explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-11 17:56:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add timer to evaluate

Browse Source
This commit is contained in:
Matthew Honnibal 2017-10-03 09:15:35 -05:00
parent 96da86b3e5
commit a44c4c3a5b
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
spacy/cli/evaluate.py
View File

@ -32,18 +32,25 @@ numpy.random.seed(0)
model=("Model name or path", "positional", None, str), model=("Model name or path", "positional", None, str),
data_path=("Location of JSON-formatted evaluation data", "positional", None, str), data_path=("Location of JSON-formatted evaluation data", "positional", None, str),
gold_preproc=("Use gold preprocessing", "flag", "G", bool), gold_preproc=("Use gold preprocessing", "flag", "G", bool),
gpu_id=("Use GPU", "option", "g", int),
) )
def evaluate(cmd, model, data_path, gold_preproc=False): def evaluate(cmd, model, data_path, gpu_id=-1, gold_preproc=False):
""" """
Train a model. Expects data in spaCy's JSON format. Train a model. Expects data in spaCy's JSON format.
""" """
util.use_gpu(gpu_id)
util.set_env_log(True) util.set_env_log(True)
data_path = util.ensure_path(data_path) data_path = util.ensure_path(data_path)
if not data_path.exists(): if not data_path.exists():
prints(data_path, title="Evaluation data not found", exits=1) prints(data_path, title="Evaluation data not found", exits=1)
corpus = GoldCorpus(data_path, data_path) corpus = GoldCorpus(data_path, data_path)
nlp = util.load_model(model) nlp = util.load_model(model)
scorer = nlp.evaluate(list(corpus.dev_docs(nlp, gold_preproc=gold_preproc))) dev_docs = list(corpus.dev_docs(nlp, gold_preproc=gold_preproc))
begin = timer()
scorer = nlp.evaluate(dev_docs, verbose=False)
end = timer()
nwords = sum(len(doc_gold[0]) for doc_gold in dev_docs)
print('Time', end-begin, 'words', nwords, 'w.p.s', nwords/(end-begin))
print_results(scorer) print_results(scorer)