mirror of
https://github.com/explosion/spaCy.git
synced 2025-02-04 21:50:35 +03:00
e48a09df4e
* OrigAnnot class instead of gold.orig_annot list of zipped tuples * from_orig to replace from_annot_tuples * rename to RawAnnot * some unit tests for GoldParse creation and internal format * removing orig_annot and switching to lists instead of tuple * rewriting tuples to use RawAnnot (+ debug statements, WIP) * fix pop() changing the data * small fixes * pop-append fixes * return RawAnnot for existing GoldParse to have uniform interface * clean up imports * fix merge_sents * add unit test for 4402 with new structure (not working yet) * introduce DocAnnot * typo fixes * add unit test for merge_sents * rename from_orig to from_raw * fixing unit tests * fix nn parser * read_annots to produce text, doc_annot pairs * _make_golds fix * rename golds_to_gold_annots * small fixes * fix encoding * have golds_to_gold_annots use DocAnnot * missed a spot * merge_sents as function in DocAnnot * allow specifying only part of the token-level annotations * refactor with Example class + underlying dicts * pipeline components to work with Example objects (wip) * input checking * fix yielding * fix calls to update * small fixes * fix scorer unit test with new format * fix kwargs order * fixes for ud and conllu scripts * fix reading data for conllu script * add in proper errors (not fixed numbering yet to avoid merge conflicts) * fixing few more small bugs * fix EL script
97 lines
3.3 KiB
Python
97 lines
3.3 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals, division, print_function
|
|
|
|
import plac
|
|
from timeit import default_timer as timer
|
|
from wasabi import Printer
|
|
|
|
from ..gold import GoldCorpus
|
|
from .. import util
|
|
from .. import displacy
|
|
|
|
|
|
@plac.annotations(
|
|
model=("Model name or path", "positional", None, str),
|
|
data_path=("Location of JSON-formatted evaluation data", "positional", None, str),
|
|
gold_preproc=("Use gold preprocessing", "flag", "G", bool),
|
|
gpu_id=("Use GPU", "option", "g", int),
|
|
displacy_path=("Directory to output rendered parses as HTML", "option", "dp", str),
|
|
displacy_limit=("Limit of parses to render as HTML", "option", "dl", int),
|
|
return_scores=("Return dict containing model scores", "flag", "R", bool),
|
|
)
|
|
def evaluate(
|
|
model,
|
|
data_path,
|
|
gpu_id=-1,
|
|
gold_preproc=False,
|
|
displacy_path=None,
|
|
displacy_limit=25,
|
|
return_scores=False,
|
|
):
|
|
"""
|
|
Evaluate a model. To render a sample of parses in a HTML file, set an
|
|
output directory as the displacy_path argument.
|
|
"""
|
|
msg = Printer()
|
|
util.fix_random_seed()
|
|
if gpu_id >= 0:
|
|
util.use_gpu(gpu_id)
|
|
util.set_env_log(False)
|
|
data_path = util.ensure_path(data_path)
|
|
displacy_path = util.ensure_path(displacy_path)
|
|
if not data_path.exists():
|
|
msg.fail("Evaluation data not found", data_path, exits=1)
|
|
if displacy_path and not displacy_path.exists():
|
|
msg.fail("Visualization output directory not found", displacy_path, exits=1)
|
|
corpus = GoldCorpus(data_path, data_path)
|
|
nlp = util.load_model(model)
|
|
dev_dataset = list(corpus.dev_dataset(nlp, gold_preproc=gold_preproc))
|
|
begin = timer()
|
|
scorer = nlp.evaluate(dev_dataset, verbose=False)
|
|
end = timer()
|
|
nwords = sum(len(ex.doc) for ex in dev_dataset)
|
|
results = {
|
|
"Time": "%.2f s" % (end - begin),
|
|
"Words": nwords,
|
|
"Words/s": "%.0f" % (nwords / (end - begin)),
|
|
"TOK": "%.2f" % scorer.token_acc,
|
|
"POS": "%.2f" % scorer.tags_acc,
|
|
"UAS": "%.2f" % scorer.uas,
|
|
"LAS": "%.2f" % scorer.las,
|
|
"NER P": "%.2f" % scorer.ents_p,
|
|
"NER R": "%.2f" % scorer.ents_r,
|
|
"NER F": "%.2f" % scorer.ents_f,
|
|
"Textcat": "%.2f" % scorer.textcat_score,
|
|
}
|
|
msg.table(results, title="Results")
|
|
|
|
if displacy_path:
|
|
docs = [ex.doc for ex in dev_dataset]
|
|
render_deps = "parser" in nlp.meta.get("pipeline", [])
|
|
render_ents = "ner" in nlp.meta.get("pipeline", [])
|
|
render_parses(
|
|
docs,
|
|
displacy_path,
|
|
model_name=model,
|
|
limit=displacy_limit,
|
|
deps=render_deps,
|
|
ents=render_ents,
|
|
)
|
|
msg.good("Generated {} parses as HTML".format(displacy_limit), displacy_path)
|
|
if return_scores:
|
|
return scorer.scores
|
|
|
|
|
|
def render_parses(docs, output_path, model_name="", limit=250, deps=True, ents=True):
|
|
docs[0].user_data["title"] = model_name
|
|
if ents:
|
|
html = displacy.render(docs[:limit], style="ent", page=True)
|
|
with (output_path / "entities.html").open("w", encoding="utf8") as file_:
|
|
file_.write(html)
|
|
if deps:
|
|
html = displacy.render(
|
|
docs[:limit], style="dep", page=True, options={"compact": True}
|
|
)
|
|
with (output_path / "parses.html").open("w", encoding="utf8") as file_:
|
|
file_.write(html)
|