spaCy/spacy/tests/pipeline/test_pipe_methods.py

129 lines
3.7 KiB
Python
Raw Normal View History

2017-10-07 00:06:21 +00:00
# coding: utf8
from __future__ import unicode_literals
import pytest
💫 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.language import Language
2017-10-07 00:06:21 +00:00
@pytest.fixture
def nlp():
return Language()
def new_pipe(doc):
return doc
def test_add_pipe_no_name(nlp):
nlp.add_pipe(new_pipe)
assert "new_pipe" in nlp.pipe_names
2017-10-07 00:06:21 +00:00
def test_add_pipe_duplicate_name(nlp):
nlp.add_pipe(new_pipe, name="duplicate_name")
2017-10-07 00:06:21 +00:00
with pytest.raises(ValueError):
nlp.add_pipe(new_pipe, name="duplicate_name")
2017-10-07 00:06:21 +00:00
@pytest.mark.parametrize("name", ["parser"])
2017-10-07 00:06:21 +00:00
def test_add_pipe_first(nlp, name):
nlp.add_pipe(new_pipe, name=name, first=True)
assert nlp.pipeline[0][0] == name
@pytest.mark.parametrize("name1,name2", [("parser", "lambda_pipe")])
2017-10-07 00:06:21 +00:00
def test_add_pipe_last(nlp, name1, name2):
nlp.add_pipe(lambda doc: doc, name=name2)
nlp.add_pipe(new_pipe, name=name1, last=True)
assert nlp.pipeline[0][0] != name1
assert nlp.pipeline[-1][0] == name1
def test_cant_add_pipe_first_and_last(nlp):
with pytest.raises(ValueError):
nlp.add_pipe(new_pipe, first=True, last=True)
@pytest.mark.parametrize("name", ["my_component"])
2017-10-07 00:06:21 +00:00
def test_get_pipe(nlp, name):
with pytest.raises(KeyError):
nlp.get_pipe(name)
nlp.add_pipe(new_pipe, name=name)
assert nlp.get_pipe(name) == new_pipe
@pytest.mark.parametrize("name,replacement,not_callable", [("my_component", lambda doc: doc, {})])
def test_replace_pipe(nlp, name, replacement, not_callable):
2017-10-07 00:06:21 +00:00
with pytest.raises(ValueError):
nlp.replace_pipe(name, new_pipe)
nlp.add_pipe(new_pipe, name=name)
with pytest.raises(ValueError):
nlp.replace_pipe(name, not_callable)
2017-10-07 00:06:21 +00:00
nlp.replace_pipe(name, replacement)
assert nlp.get_pipe(name) != new_pipe
assert nlp.get_pipe(name) == replacement
@pytest.mark.parametrize("old_name,new_name", [("old_pipe", "new_pipe")])
2017-10-07 00:06:21 +00:00
def test_rename_pipe(nlp, old_name, new_name):
with pytest.raises(ValueError):
nlp.rename_pipe(old_name, new_name)
nlp.add_pipe(new_pipe, name=old_name)
nlp.rename_pipe(old_name, new_name)
assert nlp.pipeline[0][0] == new_name
@pytest.mark.parametrize("name", ["my_component"])
2017-10-07 00:06:21 +00:00
def test_remove_pipe(nlp, name):
with pytest.raises(ValueError):
nlp.remove_pipe(name)
nlp.add_pipe(new_pipe, name=name)
assert len(nlp.pipeline) == 1
removed_name, removed_component = nlp.remove_pipe(name)
assert not len(nlp.pipeline)
assert removed_name == name
assert removed_component == new_pipe
2017-10-25 11:46:41 +00:00
@pytest.mark.parametrize("name", ["my_component"])
2017-10-25 11:46:41 +00:00
def test_disable_pipes_method(nlp, name):
nlp.add_pipe(new_pipe, name=name)
assert nlp.has_pipe(name)
disabled = nlp.disable_pipes(name)
assert not nlp.has_pipe(name)
disabled.restore()
@pytest.mark.parametrize("name", ["my_component"])
2017-10-25 11:46:41 +00:00
def test_disable_pipes_context(nlp, name):
nlp.add_pipe(new_pipe, name=name)
assert nlp.has_pipe(name)
with nlp.disable_pipes(name):
assert not nlp.has_pipe(name)
assert nlp.has_pipe(name)
@pytest.mark.parametrize("n_pipes", [100])
def test_add_lots_of_pipes(nlp, n_pipes):
for i in range(n_pipes):
nlp.add_pipe(lambda doc: doc, name="pipe_%d" % i)
assert len(nlp.pipe_names) == n_pipes
@pytest.mark.parametrize("component", ["ner", {"hello": "world"}])
def test_raise_for_invalid_components(nlp, component):
with pytest.raises(ValueError):
nlp.add_pipe(component)
@pytest.mark.parametrize("component", ["ner", "tagger", "parser", "textcat"])
def test_pipe_base_class_add_label(nlp, component):
label = "TEST"
pipe = nlp.create_pipe(component)
pipe.add_label(label)
if component == "tagger":
# Tagger always has the default coarse-grained label scheme
assert label in pipe.labels
else:
assert pipe.labels == (label,)