explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-04 13:40:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

Read features.msgpack instead of features.pkl

Browse Source
This commit is contained in:
Adriane Boyd 2020-10-05 17:47:39 +02:00
parent 187234648c
commit f102ef6b54
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/lang/zh/__init__.py
View File

@ -157,7 +157,7 @@ class ChineseTokenizer(DummyTokenizer):
self.pkuseg_seg.feature_extractor.save(tempdir) self.pkuseg_seg.feature_extractor.save(tempdir)
self.pkuseg_seg.model.save(tempdir) self.pkuseg_seg.model.save(tempdir)
tempdir = Path(tempdir) tempdir = Path(tempdir)
with open(tempdir / "features.pkl", "rb") as fileh: with open(tempdir / "features.msgpack", "rb") as fileh:
pkuseg_features_b = fileh.read() pkuseg_features_b = fileh.read()
with open(tempdir / "weights.npz", "rb") as fileh: with open(tempdir / "weights.npz", "rb") as fileh:
pkuseg_weights_b = fileh.read() pkuseg_weights_b = fileh.read()
@ -198,7 +198,7 @@ class ChineseTokenizer(DummyTokenizer):
if pkuseg_data["features_b"] and pkuseg_data["weights_b"]: if pkuseg_data["features_b"] and pkuseg_data["weights_b"]:
with tempfile.TemporaryDirectory() as tempdir: with tempfile.TemporaryDirectory() as tempdir:
tempdir = Path(tempdir) tempdir = Path(tempdir)
with open(tempdir / "features.pkl", "wb") as fileh: with open(tempdir / "features.msgpack", "wb") as fileh:
fileh.write(pkuseg_data["features_b"]) fileh.write(pkuseg_data["features_b"])
with open(tempdir / "weights.npz", "wb") as fileh: with open(tempdir / "weights.npz", "wb") as fileh:
fileh.write(pkuseg_data["weights_b"]) fileh.write(pkuseg_data["weights_b"])