2020-10-05 20:50:14 +00:00
|
|
|
from typing import Optional, Union, List, Dict, Tuple, Iterable, Any, Callable, Sequence
|
2022-09-29 12:24:40 +00:00
|
|
|
import warnings
|
2019-12-22 00:53:56 +00:00
|
|
|
from collections import defaultdict
|
2020-07-22 11:42:59 +00:00
|
|
|
from pathlib import Path
|
2019-02-10 11:14:51 +00:00
|
|
|
import srsly
|
|
|
|
|
2020-10-05 15:43:42 +00:00
|
|
|
from .pipe import Pipe
|
|
|
|
from ..training import Example
|
2020-07-22 11:42:59 +00:00
|
|
|
from ..language import Language
|
2021-05-31 08:20:27 +00:00
|
|
|
from ..errors import Errors, Warnings
|
2021-08-10 13:13:39 +00:00
|
|
|
from ..util import ensure_path, to_disk, from_disk, SimpleFrozenList, registry
|
2020-02-16 17:17:47 +00:00
|
|
|
from ..tokens import Doc, Span
|
2019-02-10 11:14:51 +00:00
|
|
|
from ..matcher import Matcher, PhraseMatcher
|
2023-01-10 09:36:17 +00:00
|
|
|
from ..matcher.levenshtein import levenshtein_compare
|
2020-11-03 14:47:18 +00:00
|
|
|
from ..scorer import get_ner_prf
|
2019-07-08 15:28:28 +00:00
|
|
|
|
2019-02-10 11:14:51 +00:00
|
|
|
|
2019-07-10 10:03:05 +00:00
|
|
|
DEFAULT_ENT_ID_SEP = "||"
|
2020-07-22 11:42:59 +00:00
|
|
|
PatternType = Dict[str, Union[str, List[Dict[str, Any]]]]
|
|
|
|
|
|
|
|
|
|
|
|
@Language.factory(
|
|
|
|
"entity_ruler",
|
|
|
|
assigns=["doc.ents", "token.ent_type", "token.ent_iob"],
|
|
|
|
default_config={
|
|
|
|
"phrase_matcher_attr": None,
|
2023-01-10 09:36:17 +00:00
|
|
|
"matcher_fuzzy_compare": {"@misc": "spacy.levenshtein_compare.v1"},
|
2020-08-07 12:43:47 +00:00
|
|
|
"validate": False,
|
2020-07-22 11:42:59 +00:00
|
|
|
"overwrite_ents": False,
|
|
|
|
"ent_id_sep": DEFAULT_ENT_ID_SEP,
|
2021-08-10 13:13:39 +00:00
|
|
|
"scorer": {"@scorers": "spacy.entity_ruler_scorer.v1"},
|
2020-07-22 11:42:59 +00:00
|
|
|
},
|
2020-09-24 08:27:33 +00:00
|
|
|
default_score_weights={
|
|
|
|
"ents_f": 1.0,
|
|
|
|
"ents_p": 0.0,
|
|
|
|
"ents_r": 0.0,
|
|
|
|
"ents_per_type": None,
|
|
|
|
},
|
2020-07-22 11:42:59 +00:00
|
|
|
)
|
|
|
|
def make_entity_ruler(
|
|
|
|
nlp: Language,
|
|
|
|
name: str,
|
|
|
|
phrase_matcher_attr: Optional[Union[int, str]],
|
2023-01-10 09:36:17 +00:00
|
|
|
matcher_fuzzy_compare: Callable,
|
2020-08-07 12:43:47 +00:00
|
|
|
validate: bool,
|
2020-07-22 11:42:59 +00:00
|
|
|
overwrite_ents: bool,
|
|
|
|
ent_id_sep: str,
|
2021-08-10 13:13:39 +00:00
|
|
|
scorer: Optional[Callable],
|
2020-07-22 11:42:59 +00:00
|
|
|
):
|
|
|
|
return EntityRuler(
|
|
|
|
nlp,
|
|
|
|
name,
|
|
|
|
phrase_matcher_attr=phrase_matcher_attr,
|
2023-01-10 09:36:17 +00:00
|
|
|
matcher_fuzzy_compare=matcher_fuzzy_compare,
|
2020-08-07 12:43:47 +00:00
|
|
|
validate=validate,
|
2020-07-22 11:42:59 +00:00
|
|
|
overwrite_ents=overwrite_ents,
|
|
|
|
ent_id_sep=ent_id_sep,
|
2021-08-10 13:13:39 +00:00
|
|
|
scorer=scorer,
|
2020-07-22 11:42:59 +00:00
|
|
|
)
|
2019-07-08 15:28:28 +00:00
|
|
|
|
2019-02-10 11:14:51 +00:00
|
|
|
|
2021-08-10 13:13:39 +00:00
|
|
|
def entity_ruler_score(examples, **kwargs):
|
|
|
|
return get_ner_prf(examples)
|
|
|
|
|
|
|
|
|
|
|
|
@registry.scorers("spacy.entity_ruler_scorer.v1")
|
|
|
|
def make_entity_ruler_scorer():
|
|
|
|
return entity_ruler_score
|
|
|
|
|
|
|
|
|
2020-10-05 15:43:42 +00:00
|
|
|
class EntityRuler(Pipe):
|
2019-03-08 10:42:26 +00:00
|
|
|
"""The EntityRuler lets you add spans to the `Doc.ents` using token-based
|
|
|
|
rules or exact phrase matches. It can be combined with the statistical
|
|
|
|
`EntityRecognizer` to boost accuracy, or used on its own to implement a
|
|
|
|
purely rule-based entity recognition system. After initialization, the
|
|
|
|
component is typically added to the pipeline using `nlp.add_pipe`.
|
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/entityruler
|
|
|
|
USAGE: https://spacy.io/usage/rule-based-matching#entityruler
|
2019-03-08 10:42:26 +00:00
|
|
|
"""
|
|
|
|
|
2020-07-22 11:42:59 +00:00
|
|
|
def __init__(
|
|
|
|
self,
|
|
|
|
nlp: Language,
|
|
|
|
name: str = "entity_ruler",
|
|
|
|
*,
|
|
|
|
phrase_matcher_attr: Optional[Union[int, str]] = None,
|
2023-01-10 09:36:17 +00:00
|
|
|
matcher_fuzzy_compare: Callable = levenshtein_compare,
|
2020-07-22 11:42:59 +00:00
|
|
|
validate: bool = False,
|
|
|
|
overwrite_ents: bool = False,
|
|
|
|
ent_id_sep: str = DEFAULT_ENT_ID_SEP,
|
|
|
|
patterns: Optional[List[PatternType]] = None,
|
2021-08-10 13:13:39 +00:00
|
|
|
scorer: Optional[Callable] = entity_ruler_score,
|
2020-07-25 13:01:15 +00:00
|
|
|
) -> None:
|
2020-08-26 13:24:33 +00:00
|
|
|
"""Initialize the entity ruler. If patterns are supplied here, they
|
2019-02-10 11:14:51 +00:00
|
|
|
need to be a list of dictionaries with a `"label"` and `"pattern"`
|
|
|
|
key. A pattern can either be a token pattern (list) or a phrase pattern
|
|
|
|
(string). For example: `{'label': 'ORG', 'pattern': 'Apple'}`.
|
|
|
|
|
|
|
|
nlp (Language): The shared nlp object to pass the vocab to the matchers
|
|
|
|
and process phrase patterns.
|
2020-07-27 16:11:45 +00:00
|
|
|
name (str): Instance name of the current pipeline component. Typically
|
|
|
|
passed in automatically from the factory when the component is
|
|
|
|
added. Used to disable the current entity ruler while creating
|
|
|
|
phrase patterns with the nlp object.
|
2020-05-24 16:51:10 +00:00
|
|
|
phrase_matcher_attr (int / str): Token attribute to match on, passed
|
2023-01-10 09:36:17 +00:00
|
|
|
to the internal PhraseMatcher as `attr`.
|
|
|
|
matcher_fuzzy_compare (Callable): The fuzzy comparison method for the
|
|
|
|
internal Matcher. Defaults to
|
|
|
|
spacy.matcher.levenshtein.levenshtein_compare.
|
2019-08-06 22:40:53 +00:00
|
|
|
validate (bool): Whether patterns should be validated, passed to
|
|
|
|
Matcher and PhraseMatcher as `validate`
|
2019-02-10 11:14:51 +00:00
|
|
|
patterns (iterable): Optional patterns to load in.
|
|
|
|
overwrite_ents (bool): If existing entities are present, e.g. entities
|
|
|
|
added by the model, overwrite them by matches if necessary.
|
2020-07-22 11:42:59 +00:00
|
|
|
ent_id_sep (str): Separator used internally for entity IDs.
|
2021-08-12 10:50:03 +00:00
|
|
|
scorer (Optional[Callable]): The scoring method. Defaults to
|
|
|
|
spacy.scorer.get_ner_prf.
|
2019-10-25 09:19:46 +00:00
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/entityruler#init
|
2019-02-10 11:14:51 +00:00
|
|
|
"""
|
|
|
|
self.nlp = nlp
|
2020-07-22 11:42:59 +00:00
|
|
|
self.name = name
|
|
|
|
self.overwrite = overwrite_ents
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
self.token_patterns = defaultdict(list) # type: ignore
|
|
|
|
self.phrase_patterns = defaultdict(list) # type: ignore
|
2021-06-03 07:05:26 +00:00
|
|
|
self._validate = validate
|
2023-01-10 09:36:17 +00:00
|
|
|
self.matcher_fuzzy_compare = matcher_fuzzy_compare
|
|
|
|
self.matcher = Matcher(
|
|
|
|
nlp.vocab, validate=validate, fuzzy_compare=self.matcher_fuzzy_compare
|
|
|
|
)
|
2021-06-03 07:05:26 +00:00
|
|
|
self.phrase_matcher_attr = phrase_matcher_attr
|
|
|
|
self.phrase_matcher = PhraseMatcher(
|
|
|
|
nlp.vocab, attr=self.phrase_matcher_attr, validate=validate
|
|
|
|
)
|
2020-07-22 11:42:59 +00:00
|
|
|
self.ent_id_sep = ent_id_sep
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
self._ent_ids = defaultdict(tuple) # type: ignore
|
2019-02-10 11:14:51 +00:00
|
|
|
if patterns is not None:
|
|
|
|
self.add_patterns(patterns)
|
2021-08-10 13:13:39 +00:00
|
|
|
self.scorer = scorer
|
2019-02-10 11:14:51 +00:00
|
|
|
|
2020-07-22 11:42:59 +00:00
|
|
|
def __len__(self) -> int:
|
2019-02-10 11:14:51 +00:00
|
|
|
"""The number of all patterns added to the entity ruler."""
|
|
|
|
n_token_patterns = sum(len(p) for p in self.token_patterns.values())
|
|
|
|
n_phrase_patterns = sum(len(p) for p in self.phrase_patterns.values())
|
|
|
|
return n_token_patterns + n_phrase_patterns
|
|
|
|
|
2020-07-22 11:42:59 +00:00
|
|
|
def __contains__(self, label: str) -> bool:
|
2019-02-10 11:14:51 +00:00
|
|
|
"""Whether a label is present in the patterns."""
|
|
|
|
return label in self.token_patterns or label in self.phrase_patterns
|
|
|
|
|
2020-07-22 11:42:59 +00:00
|
|
|
def __call__(self, doc: Doc) -> Doc:
|
2019-02-10 11:14:51 +00:00
|
|
|
"""Find matches in document and add them as entities.
|
|
|
|
|
|
|
|
doc (Doc): The Doc object in the pipeline.
|
2019-10-25 09:16:42 +00:00
|
|
|
RETURNS (Doc): The Doc with added entities, if available.
|
2019-10-25 09:19:46 +00:00
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/entityruler#call
|
2019-02-10 11:14:51 +00:00
|
|
|
"""
|
2021-01-29 00:51:21 +00:00
|
|
|
error_handler = self.get_error_handler()
|
|
|
|
try:
|
|
|
|
matches = self.match(doc)
|
|
|
|
self.set_annotations(doc, matches)
|
|
|
|
return doc
|
|
|
|
except Exception as e:
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
return error_handler(self.name, self, [doc], e)
|
2021-01-29 00:51:21 +00:00
|
|
|
|
|
|
|
def match(self, doc: Doc):
|
2021-05-31 08:20:27 +00:00
|
|
|
self._require_patterns()
|
2021-06-21 07:34:29 +00:00
|
|
|
with warnings.catch_warnings():
|
|
|
|
warnings.filterwarnings("ignore", message="\\[W036")
|
2022-05-25 07:33:54 +00:00
|
|
|
matches = list(self.matcher(doc)) + list(self.phrase_matcher(doc))
|
|
|
|
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
final_matches = set(
|
2019-02-10 11:14:51 +00:00
|
|
|
[(m_id, start, end) for m_id, start, end in matches if start != end]
|
|
|
|
)
|
2020-07-31 14:09:32 +00:00
|
|
|
get_sort_key = lambda m: (m[2] - m[1], -m[1])
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
final_matches = sorted(final_matches, key=get_sort_key, reverse=True)
|
|
|
|
return final_matches
|
2021-01-29 00:51:21 +00:00
|
|
|
|
|
|
|
def set_annotations(self, doc, matches):
|
|
|
|
"""Modify the document in place"""
|
2019-02-10 11:14:51 +00:00
|
|
|
entities = list(doc.ents)
|
|
|
|
new_entities = []
|
|
|
|
seen_tokens = set()
|
|
|
|
for match_id, start, end in matches:
|
|
|
|
if any(t.ent_type for t in doc[start:end]) and not self.overwrite:
|
|
|
|
continue
|
|
|
|
# check for end - 1 here because boundaries are inclusive
|
|
|
|
if start not in seen_tokens and end - 1 not in seen_tokens:
|
2019-10-25 09:16:42 +00:00
|
|
|
if match_id in self._ent_ids:
|
|
|
|
label, ent_id = self._ent_ids[match_id]
|
2022-06-02 11:12:53 +00:00
|
|
|
span = Span(doc, start, end, label=label, span_id=ent_id)
|
2019-06-16 11:29:04 +00:00
|
|
|
else:
|
|
|
|
span = Span(doc, start, end, label=match_id)
|
|
|
|
new_entities.append(span)
|
2019-02-10 11:14:51 +00:00
|
|
|
entities = [
|
|
|
|
e for e in entities if not (e.start < end and e.end > start)
|
|
|
|
]
|
|
|
|
seen_tokens.update(range(start, end))
|
|
|
|
doc.ents = entities + new_entities
|
|
|
|
|
|
|
|
@property
|
2020-07-22 11:42:59 +00:00
|
|
|
def labels(self) -> Tuple[str, ...]:
|
2019-02-10 11:14:51 +00:00
|
|
|
"""All labels present in the match patterns.
|
2019-10-25 09:25:44 +00:00
|
|
|
|
2019-02-10 11:14:51 +00:00
|
|
|
RETURNS (set): The string labels.
|
2019-10-25 09:19:46 +00:00
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/entityruler#labels
|
2019-02-10 11:14:51 +00:00
|
|
|
"""
|
2020-01-16 01:01:31 +00:00
|
|
|
keys = set(self.token_patterns.keys())
|
|
|
|
keys.update(self.phrase_patterns.keys())
|
|
|
|
all_labels = set()
|
|
|
|
|
|
|
|
for l in keys:
|
|
|
|
if self.ent_id_sep in l:
|
|
|
|
label, _ = self._split_label(l)
|
|
|
|
all_labels.add(label)
|
|
|
|
else:
|
|
|
|
all_labels.add(l)
|
2021-03-09 09:49:53 +00:00
|
|
|
return tuple(sorted(all_labels))
|
2019-02-10 11:14:51 +00:00
|
|
|
|
2020-10-05 12:59:13 +00:00
|
|
|
def initialize(
|
|
|
|
self,
|
|
|
|
get_examples: Callable[[], Iterable[Example]],
|
|
|
|
*,
|
|
|
|
nlp: Optional[Language] = None,
|
2020-10-05 20:50:14 +00:00
|
|
|
patterns: Optional[Sequence[PatternType]] = None,
|
2020-10-05 12:59:13 +00:00
|
|
|
):
|
|
|
|
"""Initialize the pipe for training.
|
|
|
|
|
|
|
|
get_examples (Callable[[], Iterable[Example]]): Function that
|
|
|
|
returns a representative sample of gold-standard Example objects.
|
|
|
|
nlp (Language): The current nlp object the component is part of.
|
2020-10-05 20:50:14 +00:00
|
|
|
patterns Optional[Iterable[PatternType]]: The list of patterns.
|
2020-10-05 12:59:13 +00:00
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/entityruler#initialize
|
2020-10-05 12:59:13 +00:00
|
|
|
"""
|
2020-10-08 07:51:31 +00:00
|
|
|
self.clear()
|
2020-10-05 20:50:14 +00:00
|
|
|
if patterns:
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
self.add_patterns(patterns) # type: ignore[arg-type]
|
2020-10-05 12:59:13 +00:00
|
|
|
|
2019-06-16 11:29:04 +00:00
|
|
|
@property
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
def ent_ids(self) -> Tuple[Optional[str], ...]:
|
2020-01-16 01:01:31 +00:00
|
|
|
"""All entity ids present in the match patterns `id` properties
|
2019-10-25 09:25:44 +00:00
|
|
|
|
2019-06-16 11:29:04 +00:00
|
|
|
RETURNS (set): The string entity ids.
|
2019-10-25 09:19:46 +00:00
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/entityruler#ent_ids
|
2019-06-16 11:29:04 +00:00
|
|
|
"""
|
2020-01-16 01:01:31 +00:00
|
|
|
keys = set(self.token_patterns.keys())
|
|
|
|
keys.update(self.phrase_patterns.keys())
|
2019-06-16 11:29:04 +00:00
|
|
|
all_ent_ids = set()
|
2020-01-16 01:01:31 +00:00
|
|
|
|
|
|
|
for l in keys:
|
2019-06-16 11:29:04 +00:00
|
|
|
if self.ent_id_sep in l:
|
|
|
|
_, ent_id = self._split_label(l)
|
|
|
|
all_ent_ids.add(ent_id)
|
|
|
|
return tuple(all_ent_ids)
|
|
|
|
|
2019-02-10 11:14:51 +00:00
|
|
|
@property
|
2020-07-22 11:42:59 +00:00
|
|
|
def patterns(self) -> List[PatternType]:
|
2019-02-10 11:14:51 +00:00
|
|
|
"""Get all patterns that were added to the entity ruler.
|
2020-02-16 17:17:47 +00:00
|
|
|
|
2019-02-10 11:14:51 +00:00
|
|
|
RETURNS (list): The original patterns, one dictionary per pattern.
|
2019-10-25 09:19:46 +00:00
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/entityruler#patterns
|
2019-02-10 11:14:51 +00:00
|
|
|
"""
|
|
|
|
all_patterns = []
|
|
|
|
for label, patterns in self.token_patterns.items():
|
|
|
|
for pattern in patterns:
|
2019-06-16 11:29:04 +00:00
|
|
|
ent_label, ent_id = self._split_label(label)
|
|
|
|
p = {"label": ent_label, "pattern": pattern}
|
|
|
|
if ent_id:
|
|
|
|
p["id"] = ent_id
|
|
|
|
all_patterns.append(p)
|
2019-02-10 11:14:51 +00:00
|
|
|
for label, patterns in self.phrase_patterns.items():
|
|
|
|
for pattern in patterns:
|
2019-06-16 11:29:04 +00:00
|
|
|
ent_label, ent_id = self._split_label(label)
|
|
|
|
p = {"label": ent_label, "pattern": pattern.text}
|
|
|
|
if ent_id:
|
|
|
|
p["id"] = ent_id
|
|
|
|
all_patterns.append(p)
|
2019-02-10 11:14:51 +00:00
|
|
|
return all_patterns
|
|
|
|
|
2020-07-22 11:42:59 +00:00
|
|
|
def add_patterns(self, patterns: List[PatternType]) -> None:
|
2020-08-26 13:24:33 +00:00
|
|
|
"""Add patterns to the entity ruler. A pattern can either be a token
|
2019-02-10 11:14:51 +00:00
|
|
|
pattern (list of dicts) or a phrase pattern (string). For example:
|
|
|
|
{'label': 'ORG', 'pattern': 'Apple'}
|
|
|
|
{'label': 'GPE', 'pattern': [{'lower': 'san'}, {'lower': 'francisco'}]}
|
2019-10-25 09:19:46 +00:00
|
|
|
|
2019-02-10 11:14:51 +00:00
|
|
|
patterns (list): The patterns to add.
|
2019-03-08 10:42:26 +00:00
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/entityruler#add_patterns
|
2019-02-10 11:14:51 +00:00
|
|
|
"""
|
2020-02-16 17:17:47 +00:00
|
|
|
|
2019-09-27 18:57:13 +00:00
|
|
|
# disable the nlp components after this one in case they hadn't been initialized / deserialised yet
|
|
|
|
try:
|
2020-12-08 09:01:30 +00:00
|
|
|
current_index = -1
|
|
|
|
for i, (name, pipe) in enumerate(self.nlp.pipeline):
|
|
|
|
if self == pipe:
|
|
|
|
current_index = i
|
|
|
|
break
|
2021-06-28 09:48:00 +00:00
|
|
|
subsequent_pipes = [pipe for pipe in self.nlp.pipe_names[current_index:]]
|
2019-09-27 18:57:13 +00:00
|
|
|
except ValueError:
|
|
|
|
subsequent_pipes = []
|
2020-05-18 20:27:10 +00:00
|
|
|
with self.nlp.select_pipes(disable=subsequent_pipes):
|
2020-02-16 17:17:47 +00:00
|
|
|
token_patterns = []
|
|
|
|
phrase_pattern_labels = []
|
|
|
|
phrase_pattern_texts = []
|
|
|
|
phrase_pattern_ids = []
|
2019-09-27 18:57:13 +00:00
|
|
|
for entry in patterns:
|
2020-02-18 13:47:23 +00:00
|
|
|
if isinstance(entry["pattern"], str):
|
2020-02-16 17:17:47 +00:00
|
|
|
phrase_pattern_labels.append(entry["label"])
|
|
|
|
phrase_pattern_texts.append(entry["pattern"])
|
|
|
|
phrase_pattern_ids.append(entry.get("id"))
|
|
|
|
elif isinstance(entry["pattern"], list):
|
|
|
|
token_patterns.append(entry)
|
|
|
|
phrase_patterns = []
|
|
|
|
for label, pattern, ent_id in zip(
|
|
|
|
phrase_pattern_labels,
|
|
|
|
self.nlp.pipe(phrase_pattern_texts),
|
2020-03-25 11:28:12 +00:00
|
|
|
phrase_pattern_ids,
|
2020-02-16 17:17:47 +00:00
|
|
|
):
|
2021-05-31 08:38:53 +00:00
|
|
|
phrase_pattern = {"label": label, "pattern": pattern}
|
2020-02-16 17:17:47 +00:00
|
|
|
if ent_id:
|
|
|
|
phrase_pattern["id"] = ent_id
|
|
|
|
phrase_patterns.append(phrase_pattern)
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
for entry in token_patterns + phrase_patterns: # type: ignore[operator]
|
2022-09-29 12:24:40 +00:00
|
|
|
label = entry["label"] # type: ignore
|
2019-09-27 18:57:13 +00:00
|
|
|
if "id" in entry:
|
2019-10-25 09:16:42 +00:00
|
|
|
ent_label = label
|
2019-09-27 18:57:13 +00:00
|
|
|
label = self._create_label(label, entry["id"])
|
2019-10-25 09:16:42 +00:00
|
|
|
key = self.matcher._normalize_key(label)
|
|
|
|
self._ent_ids[key] = (ent_label, entry["id"])
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
pattern = entry["pattern"] # type: ignore
|
2020-02-16 17:17:47 +00:00
|
|
|
if isinstance(pattern, Doc):
|
|
|
|
self.phrase_patterns[label].append(pattern)
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
self.phrase_matcher.add(label, [pattern]) # type: ignore
|
2019-09-27 18:57:13 +00:00
|
|
|
elif isinstance(pattern, list):
|
|
|
|
self.token_patterns[label].append(pattern)
|
2021-06-03 07:05:26 +00:00
|
|
|
self.matcher.add(label, [pattern])
|
2019-09-27 18:57:13 +00:00
|
|
|
else:
|
|
|
|
raise ValueError(Errors.E097.format(pattern=pattern))
|
2019-02-10 11:14:51 +00:00
|
|
|
|
2020-07-22 11:42:59 +00:00
|
|
|
def clear(self) -> None:
|
|
|
|
"""Reset all patterns."""
|
|
|
|
self.token_patterns = defaultdict(list)
|
|
|
|
self.phrase_patterns = defaultdict(list)
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
self._ent_ids = defaultdict(tuple)
|
2023-01-10 09:36:17 +00:00
|
|
|
self.matcher = Matcher(
|
|
|
|
self.nlp.vocab,
|
|
|
|
validate=self._validate,
|
|
|
|
fuzzy_compare=self.matcher_fuzzy_compare,
|
|
|
|
)
|
2021-06-03 07:05:26 +00:00
|
|
|
self.phrase_matcher = PhraseMatcher(
|
|
|
|
self.nlp.vocab, attr=self.phrase_matcher_attr, validate=self._validate
|
|
|
|
)
|
2020-07-22 11:42:59 +00:00
|
|
|
|
2021-12-06 14:32:49 +00:00
|
|
|
def remove(self, ent_id: str) -> None:
|
|
|
|
"""Remove a pattern by its ent_id if a pattern with this ent_id was added before
|
|
|
|
|
|
|
|
ent_id (str): id of the pattern to be removed
|
|
|
|
RETURNS: None
|
|
|
|
DOCS: https://spacy.io/api/entityruler#remove
|
|
|
|
"""
|
|
|
|
label_id_pairs = [
|
|
|
|
(label, eid) for (label, eid) in self._ent_ids.values() if eid == ent_id
|
|
|
|
]
|
|
|
|
if not label_id_pairs:
|
2022-06-02 11:12:53 +00:00
|
|
|
raise ValueError(
|
|
|
|
Errors.E1024.format(attr_type="ID", label=ent_id, component=self.name)
|
|
|
|
)
|
2021-12-06 14:32:49 +00:00
|
|
|
created_labels = [
|
|
|
|
self._create_label(label, eid) for (label, eid) in label_id_pairs
|
|
|
|
]
|
|
|
|
# remove the patterns from self.phrase_patterns
|
|
|
|
self.phrase_patterns = defaultdict(
|
|
|
|
list,
|
|
|
|
{
|
|
|
|
label: val
|
|
|
|
for (label, val) in self.phrase_patterns.items()
|
|
|
|
if label not in created_labels
|
|
|
|
},
|
|
|
|
)
|
|
|
|
# remove the patterns from self.token_pattern
|
|
|
|
self.token_patterns = defaultdict(
|
|
|
|
list,
|
|
|
|
{
|
|
|
|
label: val
|
|
|
|
for (label, val) in self.token_patterns.items()
|
|
|
|
if label not in created_labels
|
|
|
|
},
|
|
|
|
)
|
|
|
|
# remove the patterns from self.token_pattern
|
|
|
|
for label in created_labels:
|
|
|
|
if label in self.phrase_matcher:
|
|
|
|
self.phrase_matcher.remove(label)
|
|
|
|
else:
|
|
|
|
self.matcher.remove(label)
|
|
|
|
|
2021-05-31 08:20:27 +00:00
|
|
|
def _require_patterns(self) -> None:
|
|
|
|
"""Raise a warning if this component has no patterns defined."""
|
|
|
|
if len(self) == 0:
|
|
|
|
warnings.warn(Warnings.W036.format(name=self.name))
|
2020-07-22 11:42:59 +00:00
|
|
|
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
def _split_label(self, label: str) -> Tuple[str, Optional[str]]:
|
2019-06-16 11:29:04 +00:00
|
|
|
"""Split Entity label into ent_label and ent_id if it contains self.ent_id_sep
|
|
|
|
|
2020-02-16 17:17:47 +00:00
|
|
|
label (str): The value of label in a pattern entry
|
2019-06-16 11:29:04 +00:00
|
|
|
RETURNS (tuple): ent_label, ent_id
|
|
|
|
"""
|
|
|
|
if self.ent_id_sep in label:
|
|
|
|
ent_label, ent_id = label.rsplit(self.ent_id_sep, 1)
|
|
|
|
else:
|
|
|
|
ent_label = label
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
ent_id = None # type: ignore
|
2019-06-16 11:29:04 +00:00
|
|
|
return ent_label, ent_id
|
|
|
|
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
def _create_label(self, label: Any, ent_id: Any) -> str:
|
2019-06-16 11:29:04 +00:00
|
|
|
"""Join Entity label with ent_id if the pattern has an `id` attribute
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
If ent_id is not a string, the label is returned as is.
|
2019-07-08 15:28:28 +00:00
|
|
|
|
2020-02-16 17:17:47 +00:00
|
|
|
label (str): The label to set for ent.label_
|
|
|
|
ent_id (str): The label
|
2019-06-16 11:29:04 +00:00
|
|
|
RETURNS (str): The ent_label joined with configured `ent_id_sep`
|
|
|
|
"""
|
2019-12-22 00:53:56 +00:00
|
|
|
if isinstance(ent_id, str):
|
|
|
|
label = f"{label}{self.ent_id_sep}{ent_id}"
|
2019-06-16 11:29:04 +00:00
|
|
|
return label
|
|
|
|
|
2020-07-22 11:42:59 +00:00
|
|
|
def from_bytes(
|
2020-08-29 13:20:11 +00:00
|
|
|
self, patterns_bytes: bytes, *, exclude: Iterable[str] = SimpleFrozenList()
|
2020-07-22 11:42:59 +00:00
|
|
|
) -> "EntityRuler":
|
2019-02-10 11:14:51 +00:00
|
|
|
"""Load the entity ruler from a bytestring.
|
|
|
|
|
|
|
|
patterns_bytes (bytes): The bytestring to load.
|
2019-10-25 09:16:42 +00:00
|
|
|
RETURNS (EntityRuler): The loaded entity ruler.
|
2019-10-25 09:19:46 +00:00
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/entityruler#from_bytes
|
2019-02-10 11:14:51 +00:00
|
|
|
"""
|
2019-07-08 15:28:28 +00:00
|
|
|
cfg = srsly.msgpack_loads(patterns_bytes)
|
2020-07-22 11:42:59 +00:00
|
|
|
self.clear()
|
2019-07-08 15:28:28 +00:00
|
|
|
if isinstance(cfg, dict):
|
2019-07-10 10:03:05 +00:00
|
|
|
self.add_patterns(cfg.get("patterns", cfg))
|
|
|
|
self.overwrite = cfg.get("overwrite", False)
|
|
|
|
self.phrase_matcher_attr = cfg.get("phrase_matcher_attr", None)
|
2021-06-03 07:05:26 +00:00
|
|
|
self.phrase_matcher = PhraseMatcher(
|
2023-01-10 09:36:17 +00:00
|
|
|
self.nlp.vocab,
|
|
|
|
attr=self.phrase_matcher_attr,
|
2021-06-03 07:05:26 +00:00
|
|
|
)
|
2019-07-10 10:03:05 +00:00
|
|
|
self.ent_id_sep = cfg.get("ent_id_sep", DEFAULT_ENT_ID_SEP)
|
2019-07-08 15:28:28 +00:00
|
|
|
else:
|
|
|
|
self.add_patterns(cfg)
|
2019-02-10 11:14:51 +00:00
|
|
|
return self
|
|
|
|
|
2020-08-29 13:20:11 +00:00
|
|
|
def to_bytes(self, *, exclude: Iterable[str] = SimpleFrozenList()) -> bytes:
|
2019-02-10 11:14:51 +00:00
|
|
|
"""Serialize the entity ruler patterns to a bytestring.
|
|
|
|
|
|
|
|
RETURNS (bytes): The serialized patterns.
|
2019-10-25 09:19:46 +00:00
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/entityruler#to_bytes
|
2019-02-10 11:14:51 +00:00
|
|
|
"""
|
2019-12-22 00:53:56 +00:00
|
|
|
serial = {
|
|
|
|
"overwrite": self.overwrite,
|
|
|
|
"ent_id_sep": self.ent_id_sep,
|
|
|
|
"phrase_matcher_attr": self.phrase_matcher_attr,
|
|
|
|
"patterns": self.patterns,
|
|
|
|
}
|
2019-07-08 15:28:28 +00:00
|
|
|
return srsly.msgpack_dumps(serial)
|
2019-02-10 11:14:51 +00:00
|
|
|
|
2020-07-22 11:42:59 +00:00
|
|
|
def from_disk(
|
2020-08-29 13:20:11 +00:00
|
|
|
self, path: Union[str, Path], *, exclude: Iterable[str] = SimpleFrozenList()
|
2020-07-22 11:42:59 +00:00
|
|
|
) -> "EntityRuler":
|
2019-02-10 11:14:51 +00:00
|
|
|
"""Load the entity ruler from a file. Expects a file containing
|
|
|
|
newline-delimited JSON (JSONL) with one entry per line.
|
|
|
|
|
2020-05-24 15:20:58 +00:00
|
|
|
path (str / Path): The JSONL file to load.
|
2019-10-25 09:16:42 +00:00
|
|
|
RETURNS (EntityRuler): The loaded entity ruler.
|
2019-10-25 09:19:46 +00:00
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/entityruler#from_disk
|
2019-02-10 11:14:51 +00:00
|
|
|
"""
|
|
|
|
path = ensure_path(path)
|
2020-07-22 11:42:59 +00:00
|
|
|
self.clear()
|
2019-07-10 10:14:12 +00:00
|
|
|
depr_patterns_path = path.with_suffix(".jsonl")
|
2021-11-23 15:26:05 +00:00
|
|
|
if path.suffix == ".jsonl": # user provides a jsonl
|
|
|
|
if path.is_file:
|
|
|
|
patterns = srsly.read_jsonl(path)
|
|
|
|
self.add_patterns(patterns)
|
|
|
|
else:
|
|
|
|
raise ValueError(Errors.E1023.format(path=path))
|
|
|
|
elif depr_patterns_path.is_file():
|
2019-07-10 10:14:12 +00:00
|
|
|
patterns = srsly.read_jsonl(depr_patterns_path)
|
2019-07-08 15:28:28 +00:00
|
|
|
self.add_patterns(patterns)
|
2021-11-23 15:26:05 +00:00
|
|
|
elif path.is_dir(): # path is a valid directory
|
2019-07-08 15:28:28 +00:00
|
|
|
cfg = {}
|
2019-11-21 15:26:37 +00:00
|
|
|
deserializers_patterns = {
|
2019-07-10 10:03:05 +00:00
|
|
|
"patterns": lambda p: self.add_patterns(
|
|
|
|
srsly.read_jsonl(p.with_suffix(".jsonl"))
|
2019-12-21 18:04:17 +00:00
|
|
|
)
|
2019-07-08 15:28:28 +00:00
|
|
|
}
|
2019-12-21 18:04:17 +00:00
|
|
|
deserializers_cfg = {"cfg": lambda p: cfg.update(srsly.read_json(p))}
|
2019-11-21 15:26:37 +00:00
|
|
|
from_disk(path, deserializers_cfg, {})
|
2019-07-10 10:03:05 +00:00
|
|
|
self.overwrite = cfg.get("overwrite", False)
|
|
|
|
self.phrase_matcher_attr = cfg.get("phrase_matcher_attr")
|
|
|
|
self.ent_id_sep = cfg.get("ent_id_sep", DEFAULT_ENT_ID_SEP)
|
2019-07-09 18:09:17 +00:00
|
|
|
|
2021-06-03 07:05:26 +00:00
|
|
|
self.phrase_matcher = PhraseMatcher(
|
|
|
|
self.nlp.vocab, attr=self.phrase_matcher_attr
|
|
|
|
)
|
2019-11-21 15:26:37 +00:00
|
|
|
from_disk(path, deserializers_patterns, {})
|
2021-11-23 15:26:05 +00:00
|
|
|
else: # path is not a valid directory or file
|
|
|
|
raise ValueError(Errors.E146.format(path=path))
|
2019-02-10 11:14:51 +00:00
|
|
|
return self
|
|
|
|
|
2020-07-29 13:14:07 +00:00
|
|
|
def to_disk(
|
2020-08-29 13:20:11 +00:00
|
|
|
self, path: Union[str, Path], *, exclude: Iterable[str] = SimpleFrozenList()
|
2020-07-29 13:14:07 +00:00
|
|
|
) -> None:
|
2019-02-10 11:14:51 +00:00
|
|
|
"""Save the entity ruler patterns to a directory. The patterns will be
|
|
|
|
saved as newline-delimited JSON (JSONL).
|
|
|
|
|
2020-05-24 15:20:58 +00:00
|
|
|
path (str / Path): The JSONL file to save.
|
2019-03-08 10:42:26 +00:00
|
|
|
|
2021-01-30 09:09:38 +00:00
|
|
|
DOCS: https://spacy.io/api/entityruler#to_disk
|
2019-02-10 11:14:51 +00:00
|
|
|
"""
|
2019-07-10 10:25:45 +00:00
|
|
|
path = ensure_path(path)
|
2019-07-10 10:03:05 +00:00
|
|
|
cfg = {
|
|
|
|
"overwrite": self.overwrite,
|
|
|
|
"phrase_matcher_attr": self.phrase_matcher_attr,
|
|
|
|
"ent_id_sep": self.ent_id_sep,
|
|
|
|
}
|
2019-07-08 15:28:28 +00:00
|
|
|
serializers = {
|
2019-07-10 10:03:05 +00:00
|
|
|
"patterns": lambda p: srsly.write_jsonl(
|
|
|
|
p.with_suffix(".jsonl"), self.patterns
|
|
|
|
),
|
|
|
|
"cfg": lambda p: srsly.write_json(p, cfg),
|
2019-07-08 15:28:28 +00:00
|
|
|
}
|
2019-07-10 10:25:45 +00:00
|
|
|
if path.suffix == ".jsonl": # user wants to save only JSONL
|
|
|
|
srsly.write_jsonl(path, self.patterns)
|
|
|
|
else:
|
|
|
|
to_disk(path, serializers, {})
|