spaCy/spacy/cli/info.py
Ines Montani 43b960c01b
Refactor pipeline components, config and language data (#5759)
* Update with WIP

* Update with WIP

* Update with pipeline serialization

* Update types and pipe factories

* Add deep merge, tidy up and add tests

* Fix pipe creation from config

* Don't validate default configs on load

* Update spacy/language.py

Co-authored-by: Ines Montani <ines@ines.io>

* Adjust factory/component meta error

* Clean up factory args and remove defaults

* Add test for failing empty dict defaults

* Update pipeline handling and methods

* provide KB as registry function instead of as object

* small change in test to make functionality more clear

* update example script for EL configuration

* Fix typo

* Simplify test

* Simplify test

* splitting pipes.pyx into separate files

* moving default configs to each component file

* fix batch_size type

* removing default values from component constructors where possible (TODO: test 4725)

* skip instead of xfail

* Add test for config -> nlp with multiple instances

* pipeline.pipes -> pipeline.pipe

* Tidy up, document, remove kwargs

* small cleanup/generalization for Tok2VecListener

* use DEFAULT_UPSTREAM field

* revert to avoid circular imports

* Fix tests

* Replace deprecated arg

* Make model dirs require config

* fix pickling of keyword-only arguments in constructor

* WIP: clean up and integrate full config

* Add helper to handle function args more reliably

Now also includes keyword-only args

* Fix config composition and serialization

* Improve config debugging and add visual diff

* Remove unused defaults and fix type

* Remove pipeline and factories from meta

* Update spacy/default_config.cfg

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Update spacy/default_config.cfg

* small UX edits

* avoid printing stack trace for debug CLI commands

* Add support for language-specific factories

* specify the section of the config which holds the model to debug

* WIP: add Language.from_config

* Update with language data refactor WIP

* Auto-format

* Add backwards-compat handling for Language.factories

* Update morphologizer.pyx

* Fix morphologizer

* Update and simplify lemmatizers

* Fix Japanese tests

* Port over tagger changes

* Fix Chinese and tests

* Update to latest Thinc

* WIP: xfail first Russian lemmatizer test

* Fix component-specific overrides

* fix nO for output layers in debug_model

* Fix default value

* Fix tests and don't pass objects in config

* Fix deep merging

* Fix lemma lookup data registry

Only load the lookups if an entry is available in the registry (and if spacy-lookups-data is installed)

* Add types

* Add Vocab.from_config

* Fix typo

* Fix tests

* Make config copying more elegant

* Fix pipe analysis

* Fix lemmatizers and is_base_form

* WIP: move language defaults to config

* Fix morphology type

* Fix vocab

* Remove comment

* Update to latest Thinc

* Add morph rules to config

* Tidy up

* Remove set_morphology option from tagger factory

* Hack use_gpu

* Move [pipeline] to top-level block and make [nlp.pipeline] list

Allows separating component blocks from component order – otherwise, ordering the config would mean a changed component order, which is bad. Also allows initial config to define more components and not use all of them

* Fix use_gpu and resume in CLI

* Auto-format

* Remove resume from config

* Fix formatting and error

* [pipeline] -> [components]

* Fix types

* Fix tagger test: requires set_morphology?

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
2020-07-22 13:42:59 +02:00

109 lines
3.6 KiB
Python

from typing import Optional, Dict, Any, Union
import platform
from pathlib import Path
from wasabi import Printer
import srsly
from ._util import app, Arg, Opt
from .. import util
from .. import about
@app.command("info")
def info_cli(
# fmt: off
model: Optional[str] = Arg(None, help="Optional model name"),
markdown: bool = Opt(False, "--markdown", "-md", help="Generate Markdown for GitHub issues"),
silent: bool = Opt(False, "--silent", "-s", "-S", help="Don't print anything (just return)"),
# fmt: on
):
"""
Print info about spaCy installation. If a model is speficied as an argument,
print model information. Flag --markdown prints details in Markdown for easy
copy-pasting to GitHub issues.
"""
info(model, markdown=markdown, silent=silent)
def info(
model: Optional[str] = None, *, markdown: bool = False, silent: bool = True
) -> Union[str, dict]:
msg = Printer(no_print=silent, pretty=not silent)
if model:
title = f"Info about model '{model}'"
data = info_model(model, silent=silent)
else:
title = "Info about spaCy"
data = info_spacy()
raw_data = {k.lower().replace(" ", "_"): v for k, v in data.items()}
if "Models" in data and isinstance(data["Models"], dict):
data["Models"] = ", ".join(f"{n} ({v})" for n, v in data["Models"].items())
markdown_data = get_markdown(data, title=title)
if markdown:
if not silent:
print(markdown_data)
return markdown_data
if not silent:
table_data = dict(data)
msg.table(table_data, title=title)
return raw_data
def info_spacy() -> Dict[str, any]:
"""Generate info about the current spaCy intallation.
RETURNS (dict): The spaCy info.
"""
all_models = {}
for pkg_name in util.get_installed_models():
package = pkg_name.replace("-", "_")
all_models[package] = util.get_package_version(pkg_name)
return {
"spaCy version": about.__version__,
"Location": str(Path(__file__).parent.parent),
"Platform": platform.platform(),
"Python version": platform.python_version(),
"Models": all_models,
}
def info_model(model: str, *, silent: bool = True) -> Dict[str, Any]:
"""Generate info about a specific model.
model (str): Model name of path.
silent (bool): Don't print anything, just return.
RETURNS (dict): The model meta.
"""
msg = Printer(no_print=silent, pretty=not silent)
if util.is_package(model):
model_path = util.get_package_path(model)
else:
model_path = model
meta_path = model_path / "meta.json"
if not meta_path.is_file():
msg.fail("Can't find model meta.json", meta_path, exits=1)
meta = srsly.read_json(meta_path)
if model_path.resolve() != model_path:
meta["source"] = str(model_path.resolve())
else:
meta["source"] = str(model_path)
return {k: v for k, v in meta.items() if k not in ("accuracy", "speed")}
def get_markdown(data: Dict[str, Any], title: Optional[str] = None) -> str:
"""Get data in GitHub-flavoured Markdown format for issues etc.
data (dict or list of tuples): Label/value pairs.
title (str / None): Title, will be rendered as headline 2.
RETURNS (str): The Markdown string.
"""
markdown = []
for key, value in data.items():
if isinstance(value, str) and Path(value).exists():
continue
markdown.append(f"* **{key}:** {value}")
result = "\n{}\n".format("\n".join(markdown))
if title:
result = f"\n## {title}\n{result}"
return result