mirror of
https://github.com/explosion/spaCy.git
synced 2025-08-07 13:44:55 +03:00
Merge branch 'master' into feature/use-cloudpathlib
This commit is contained in:
Adriane Boyd
GitHub
commit
8f521c34de
2
.github/workflows/spacy_universe_alert.yml
vendored
2
.github/workflows/spacy_universe_alert.yml
vendored
|
|
@ -19,6 +19,8 @@ jobs:
|
||||||
|
|
||||||
- uses: actions/checkout@v3
|
- uses: actions/checkout@v3
|
||||||
- uses: actions/setup-python@v4
|
- uses: actions/setup-python@v4
|
||||||
|
with:
|
||||||
|
python-version: '3.10'
|
||||||
- name: Install Bernadette app dependency and send an alert
|
- name: Install Bernadette app dependency and send an alert
|
||||||
env:
|
env:
|
||||||
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
|
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
|
||||||
|
|
|
||||||
|
|
@ -53,6 +53,7 @@ def project_run(
|
||||||
force: bool = False,
|
force: bool = False,
|
||||||
dry: bool = False,
|
dry: bool = False,
|
||||||
capture: bool = False,
|
capture: bool = False,
|
||||||
|
skip_requirements_check: bool = False,
|
||||||
) -> None:
|
) -> None:
|
||||||
"""Run a named script defined in the project.yml. If the script is part
|
"""Run a named script defined in the project.yml. If the script is part
|
||||||
of the default pipeline (defined in the "run" section), DVC is used to
|
of the default pipeline (defined in the "run" section), DVC is used to
|
||||||
|
|
@ -69,6 +70,7 @@ def project_run(
|
||||||
sys.exit will be called with the return code. You should use capture=False
|
sys.exit will be called with the return code. You should use capture=False
|
||||||
when you want to turn over execution to the command, and capture=True
|
when you want to turn over execution to the command, and capture=True
|
||||||
when you want to run the command more like a function.
|
when you want to run the command more like a function.
|
||||||
|
skip_requirements_check (bool): Whether to skip the requirements check.
|
||||||
"""
|
"""
|
||||||
config = load_project_config(project_dir, overrides=overrides)
|
config = load_project_config(project_dir, overrides=overrides)
|
||||||
commands = {cmd["name"]: cmd for cmd in config.get("commands", [])}
|
commands = {cmd["name"]: cmd for cmd in config.get("commands", [])}
|
||||||
|
|
@ -76,9 +78,10 @@ def project_run(
|
||||||
validate_subcommand(list(commands.keys()), list(workflows.keys()), subcommand)
|
validate_subcommand(list(commands.keys()), list(workflows.keys()), subcommand)
|
||||||
|
|
||||||
req_path = project_dir / "requirements.txt"
|
req_path = project_dir / "requirements.txt"
|
||||||
if config.get("check_requirements", True) and os.path.exists(req_path):
|
if not skip_requirements_check:
|
||||||
with req_path.open() as requirements_file:
|
if config.get("check_requirements", True) and os.path.exists(req_path):
|
||||||
_check_requirements([req.replace("\n", "") for req in requirements_file])
|
with req_path.open() as requirements_file:
|
||||||
|
_check_requirements([req.strip() for req in requirements_file])
|
||||||
|
|
||||||
if subcommand in workflows:
|
if subcommand in workflows:
|
||||||
msg.info(f"Running workflow '{subcommand}'")
|
msg.info(f"Running workflow '{subcommand}'")
|
||||||
|
|
@ -90,6 +93,7 @@ def project_run(
|
||||||
force=force,
|
force=force,
|
||||||
dry=dry,
|
dry=dry,
|
||||||
capture=capture,
|
capture=capture,
|
||||||
|
skip_requirements_check=True,
|
||||||
)
|
)
|
||||||
else:
|
else:
|
||||||
cmd = commands[subcommand]
|
cmd = commands[subcommand]
|
||||||
|
|
@ -338,6 +342,12 @@ def _check_requirements(requirements: List[str]) -> Tuple[bool, bool]:
|
||||||
failed_pkgs_msgs.append(dnf.report())
|
failed_pkgs_msgs.append(dnf.report())
|
||||||
except pkg_resources.VersionConflict as vc:
|
except pkg_resources.VersionConflict as vc:
|
||||||
conflicting_pkgs_msgs.append(vc.report())
|
conflicting_pkgs_msgs.append(vc.report())
|
||||||
|
except Exception:
|
||||||
|
msg.warn(
|
||||||
|
f"Unable to check requirement: {req} "
|
||||||
|
"Checks are currently limited to requirement specifiers "
|
||||||
|
"(PEP 508)"
|
||||||
|
)
|
||||||
|
|
||||||
if len(failed_pkgs_msgs) or len(conflicting_pkgs_msgs):
|
if len(failed_pkgs_msgs) or len(conflicting_pkgs_msgs):
|
||||||
msg.warn(
|
msg.warn(
|
||||||
|
|
|
||||||
|
|
@ -212,8 +212,8 @@ class Warnings(metaclass=ErrorsWithCodes):
|
||||||
W121 = ("Attempting to trace non-existent method '{method}' in pipe '{pipe}'")
|
W121 = ("Attempting to trace non-existent method '{method}' in pipe '{pipe}'")
|
||||||
W122 = ("Couldn't trace method '{method}' in pipe '{pipe}'. This can happen if the pipe class "
|
W122 = ("Couldn't trace method '{method}' in pipe '{pipe}'. This can happen if the pipe class "
|
||||||
"is a Cython extension type.")
|
"is a Cython extension type.")
|
||||||
W123 = ("Argument {arg} with value {arg_value} is used instead of {config_value} as specified in the config. Be "
|
W123 = ("Argument `enable` with value {enable} does not contain all values specified in the config option "
|
||||||
"aware that this might affect other components in your pipeline.")
|
"`enabled` ({enabled}). Be aware that this might affect other components in your pipeline.")
|
||||||
|
|
||||||
|
|
||||||
class Errors(metaclass=ErrorsWithCodes):
|
class Errors(metaclass=ErrorsWithCodes):
|
||||||
|
|
|
||||||
|
|
@ -1879,31 +1879,22 @@ class Language:
|
||||||
if isinstance(exclude, str):
|
if isinstance(exclude, str):
|
||||||
exclude = [exclude]
|
exclude = [exclude]
|
||||||
|
|
||||||
def fetch_pipes_status(value: Iterable[str], key: str) -> Iterable[str]:
|
# `enable` should not be merged with `enabled` (the opposite is true for `disable`/`disabled`). If the config
|
||||||
"""Fetch value for `enable` or `disable` w.r.t. the specified config and passed arguments passed to
|
# specifies values for `enabled` not included in `enable`, emit warning.
|
||||||
.load(). If both arguments and config specified values for this field, the passed arguments take precedence
|
if id(enable) != id(_DEFAULT_EMPTY_PIPES):
|
||||||
and a warning is printed.
|
enabled = config["nlp"].get("enabled", [])
|
||||||
value (Iterable[str]): Passed value for `enable` or `disable`.
|
if len(enabled) and not set(enabled).issubset(enable):
|
||||||
key (str): Key for field in config (either "enabled" or "disabled").
|
warnings.warn(
|
||||||
RETURN (Iterable[str]):
|
Warnings.W123.format(
|
||||||
"""
|
enable=enable,
|
||||||
# We assume that no argument was passed if the value is the specified default value.
|
enabled=enabled,
|
||||||
if id(value) == id(_DEFAULT_EMPTY_PIPES):
|
|
||||||
return config["nlp"].get(key, [])
|
|
||||||
else:
|
|
||||||
if len(config["nlp"].get(key, [])):
|
|
||||||
warnings.warn(
|
|
||||||
Warnings.W123.format(
|
|
||||||
arg=key[:-1],
|
|
||||||
arg_value=value,
|
|
||||||
config_value=config["nlp"][key],
|
|
||||||
)
|
|
||||||
)
|
)
|
||||||
return value
|
)
|
||||||
|
|
||||||
|
# Ensure sets of disabled/enabled pipe names are not contradictory.
|
||||||
disabled_pipes = cls._resolve_component_status(
|
disabled_pipes = cls._resolve_component_status(
|
||||||
fetch_pipes_status(disable, "disabled"),
|
list({*disable, *config["nlp"].get("disabled", [])}),
|
||||||
fetch_pipes_status(enable, "enabled"),
|
enable,
|
||||||
config["nlp"]["pipeline"],
|
config["nlp"]["pipeline"],
|
||||||
)
|
)
|
||||||
nlp._disabled = set(p for p in disabled_pipes if p not in exclude)
|
nlp._disabled = set(p for p in disabled_pipes if p not in exclude)
|
||||||
|
|
@ -2084,10 +2075,12 @@ class Language:
|
||||||
if enable:
|
if enable:
|
||||||
if isinstance(enable, str):
|
if isinstance(enable, str):
|
||||||
enable = [enable]
|
enable = [enable]
|
||||||
to_disable = [
|
to_disable = {
|
||||||
pipe_name for pipe_name in pipe_names if pipe_name not in enable
|
*[pipe_name for pipe_name in pipe_names if pipe_name not in enable],
|
||||||
]
|
*disable,
|
||||||
if disable and disable != to_disable:
|
}
|
||||||
|
# If any pipe to be enabled is in to_disable, the specification is inconsistent.
|
||||||
|
if len(set(enable) & to_disable):
|
||||||
raise ValueError(Errors.E1042.format(enable=enable, disable=disable))
|
raise ValueError(Errors.E1042.format(enable=enable, disable=disable))
|
||||||
|
|
||||||
return tuple(to_disable)
|
return tuple(to_disable)
|
||||||
|
|
|
||||||
|
|
@ -615,20 +615,18 @@ def test_enable_disable_conflict_with_config():
|
||||||
|
|
||||||
with make_tempdir() as tmp_dir:
|
with make_tempdir() as tmp_dir:
|
||||||
nlp.to_disk(tmp_dir)
|
nlp.to_disk(tmp_dir)
|
||||||
# Expected to fail, as config and arguments conflict.
|
# Expected to succeed, as config and arguments do not conflict.
|
||||||
with pytest.raises(ValueError):
|
assert spacy.load(
|
||||||
spacy.load(
|
tmp_dir, enable=["tagger"], config={"nlp": {"disabled": ["senter"]}}
|
||||||
tmp_dir, enable=["tagger"], config={"nlp": {"disabled": ["senter"]}}
|
).disabled == ["senter", "sentencizer"]
|
||||||
)
|
|
||||||
# Expected to succeed without warning due to the lack of a conflicting config option.
|
# Expected to succeed without warning due to the lack of a conflicting config option.
|
||||||
spacy.load(tmp_dir, enable=["tagger"])
|
spacy.load(tmp_dir, enable=["tagger"])
|
||||||
# Expected to succeed with a warning, as disable=[] should override the config setting.
|
# Expected to fail due to conflict between enable and disabled.
|
||||||
with pytest.warns(UserWarning):
|
with pytest.raises(ValueError):
|
||||||
spacy.load(
|
spacy.load(
|
||||||
tmp_dir,
|
tmp_dir,
|
||||||
enable=["tagger"],
|
enable=["senter"],
|
||||||
disable=[],
|
config={"nlp": {"disabled": ["senter", "tagger"]}},
|
||||||
config={"nlp": {"disabled": ["senter"]}},
|
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -404,11 +404,10 @@ def test_serialize_pipeline_disable_enable():
|
||||||
assert nlp3.component_names == ["ner", "tagger"]
|
assert nlp3.component_names == ["ner", "tagger"]
|
||||||
with make_tempdir() as d:
|
with make_tempdir() as d:
|
||||||
nlp3.to_disk(d)
|
nlp3.to_disk(d)
|
||||||
with pytest.warns(UserWarning):
|
nlp4 = spacy.load(d, disable=["ner"])
|
||||||
nlp4 = spacy.load(d, disable=["ner"])
|
assert nlp4.pipe_names == []
|
||||||
assert nlp4.pipe_names == ["tagger"]
|
|
||||||
assert nlp4.component_names == ["ner", "tagger"]
|
assert nlp4.component_names == ["ner", "tagger"]
|
||||||
assert nlp4.disabled == ["ner"]
|
assert nlp4.disabled == ["ner", "tagger"]
|
||||||
with make_tempdir() as d:
|
with make_tempdir() as d:
|
||||||
nlp.to_disk(d)
|
nlp.to_disk(d)
|
||||||
nlp5 = spacy.load(d, exclude=["tagger"])
|
nlp5 = spacy.load(d, exclude=["tagger"])
|
||||||
|
|
|
||||||
|
|
@ -1,5 +1,6 @@
|
||||||
import os
|
import os
|
||||||
import math
|
import math
|
||||||
|
import pkg_resources
|
||||||
from random import sample
|
from random import sample
|
||||||
from typing import Counter
|
from typing import Counter
|
||||||
|
|
||||||
|
|
@ -26,6 +27,7 @@ from spacy.cli.init_config import RECOMMENDATIONS, init_config, fill_config
|
||||||
from spacy.cli.package import get_third_party_dependencies
|
from spacy.cli.package import get_third_party_dependencies
|
||||||
from spacy.cli.package import _is_permitted_package_name
|
from spacy.cli.package import _is_permitted_package_name
|
||||||
from spacy.cli.project.remote_storage import RemoteStorage
|
from spacy.cli.project.remote_storage import RemoteStorage
|
||||||
|
from spacy.cli.project.run import _check_requirements
|
||||||
from spacy.cli.validate import get_model_pkgs
|
from spacy.cli.validate import get_model_pkgs
|
||||||
from spacy.lang.en import English
|
from spacy.lang.en import English
|
||||||
from spacy.lang.nl import Dutch
|
from spacy.lang.nl import Dutch
|
||||||
|
|
@ -897,3 +899,42 @@ def test_local_remote_storage():
|
||||||
remote.pull(filename)
|
remote.pull(filename)
|
||||||
with loc_file.open(mode="r") as file_:
|
with loc_file.open(mode="r") as file_:
|
||||||
assert file_.read() == content
|
assert file_.read() == content
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize(
|
||||||
|
"reqs,output",
|
||||||
|
[
|
||||||
|
[
|
||||||
|
"""
|
||||||
|
spacy
|
||||||
|
|
||||||
|
# comment
|
||||||
|
|
||||||
|
thinc""",
|
||||||
|
(False, False),
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"""# comment
|
||||||
|
--some-flag
|
||||||
|
spacy""",
|
||||||
|
(False, False),
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"""# comment
|
||||||
|
--some-flag
|
||||||
|
spacy; python_version >= '3.6'""",
|
||||||
|
(False, False),
|
||||||
|
],
|
||||||
|
[
|
||||||
|
"""# comment
|
||||||
|
spacyunknowndoesnotexist12345""",
|
||||||
|
(True, False),
|
||||||
|
],
|
||||||
|
],
|
||||||
|
)
|
||||||
|
def test_project_check_requirements(reqs, output):
|
||||||
|
# excessive guard against unlikely package name
|
||||||
|
try:
|
||||||
|
pkg_resources.require("spacyunknowndoesnotexist12345")
|
||||||
|
except pkg_resources.DistributionNotFound:
|
||||||
|
assert output == _check_requirements([req.strip() for req in reqs.split("\n")])
|
||||||
|
|
|
||||||
|
|
@ -63,18 +63,18 @@ spaCy loads a model under the hood based on its
|
||||||
> nlp = Language.from_config(config)
|
> nlp = Language.from_config(config)
|
||||||
> ```
|
> ```
|
||||||
|
|
||||||
| Name | Description |
|
| Name | Description |
|
||||||
| ------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
| ------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||||
| `config` | The loaded config. ~~Union[Dict[str, Any], Config]~~ |
|
| `config` | The loaded config. ~~Union[Dict[str, Any], Config]~~ |
|
||||||
| _keyword-only_ | |
|
| _keyword-only_ | |
|
||||||
| `vocab` | A `Vocab` object. If `True`, a vocab is created using the default language data settings. ~~Vocab~~ |
|
| `vocab` | A `Vocab` object. If `True`, a vocab is created using the default language data settings. ~~Vocab~~ |
|
||||||
| `disable` | Name(s) of pipeline component(s) to [disable](/usage/processing-pipelines#disabling). Disabled pipes will be loaded but they won't be run unless you explicitly enable them by calling [`nlp.enable_pipe`](/api/language#enable_pipe). ~~Union[str, Iterable[str]]~~ |
|
| `disable` | Name(s) of pipeline component(s) to [disable](/usage/processing-pipelines#disabling). Disabled pipes will be loaded but they won't be run unless you explicitly enable them by calling [nlp.enable_pipe](/api/language#enable_pipe). Is merged with the config entry `nlp.disabled`. ~~Union[str, Iterable[str]]~~ |
|
||||||
| `enable` <Tag variant="new">3.4</Tag> | Name(s) of pipeline component(s) to [enable](/usage/processing-pipelines#disabling). All other pipes will be disabled, but can be enabled again using [`nlp.enable_pipe`](/api/language#enable_pipe). ~~Union[str, Iterable[str]]~~ |
|
| `enable` <Tag variant="new">3.4</Tag> | Name(s) of pipeline component(s) to [enable](/usage/processing-pipelines#disabling). All other pipes will be disabled, but can be enabled again using [nlp.enable_pipe](/api/language#enable_pipe). ~~Union[str, Iterable[str]]~~ |
|
||||||
| `exclude` | Name(s) of pipeline component(s) to [exclude](/usage/processing-pipelines#disabling). Excluded components won't be loaded. ~~Union[str, Iterable[str]]~~ |
|
| `exclude` | Name(s) of pipeline component(s) to [exclude](/usage/processing-pipelines#disabling). Excluded components won't be loaded. ~~Union[str, Iterable[str]]~~ |
|
||||||
| `meta` | [Meta data](/api/data-formats#meta) overrides. ~~Dict[str, Any]~~ |
|
| `meta` | [Meta data](/api/data-formats#meta) overrides. ~~Dict[str, Any]~~ |
|
||||||
| `auto_fill` | Whether to automatically fill in missing values in the config, based on defaults and function argument annotations. Defaults to `True`. ~~bool~~ |
|
| `auto_fill` | Whether to automatically fill in missing values in the config, based on defaults and function argument annotations. Defaults to `True`. ~~bool~~ |
|
||||||
| `validate` | Whether to validate the component config and arguments against the types expected by the factory. Defaults to `True`. ~~bool~~ |
|
| `validate` | Whether to validate the component config and arguments against the types expected by the factory. Defaults to `True`. ~~bool~~ |
|
||||||
| **RETURNS** | The initialized object. ~~Language~~ |
|
| **RETURNS** | The initialized object. ~~Language~~ |
|
||||||
|
|
||||||
## Language.component {#component tag="classmethod" new="3"}
|
## Language.component {#component tag="classmethod" new="3"}
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -45,16 +45,16 @@ specified separately using the new `exclude` keyword argument.
|
||||||
> nlp = spacy.load("en_core_web_sm", exclude=["parser", "tagger"])
|
> nlp = spacy.load("en_core_web_sm", exclude=["parser", "tagger"])
|
||||||
> ```
|
> ```
|
||||||
|
|
||||||
| Name | Description |
|
| Name | Description |
|
||||||
| ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
| ------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||||
| `name` | Pipeline to load, i.e. package name or path. ~~Union[str, Path]~~ |
|
| `name` | Pipeline to load, i.e. package name or path. ~~Union[str, Path]~~ |
|
||||||
| _keyword-only_ | |
|
| _keyword-only_ | |
|
||||||
| `vocab` | Optional shared vocab to pass in on initialization. If `True` (default), a new `Vocab` object will be created. ~~Union[Vocab, bool]~~ |
|
| `vocab` | Optional shared vocab to pass in on initialization. If `True` (default), a new `Vocab` object will be created. ~~Union[Vocab, bool]~~ |
|
||||||
| `disable` | Name(s) of pipeline component(s) to [disable](/usage/processing-pipelines#disabling). Disabled pipes will be loaded but they won't be run unless you explicitly enable them by calling [nlp.enable_pipe](/api/language#enable_pipe). ~~Union[str, Iterable[str]]~~ |
|
| `disable` | Name(s) of pipeline component(s) to [disable](/usage/processing-pipelines#disabling). Disabled pipes will be loaded but they won't be run unless you explicitly enable them by calling [nlp.enable_pipe](/api/language#enable_pipe). Is merged with the config entry `nlp.disabled`. ~~Union[str, Iterable[str]]~~ |
|
||||||
| `enable` <Tag variant="new">3.4</Tag> | Name(s) of pipeline component(s) to [enable](/usage/processing-pipelines#disabling). All other pipes will be disabled. ~~Union[str, Iterable[str]]~~ |
|
| `enable` <Tag variant="new">3.4</Tag> | Name(s) of pipeline component(s) to [enable](/usage/processing-pipelines#disabling). All other pipes will be disabled. ~~Union[str, Iterable[str]]~~ |
|
||||||
| `exclude` <Tag variant="new">3</Tag> | Name(s) of pipeline component(s) to [exclude](/usage/processing-pipelines#disabling). Excluded components won't be loaded. ~~Union[str, Iterable[str]]~~ |
|
| `exclude` <Tag variant="new">3</Tag> | Name(s) of pipeline component(s) to [exclude](/usage/processing-pipelines#disabling). Excluded components won't be loaded. ~~Union[str, Iterable[str]]~~ |
|
||||||
| `config` <Tag variant="new">3</Tag> | Optional config overrides, either as nested dict or dict keyed by section value in dot notation, e.g. `"components.name.value"`. ~~Union[Dict[str, Any], Config]~~ |
|
| `config` <Tag variant="new">3</Tag> | Optional config overrides, either as nested dict or dict keyed by section value in dot notation, e.g. `"components.name.value"`. ~~Union[Dict[str, Any], Config]~~ |
|
||||||
| **RETURNS** | A `Language` object with the loaded pipeline. ~~Language~~ |
|
| **RETURNS** | A `Language` object with the loaded pipeline. ~~Language~~ |
|
||||||
|
|
||||||
Essentially, `spacy.load()` is a convenience wrapper that reads the pipeline's
|
Essentially, `spacy.load()` is a convenience wrapper that reads the pipeline's
|
||||||
[`config.cfg`](/api/data-formats#config), uses the language and pipeline
|
[`config.cfg`](/api/data-formats#config), uses the language and pipeline
|
||||||
|
|
|
||||||
|
|
@ -363,7 +363,8 @@ nlp.enable_pipe("tagger")
|
||||||
```
|
```
|
||||||
|
|
||||||
In addition to `disable`, `spacy.load()` also accepts `enable`. If `enable` is
|
In addition to `disable`, `spacy.load()` also accepts `enable`. If `enable` is
|
||||||
set, all components except for those in `enable` are disabled.
|
set, all components except for those in `enable` are disabled. If `enable` and
|
||||||
|
`disable` conflict (i.e. the same component is included in both), an error is raised.
|
||||||
|
|
||||||
```python
|
```python
|
||||||
# Load the complete pipeline, but disable all components except for tok2vec and tagger
|
# Load the complete pipeline, but disable all components except for tok2vec and tagger
|
||||||
|
|
|
||||||
|
|
@ -1,5 +1,31 @@
|
||||||
{
|
{
|
||||||
"resources": [
|
"resources": [
|
||||||
|
{
|
||||||
|
"id": "grecy",
|
||||||
|
"title": "greCy",
|
||||||
|
"slogan": "Ancient Greek pipelines for spaCy",
|
||||||
|
"description": "greCy offers state-of-the-art pipelines for ancient Greek NLP. The repository makes language models available in various sizes, some of them containing floret word vectors and a BERT transformer layer.",
|
||||||
|
"github": "jmyerston/greCy",
|
||||||
|
"code_example": [
|
||||||
|
"import spacy",
|
||||||
|
"#After installing the grc_ud_proiel_trf wheel package from the greCy repository",
|
||||||
|
"",
|
||||||
|
"nlp = spacy.load('grc_ud_proiel_trf')",
|
||||||
|
"doc = nlp('δοκῶ μοι περὶ ὧν πυνθάνεσθε οὐκ ἀμελέτητος εἶναι.')",
|
||||||
|
"",
|
||||||
|
"for token in doc:",
|
||||||
|
" print(token.text, token.norm_, token.lemma_, token.pos_, token.tag_)"
|
||||||
|
],
|
||||||
|
"code_language": "python",
|
||||||
|
"author": "Jacobo Myerston",
|
||||||
|
"author_links": {
|
||||||
|
"twitter": "@jcbmyrstn",
|
||||||
|
"github": "jmyerston",
|
||||||
|
"website": "https://huggingface.co/spaces/Jacobo/syntax"
|
||||||
|
},
|
||||||
|
"category": ["pipeline", "research"],
|
||||||
|
"tags": ["ancient Greek"]
|
||||||
|
},
|
||||||
{
|
{
|
||||||
"id": "spacy-cleaner",
|
"id": "spacy-cleaner",
|
||||||
"title": "spacy-cleaner",
|
"title": "spacy-cleaner",
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue
Block a user