explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-10 16:22:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix kb/kb.pyx.

Browse Source
This commit is contained in:
Raphael Mitsch 2023-07-03 09:53:23 +02:00
parent 8d770a6c8f
commit 349f190122
1 changed files with 35 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
spacy/kb/kb.pyx
View File

@ -11,8 +11,9 @@ from ..errors import Errors
cdef class KnowledgeBase: cdef class KnowledgeBase:
"""A `KnowledgeBase` instance stores unique identifiers for entities and their textual aliases, """A `KnowledgeBase` instance stores unique identifiers for entities and
to support entity linking of named entities to real-world concepts. their textual aliases, to support entity linking of named entities to
real-world concepts.
This is an abstract class and requires its operations to be implemented. This is an abstract class and requires its operations to be implemented.
DOCS: https://spacy.io/api/kb DOCS: https://spacy.io/api/kb
@ -30,10 +31,13 @@ cdef class KnowledgeBase:
self.entity_vector_length = entity_vector_length self.entity_vector_length = entity_vector_length
self.mem = Pool() self.mem = Pool()
def get_candidates_batch(self, mentions: Iterable[Span]) -> Iterable[Iterable[Candidate]]: def get_candidates_batch(
self, mentions: Iterable[Span]
) -> Iterable[Iterable[Candidate]]:
""" """
Return candidate entities for specified texts. Each candidate defines the entity, the original alias, Return candidate entities for specified texts. Each candidate defines
and the prior probability of that alias resolving to that entity. the entity, the original alias, and the prior probability of that
alias resolving to that entity.
If no candidate is found for a given text, an empty list is returned. If no candidate is found for a given text, an empty list is returned.
mentions (Iterable[Span]): Mentions for which to get candidates. mentions (Iterable[Span]): Mentions for which to get candidates.
RETURNS (Iterable[Iterable[Candidate]]): Identified candidates. RETURNS (Iterable[Iterable[Candidate]]): Identified candidates.
@ -42,14 +46,17 @@ cdef class KnowledgeBase:
def get_candidates(self, mention: Span) -> Iterable[Candidate]: def get_candidates(self, mention: Span) -> Iterable[Candidate]:
""" """
Return candidate entities for specified text. Each candidate defines the entity, the original alias, Return candidate entities for specified text. Each candidate defines
the entity, the original alias,
and the prior probability of that alias resolving to that entity. and the prior probability of that alias resolving to that entity.
If the no candidate is found for a given text, an empty list is returned. If the no candidate is found for a given text, an empty list is returned.
mention (Span): Mention for which to get candidates. mention (Span): Mention for which to get candidates.
RETURNS (Iterable[Candidate]): Identified candidates. RETURNS (Iterable[Candidate]): Identified candidates.
""" """
raise NotImplementedError( raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="get_candidates", name=self.__name__) Errors.E1045.format(
parent="KnowledgeBase", method="get_candidates", name=self.__name__
)
) )
def get_vectors(self, entities: Iterable[str]) -> Iterable[Iterable[float]]: def get_vectors(self, entities: Iterable[str]) -> Iterable[Iterable[float]]:
@ -67,7 +74,9 @@ cdef class KnowledgeBase:
RETURNS (Iterable[float]): Vector for specified entity. RETURNS (Iterable[float]): Vector for specified entity.
""" """
raise NotImplementedError( raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="get_vector", name=self.__name__) Errors.E1045.format(
parent="KnowledgeBase", method="get_vector", name=self.__name__
)
) )
def to_bytes(self, **kwargs) -> bytes: def to_bytes(self, **kwargs) -> bytes:
@ -75,7 +84,9 @@ cdef class KnowledgeBase:
RETURNS (bytes): Current state as binary string. RETURNS (bytes): Current state as binary string.
""" """
raise NotImplementedError( raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="to_bytes", name=self.__name__) Errors.E1045.format(
parent="KnowledgeBase", method="to_bytes", name=self.__name__
)
) )
def from_bytes(self, bytes_data: bytes, *, exclude: Tuple[str] = tuple()): def from_bytes(self, bytes_data: bytes, *, exclude: Tuple[str] = tuple()):
@ -84,25 +95,35 @@ cdef class KnowledgeBase:
exclude (Tuple[str]): Properties to exclude when restoring KB. exclude (Tuple[str]): Properties to exclude when restoring KB.
""" """
raise NotImplementedError( raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="from_bytes", name=self.__name__) Errors.E1045.format(
parent="KnowledgeBase", method="from_bytes", name=self.__name__
)
) )
def to_disk(self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()) -> None: def to_disk(
self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()
) -> None:
""" """
Write KnowledgeBase content to disk. Write KnowledgeBase content to disk.
path (Union[str, Path]): Target file path. path (Union[str, Path]): Target file path.
exclude (Iterable[str]): List of components to exclude. exclude (Iterable[str]): List of components to exclude.
""" """
raise NotImplementedError( raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="to_disk", name=self.__name__) Errors.E1045.format(
parent="KnowledgeBase", method="to_disk", name=self.__name__
)
) )
def from_disk(self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()) -> None: def from_disk(
self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()
) -> None:
""" """
Load KnowledgeBase content from disk. Load KnowledgeBase content from disk.
path (Union[str, Path]): Target file path. path (Union[str, Path]): Target file path.
exclude (Iterable[str]): List of components to exclude. exclude (Iterable[str]): List of components to exclude.
""" """
raise NotImplementedError( raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="from_disk", name=self.__name__) Errors.E1045.format(
parent="KnowledgeBase", method="from_disk", name=self.__name__
)
) )