2023-06-26 12:41:03 +03:00
import hashlib
import os
2020-08-25 01:30:52 +03:00
import shutil
2023-06-26 12:41:03 +03:00
import sys
from configparser import InterpolationError
from contextlib import contextmanager
2020-07-09 02:42:51 +03:00
from pathlib import Path
2023-06-26 12:41:03 +03:00
from typing import (
TYPE_CHECKING ,
Any ,
Dict ,
Iterable ,
List ,
Literal ,
Optional ,
Tuple ,
Union ,
overload ,
)
2020-07-09 02:42:51 +03:00
import srsly
2020-07-10 18:57:40 +03:00
import typer
2020-08-27 19:56:55 +03:00
from click import NoSuchOption
2020-09-21 13:50:13 +03:00
from click . parser import split_arg_string
2020-09-28 16:09:59 +03:00
from thinc . api import Config , ConfigValidationError , require_gpu
2022-05-25 15:06:45 +03:00
from thinc . util import gpu_is_available
2023-06-26 12:41:03 +03:00
from typer . main import get_command
from wasabi import Printer , msg
2023-07-07 10:10:27 +03:00
from weasel import app as project_cli
2020-07-09 02:42:51 +03:00
2020-10-05 21:00:42 +03:00
from . . import about
2023-06-26 12:41:03 +03:00
from . . errors import RENAMED_LANGUAGE_CODES
2023-07-07 10:10:27 +03:00
from . . schemas import validate
2023-06-26 12:41:03 +03:00
from . . util import (
ENV_VARS ,
SimpleFrozenDict ,
import_file ,
is_compatible_version ,
logger ,
make_tempdir ,
registry ,
run_command ,
)
2020-07-09 02:42:51 +03:00
2021-01-30 13:03:25 +03:00
SDIST_SUFFIX = " .tar.gz "
WHEEL_SUFFIX = " -py3-none-any.whl "
2020-07-09 02:42:51 +03:00
PROJECT_FILE = " project.yml "
2020-07-10 18:57:40 +03:00
COMMAND = " python -m spacy "
NAME = " spacy "
HELP = """ spaCy Command-line Interface
2021-01-30 12:09:38 +03:00
DOCS : https : / / spacy . io / api / cli
2020-07-10 18:57:40 +03:00
"""
2020-07-12 14:53:41 +03:00
PROJECT_HELP = f """ Command-line interface for spaCy projects and templates.
You ' d typically start by cloning a project template to a local directory and
fetching its assets like datasets etc . See the project ' s {PROJECT_FILE} for the
available commands .
"""
DEBUG_HELP = """ Suite of helpful commands for debugging and profiling. Includes
commands to check and validate your config files , training and evaluation data ,
and custom model implementations .
2020-07-10 18:57:40 +03:00
"""
2023-01-12 13:55:21 +03:00
BENCHMARK_HELP = """ Commands for benchmarking pipelines. """
2020-09-03 14:13:03 +03:00
INIT_HELP = """ Commands for initializing configs and pipeline packages. """
2020-07-10 18:57:40 +03:00
# Wrappers for Typer's annotations. Initially created to set defaults and to
# keep the names short, but not needed at the moment.
Arg = typer . Argument
Opt = typer . Option
app = typer . Typer ( name = NAME , help = HELP )
2023-01-12 13:55:21 +03:00
benchmark_cli = typer . Typer ( name = " benchmark " , help = BENCHMARK_HELP , no_args_is_help = True )
2020-07-12 14:53:41 +03:00
debug_cli = typer . Typer ( name = " debug " , help = DEBUG_HELP , no_args_is_help = True )
2020-08-02 16:18:30 +03:00
init_cli = typer . Typer ( name = " init " , help = INIT_HELP , no_args_is_help = True )
2020-07-12 14:53:41 +03:00
2023-07-07 10:10:27 +03:00
app . add_typer ( project_cli , name = " project " , help = PROJECT_HELP , no_args_is_help = True )
2020-07-12 14:53:41 +03:00
app . add_typer ( debug_cli )
2023-01-12 13:55:21 +03:00
app . add_typer ( benchmark_cli )
2020-08-02 16:18:30 +03:00
app . add_typer ( init_cli )
2020-07-10 18:57:40 +03:00
def setup_cli ( ) - > None :
2020-09-08 16:23:34 +03:00
# Make sure the entry-point for CLI runs, so that they get imported.
registry . cli . get_all ( )
2020-07-10 18:57:40 +03:00
# Ensure that the help messages always display the correct prompt
command = get_command ( app )
command ( prog_name = COMMAND )
2020-09-21 13:50:13 +03:00
def parse_config_overrides (
2020-09-30 16:15:11 +03:00
args : List [ str ] , env_var : Optional [ str ] = ENV_VARS . CONFIG_OVERRIDES
2020-09-21 12:25:10 +03:00
) - > Dict [ str , Any ] :
2020-07-10 18:57:40 +03:00
""" Generate a dictionary of config overrides based on the extra arguments
provided on the CLI , e . g . - - training . batch_size to override
" training.batch_size " . Arguments without a " . " are considered invalid ,
since the config only allows top - level sections to exist .
2020-09-21 13:50:13 +03:00
env_vars ( Optional [ str ] ) : Optional environment variable to read from .
2020-07-10 18:57:40 +03:00
RETURNS ( Dict [ str , Any ] ) : The parsed dict , keyed by nested config setting .
"""
2020-09-21 13:50:13 +03:00
env_string = os . environ . get ( env_var , " " ) if env_var else " "
env_overrides = _parse_overrides ( split_arg_string ( env_string ) )
cli_overrides = _parse_overrides ( args , is_cli = True )
if cli_overrides :
keys = [ k for k in cli_overrides if k not in env_overrides ]
2023-02-02 13:15:22 +03:00
logger . debug ( " Config overrides from CLI: %s " , keys )
2020-09-21 13:50:13 +03:00
if env_overrides :
2023-02-02 13:15:22 +03:00
logger . debug ( " Config overrides from env variables: %s " , list ( env_overrides ) )
2020-09-21 13:50:13 +03:00
return { * * cli_overrides , * * env_overrides }
def _parse_overrides ( args : List [ str ] , is_cli : bool = False ) - > Dict [ str , Any ] :
result = { }
2020-07-10 18:57:40 +03:00
while args :
opt = args . pop ( 0 )
2020-09-21 13:50:13 +03:00
err = f " Invalid config override ' { opt } ' "
2020-07-10 18:57:40 +03:00
if opt . startswith ( " -- " ) : # new argument
2020-08-27 19:56:55 +03:00
orig_opt = opt
2020-08-18 17:06:37 +03:00
opt = opt . replace ( " -- " , " " )
2020-07-10 18:57:40 +03:00
if " . " not in opt :
2020-09-21 13:50:13 +03:00
if is_cli :
raise NoSuchOption ( orig_opt )
else :
msg . fail ( f " { err } : can ' t override top-level sections " , exits = 1 )
2020-07-28 14:43:15 +03:00
if " = " in opt : # we have --opt=value
opt , value = opt . split ( " = " , 1 )
2020-08-18 17:06:37 +03:00
opt = opt . replace ( " - " , " _ " )
2020-07-10 18:57:40 +03:00
else :
2020-07-28 14:43:15 +03:00
if not args or args [ 0 ] . startswith ( " -- " ) : # flag with no value
value = " true "
else :
value = args . pop ( 0 )
2021-02-10 05:45:27 +03:00
result [ opt ] = _parse_override ( value )
2020-07-10 18:57:40 +03:00
else :
2020-09-21 13:50:13 +03:00
msg . fail ( f " { err } : name should start with -- " , exits = 1 )
return result
2020-07-09 02:42:51 +03:00
2021-02-10 05:45:27 +03:00
def _parse_override ( value : Any ) - > Any :
# Just like we do in the config, we're calling json.loads on the
# values. But since they come from the CLI, it'd be unintuitive to
# explicitly mark strings with escaped quotes. So we're working
# around that here by falling back to a string if parsing fails.
# TODO: improve logic to handle simple types like list of strings?
try :
return srsly . json_loads ( value )
except ValueError :
return str ( value )
2023-01-31 19:30:43 +03:00
def _handle_renamed_language_codes ( lang : Optional [ str ] ) - > None :
# Throw error for renamed language codes in v4
if lang in RENAMED_LANGUAGE_CODES :
msg . fail (
title = " Renamed language code " ,
text = f " Language code ' { lang } ' was replaced with ' { RENAMED_LANGUAGE_CODES [ lang ] } ' in spaCy v4. Update the language code from ' { lang } ' to ' { RENAMED_LANGUAGE_CODES [ lang ] } ' . " ,
exits = 1 ,
)
2020-07-11 00:34:17 +03:00
@contextmanager
2020-08-02 16:18:30 +03:00
def show_validation_error (
file_path : Optional [ Union [ str , Path ] ] = None ,
* ,
2020-09-26 14:13:57 +03:00
title : Optional [ str ] = None ,
desc : str = " " ,
show_config : Optional [ bool ] = None ,
2020-08-14 17:49:26 +03:00
hint_fill : bool = True ,
2020-08-02 16:18:30 +03:00
) :
2020-07-11 00:34:17 +03:00
""" Helper to show custom config validation errors on the CLI.
2020-08-02 16:18:30 +03:00
file_path ( str / Path ) : Optional file path of config file , used in hints .
2020-09-26 14:13:57 +03:00
title ( str ) : Override title of custom formatted error .
desc ( str ) : Override description of custom formatted error .
show_config ( bool ) : Whether to output the config the error refers to .
2020-08-14 17:49:26 +03:00
hint_fill ( bool ) : Show hint about filling config .
2020-07-11 00:34:17 +03:00
"""
try :
yield
2020-09-26 14:13:57 +03:00
except ConfigValidationError as e :
title = title if title is not None else e . title
2020-09-27 23:31:57 +03:00
if e . desc :
desc = f " { e . desc } " if not desc else f " { e . desc } \n \n { desc } "
2020-09-26 14:13:57 +03:00
# Re-generate a new error object with overrides
err = e . from_error ( e , title = " " , desc = desc , show_config = show_config )
msg . fail ( title )
print ( err . text . strip ( ) )
if hint_fill and " value_error.missing " in err . error_types :
2020-12-08 12:44:59 +03:00
config_path = (
2020-12-08 12:41:18 +03:00
file_path
if file_path is not None and str ( file_path ) != " - "
else " config.cfg "
)
2020-08-02 16:18:30 +03:00
msg . text (
" If your config contains missing values, you can run the ' init "
2020-08-14 17:49:26 +03:00
" fill-config ' command to fill in all the defaults, if possible: " ,
2020-08-02 16:18:30 +03:00
spaced = True ,
)
2020-10-06 10:47:23 +03:00
print ( f " { COMMAND } init fill-config { config_path } { config_path } \n " )
2020-07-11 00:34:17 +03:00
sys . exit ( 1 )
2020-09-27 23:41:00 +03:00
except InterpolationError as e :
msg . fail ( " Config validation error " , e , exits = 1 )
2020-07-11 14:03:53 +03:00
Accept multiple code files in all CLI commands (#12101)
* Add support for multiple code files to all relevant commands
Prior to this, only the package command supported multiple code files.
* Update docs
* Add debug data test, plus generic fixtures
One tricky thing here: it's tempting to create the config by creating a
pipeline in code, but that requires declaring the custom components
here. However the CliRunner appears to be run in the same process or
otherwise have access to our registry, so it works even without any
code arguments. So it's necessary to avoid declaring the components in
the tests.
* Add debug config test and restructure
The code argument imports the provided file. If it adds item to the
registry, that affects global state, which CliRunner doesn't isolate.
Since there's no standard way to remove things from the registry, this
instead uses subprocess.run to run commands.
* Use a more generic, parametrized test
* Add output arg for assemble and pretrain
Assemble and pretrain require an output argument. This commit adds
assemble testing, but not pretrain, as that requires an actual trainable
component, which is not currently in the test config.
* Add evaluate test and some cleanup
* Mark tests as slow
* Revert argument name change
* Apply suggestions from code review
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
* Format API CLI docs
* isort
* Fix imports in tests
* isort
* Undo changes to package CLI help
* Fix python executable and lang code in test
* Fix executable in another test
---------
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: Raphael Mitsch <r.mitsch@outlook.com>
2023-08-01 16:24:02 +03:00
def import_code_paths ( code_paths : str ) - > None :
""" Helper to import comma-separated list of code paths. """
code_paths = [ Path ( p . strip ( ) ) for p in string_to_list ( code_paths ) ]
for code_path in code_paths :
import_code ( code_path )
2020-07-11 14:03:53 +03:00
def import_code ( code_path : Optional [ Union [ Path , str ] ] ) - > None :
""" Helper to import Python file provided in training commands / commands
using the config . This makes custom registered functions available .
"""
if code_path is not None :
if not Path ( code_path ) . exists ( ) :
msg . fail ( " Path to Python code not found " , code_path , exits = 1 )
try :
import_file ( " python_code " , code_path )
except Exception as e :
msg . fail ( f " Couldn ' t load Python code: { code_path } " , e , exits = 1 )
2020-08-05 00:39:19 +03:00
2020-09-13 11:52:28 +03:00
def get_git_version (
error : str = " Could not run ' git ' . Make sure it ' s installed and the executable is available. " ,
) - > Tuple [ int , int ] :
""" Get the version of git and raise an error if calling ' git --version ' fails.
error ( str ) : The error message to show .
RETURNS ( Tuple [ int , int ] ) : The version as a ( major , minor ) tuple . Returns
( 0 , 0 ) if the version couldn ' t be determined.
"""
🏷 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 16:21:40 +03:00
try :
ret = run_command ( " git --version " , capture = True )
except :
raise RuntimeError ( error )
2020-09-13 11:52:28 +03:00
stdout = ret . stdout . strip ( )
if not stdout or not stdout . startswith ( " git version " ) :
🏷 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 16:21:40 +03:00
return 0 , 0
2020-09-13 11:52:28 +03:00
version = stdout [ 11 : ] . strip ( ) . split ( " . " )
🏷 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 16:21:40 +03:00
return int ( version [ 0 ] ) , int ( version [ 1 ] )
2020-09-10 16:49:13 +03:00
🏷 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 16:21:40 +03:00
@overload
def string_to_list ( value : str , intify : Literal [ False ] = . . . ) - > List [ str ] :
. . .
@overload
def string_to_list ( value : str , intify : Literal [ True ] ) - > List [ int ] :
. . .
2020-09-13 11:52:02 +03:00
def string_to_list ( value : str , intify : bool = False ) - > Union [ List [ str ] , List [ int ] ] :
""" Parse a comma-separated string to a list and account for various
formatting options . Mostly used to handle CLI arguments that take a list of
comma - separated values .
value ( str ) : The value to parse .
intify ( bool ) : Whether to convert values to ints .
RETURNS ( Union [ List [ str ] , List [ int ] ] ) : A list of strings or ints .
"""
2020-09-12 15:43:22 +03:00
if not value :
🏷 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 16:21:40 +03:00
return [ ] # type: ignore[return-value]
2020-09-12 15:43:22 +03:00
if value . startswith ( " [ " ) and value . endswith ( " ] " ) :
value = value [ 1 : - 1 ]
result = [ ]
for p in value . split ( " , " ) :
p = p . strip ( )
if p . startswith ( " ' " ) and p . endswith ( " ' " ) :
p = p [ 1 : - 1 ]
if p . startswith ( ' " ' ) and p . endswith ( ' " ' ) :
p = p [ 1 : - 1 ]
p = p . strip ( )
if intify :
🏷 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 16:21:40 +03:00
p = int ( p ) # type: ignore[assignment]
2020-09-12 15:43:22 +03:00
result . append ( p )
return result
2020-09-28 16:09:59 +03:00
2021-07-06 15:16:19 +03:00
def setup_gpu ( use_gpu : int , silent = None ) - > None :
2020-09-28 22:17:10 +03:00
""" Configure the GPU and log info. """
2021-07-06 20:08:08 +03:00
if silent is None :
local_msg = Printer ( )
else :
local_msg = Printer ( no_print = silent , pretty = not silent )
2020-09-28 16:09:59 +03:00
if use_gpu > = 0 :
2021-07-06 20:08:08 +03:00
local_msg . info ( f " Using GPU: { use_gpu } " )
2020-09-28 16:09:59 +03:00
require_gpu ( use_gpu )
else :
2021-07-06 20:08:08 +03:00
local_msg . info ( " Using CPU " )
2022-05-25 15:06:45 +03:00
if gpu_is_available ( ) :
2021-07-06 20:08:08 +03:00
local_msg . info ( " To switch to GPU 0, use the option: --gpu-id 0 " )
2022-09-28 18:16:05 +03:00
2022-12-20 19:11:33 +03:00
def walk_directory ( path : Path , suffix : Optional [ str ] = None ) - > List [ Path ] :
2023-01-05 12:21:00 +03:00
""" Given a directory and a suffix, recursively find all files matching the suffix.
Directories or files with names beginning with a . are ignored , but hidden flags on
filesystems are not checked .
When provided with a suffix ` None ` , there is no suffix - based filtering . """
2022-12-20 19:11:33 +03:00
if not path . is_dir ( ) :
return [ path ]
paths = [ path ]
locs = [ ]
seen = set ( )
for path in paths :
if str ( path ) in seen :
continue
seen . add ( str ( path ) )
if path . parts [ - 1 ] . startswith ( " . " ) :
continue
elif path . is_dir ( ) :
paths . extend ( path . iterdir ( ) )
elif suffix is not None and not path . parts [ - 1 ] . endswith ( suffix ) :
continue
else :
locs . append ( path )
# It's good to sort these, in case the ordering messes up cache.
locs . sort ( )
return locs
2022-09-28 18:16:05 +03:00
def _format_number ( number : Union [ int , float ] , ndigits : int = 2 ) - > str :
""" Formats a number (float or int) rounding to `ndigits`, without truncating trailing 0s,
as happens with ` round ( number , ndigits ) ` """
if isinstance ( number , float ) :
return f " { number : . { ndigits } f } "
else :
return str ( number )