mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 17:06:29 +03:00
add doctests for website 'api'-section (merge)
This commit is contained in:
commit
5dfd2df686
|
@ -1,5 +1,6 @@
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
import pytest
|
import pytest
|
||||||
|
import spacy.en
|
||||||
|
|
||||||
|
|
||||||
@pytest.fixture()
|
@pytest.fixture()
|
||||||
|
@ -13,6 +14,7 @@ def test_load_resources_and_process_text():
|
||||||
doc = nlp('Hello, world. Here are two sentences.')
|
doc = nlp('Hello, world. Here are two sentences.')
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.models
|
||||||
def test_get_tokens_and_sentences(doc):
|
def test_get_tokens_and_sentences(doc):
|
||||||
token = doc[0]
|
token = doc[0]
|
||||||
sentence = doc.sents.next()
|
sentence = doc.sents.next()
|
||||||
|
@ -20,12 +22,11 @@ def test_get_tokens_and_sentences(doc):
|
||||||
assert sentence.text == 'Hello, world.'
|
assert sentence.text == 'Hello, world.'
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.xfail
|
|
||||||
def test_use_integer_ids_for_any_strings(nlp, token):
|
def test_use_integer_ids_for_any_strings(nlp, token):
|
||||||
hello_id = nlp.vocab.strings['Hello']
|
hello_id = nlp.vocab.strings['Hello']
|
||||||
hello_str = nlp.vocab.strings[hello_id]
|
hello_str = nlp.vocab.strings[hello_id]
|
||||||
|
|
||||||
assert token.orth == hello_id == 469755
|
assert token.orth == hello_id == 3404
|
||||||
assert token.orth_ == hello_str == 'Hello'
|
assert token.orth_ == hello_str == 'Hello'
|
||||||
|
|
||||||
|
|
||||||
|
@ -55,19 +56,18 @@ def test_export_to_numpy_arrays(nlp, doc):
|
||||||
assert list(doc_array[:, 1]) == [t.like_url for t in doc]
|
assert list(doc_array[:, 1]) == [t.like_url for t in doc]
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.xfail
|
@pytest.mark.models
|
||||||
def test_word_vectors(nlp):
|
def test_word_vectors(nlp):
|
||||||
doc = nlp("Apples and oranges are similar. Boots and hippos aren't.")
|
doc = nlp("Apples and oranges are similar. Boots and hippos aren't.")
|
||||||
|
|
||||||
apples = doc[0]
|
apples = doc[0]
|
||||||
oranges = doc[1]
|
oranges = doc[2]
|
||||||
boots = doc[6]
|
boots = doc[6]
|
||||||
hippos = doc[8]
|
hippos = doc[8]
|
||||||
|
|
||||||
assert apples.similarity(oranges) > boots.similarity(hippos)
|
assert apples.similarity(oranges) > boots.similarity(hippos)
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.xfail
|
|
||||||
def test_part_of_speech_tags(nlp):
|
def test_part_of_speech_tags(nlp):
|
||||||
from spacy.parts_of_speech import ADV
|
from spacy.parts_of_speech import ADV
|
||||||
|
|
||||||
|
@ -88,6 +88,7 @@ def test_part_of_speech_tags(nlp):
|
||||||
print(token.tag_)
|
print(token.tag_)
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.models
|
||||||
def test_syntactic_dependencies():
|
def test_syntactic_dependencies():
|
||||||
def dependency_labels_to_root(token):
|
def dependency_labels_to_root(token):
|
||||||
'''Walk up the syntactic tree, collecting the arc labels.'''
|
'''Walk up the syntactic tree, collecting the arc labels.'''
|
||||||
|
@ -98,6 +99,7 @@ def test_syntactic_dependencies():
|
||||||
return dep_labels
|
return dep_labels
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.models
|
||||||
def test_named_entities():
|
def test_named_entities():
|
||||||
def iter_products(docs):
|
def iter_products(docs):
|
||||||
for doc in docs:
|
for doc in docs:
|
||||||
|
@ -143,12 +145,14 @@ def test_calculate_inline_mark_up_on_original_string():
|
||||||
return string
|
return string
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.xfail
|
@pytest.mark.models
|
||||||
def test_efficient_binary_serialization(doc):
|
def test_efficient_binary_serialization(doc):
|
||||||
byte_string = doc.as_bytes()
|
from spacy.tokens.doc import Doc
|
||||||
|
|
||||||
|
byte_string = doc.to_bytes()
|
||||||
open('/tmp/moby_dick.bin', 'wb').write(byte_string)
|
open('/tmp/moby_dick.bin', 'wb').write(byte_string)
|
||||||
|
|
||||||
nlp = spacy.en.English()
|
nlp = spacy.en.English()
|
||||||
for byte_string in Doc.read(open('/tmp/moby_dick.bin', 'rb')):
|
for byte_string in Doc.read_bytes(open('/tmp/moby_dick.bin', 'rb')):
|
||||||
doc = Doc(nlp.vocab)
|
doc = Doc(nlp.vocab)
|
||||||
doc.from_bytes(byte_string)
|
doc.from_bytes(byte_string)
|
|
@ -1,8 +1,8 @@
|
||||||
all: src/code site
|
all: src/code site
|
||||||
|
|
||||||
src/code: tests/test_*.py
|
src/code:
|
||||||
mkdir -p src/code/
|
mkdir -p src/code/
|
||||||
./create_code_samples tests/ src/code/
|
./create_code_samples ../tests/website/ src/code/
|
||||||
|
|
||||||
site: site/index.html site/blog/ site/docs/ site/license/ site/blog/introducing-spacy/ site/blog/parsing-english-in-python/ site/blog/part-of-speech-POS-tagger-in-python/ site/tutorials/twitter-filter/ site/tutorials/syntax-search/ site/tutorials/mark-adverbs/ site/blog/writing-c-in-cython/ site/blog/how-spacy-works/
|
site: site/index.html site/blog/ site/docs/ site/license/ site/blog/introducing-spacy/ site/blog/parsing-english-in-python/ site/blog/part-of-speech-POS-tagger-in-python/ site/tutorials/twitter-filter/ site/tutorials/syntax-search/ site/tutorials/mark-adverbs/ site/blog/writing-c-in-cython/ site/blog/how-spacy-works/
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue
Block a user