mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 09:57:26 +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.
41 lines
1.3 KiB
Python
41 lines
1.3 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
import dill as pickle
|
|
import numpy
|
|
from spacy.strings import StringStore
|
|
from spacy.vocab import Vocab
|
|
from spacy.attrs import NORM
|
|
|
|
|
|
@pytest.mark.parametrize('text1,text2', [('hello', 'bye')])
|
|
def test_pickle_string_store(text1, text2):
|
|
stringstore = StringStore()
|
|
store1 = stringstore[text1]
|
|
store2 = stringstore[text2]
|
|
data = pickle.dumps(stringstore, protocol=-1)
|
|
unpickled = pickle.loads(data)
|
|
assert unpickled[text1] == store1
|
|
assert unpickled[text2] == store2
|
|
assert len(stringstore) == len(unpickled)
|
|
|
|
|
|
@pytest.mark.parametrize('text1,text2', [('dog', 'cat')])
|
|
def test_pickle_vocab(text1, text2):
|
|
vocab = Vocab(lex_attr_getters={int(NORM): lambda string: string[:-1]})
|
|
vocab.set_vector('dog', numpy.ones((5,), dtype='f'))
|
|
lex1 = vocab[text1]
|
|
lex2 = vocab[text2]
|
|
assert lex1.norm_ == text1[:-1]
|
|
assert lex2.norm_ == text2[:-1]
|
|
data = pickle.dumps(vocab)
|
|
unpickled = pickle.loads(data)
|
|
assert unpickled[text1].orth == lex1.orth
|
|
assert unpickled[text2].orth == lex2.orth
|
|
assert unpickled[text1].norm == lex1.norm
|
|
assert unpickled[text2].norm == lex2.norm
|
|
assert unpickled[text1].norm != unpickled[text2].norm
|
|
assert unpickled.vectors is not None
|
|
assert list(vocab['dog'].vector) == [1.,1.,1.,1.,1.]
|