Tidy up and adjust logging [ci skip]

This commit is contained in:
Ines Montani 2020-09-30 01:22:08 +02:00
parent 56a2f778c4
commit a5debb356d
3 changed files with 12 additions and 8 deletions

View File

@ -27,7 +27,7 @@ def init_vectors_cli(
you can use in the [initialize.vocab] block of your config to initialize you can use in the [initialize.vocab] block of your config to initialize
a model with vectors. a model with vectors.
""" """
util.logger.setLevel(logging.DEBUG if verbose else logging.ERROR) util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
msg.info(f"Creating blank nlp object for language '{lang}'") msg.info(f"Creating blank nlp object for language '{lang}'")
nlp = util.get_lang_class(lang)() nlp = util.get_lang_class(lang)()
convert_vectors(nlp, vectors_loc, truncate=truncate, prune=prune, name=name) convert_vectors(nlp, vectors_loc, truncate=truncate, prune=prune, name=name)
@ -55,14 +55,14 @@ def init_pipeline_cli(
use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU") use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU")
# fmt: on # fmt: on
): ):
util.logger.setLevel(logging.DEBUG if verbose else logging.ERROR) util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
overrides = parse_config_overrides(ctx.args) overrides = parse_config_overrides(ctx.args)
import_code(code_path) import_code(code_path)
setup_gpu(use_gpu) setup_gpu(use_gpu)
with show_validation_error(config_path): with show_validation_error(config_path):
config = util.load_config(config_path, overrides=overrides) config = util.load_config(config_path, overrides=overrides)
with show_validation_error(hint_fill=False): with show_validation_error(hint_fill=False):
nlp = init_nlp(config, use_gpu=use_gpu, silent=False) nlp = init_nlp(config, use_gpu=use_gpu)
nlp.to_disk(output_path) nlp.to_disk(output_path)
msg.good(f"Saved initialized pipeline to {output_path}") msg.good(f"Saved initialized pipeline to {output_path}")
@ -81,9 +81,12 @@ def init_labels_cli(
use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU") use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU")
# fmt: on # fmt: on
): ):
"""Generate a JSON file for labels in the data. This helps speed up the
training process, since spaCy won't have to preprocess the data to
extract the labels."""
util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
if not output_path.exists(): if not output_path.exists():
output_path.mkdir() output_path.mkdir()
util.logger.setLevel(logging.DEBUG if verbose else logging.ERROR)
overrides = parse_config_overrides(ctx.args) overrides = parse_config_overrides(ctx.args)
import_code(code_path) import_code(code_path)
setup_gpu(use_gpu) setup_gpu(use_gpu)
@ -93,7 +96,8 @@ def init_labels_cli(
nlp = init_nlp(config, use_gpu=use_gpu) nlp = init_nlp(config, use_gpu=use_gpu)
for name, component in nlp.pipeline: for name, component in nlp.pipeline:
if getattr(component, "label_data", None) is not None: if getattr(component, "label_data", None) is not None:
srsly.write_json(output_path / f"{name}.json", component.label_data) output_file = output_path / f"{name}.json"
msg.good(f"Saving {name} labels to {output_path}/{name}.json") srsly.write_json(output_file, component.label_data)
msg.good(f"Saving {name} labels to {output_file}")
else: else:
msg.info(f"No labels found for {name}") msg.info(f"No labels found for {name}")

View File

@ -40,7 +40,7 @@ def train_cli(
DOCS: https://nightly.spacy.io/api/cli#train DOCS: https://nightly.spacy.io/api/cli#train
""" """
util.logger.setLevel(logging.DEBUG if verbose else logging.ERROR) util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
verify_cli_args(config_path, output_path) verify_cli_args(config_path, output_path)
overrides = parse_config_overrides(ctx.args) overrides = parse_config_overrides(ctx.args)
import_code(code_path) import_code(code_path)

View File

@ -67,7 +67,7 @@ CONFIG_SECTION_ORDER = ["paths", "variables", "system", "nlp", "components", "co
# fmt: on # fmt: on
logging.basicConfig() logging.basicConfig(format="%(message)s")
logger = logging.getLogger("spacy") logger = logging.getLogger("spacy")