mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 10:56:31 +03:00
75f3234404
## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
62 lines
2.1 KiB
Python
62 lines
2.1 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from spacy.attrs import ORTH, SHAPE, POS, DEP
|
|
|
|
from ..util import get_doc
|
|
|
|
|
|
def test_doc_array_attr_of_token(en_tokenizer, en_vocab):
|
|
text = "An example sentence"
|
|
tokens = en_tokenizer(text)
|
|
example = tokens.vocab["example"]
|
|
assert example.orth != example.shape
|
|
feats_array = tokens.to_array((ORTH, SHAPE))
|
|
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):
|
|
text = "An example sentence"
|
|
tokens = en_tokenizer(text)
|
|
example = tokens.vocab["example"]
|
|
assert example.orth != example.shape
|
|
feats_array = tokens.to_array((ORTH, SHAPE))
|
|
feats_array_stringy = tokens.to_array(("ORTH", "SHAPE"))
|
|
assert feats_array_stringy[0][0] == feats_array[0][0]
|
|
assert feats_array_stringy[0][1] == feats_array[0][1]
|
|
|
|
|
|
def test_doc_scalar_attr_of_token(en_tokenizer, en_vocab):
|
|
text = "An example sentence"
|
|
tokens = en_tokenizer(text)
|
|
example = tokens.vocab["example"]
|
|
assert example.orth != example.shape
|
|
feats_array = tokens.to_array(ORTH)
|
|
assert feats_array.shape == (3,)
|
|
|
|
|
|
def test_doc_array_tag(en_tokenizer):
|
|
text = "A nice sentence."
|
|
pos = ['DET', 'ADJ', 'NOUN', 'PUNCT']
|
|
tokens = en_tokenizer(text)
|
|
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
|
|
feats_array = doc.to_array((ORTH, POS))
|
|
assert feats_array[0][1] == doc[0].pos
|
|
assert feats_array[1][1] == doc[1].pos
|
|
assert feats_array[2][1] == doc[2].pos
|
|
assert feats_array[3][1] == doc[3].pos
|
|
|
|
|
|
def test_doc_array_dep(en_tokenizer):
|
|
text = "A nice sentence."
|
|
deps = ['det', 'amod', 'ROOT', 'punct']
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], deps=deps)
|
|
feats_array = doc.to_array((ORTH, DEP))
|
|
assert feats_array[0][1] == doc[0].dep
|
|
assert feats_array[1][1] == doc[1].dep
|
|
assert feats_array[2][1] == doc[2].dep
|
|
assert feats_array[3][1] == doc[3].dep
|