupleList] = []
self.copy_op = copy_op
def __init__(self,
hyperparameter_optimizer: BaseHyperparameterOptimizer,
validation_technique: BaseCrossValidationWrapper = None,
higher_score_is_better=True):
BaseStep.__init__(self)
MetaStepMixin.__init__(self, None)
if validation_technique is None:
validation_technique = KFoldCrossValidationWrapper()
self.validation_technique = validation_technique
self.higher_score_is_better = higher_score_is_better
self.hyperparameter_optimizer = hyperparameter_optimizer
def __init__(self,
wrapped,
transform_callback_function,
fit_callback_function,
inverse_transform_callback_function=None,
more_arguments: List = tuple(),
hyperparams=None):
MetaStepMixin.__init__(self, wrapped)
BaseStep.__init__(self, hyperparams)
self.inverse_transform_callback_function = inverse_transform_callback_function
self.more_arguments = more_arguments
self.fit_callback_function = fit_callback_function
self.transform_callback_function = transform_callback_function
def __init__(self, wrapped: BaseStep, enabled: bool = True, nullified_return_value=None):
BaseStep.__init__(
self,
hyperparams=HyperparameterSamples({
OPTIONAL_ENABLED_HYPERPARAM: enabled
})
)
MetaStepMixin.__init__(self, wrapped)
ForceMustHandleMixin.__init__(self)
if nullified_return_value is None:
nullified_return_value = []
self.nullified_return_value = nullified_return_value
def __init__(
self,
wrapped: BaseStep,
cache_folder: str = DEFAULT_CACHE_FOLDER,
value_hasher: 'BaseValueHasher' = None,
):
BaseStep.__init__(self)
MetaStepMixin.__init__(self, wrapped)
self.value_hasher = value_hasher
if self.value_hasher is None:
self.value_hasher = Md5Hasher()
self.value_caching_folder = cache_folder
def __init__(self,
wrapped: BaseStep,
enabled: bool = True,
nullified_return_value=None,
cache_folder_when_no_handle=None):
BaseStep.__init__(self,
hyperparams=HyperparameterSamples(
{OPTIONAL_ENABLED_HYPERPARAM: enabled}))
MetaStepMixin.__init__(self, wrapped)
ForceHandleOnlyMixin.__init__(self, cache_folder_when_no_handle)
if nullified_return_value is None:
nullified_return_value = []
self.nullified_return_value = nullified_return_value
def __init__(self,
wrapped: BaseStep,
test_size: float,
scoring_function=r2_score,
run_validation_split_in_test_mode=True):
"""
: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)
"""
MetaStepMixin.__init__(self, wrapped)
BaseStep.__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
def __init__(
self,
wrapped=None,
n_iter: int = 10,
higher_score_is_better: bool = True,
validation_technique: BaseCrossValidation = KFoldCrossValidation(),
refit=True,
):
if wrapped is not None:
MetaStepMixin.__init__(self, wrapped)
BaseStep.__init__(self)
self.n_iter = n_iter
self.higher_score_is_better = higher_score_is_better
self.validation_technique: BaseCrossValidation = validation_technique
self.refit = refit
def __init__(self,
wrapped: BaseStep,
metrics: Dict,
name: str = None,
print_metrics=False,
print_fun=print):
BaseStep.__init__(self, name=name)
MetaStepMixin.__init__(self, wrapped)
self.metrics: Dict = metrics
self._initialize_metrics(metrics)
self.print_metrics = print_metrics
self.print_fun = print_fun
self.enabled = True
def update_hyperparams(self, hyperparams: HyperparameterSamples) -> BaseStep:
"""
Update the step hyperparameters without removing the already-set hyperparameters.
Please refer to :func:`~BaseStep.update_hyperparams`.
:param hyperparams: hyperparams to update
:type hyperparams: HyperparameterSamples
:return: self
:rtype: BaseStep
.. seealso::
:func:`~BaseStep.update_hyperparams`,
:class:`HyperparameterSamples`
"""
MetaStepMixin.update_hyperparams(self, hyperparams)
self.steps = [s.set_hyperparams(self.wrapped.get_hyperparams()) for s in self.steps]
return self
def __init__(self,
wrapped: BaseStep,
auto_ml_algorithm: AutoMLAlgorithm,
hyperparams_repository: HyperparamsRepository = None,
n_iters: int = 100,
refit=True):
BaseStep.__init__(self)
self.refit = refit
auto_ml_algorithm = auto_ml_algorithm.set_step(wrapped)
MetaStepMixin.__init__(self, auto_ml_algorithm)
NonTransformableMixin.__init__(self)
if hyperparams_repository is None:
hyperparams_repository = InMemoryHyperparamsRepository()
self.hyperparams_repository = hyperparams_repository
self.n_iters = n_iters
def __init__(self, wrapped: BaseStep, enabled: bool = True, nullified_return_value=None,
cache_folder_when_no_handle=None, use_hyperparameter_space=True, nullify_hyperparams=True):
hyperparameter_space = HyperparameterSpace({
OPTIONAL_ENABLED_HYPERPARAM: Boolean()
}) if use_hyperparameter_space else {}
BaseStep.__init__(
self,
hyperparams=HyperparameterSamples({
OPTIONAL_ENABLED_HYPERPARAM: enabled
}),
hyperparams_space=hyperparameter_space
)
MetaStepMixin.__init__(self, wrapped)
ForceHandleOnlyMixin.__init__(self, cache_folder_when_no_handle)
if nullified_return_value is None:
nullified_return_value = []
self.nullified_return_value = nullified_return_value
self.nullify_hyperparams = nullify_hyperparams
