explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 09:56:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Use consistent test names

Browse Source
This commit is contained in:
Ines Montani 2017-01-11 19:00:52 +01:00
parent 33800c9367
commit 7262421bb2
4 changed files with 13 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/tests/doc/test_add_entities.py
View File

@ -7,7 +7,7 @@ from ..util import get_doc
import pytest import pytest
def test_add_entities_set_ents_iob(en_vocab): def test_doc_add_entities_set_ents_iob(en_vocab):
text = ["This", "is", "a", "lion"] text = ["This", "is", "a", "lion"]
doc = get_doc(en_vocab, text) doc = get_doc(en_vocab, text)
ner = EntityRecognizer(en_vocab, features=[(2,), (3,)]) ner = EntityRecognizer(en_vocab, features=[(2,), (3,)])

6
spacy/tests/doc/test_array.py
View File

@ -7,7 +7,7 @@ from ..util import get_doc
import pytest import pytest
def test_array_attr_of_token(en_tokenizer, en_vocab): def test_doc_array_attr_of_token(en_tokenizer, en_vocab):
text = "An example sentence" text = "An example sentence"
tokens = en_tokenizer(text) tokens = en_tokenizer(text)
example = tokens.vocab["example"] example = tokens.vocab["example"]
@ -17,7 +17,7 @@ def test_array_attr_of_token(en_tokenizer, en_vocab):
assert feats_array[0][0] != feats_array[0][1] assert feats_array[0][0] != feats_array[0][1]
def test_array_tag(en_tokenizer): def test_doc_array_tag(en_tokenizer):
text = "A nice sentence." text = "A nice sentence."
tags = ['DET', 'ADJ', 'NOUN', 'PUNCT'] tags = ['DET', 'ADJ', 'NOUN', 'PUNCT']
tokens = en_tokenizer(text) tokens = en_tokenizer(text)
@ -30,7 +30,7 @@ def test_array_tag(en_tokenizer):
assert feats_array[3][1] == doc[3].pos assert feats_array[3][1] == doc[3].pos
def test_array_dep(en_tokenizer): def test_doc_array_dep(en_tokenizer):
text = "A nice sentence." text = "A nice sentence."
deps = ['det', 'amod', 'ROOT', 'punct'] deps = ['det', 'amod', 'ROOT', 'punct']
tokens = en_tokenizer(text) tokens = en_tokenizer(text)

2
spacy/tests/doc/test_noun_chunks.py
View File

@ -9,7 +9,7 @@ from ..util import get_doc
import numpy import numpy
def test_noun_chunks_not_nested(en_tokenizer): def test_doc_noun_chunks_not_nested(en_tokenizer):
text = "Peter has chronic command and control issues" text = "Peter has chronic command and control issues"
heads = [1, 0, 4, 3, -1, -2, -5] heads = [1, 0, 4, 3, -1, -2, -5]
deps = ['nsubj', 'ROOT', 'amod', 'nmod', 'cc', 'conj', 'dobj'] deps = ['nsubj', 'ROOT', 'amod', 'nmod', 'cc', 'conj', 'dobj']

16
spacy/tests/doc/test_token_api.py
View File

@ -8,7 +8,7 @@ import pytest
import numpy import numpy
def test_token_api_strings(en_tokenizer): def test_doc_token_api_strings(en_tokenizer):
text = "Give it back! He pleaded." text = "Give it back! He pleaded."
tags = ['VERB', 'PRON', 'PART', 'PUNCT', 'PRON', 'VERB', 'PUNCT'] tags = ['VERB', 'PRON', 'PART', 'PUNCT', 'PRON', 'VERB', 'PUNCT']
heads = [0, -1, -2, -3, 1, 0, -1] heads = [0, -1, -2, -3, 1, 0, -1]
@ -27,7 +27,7 @@ def test_token_api_strings(en_tokenizer):
assert doc[0].dep_ == 'ROOT' assert doc[0].dep_ == 'ROOT'
def test_token_api_flags(en_tokenizer): def test_doc_token_api_flags(en_tokenizer):
text = "Give it back! He pleaded." text = "Give it back! He pleaded."
tokens = en_tokenizer(text) tokens = en_tokenizer(text)
assert tokens[0].check_flag(IS_ALPHA) assert tokens[0].check_flag(IS_ALPHA)
@ -41,7 +41,7 @@ def test_token_api_flags(en_tokenizer):
@pytest.mark.parametrize('text', ["Give it back! He pleaded."]) @pytest.mark.parametrize('text', ["Give it back! He pleaded."])
def test_token_api_prob_inherited_from_vocab(en_tokenizer, text): def test_doc_token_api_prob_inherited_from_vocab(en_tokenizer, text):
word = text.split()[0] word = text.split()[0]
en_tokenizer.vocab[word].prob = -1 en_tokenizer.vocab[word].prob = -1
tokens = en_tokenizer(text) tokens = en_tokenizer(text)
@ -49,13 +49,13 @@ def test_token_api_prob_inherited_from_vocab(en_tokenizer, text):
@pytest.mark.parametrize('text', ["one two"]) @pytest.mark.parametrize('text', ["one two"])
def test_token_api_str_builtin(en_tokenizer, text): def test_doc_token_api_str_builtin(en_tokenizer, text):
tokens = en_tokenizer(text) tokens = en_tokenizer(text)
assert str(tokens[0]) == text.split(' ')[0] assert str(tokens[0]) == text.split(' ')[0]
assert str(tokens[1]) == text.split(' ')[1] assert str(tokens[1]) == text.split(' ')[1]
def test_token_api_is_properties(en_vocab): def test_doc_token_api_is_properties(en_vocab):
text = ["Hi", ",", "my", "email", "is", "test@me.com"] text = ["Hi", ",", "my", "email", "is", "test@me.com"]
doc = get_doc(en_vocab, text) doc = get_doc(en_vocab, text)
assert doc[0].is_title assert doc[0].is_title
@ -71,7 +71,7 @@ def test_token_api_is_properties(en_vocab):
@pytest.mark.parametrize('text,vectors', [ @pytest.mark.parametrize('text,vectors', [
("apples oranges ldskbjls", ["apples -1 -1 -1", "oranges -1 -1 0"]) ("apples oranges ldskbjls", ["apples -1 -1 -1", "oranges -1 -1 0"])
]) ])
def test_token_api_vectors(en_tokenizer, text_file, text, vectors): def test_doc_token_api_vectors(en_tokenizer, text_file, text, vectors):
text_file.write('\n'.join(vectors)) text_file.write('\n'.join(vectors))
text_file.seek(0) text_file.seek(0)
vector_length = en_tokenizer.vocab.load_vectors(text_file) vector_length = en_tokenizer.vocab.load_vectors(text_file)
@ -89,7 +89,7 @@ def test_token_api_vectors(en_tokenizer, text_file, text, vectors):
numpy.sqrt(numpy.dot(tokens[0].vector, tokens[0].vector))) numpy.sqrt(numpy.dot(tokens[0].vector, tokens[0].vector)))
def test_token_api_ancestors(en_tokenizer): def test_doc_token_api_ancestors(en_tokenizer):
# the structure of this sentence depends on the English annotation scheme # the structure of this sentence depends on the English annotation scheme
text = "Yesterday I saw a dog that barked loudly." text = "Yesterday I saw a dog that barked loudly."
heads = [2, 1, 0, 1, -2, 1, -2, -1, -6] heads = [2, 1, 0, 1, -2, 1, -2, -1, -6]
@ -103,7 +103,7 @@ def test_token_api_ancestors(en_tokenizer):
assert not doc[6].is_ancestor_of(doc[2]) assert not doc[6].is_ancestor_of(doc[2])
def test_token_api_head_setter(en_tokenizer): def test_doc_token_api_head_setter(en_tokenizer):
# the structure of this sentence depends on the English annotation scheme # the structure of this sentence depends on the English annotation scheme
text = "Yesterday I saw a dog that barked loudly." text = "Yesterday I saw a dog that barked loudly."
heads = [2, 1, 0, 1, -2, 1, -2, -1, -6] heads = [2, 1, 0, 1, -2, 1, -2, -1, -6]