mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 01:48:04 +03:00
b5d999e510
* Add doc.cats to spacy.gold at the paragraph level
Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in
the spacy JSON training format at the paragraph level.
* `spacy.gold.docs_to_json()` writes `docs.cats`
* `GoldCorpus` reads in cats in each `GoldParse`
* Update instances of gold_tuples to handle cats
Update iteration over gold_tuples / gold_parses to handle addition of
cats at the paragraph level.
* Add textcat to train CLI
* Add textcat options to train CLI
* Add textcat labels in `TextCategorizer.begin_training()`
* Add textcat evaluation to `Scorer`:
* For binary exclusive classes with provided label: F1 for label
* For 2+ exclusive classes: F1 macro average
* For multilabel (not exclusive): ROC AUC macro average (currently
relying on sklearn)
* Provide user info on textcat evaluation settings, potential
incompatibilities
* Provide pipeline to Scorer in `Language.evaluate` for textcat config
* Customize train CLI output to include only metrics relevant to current
pipeline
* Add textcat evaluation to evaluate CLI
* Fix handling of unset arguments and config params
Fix handling of unset arguments and model confiug parameters in Scorer
initialization.
* Temporarily add sklearn requirement
* Remove sklearn version number
* Improve Scorer handling of models without textcats
* Fixing Scorer handling of models without textcats
* Update Scorer output for python 2.7
* Modify inf in Scorer for python 2.7
* Auto-format
Also make small adjustments to make auto-formatting with black easier and produce nicer results
* Move error message to Errors
* Update documentation
* Add cats to annotation JSON format [ci skip]
* Fix tpl flag and docs [ci skip]
* Switch to internal roc_auc_score
Switch to internal `roc_auc_score()` adapted from scikit-learn.
* Add AUCROCScore tests and improve errors/warnings
* Add tests for AUCROCScore and roc_auc_score
* Add missing error for only positive/negative values
* Remove unnecessary warnings and errors
* Make reduced roc_auc_score functions private
Because most of the checks and warnings have been stripped for the
internal functions and access is only intended through `ROCAUCScore`,
make the functions for roc_auc_score adapted from scikit-learn private.
* Check that data corresponds with multilabel flag
Check that the training instances correspond with the multilabel flag,
adding the multilabel flag if required.
* Add textcat score to early stopping check
* Add more checks to debug-data for textcat
* Add example training data for textcat
* Add more checks to textcat train CLI
* Check configuration when extending base model
* Fix typos
* Update textcat example data
* Provide licensing details and licenses for data
* Remove two labels with no positive instances from jigsaw-toxic-comment
data.
Co-authored-by: Ines Montani <ines@ines.io>
54 lines
1.5 KiB
Python
54 lines
1.5 KiB
Python
from pathlib import Path
|
|
import plac
|
|
import spacy
|
|
from spacy.gold import docs_to_json
|
|
import srsly
|
|
import sys
|
|
|
|
@plac.annotations(
|
|
model=("Model name. Defaults to 'en'.", "option", "m", str),
|
|
input_file=("Input file (jsonl)", "positional", None, Path),
|
|
output_dir=("Output directory", "positional", None, Path),
|
|
n_texts=("Number of texts to convert", "option", "t", int),
|
|
)
|
|
def convert(model='en', input_file=None, output_dir=None, n_texts=0):
|
|
# Load model with tokenizer + sentencizer only
|
|
nlp = spacy.load(model)
|
|
nlp.disable_pipes(*nlp.pipe_names)
|
|
sentencizer = nlp.create_pipe("sentencizer")
|
|
nlp.add_pipe(sentencizer, first=True)
|
|
|
|
texts = []
|
|
cats = []
|
|
count = 0
|
|
|
|
if not input_file.exists():
|
|
print("Input file not found:", input_file)
|
|
sys.exit(1)
|
|
else:
|
|
with open(input_file) as fileh:
|
|
for line in fileh:
|
|
data = srsly.json_loads(line)
|
|
texts.append(data["text"])
|
|
cats.append(data["cats"])
|
|
|
|
if output_dir is not None:
|
|
output_dir = Path(output_dir)
|
|
if not output_dir.exists():
|
|
output_dir.mkdir()
|
|
else:
|
|
output_dir = Path(".")
|
|
|
|
docs = []
|
|
for i, doc in enumerate(nlp.pipe(texts)):
|
|
doc.cats = cats[i]
|
|
docs.append(doc)
|
|
if n_texts > 0 and count == n_texts:
|
|
break
|
|
count += 1
|
|
|
|
srsly.write_json(output_dir / input_file.with_suffix(".json"), [docs_to_json(docs)])
|
|
|
|
if __name__ == "__main__":
|
|
plac.call(convert)
|