explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-31 16:07:41 +03:00
Code Issues Packages Projects Releases Wiki Activity

Improve profiling

Browse Source
This commit is contained in:
Matthew Honnibal 2017-11-15 13:51:25 +01:00
parent b797dca977
commit 8d692771f6
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/cli/profile.py
View File

@ -11,6 +11,7 @@ import spacy
import sys
import tqdm
import cytoolz
import thinc.extra.datasets
def read_inputs(loc):
@ -32,14 +33,18 @@ def profile(cmd, lang, inputs=None):
"""
Profile a spaCy pipeline, to find out which functions take the most time.
"""
if inputs is None:
imdb_train, _ = thinc.extra.datasets.imdb()
inputs, _ = zip(*imdb_train)
inputs = inputs[:2000]
nlp = spacy.load(lang)
texts = list(cytoolz.take(10000, inputs))
cProfile.runctx("parse_texts(nlp, texts)", globals(), locals(),
"Profile.prof")
s = pstats.Stats("Profile.prof")
s.strip_dirs().sort_stats("time").print_stats()
s.strip_dirs().sort_stats("cumtime").print_stats()
def parse_texts(nlp, texts):
for doc in nlp.pipe(tqdm.tqdm(texts), batch_size=128):
for doc in nlp.pipe(tqdm.tqdm(texts), batch_size=16):
pass