spaCy/spacy/tests/vocab_vectors/test_vocab_api.py

84 lines
2.1 KiB
Python
Raw Normal View History

import os
import pytest
from spacy.attrs import IS_ALPHA, LEMMA, ORTH
from spacy.lang.en import English
💫 Refactor test suite (#2568) ## 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.
2018-07-24 21:38:44 +00:00
from spacy.parts_of_speech import NOUN, VERB
from spacy.vocab import Vocab
from ..util import make_tempdir
@pytest.mark.issue(1868)
def test_issue1868():
"""Test Vocab.__contains__ works with int keys."""
vocab = Vocab()
lex = vocab["hello"]
assert lex.orth in vocab
assert lex.orth_ in vocab
assert "some string" not in vocab
int_id = vocab.strings.add("some string")
assert int_id not in vocab
@pytest.mark.parametrize(
"text1,text2", [("Hello", "bye"), ("Hello", "hello"), ("Hello", "Hello,")]
)
def test_vocab_api_neq(en_vocab, text1, text2):
assert en_vocab[text1].orth != en_vocab[text2].orth
@pytest.mark.parametrize("text", "Hello")
def test_vocab_api_eq(en_vocab, text):
lex = en_vocab[text]
assert en_vocab[text].orth == lex.orth
@pytest.mark.parametrize("text", ["example"])
def test_vocab_api_shape_attr(en_vocab, text):
lex = en_vocab[text]
assert lex.orth != lex.shape
@pytest.mark.parametrize(
"string,symbol",
[
("IS_ALPHA", IS_ALPHA),
("NOUN", NOUN),
("VERB", VERB),
("LEMMA", LEMMA),
("ORTH", ORTH),
],
)
def test_vocab_api_symbols(en_vocab, string, symbol):
assert en_vocab.strings[string] == symbol
@pytest.mark.parametrize("text", "Hello")
2017-01-13 13:26:53 +00:00
def test_vocab_api_contains(en_vocab, text):
2018-11-30 16:43:08 +00:00
_ = en_vocab[text] # noqa: F841
assert text in en_vocab
assert "LKsdjvlsakdvlaksdvlkasjdvljasdlkfvm" not in en_vocab
def test_vocab_writing_system(en_vocab):
assert en_vocab.writing_system["direction"] == "ltr"
2019-03-11 14:28:22 +00:00
assert en_vocab.writing_system["has_case"] is True
def test_to_disk():
nlp = English()
with make_tempdir() as d:
nlp.vocab.to_disk(d)
assert "vectors" in os.listdir(d)
assert "lookups.bin" in os.listdir(d)
def test_to_disk_exclude():
nlp = English()
with make_tempdir() as d:
nlp.vocab.to_disk(d, exclude=("vectors", "lookups"))
assert "vectors" not in os.listdir(d)
assert "lookups.bin" not in os.listdir(d)