mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 07:57:35 +03:00
e61c8d2975
* Add SpanRuler component Add a `SpanRuler` component similar to `EntityRuler` that saves a list of matched spans to `Doc.spans[spans_key]`. The matches from the token and phrase matchers are deduplicated and sorted before assignment but are not otherwise filtered. * Update spacy/pipeline/span_ruler.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix cast * Add self.key property * Use number of patterns as length * Remove patterns kwarg from init * Update spacy/tests/pipeline/test_span_ruler.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Add options for spans filter and setting to ents * Add `spans_filter` option as a registered function' * Make `spans_key` optional and if `None`, set to `doc.ents` instead of `doc.spans[spans_key]`. * Update and generalize tests * Add test for setting doc.ents, fix key property type * Fix typing * Allow independent doc.spans and doc.ents * If `spans_key` is set, set `doc.spans` with `spans_filter`. * If `annotate_ents` is set, set `doc.ents` with `ents_fitler`. * Use `util.filter_spans` by default as `ents_filter`. * Use a custom warning if the filter does not work for `doc.ents`. * Enable use of SpanC.id in Span * Support id in SpanRuler as Span.id * Update types * `id` can only be provided as string (already by `PatternType` definition) * Update all uses of Span.id/ent_id in Doc * Rename Span id kwarg to span_id * Update types and docs * Add ents filter to mimic EntityRuler overwrite_ents * Refactor `ents_filter` to take `entities, spans` args for more filtering options * Give registered filters more descriptive names * Allow registered `filter_spans` filter (`spacy.first_longest_spans_filter.v1`) to take any number of `Iterable[Span]` objects as args so it can be used for spans filter or ents filter * Implement future entity ruler as span ruler Implement a compatible `entity_ruler` as `future_entity_ruler` using `SpanRuler` as the underlying component: * Add `sort_key` and `sort_reverse` to allow the sorting behavior to be customized. (Necessary for the same sorting/filtering as in `EntityRuler`.) * Implement `overwrite_overlapping_ents_filter` and `preserve_existing_ents_filter` to support `EntityRuler.overwrite_ents` settings. * Add `remove_by_id` to support `EntityRuler.remove` functionality. * Refactor `entity_ruler` tests to parametrize all tests to test both `entity_ruler` and `future_entity_ruler` * Implement `SpanRuler.token_patterns` and `SpanRuler.phrase_patterns` properties. Additional changes: * Move all config settings to top-level attributes to avoid duplicating settings in the config vs. `span_ruler/cfg`. (Also avoids a lot of casting.) * Format * Fix filter make method name * Refactor to use same error for removing by label or ID * Also provide existing spans to spans filter * Support ids property * Remove token_patterns and phrase_patterns * Update docstrings * Add span ruler docs * Fix types * Apply suggestions from code review Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Move sorting into filters * Check for all tokens in seen tokens in entity ruler filters * Remove registered sort key * Set Token.ent_id in a backwards-compatible way in Doc.set_ents * Remove sort options from API docs * Update docstrings * Rename entity ruler filters * Fix and parameterize scoring * Add id to Span API docs * Fix typo in API docs * Include explicit labeled=True for scorer Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
128 lines
3.5 KiB
Python
128 lines
3.5 KiB
Python
from typing import Callable, Protocol, Iterator, Optional, Union, Tuple, Any, overload
|
|
from thinc.types import Floats1d, Ints2d, FloatsXd
|
|
from .doc import Doc
|
|
from .token import Token
|
|
from .underscore import Underscore
|
|
from ..lexeme import Lexeme
|
|
from ..vocab import Vocab
|
|
|
|
class SpanMethod(Protocol):
|
|
def __call__(self: Span, *args: Any, **kwargs: Any) -> Any: ... # type: ignore[misc]
|
|
|
|
class Span:
|
|
@classmethod
|
|
def set_extension(
|
|
cls,
|
|
name: str,
|
|
default: Optional[Any] = ...,
|
|
getter: Optional[Callable[[Span], Any]] = ...,
|
|
setter: Optional[Callable[[Span, Any], None]] = ...,
|
|
method: Optional[SpanMethod] = ...,
|
|
force: bool = ...,
|
|
) -> None: ...
|
|
@classmethod
|
|
def get_extension(
|
|
cls, name: str
|
|
) -> Tuple[
|
|
Optional[Any],
|
|
Optional[SpanMethod],
|
|
Optional[Callable[[Span], Any]],
|
|
Optional[Callable[[Span, Any], None]],
|
|
]: ...
|
|
@classmethod
|
|
def has_extension(cls, name: str) -> bool: ...
|
|
@classmethod
|
|
def remove_extension(
|
|
cls, name: str
|
|
) -> Tuple[
|
|
Optional[Any],
|
|
Optional[SpanMethod],
|
|
Optional[Callable[[Span], Any]],
|
|
Optional[Callable[[Span, Any], None]],
|
|
]: ...
|
|
def __init__(
|
|
self,
|
|
doc: Doc,
|
|
start: int,
|
|
end: int,
|
|
label: Union[str, int] = ...,
|
|
vector: Optional[Floats1d] = ...,
|
|
vector_norm: Optional[float] = ...,
|
|
kb_id: Union[str, int] = ...,
|
|
span_id: Union[str, int] = ...,
|
|
) -> None: ...
|
|
def __richcmp__(self, other: Span, op: int) -> bool: ...
|
|
def __hash__(self) -> int: ...
|
|
def __len__(self) -> int: ...
|
|
def __repr__(self) -> str: ...
|
|
@overload
|
|
def __getitem__(self, i: int) -> Token: ...
|
|
@overload
|
|
def __getitem__(self, i: slice) -> Span: ...
|
|
def __iter__(self) -> Iterator[Token]: ...
|
|
@property
|
|
def _(self) -> Underscore: ...
|
|
def as_doc(self, *, copy_user_data: bool = ...) -> Doc: ...
|
|
def get_lca_matrix(self) -> Ints2d: ...
|
|
def similarity(self, other: Union[Doc, Span, Token, Lexeme]) -> float: ...
|
|
@property
|
|
def doc(self) -> Doc: ...
|
|
@property
|
|
def vocab(self) -> Vocab: ...
|
|
@property
|
|
def sent(self) -> Span: ...
|
|
@property
|
|
def ents(self) -> Tuple[Span]: ...
|
|
@property
|
|
def has_vector(self) -> bool: ...
|
|
@property
|
|
def vector(self) -> Floats1d: ...
|
|
@property
|
|
def vector_norm(self) -> float: ...
|
|
@property
|
|
def tensor(self) -> FloatsXd: ...
|
|
@property
|
|
def sentiment(self) -> float: ...
|
|
@property
|
|
def text(self) -> str: ...
|
|
@property
|
|
def text_with_ws(self) -> str: ...
|
|
@property
|
|
def noun_chunks(self) -> Iterator[Span]: ...
|
|
@property
|
|
def root(self) -> Token: ...
|
|
def char_span(
|
|
self,
|
|
start_idx: int,
|
|
end_idx: int,
|
|
label: int = ...,
|
|
kb_id: int = ...,
|
|
vector: Optional[Floats1d] = ...,
|
|
) -> Span: ...
|
|
@property
|
|
def conjuncts(self) -> Tuple[Token]: ...
|
|
@property
|
|
def lefts(self) -> Iterator[Token]: ...
|
|
@property
|
|
def rights(self) -> Iterator[Token]: ...
|
|
@property
|
|
def n_lefts(self) -> int: ...
|
|
@property
|
|
def n_rights(self) -> int: ...
|
|
@property
|
|
def subtree(self) -> Iterator[Token]: ...
|
|
start: int
|
|
end: int
|
|
start_char: int
|
|
end_char: int
|
|
label: int
|
|
kb_id: int
|
|
ent_id: int
|
|
ent_id_: str
|
|
@property
|
|
def orth_(self) -> str: ...
|
|
@property
|
|
def lemma_(self) -> str: ...
|
|
label_: str
|
|
kb_id_: str
|