Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Improve lemmatization tests, re #1296

This commit is contained in:
Matthew Honnibal 2017-09-04 15:17:44 +02:00
parent c0eaba8b28
commit 644d6c9e1a
1 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
spacy/tests/lang/en/test_lemmatizer.py
View File

@ -2,12 +2,18 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import pytest import pytest
from ....tokens.doc import Doc
@pytest.fixture @pytest.fixture
def en_lemmatizer(EN): def en_lemmatizer(EN):
return EN.Defaults.create_lemmatizer() return EN.Defaults.create_lemmatizer()
@pytest.mark.models('en')
def test_doc_lemmatization(EN):
doc = Doc(EN.vocab, words=['bleed'])
doc[0].tag_ = 'VBP'
assert doc[0].lemma_ == 'bleed'
@pytest.mark.models('en') @pytest.mark.models('en')
@pytest.mark.parametrize('text,lemmas', [("aardwolves", ["aardwolf"]), @pytest.mark.parametrize('text,lemmas', [("aardwolves", ["aardwolf"]),
@ -19,6 +25,16 @@ def test_en_lemmatizer_noun_lemmas(en_lemmatizer, text, lemmas):
assert en_lemmatizer.noun(text) == set(lemmas) assert en_lemmatizer.noun(text) == set(lemmas)
@pytest.mark.models('en')
@pytest.mark.parametrize('text,lemmas', [("bleed", ["bleed"]),
("feed", ["feed"]),
("need", ["need"]),
("ring", ["ring"]),
("axes", ["axis", "axe", "ax"])])
def test_en_lemmatizer_noun_lemmas(en_lemmatizer, text, lemmas):
assert en_lemmatizer.noun(text) == set(lemmas)
@pytest.mark.xfail @pytest.mark.xfail
@pytest.mark.models('en') @pytest.mark.models('en')
def test_en_lemmatizer_base_forms(en_lemmatizer): def test_en_lemmatizer_base_forms(en_lemmatizer):