Update tests

spacy/tests/doc/test_doc_api.py

@@ -2,6 +2,8 @@
 from __future__ import unicode_literals
 
 from ..util import get_doc
+from ...tokens import Doc
+from ...vocab import Vocab
 
 import pytest
 import numpy
@@ -204,17 +206,11 @@ def test_doc_api_right_edge(en_tokenizer):
     assert doc[6].right_edge.text == ','
 
 
-@pytest.mark.xfail
+def test_doc_api_has_vector():
-@pytest.mark.parametrize('text,vectors', [
+    vocab = Vocab()
-    ("apple orange pear", ["apple -1 -1 -1", "orange -1 -1 0", "pear -1 0 -1"])
+    vocab.clear_vectors(2)
-])
+    vocab.vectors.add('kitten', numpy.asarray([0., 2.], dtype='f'))
-def test_doc_api_has_vector(en_tokenizer, text_file, text, vectors):
+    doc = Doc(vocab, words=['kitten'])
-    text_file.write('\n'.join(vectors))
-    text_file.seek(0)
-    vector_length = en_tokenizer.vocab.load_vectors(text_file)
-    assert vector_length == 3
-
-    doc = en_tokenizer(text)
     assert doc.has_vector
 
 def test_lowest_common_ancestor(en_tokenizer):

spacy/tests/doc/test_token_api.py

@@ -3,6 +3,8 @@ from __future__ import unicode_literals
 
 from ...attrs import IS_ALPHA, IS_DIGIT, IS_LOWER, IS_PUNCT, IS_TITLE, IS_STOP
 from ..util import get_doc
+from ...vocab import Vocab
+from ...tokens import Doc
 
 import pytest
 import numpy
@@ -68,26 +70,21 @@ def test_doc_token_api_is_properties(en_vocab):
     assert doc[5].like_email
 
 
-@pytest.mark.xfail
+def test_doc_token_api_vectors():
-@pytest.mark.parametrize('text,vectors', [
+    vocab = Vocab()
-    ("apples oranges ldskbjls", ["apples -1 -1 -1", "oranges -1 -1 0"])
+    vocab.clear_vectors(2)
-])
+    vocab.vectors.add('apples', numpy.asarray([0., 2.], dtype='f'))
-def test_doc_token_api_vectors(en_tokenizer, text_file, text, vectors):
+    vocab.vectors.add('oranges', numpy.asarray([0., 1.], dtype='f'))
-    text_file.write('\n'.join(vectors))
+    doc = Doc(vocab, words=['apples', 'oranges', 'oov'])
-    text_file.seek(0)
+    assert doc.has_vector
-    vector_length = en_tokenizer.vocab.load_vectors(text_file)
-    assert vector_length == 3
 
-    tokens = en_tokenizer(text)
+    assert doc[0].has_vector
-    assert tokens[0].has_vector
+    assert doc[1].has_vector
-    assert tokens[1].has_vector
+    assert not doc[2].has_vector
-    assert not tokens[2].has_vector
+    apples_norm = (0*0 + 2*2) ** 0.5
-    assert tokens[0].similarity(tokens[1]) > tokens[0].similarity(tokens[2])
+    oranges_norm = (0*0 + 1*1) ** 0.5
-    assert tokens[0].similarity(tokens[1]) == tokens[1].similarity(tokens[0])
+    cosine = ((0*0) + (2*1)) / (apples_norm * oranges_norm)
-    assert sum(tokens[0].vector) != sum(tokens[1].vector)
+    assert doc[0].similarity(doc[1]) == cosine
-    assert numpy.isclose(
-        tokens[0].vector_norm,
-        numpy.sqrt(numpy.dot(tokens[0].vector, tokens[0].vector)))
 
 
 def test_doc_token_api_ancestors(en_tokenizer):

spacy/tests/regression/test_issue1305.py

@@ -1,8 +1,11 @@
 import pytest
+import spacy
 
-@pytest.mark.models('en')
+#@pytest.mark.models('en')
-def test_issue1305(EN):
+def test_issue1305():
     '''Test lemmatization of English VBZ'''
-    assert EN.vocab.morphology.lemmatizer('works', 'verb') == set(['work'])
+    nlp = spacy.load('en_core_web_sm')
-    doc = EN(u'This app works well')
+    assert nlp.vocab.morphology.lemmatizer('works', 'verb') == ['work']
+    doc = nlp(u'This app works well')
+    print([(w.text, w.tag_) for w in doc])
     assert doc[2].lemma_ == 'work'

spacy/tests/regression/test_issue781.py

@@ -9,4 +9,4 @@ import pytest
 @pytest.mark.parametrize('word,lemmas', [("chromosomes", ["chromosome"]), ("endosomes", ["endosome"]), ("colocalizes", ["colocalize", "colocaliz"])])
 def test_issue781(EN, word, lemmas):
     lemmatizer = EN.Defaults.create_lemmatizer()
-    assert lemmatizer(word, 'noun', morphology={'number': 'plur'}) == set(lemmas)
+    assert lemmatizer(word, 'noun', morphology={'number': 'plur'}) == lemmas