Fix tests

This commit is contained in:
Ines Montani 2020-10-15 09:29:15 +02:00
parent 178760855f
commit 5d62499266
3 changed files with 5 additions and 55 deletions

View File

@ -127,7 +127,7 @@ def he_tokenizer():
@pytest.fixture(scope="session")
def hi_tokenizer():
return get_lang_class("hi").Defaults.create_tokenizer()
return get_lang_class("hi")().tokenizer
@pytest.fixture(scope="session")
@ -245,14 +245,6 @@ def tr_tokenizer():
return get_lang_class("tr")().tokenizer
@pytest.fixture(scope="session")
def tr_vocab():
return get_lang_class("tr").Defaults.create_vocab()
@pytest.fixture(scope="session")
def tr_vocab():
return get_lang_class("tr").Defaults.create_vocab()
@pytest.fixture(scope="session")
def tt_tokenizer():
return get_lang_class("tt")().tokenizer
@ -305,11 +297,7 @@ def zh_tokenizer_pkuseg():
"segmenter": "pkuseg",
}
},
"initialize": {
"tokenizer": {
"pkuseg_model": "web",
}
},
"initialize": {"tokenizer": {"pkuseg_model": "web",}},
}
nlp = get_lang_class("zh").from_config(config)
nlp.initialize()

View File

@ -1,15 +1,12 @@
# coding: utf-8
from __future__ import unicode_literals
import pytest
from spacy.lang.hi.lex_attrs import norm, like_num
def test_hi_tokenizer_handles_long_text(hi_tokenizer):
text = """
कह 1900 दशक शल (ि जयकर) पत चलत ि उसक
, वद (हर ) पस घर रह वद 10 पहल
पढ करन ि गय उसक टन शल अपन पड
कह 1900 दशक शल (ि जयकर) पत चलत ि उसक
, वद (हर ) पस घर रह वद 10 पहल
पढ करन ि गय उसक टन शल अपन पड
रहन ि (िरण ) बत इस खबर
"""
tokens = hi_tokenizer(text)

View File

@ -1,35 +0,0 @@
# coding: utf8
from __future__ import unicode_literals
from spacy.lang.en import English
from spacy.util import fix_random_seed
def test_issue6177():
"""Test that after fixing the random seed, the results of the pipeline are truly identical"""
# NOTE: no need to transform this code to v3 when 'master' is merged into 'develop'.
# A similar test exists already for v3: test_issue5551
# This is just a backport
results = []
for i in range(3):
fix_random_seed(0)
nlp = English()
example = (
"Once hot, form ping-pong-ball-sized balls of the mixture, each weighing roughly 25 g.",
{"cats": {"Labe1": 1.0, "Label2": 0.0, "Label3": 0.0}},
)
textcat = nlp.create_pipe("textcat")
nlp.add_pipe(textcat)
for label in set(example[1]["cats"]):
textcat.add_label(label)
nlp.begin_training()
# Store the result of each iteration
result = textcat.model.predict([nlp.make_doc(example[0])])
results.append(list(result[0]))
# All results should be the same because of the fixed seed
assert len(results) == 3
assert results[0] == results[1]
assert results[0] == results[2]