spaCy/spacy/tests/test_pickles.py

63 lines
2.0 KiB
Python
Raw Normal View History

2017-12-07 11:53:30 +03:00
import numpy
2023-06-26 12:41:03 +03:00
import pytest
2018-12-06 22:43:47 +03:00
import srsly
2023-06-26 12:41:03 +03:00
from spacy.attrs import NORM
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.
2018-07-25 00:38:44 +03:00
from spacy.strings import StringStore
from spacy.tokens import Doc
💫 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.
2018-07-25 00:38:44 +03:00
from spacy.vocab import Vocab
2017-03-07 19:15:18 +03:00
@pytest.mark.parametrize("text1,text2", [("hello", "bye")])
💫 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.
2018-07-25 00:38:44 +03:00
def test_pickle_string_store(text1, text2):
stringstore = StringStore()
2017-03-15 19:39:54 +03:00
store1 = stringstore[text1]
store2 = stringstore[text2]
2018-12-06 22:43:47 +03:00
data = srsly.pickle_dumps(stringstore, protocol=-1)
unpickled = srsly.pickle_loads(data)
2017-03-15 19:39:54 +03:00
assert unpickled[text1] == store1
assert unpickled[text2] == store2
assert len(stringstore) == len(unpickled)
2017-03-07 19:15:18 +03:00
2017-03-07 22:58:55 +03:00
@pytest.mark.parametrize("text1,text2", [("dog", "cat")])
2017-03-15 19:39:54 +03:00
def test_pickle_vocab(text1, text2):
vocab = Vocab(
lex_attr_getters={int(NORM): lambda string: string[:-1]},
get_noun_chunks=English.Defaults.syntax_iterators.get("noun_chunks"),
)
vocab.set_vector("dog", numpy.ones((5,), dtype="f"))
2017-03-15 19:39:54 +03:00
lex1 = vocab[text1]
lex2 = vocab[text2]
assert lex1.norm_ == text1[:-1]
assert lex2.norm_ == text2[:-1]
2018-12-06 22:46:36 +03:00
data = srsly.pickle_dumps(vocab)
unpickled = srsly.pickle_loads(data)
2017-03-15 19:39:54 +03:00
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
2017-12-07 11:53:30 +03:00
assert unpickled.vectors is not None
assert unpickled.get_noun_chunks is not None
assert list(vocab["dog"].vector) == [1.0, 1.0, 1.0, 1.0, 1.0]
def test_pickle_doc(en_vocab):
words = ["a", "b", "c"]
deps = ["dep"] * len(words)
heads = [0] * len(words)
doc = Doc(
en_vocab,
words=words,
deps=deps,
heads=heads,
)
data = srsly.pickle_dumps(doc)
unpickled = srsly.pickle_loads(data)
assert [t.text for t in unpickled] == words
assert [t.dep_ for t in unpickled] == deps
assert [t.head.i for t in unpickled] == heads
assert list(doc.noun_chunks) == []