mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-10 19:57:17 +03:00
f98b41c390
* Add vector deduplication * Add `Vocab.deduplicate_vectors()` * Always run deduplication in `spacy init vectors` * Clean up a few vector-related error messages and docs examples * Always unique with numpy * Fix types
80 lines
2.7 KiB
Python
80 lines
2.7 KiB
Python
from typing import Callable, Iterator, Optional, Union, List, Dict
|
|
from typing import Any, Iterable
|
|
from thinc.types import Floats1d, FloatsXd
|
|
from . import Language
|
|
from .strings import StringStore
|
|
from .lexeme import Lexeme
|
|
from .lookups import Lookups
|
|
from .morphology import Morphology
|
|
from .tokens import Doc, Span
|
|
from .vectors import Vectors
|
|
from pathlib import Path
|
|
|
|
def create_vocab(
|
|
lang: Optional[str], defaults: Any, vectors_name: Optional[str] = ...
|
|
) -> Vocab: ...
|
|
|
|
class Vocab:
|
|
cfg: Dict[str, Any]
|
|
get_noun_chunks: Optional[Callable[[Union[Doc, Span]], Iterator[Span]]]
|
|
lookups: Lookups
|
|
morphology: Morphology
|
|
strings: StringStore
|
|
vectors: Vectors
|
|
writing_system: Dict[str, Any]
|
|
def __init__(
|
|
self,
|
|
lex_attr_getters: Optional[Dict[str, Callable[[str], Any]]] = ...,
|
|
strings: Optional[Union[List[str], StringStore]] = ...,
|
|
lookups: Optional[Lookups] = ...,
|
|
oov_prob: float = ...,
|
|
vectors_name: Optional[str] = ...,
|
|
writing_system: Dict[str, Any] = ...,
|
|
get_noun_chunks: Optional[Callable[[Union[Doc, Span]], Iterator[Span]]] = ...,
|
|
) -> None: ...
|
|
@property
|
|
def lang(self) -> str: ...
|
|
def __len__(self) -> int: ...
|
|
def add_flag(
|
|
self, flag_getter: Callable[[str], bool], flag_id: int = ...
|
|
) -> int: ...
|
|
def __contains__(self, key: str) -> bool: ...
|
|
def __iter__(self) -> Iterator[Lexeme]: ...
|
|
def __getitem__(self, id_or_string: Union[str, int]) -> Lexeme: ...
|
|
@property
|
|
def vectors_length(self) -> int: ...
|
|
def reset_vectors(
|
|
self, *, width: Optional[int] = ..., shape: Optional[int] = ...
|
|
) -> None: ...
|
|
def deduplicate_vectors(self) -> None: ...
|
|
def prune_vectors(self, nr_row: int, batch_size: int = ...) -> Dict[str, float]: ...
|
|
def get_vector(
|
|
self,
|
|
orth: Union[int, str],
|
|
minn: Optional[int] = ...,
|
|
maxn: Optional[int] = ...,
|
|
) -> FloatsXd: ...
|
|
def set_vector(self, orth: Union[int, str], vector: Floats1d) -> None: ...
|
|
def has_vector(self, orth: Union[int, str]) -> bool: ...
|
|
def to_disk(
|
|
self, path: Union[str, Path], *, exclude: Iterable[str] = ...
|
|
) -> None: ...
|
|
def from_disk(
|
|
self, path: Union[str, Path], *, exclude: Iterable[str] = ...
|
|
) -> Vocab: ...
|
|
def to_bytes(self, *, exclude: Iterable[str] = ...) -> bytes: ...
|
|
def from_bytes(
|
|
self, bytes_data: bytes, *, exclude: Iterable[str] = ...
|
|
) -> Vocab: ...
|
|
|
|
def pickle_vocab(vocab: Vocab) -> Any: ...
|
|
def unpickle_vocab(
|
|
sstore: StringStore,
|
|
vectors: Any,
|
|
morphology: Any,
|
|
_unused_object: Any,
|
|
lex_attr_getters: Any,
|
|
lookups: Any,
|
|
get_noun_chunks: Any,
|
|
) -> Vocab: ...
|