explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 11:29:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Remove model dependency from French lemmatizer tests

Browse Source
This commit is contained in:
ines 2018-07-04 14:46:45 +02:00
parent a0db2e0077
commit 8feb7cfe2d
1 changed files with 8 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
spacy/tests/lang/fr/test_lemmatization.py
View File

@ -4,30 +4,25 @@ from __future__ import unicode_literals
import pytest import pytest
@pytest.mark.models('fr') def test_lemmatizer_verb(fr_tokenizer):
def test_lemmatizer_verb(FR): tokens = fr_tokenizer("Qu'est-ce que tu fais?")
tokens = FR("Qu'est-ce que tu fais?")
assert tokens[0].lemma_ == "que" assert tokens[0].lemma_ == "que"
assert tokens[1].lemma_ == "être" assert tokens[1].lemma_ == "être"
assert tokens[5].lemma_ == "faire" assert tokens[5].lemma_ == "faire"
@pytest.mark.models('fr') def test_lemmatizer_noun_verb_2(fr_tokenizer):
@pytest.mark.xfail(reason="sont tagged as AUX") tokens = fr_tokenizer("Les abaissements de température sont gênants.")
def test_lemmatizer_noun_verb_2(FR):
tokens = FR("Les abaissements de température sont gênants.")
assert tokens[4].lemma_ == "être" assert tokens[4].lemma_ == "être"
@pytest.mark.models('fr')
@pytest.mark.xfail(reason="Costaricienne TAG is PROPN instead of NOUN and spacy don't lemmatize PROPN") @pytest.mark.xfail(reason="Costaricienne TAG is PROPN instead of NOUN and spacy don't lemmatize PROPN")
def test_lemmatizer_noun(FR): def test_lemmatizer_noun(fr_tokenizer):
tokens = FR("il y a des Costaricienne.") tokens = fr_tokenizer("il y a des Costaricienne.")
assert tokens[4].lemma_ == "Costaricain" assert tokens[4].lemma_ == "Costaricain"
@pytest.mark.models('fr') def test_lemmatizer_noun_2(fr_tokenizer):
def test_lemmatizer_noun_2(FR): tokens = fr_tokenizer("Les abaissements de température sont gênants.")
tokens = FR("Les abaissements de température sont gênants.")
assert tokens[1].lemma_ == "abaissement" assert tokens[1].lemma_ == "abaissement"
assert tokens[5].lemma_ == "gênant" assert tokens[5].lemma_ == "gênant"