mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-13 13:17:06 +03:00
37c7c85a86
* Support nowrap setting in util.prints * Tidy up and fix whitespace * Simplify script and use read_jsonl helper * Add JSON schemas (see #2928) * Deprecate Doc.print_tree Will be replaced with Doc.to_json, which will produce a unified format * Add Doc.to_json() method (see #2928) Converts Doc objects to JSON using the same unified format as the training data. Method also supports serializing selected custom attributes in the doc._. space. * Remove outdated test * Add write_json and write_jsonl helpers * WIP: Update spacy train * Tidy up spacy train * WIP: Use wasabi for formatting * Add GoldParse helpers for JSON format * WIP: add debug-data command * Fix typo * Add missing import * Update wasabi pin * Add missing import * 💫 Refactor CLI (#2943) To be merged into #2932. ## Description - [x] refactor CLI To use [`wasabi`](https://github.com/ines/wasabi) - [x] use [`black`](https://github.com/ambv/black) for auto-formatting - [x] add `flake8` config - [x] move all messy UD-related scripts to `cli.ud` - [x] make converters function that take the opened file and return the converted data (instead of having them handle the IO) ### Types of change enhancement ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [x] My changes don't require a change to the documentation, or if they do, I've added all required information. * Update wasabi pin * Delete old test * Update errors * Fix typo * Tidy up and format remaining code * Fix formatting * Improve formatting of messages * Auto-format remaining code * Add tok2vec stuff to spacy.train * Fix typo * Update wasabi pin * Fix path checks for when train() is called as function * Reformat and tidy up pretrain script * Update argument annotations * Raise error if model language doesn't match lang * Document new train command
78 lines
2.5 KiB
Python
78 lines
2.5 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import plac
|
|
import platform
|
|
from pathlib import Path
|
|
from wasabi import Printer
|
|
|
|
from ._messages import Messages
|
|
from ..compat import path2str
|
|
from .. import util
|
|
from .. import about
|
|
|
|
|
|
@plac.annotations(
|
|
model=("Optional shortcut link of model", "positional", None, str),
|
|
markdown=("Generate Markdown for GitHub issues", "flag", "md", str),
|
|
silent=("Don't print anything (just return)", "flag", "s"),
|
|
)
|
|
def info(model=None, markdown=False, silent=False):
|
|
"""
|
|
Print info about spaCy installation. If a model shortcut link is
|
|
speficied as an argument, print model information. Flag --markdown
|
|
prints details in Markdown for easy copy-pasting to GitHub issues.
|
|
"""
|
|
msg = Printer()
|
|
if model:
|
|
if util.is_package(model):
|
|
model_path = util.get_package_path(model)
|
|
else:
|
|
model_path = util.get_data_path() / model
|
|
meta_path = model_path / "meta.json"
|
|
if not meta_path.is_file():
|
|
msg.fail(Messages.M020, meta_path, exits=1)
|
|
meta = util.read_json(meta_path)
|
|
if model_path.resolve() != model_path:
|
|
meta["link"] = path2str(model_path)
|
|
meta["source"] = path2str(model_path.resolve())
|
|
else:
|
|
meta["source"] = path2str(model_path)
|
|
if not silent:
|
|
title = "Info about model '{}'".format(model)
|
|
model_meta = {
|
|
k: v for k, v in meta.items() if k not in ("accuracy", "speed")
|
|
}
|
|
if markdown:
|
|
util.print_markdown(model_meta, title=title)
|
|
else:
|
|
msg.table(model_meta, title=title)
|
|
return meta
|
|
data = {
|
|
"spaCy version": about.__version__,
|
|
"Location": path2str(Path(__file__).parent.parent),
|
|
"Platform": platform.platform(),
|
|
"Python version": platform.python_version(),
|
|
"Models": list_models(),
|
|
}
|
|
if not silent:
|
|
title = "Info about spaCy"
|
|
if markdown:
|
|
util.print_markdown(data, title=title)
|
|
else:
|
|
msg.table(data, title=title)
|
|
return data
|
|
|
|
|
|
def list_models():
|
|
def exclude_dir(dir_name):
|
|
# exclude common cache directories and hidden directories
|
|
exclude = ("cache", "pycache", "__pycache__")
|
|
return dir_name in exclude or dir_name.startswith(".")
|
|
|
|
data_path = util.get_data_path()
|
|
if data_path:
|
|
models = [f.parts[-1] for f in data_path.iterdir() if f.is_dir()]
|
|
return ", ".join([m for m in models if not exclude_dir(m)])
|
|
return "-"
|