def apply(self, docs=None, split=0, train=False, clear=True, **kwargs):
"""Apply features to the specified candidates.
:param docs: If provided, apply features to all the candidates in these
documents.
:param split: If docs is None, apply features to the candidates in this
particular split.
:param train: Whether or not to update the global key set of features and
the features of candidates.
:param clear: Whether or not to clear the features table before applying
features.
"""
if docs:
# Call apply on the specified docs for all splits
split = ALL_SPLITS
super(Featurizer, self).apply(
docs, split=split, train=train, clear=clear, **kwargs
)
# Needed to sync the bulk operations
self.session.commit()
else:
# Only grab the docs containing candidates from the given split.
split_docs = get_docs_from_split(
self.session, self.candidate_classes, split
)
super(Featurizer, self).apply(
split_docs, split=split, train=train, clear=clear, **kwargs
)
# Needed to sync the bulk operations
self.session.commit()
def apply( # type: ignore
self,
docs: Optional[Collection[Document]] = None,
split: int = 0,
train: bool = False,
clear: bool = True,
parallelism: Optional[int] = None,
progress_bar: bool = True,
) -> None:
"""Apply features to the specified candidates.
:param docs: If provided, apply features to all the candidates in these
documents.
:param split: If docs is None, apply features to the candidates in this
particular split.
:type split: int
:param train: Whether or not to update the global key set of features
and the features of candidates.
:type train: bool
:param clear: Whether or not to clear the features table before
applying features.
:type clear: bool
:param parallelism: How many threads to use for extraction. This will
override the parallelism value used to initialize the Featurizer if
it is provided.
:type parallelism: int
:param progress_bar: Whether or not to display a progress bar. The
progress bar is measured per document.
:type progress_bar: bool
"""
if docs:
# Call apply on the specified docs for all splits
# TODO: split is int
split = ALL_SPLITS # type: ignore
super().apply(
docs,
split=split,
train=train,
clear=clear,
parallelism=parallelism,
progress_bar=progress_bar,
)
# Needed to sync the bulk operations
self.session.commit()
else:
# Only grab the docs containing candidates from the given split.
split_docs = get_docs_from_split(
self.session, self.candidate_classes, split
)
super().apply(
split_docs,
split=split,
train=train,
clear=clear,
parallelism=parallelism,
progress_bar=progress_bar,
)
# Needed to sync the bulk operations
self.session.commit()
def apply(self,
docs=None,
split=0,
train=False,
lfs=None,
clear=True,
**kwargs):
"""Apply the labels of the specified candidates based on the provided LFs.
:param docs: If provided, apply the LFs to all the candidates in these
documents.
:param split: If docs is None, apply the LFs to the candidates in this
particular split.
:param train: Whether or not to update the global key set of labels and
the labels of candidates.
:param lfs: A list of lists of labeling functions to apply. Each list
should correspond with the candidate_classes used to initialize the
Labeler.
:param clear: Whether or not to clear the labels table before applying
these LFs.
"""
if lfs is None:
raise ValueError("Please provide a list of labeling functions.")
if len(lfs) != len(self.candidate_classes):
raise ValueError("Please provide LFs for each candidate class.")
self.lfs = lfs
if docs:
# Call apply on the specified docs for all splits
split = ALL_SPLITS
super(Labeler, self).apply(docs,
split=split,
train=train,
lfs=self.lfs,
clear=clear,
**kwargs)
# Needed to sync the bulk operations
self.session.commit()
else:
# Only grab the docs containing candidates from the given split.
split_docs = get_docs_from_split(self.session,
self.candidate_classes, split)
super(Labeler, self).apply(split_docs,
split=split,
train=train,
lfs=self.lfs,
clear=clear,
**kwargs)
# Needed to sync the bulk operations
self.session.commit()
def apply(
self,
docs=None,
split=0,
train=False,
lfs=None,
clear=True,
parallelism=None,
progress_bar=True,
):
"""Apply the labels of the specified candidates based on the provided LFs.
:param docs: If provided, apply the LFs to all the candidates in these
documents.
:param split: If docs is None, apply the LFs to the candidates in this
particular split.
:type split: int
:param train: Whether or not to update the global key set of labels and
the labels of candidates.
:type train: bool
:param lfs: A list of lists of labeling functions to apply. Each list
should correspond with the candidate_classes used to initialize the
Labeler.
:type lfs: list of lists
:param clear: Whether or not to clear the labels table before applying
these LFs.
:type clear: bool
:param parallelism: How many threads to use for extraction. This will
override the parallelism value used to initialize the Labeler if
it is provided.
:type parallelism: int
:param progress_bar: Whether or not to display a progress bar. The
progress bar is measured per document.
:type progress_bar: bool
:raises ValueError: If labeling functions are not provided for each
candidate class.
"""
if lfs is None:
raise ValueError("Please provide a list of labeling functions.")
if len(lfs) != len(self.candidate_classes):
raise ValueError("Please provide LFs for each candidate class.")
self.lfs = lfs
if docs:
# Call apply on the specified docs for all splits
split = ALL_SPLITS
super(Labeler, self).apply(
docs,
split=split,
train=train,
lfs=self.lfs,
clear=clear,
parallelism=parallelism,
progress_bar=progress_bar,
)
# Needed to sync the bulk operations
self.session.commit()
else:
# Only grab the docs containing candidates from the given split.
split_docs = get_docs_from_split(self.session,
self.candidate_classes, split)
super(Labeler, self).apply(
split_docs,
split=split,
train=train,
lfs=self.lfs,
clear=clear,
parallelism=parallelism,
progress_bar=progress_bar,
)
# Needed to sync the bulk operations
self.session.commit()
