def __init__(self, operator=None, **hyperparams):
if operator is None:
raise ValueError("Operator is a required argument.")
self._hyperparams = hyperparams
resampler_instance = OrigModel(**self._hyperparams)
super(EditedNearestNeighboursImpl,
self).__init__(operator=operator, resampler=resampler_instance)
def __init__(self, operator = None, sampling_strategy='auto', random_state=None,
n_neighbors=None, n_seeds_S=1, n_jobs=1):
if operator is None:
raise ValueError("Operator is a required argument.")
self._hyperparams = {
'sampling_strategy': sampling_strategy,
'random_state': random_state,
'n_neighbors': n_neighbors,
'n_seeds_S': n_seeds_S,
'n_jobs': n_jobs}
resampler_instance = OrigModel(**self._hyperparams)
super(CondensedNearestNeighbourImpl, self).__init__(
operator = operator,
resampler = resampler_instance)
def __init__(self, operator = None, sampling_strategy='auto', random_state=None,
n_neighbors=3, max_iter=100, kind_sel='all', n_jobs=1):
if operator is None:
raise ValueError("Operator is a required argument.")
self._hyperparams = {
'sampling_strategy': sampling_strategy,
'random_state': random_state,
'n_neighbors': n_neighbors,
'max_iter': max_iter,
'kind_sel': kind_sel,
'n_jobs': n_jobs}
resampler_instance = OrigModel(**self._hyperparams)
super(RepeatedEditedNearestNeighboursImpl, self).__init__(
operator = operator,
resampler = resampler_instance)
def __init__(self,
operator=None,
estimator=None,
sampling_strategy='auto',
random_state=None,
cv=5,
n_jobs=1):
if operator is None:
raise ValueError("Operator is a required argument.")
self._hyperparams = {
'estimator': estimator,
'sampling_strategy': sampling_strategy,
'random_state': random_state,
'cv': cv,
'n_jobs': n_jobs
}
resampler_instance = OrigModel(**self._hyperparams)
super(InstanceHardnessThresholdImpl,
self).__init__(operator=operator, resampler=resampler_instance)
def __init__(
self,
operator=None,
estimator=None,
sampling_strategy="auto",
random_state=None,
cv=5,
n_jobs=1,
):
if operator is None:
raise ValueError("Operator is a required argument.")
self._hyperparams = {
"estimator": estimator,
"sampling_strategy": sampling_strategy,
"random_state": random_state,
"cv": cv,
"n_jobs": n_jobs,
}
resampler_instance = OrigModel(**self._hyperparams)
super(_InstanceHardnessThresholdImpl,
self).__init__(operator=operator, resampler=resampler_instance)
def __init__(
self,
operator=None,
sampling_strategy="auto",
random_state=None,
n_neighbors=None,
n_seeds_S=1,
n_jobs=1,
):
if operator is None:
raise ValueError("Operator is a required argument.")
self._hyperparams = {
"sampling_strategy": sampling_strategy,
"random_state": random_state,
"n_neighbors": n_neighbors,
"n_seeds_S": n_seeds_S,
"n_jobs": n_jobs,
}
resampler_instance = OrigModel(**self._hyperparams)
super(CondensedNearestNeighbourImpl,
self).__init__(operator=operator, resampler=resampler_instance)
def __init__(self,
operator=None,
sampling_strategy='auto',
random_state=None,
n_neighbors=3,
kind_sel='all',
allow_minority=False,
n_jobs=1):
if operator is None:
raise ValueError("Operator is a required argument.")
self._hyperparams = {
'sampling_strategy': sampling_strategy,
'random_state': random_state,
'n_neighbors': n_neighbors,
'kind_sel': kind_sel,
'allow_minority': allow_minority,
'n_jobs': n_jobs
}
resampler_instance = OrigModel(**self._hyperparams)
super(AllKNNImpl, self).__init__(operator=operator,
resampler=resampler_instance)