explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-10 16:22:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Refactor CLI

Browse Source
This commit is contained in:
Matthew Honnibal 2017-05-21 17:49:10 -05:00
parent cc569a348d
commit 7811d97339
1 changed files with 95 additions and 102 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

73
spacy/__main__.py
View File

@ -13,18 +13,12 @@ from spacy.cli import model as cli_model
from spacy.cli import convert as cli_convert
class CLI(object):
"""
Command-line interface for spaCy
"""
commands = ('download', 'link', 'info', 'package', 'train', 'model', 'convert')
@plac.annotations(
@plac.annotations(
model=("model to download (shortcut or model name)", "positional", None, str),
direct=("force direct download. Needs model name with version and won't "
"perform compatibility check", "flag", "d", bool)
)
def download(self, model, direct=False):
)
def download(model, direct=False):
"""
Download compatible model from default download path using pip. Model
can be shortcut, model name or, if --direct flag is set, full model name
@ -33,12 +27,12 @@ class CLI(object):
cli_download(model, direct)
@plac.annotations(
@plac.annotations(
origin=("package name or local path to model", "positional", None, str),
link_name=("name of shortuct link to create", "positional", None, str),
force=("force overwriting of existing link", "flag", "f", bool)
)
def link(self, origin, link_name, force=False):
)
def link(origin, link_name, force=False):
"""
Create a symlink for models within the spacy/data directory. Accepts
either the name of a pip package, or the local path to the model data
@ -47,11 +41,11 @@ class CLI(object):
cli_link(origin, link_name, force)
@plac.annotations(
@plac.annotations(
model=("optional: shortcut link of model", "positional", None, str),
markdown=("generate Markdown for GitHub issues", "flag", "md", str)
)
def info(self, model=None, markdown=False):
)
def info(model=None, markdown=False):
"""
Print info about spaCy installation. If a model shortcut link is
speficied as an argument, print model information. Flag --markdown
@ -60,13 +54,13 @@ class CLI(object):
cli_info(model, markdown)
@plac.annotations(
@plac.annotations(
input_dir=("directory with model data", "positional", None, str),
output_dir=("output parent directory", "positional", None, str),
meta=("path to meta.json", "option", "m", str),
force=("force overwriting of existing folder in output directory", "flag", "f", bool)
)
def package(self, input_dir, output_dir, meta=None, force=False):
)
def package(input_dir, output_dir, meta=None, force=False):
"""
Generate Python package for model data, including meta and required
installation files. A new directory will be created in the specified
@ -75,7 +69,7 @@ class CLI(object):
cli_package(input_dir, output_dir, meta, force)
@plac.annotations(
@plac.annotations(
lang=("model language", "positional", None, str),
output_dir=("output directory to store model in", "positional", None, str),
train_data=("location of JSON-formatted training data", "positional", None, str),
@ -87,8 +81,8 @@ class CLI(object):
no_tagger=("Don't train tagger", "flag", "T", bool),
no_parser=("Don't train parser", "flag", "P", bool),
no_entities=("Don't train NER", "flag", "N", bool)
)
def train(self, lang, output_dir, train_data, dev_data=None, n_iter=15,
)
def train(lang, output_dir, train_data, dev_data=None, n_iter=15,
nsents=0, parser_L1=0.0, use_gpu=False,
no_tagger=False, no_parser=False, no_entities=False):
"""
@ -98,36 +92,32 @@ class CLI(object):
cli_train(lang, output_dir, train_data, dev_data, n_iter, nsents,
use_gpu, no_tagger, no_parser, no_entities, parser_L1)
@plac.annotations(
lang=("model language", "positional", None, str),
model_dir=("output directory to store model in", "positional", None, str),
freqs_data=("tab-separated frequencies file", "positional", None, str),
clusters_data=("Brown clusters file", "positional", None, str),
vectors_data=("word vectors file", "positional", None, str)
)
def model(self, lang, model_dir, freqs_data, clusters_data=None, vectors_data=None):
"""
Initialize a new model and its data directory.
"""
cli_model(lang, model_dir, freqs_data, clusters_data, vectors_data)
@plac.annotations(
@plac.annotations(
input_file=("input file", "positional", None, str),
output_dir=("output directory for converted file", "positional", None, str),
n_sents=("Number of sentences per doc", "option", "n", float),
morphology=("Enable appending morphology to tags", "flag", "m", bool)
)
def convert(self, input_file, output_dir, n_sents=10, morphology=False):
)
def convert(input_file, output_dir, n_sents=10, morphology=False):
"""
Convert files into JSON format for use with train command and other
experiment management functions.
"""
cli_convert(input_file, output_dir, n_sents, morphology)
@plac.annotations(
lang=("model language", "positional", None, str),
model_dir=("output directory to store model in", "positional", None, str),
freqs_data=("tab-separated frequencies file", "positional", None, str),
clusters_data=("Brown clusters file", "positional", None, str),
vectors_data=("word vectors file", "positional", None, str)
)
def model(lang, model_dir, freqs_data, clusters_data=None, vectors_data=None):
"""
Initialize a new model and its data directory.
"""
cli_model(lang, model_dir, freqs_data, clusters_data, vectors_data)
def __missing__(self, name):
print("\n Command %r does not exist."
"\n Use the --help flag for a list of available commands.\n" % name)
@plac.annotations(
lang=("model language", "positional", None, str),
@ -147,6 +137,7 @@ def train(self, lang, output_dir, train_data, dev_data=None, n_iter=15,
"""
Train a model. Expects data in spaCy's JSON format.
"""
print(train_data, dev_data)
nsents = nsents or None
cli_train(lang, output_dir, train_data, dev_data, n_iter, nsents,
use_gpu, no_tagger, no_parser, no_entities)
@ -157,3 +148,5 @@ if __name__ == '__main__':
import sys
if sys.argv[1] == 'train':
plac.call(train)
if sys.argv[1] == 'convert':
plac.call(convert)