explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-26 09:14:32 +03:00
Code Issues Packages Projects Releases Wiki Activity

Try to make test999 less flakey

Browse Source
This commit is contained in:
Matthew Honnibal 2017-04-26 18:42:06 +02:00
parent 527d51ac9a
commit 24c4c51f13
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/tests/regression/test_issue999.py
View File

@ -1,5 +1,4 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import json
import os import os
import random import random
import contextlib import contextlib
@ -12,7 +11,7 @@ from pathlib import Path
import pathlib import pathlib
from ...gold import GoldParse from ...gold import GoldParse
from ...pipeline import EntityRecognizer from ...pipeline import EntityRecognizer
from ...en import English from ...language import Language
try: try:
unicode unicode
@ -51,8 +50,8 @@ def test_issue999(train_data):
2) There's no way to set the learning rate for the weight update, so we 2) There's no way to set the learning rate for the weight update, so we
end up out-of-scale, causing it to learn too fast. end up out-of-scale, causing it to learn too fast.
''' '''
nlp = English(entity=False) nlp = Language(path=None, entity=False, tagger=False, parser=False)
nlp.entity = EntityRecognizer(nlp.vocab, features=English.Defaults.entity_features) nlp.entity = EntityRecognizer(nlp.vocab, features=Language.Defaults.entity_features)
for _, offsets in train_data: for _, offsets in train_data:
for start, end, ent_type in offsets: for start, end, ent_type in offsets:
nlp.entity.add_label(ent_type) nlp.entity.add_label(ent_type)
@ -65,7 +64,7 @@ def test_issue999(train_data):
loss = nlp.entity.update(doc, gold) loss = nlp.entity.update(doc, gold)
with temp_save_model(nlp) as model_dir: with temp_save_model(nlp) as model_dir:
nlp2 = English(path=model_dir) nlp2 = Language(path=model_dir)
for raw_text, entity_offsets in train_data: for raw_text, entity_offsets in train_data:
doc = nlp2(raw_text) doc = nlp2(raw_text)