explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-05 14:10:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

Simplify tests and avoid tokenizing

Browse Source
This commit is contained in:
Ines Montani 2019-03-10 15:05:56 +01:00
parent a5b1f6dcec
commit 6bbf4ea309
1 changed files with 20 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
spacy/tests/doc/test_array.py
View File

@ -1,46 +1,43 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from spacy.tokens import Doc
from spacy.attrs import ORTH, SHAPE, POS, DEP from spacy.attrs import ORTH, SHAPE, POS, DEP
from ..util import get_doc from ..util import get_doc
def test_doc_array_attr_of_token(en_tokenizer, en_vocab): def test_doc_array_attr_of_token(en_vocab):
text = "An example sentence" doc = Doc(en_vocab, words=["An", "example", "sentence"])
tokens = en_tokenizer(text) example = doc.vocab["example"]
example = tokens.vocab["example"]
assert example.orth != example.shape assert example.orth != example.shape
feats_array = tokens.to_array((ORTH, SHAPE)) feats_array = doc.to_array((ORTH, SHAPE))
assert feats_array[0][0] != feats_array[0][1] assert feats_array[0][0] != feats_array[0][1]
assert feats_array[0][0] != feats_array[0][1] assert feats_array[0][0] != feats_array[0][1]
def test_doc_stringy_array_attr_of_token(en_tokenizer, en_vocab): def test_doc_stringy_array_attr_of_token(en_vocab):
text = "An example sentence" doc = Doc(en_vocab, words=["An", "example", "sentence"])
tokens = en_tokenizer(text) example = doc.vocab["example"]
example = tokens.vocab["example"]
assert example.orth != example.shape assert example.orth != example.shape
feats_array = tokens.to_array((ORTH, SHAPE)) feats_array = doc.to_array((ORTH, SHAPE))
feats_array_stringy = tokens.to_array(("ORTH", "SHAPE")) feats_array_stringy = doc.to_array(("ORTH", "SHAPE"))
assert feats_array_stringy[0][0] == feats_array[0][0] assert feats_array_stringy[0][0] == feats_array[0][0]
assert feats_array_stringy[0][1] == feats_array[0][1] assert feats_array_stringy[0][1] == feats_array[0][1]
def test_doc_scalar_attr_of_token(en_tokenizer, en_vocab): def test_doc_scalar_attr_of_token(en_vocab):
text = "An example sentence" doc = Doc(en_vocab, words=["An", "example", "sentence"])
tokens = en_tokenizer(text) example = doc.vocab["example"]
example = tokens.vocab["example"]
assert example.orth != example.shape assert example.orth != example.shape
feats_array = tokens.to_array(ORTH) feats_array = doc.to_array(ORTH)
assert feats_array.shape == (3,) assert feats_array.shape == (3,)
def test_doc_array_tag(en_tokenizer): def test_doc_array_tag(en_vocab):
text = "A nice sentence." words = ["A", "nice", "sentence", "."]
pos = ["DET", "ADJ", "NOUN", "PUNCT"] pos = ["DET", "ADJ", "NOUN", "PUNCT"]
tokens = en_tokenizer(text) doc = get_doc(en_vocab, words=words, pos=pos)
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], pos=pos)
assert doc[0].pos != doc[1].pos != doc[2].pos != doc[3].pos assert doc[0].pos != doc[1].pos != doc[2].pos != doc[3].pos
feats_array = doc.to_array((ORTH, POS)) feats_array = doc.to_array((ORTH, POS))
assert feats_array[0][1] == doc[0].pos assert feats_array[0][1] == doc[0].pos
@ -49,11 +46,10 @@ def test_doc_array_tag(en_tokenizer):
assert feats_array[3][1] == doc[3].pos assert feats_array[3][1] == doc[3].pos
def test_doc_array_dep(en_tokenizer): def test_doc_array_dep(en_vocab):
text = "A nice sentence." words = ["A", "nice", "sentence", "."]
deps = ["det", "amod", "ROOT", "punct"] deps = ["det", "amod", "ROOT", "punct"]
tokens = en_tokenizer(text) doc = get_doc(en_vocab, words=words, deps=deps)
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], deps=deps)
feats_array = doc.to_array((ORTH, DEP)) feats_array = doc.to_array((ORTH, DEP))
assert feats_array[0][1] == doc[0].dep assert feats_array[0][1] == doc[0].dep
assert feats_array[1][1] == doc[1].dep assert feats_array[1][1] == doc[1].dep