mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +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.
69 lines
2.0 KiB
Python
69 lines
2.0 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy._align import align, multi_align
|
|
|
|
|
|
@pytest.mark.parametrize('string1,string2,cost', [
|
|
('hello', 'hell', 1),
|
|
('rat', 'cat', 1),
|
|
('rat', 'rat', 0),
|
|
('rat', 'catsie', 4),
|
|
('t', 'catsie', 5),
|
|
])
|
|
def test_align_costs(string1, string2, cost):
|
|
output_cost, i2j, j2i, matrix = align(string1, string2)
|
|
assert output_cost == cost
|
|
|
|
|
|
@pytest.mark.parametrize('string1,string2,i2j', [
|
|
('hello', 'hell', [0,1,2,3,-1]),
|
|
('rat', 'cat', [0,1,2]),
|
|
('rat', 'rat', [0,1,2]),
|
|
('rat', 'catsie', [0,1,2]),
|
|
('t', 'catsie', [2]),
|
|
])
|
|
def test_align_i2j(string1, string2, i2j):
|
|
output_cost, output_i2j, j2i, matrix = align(string1, string2)
|
|
assert list(output_i2j) == i2j
|
|
|
|
|
|
@pytest.mark.parametrize('string1,string2,j2i', [
|
|
('hello', 'hell', [0,1,2,3]),
|
|
('rat', 'cat', [0,1,2]),
|
|
('rat', 'rat', [0,1,2]),
|
|
('rat', 'catsie', [0,1,2, -1, -1, -1]),
|
|
('t', 'catsie', [-1, -1, 0, -1, -1, -1]),
|
|
])
|
|
def test_align_i2j(string1, string2, j2i):
|
|
output_cost, output_i2j, output_j2i, matrix = align(string1, string2)
|
|
assert list(output_j2i) == j2i
|
|
|
|
def test_align_strings():
|
|
words1 = ['hello', 'this', 'is', 'test!']
|
|
words2 = ['hellothis', 'is', 'test', '!']
|
|
cost, i2j, j2i, matrix = align(words1, words2)
|
|
assert cost == 4
|
|
assert list(i2j) == [-1, -1, 1, -1]
|
|
assert list(j2i) == [-1, 2, -1, -1]
|
|
|
|
def test_align_many_to_one():
|
|
words1 = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h']
|
|
words2 = ['ab', 'bc', 'e', 'fg', 'h']
|
|
cost, i2j, j2i, matrix = align(words1, words2)
|
|
assert list(i2j) == [-1, -1, -1, -1, 2, -1, -1, 4]
|
|
lengths1 = [len(w) for w in words1]
|
|
lengths2 = [len(w) for w in words2]
|
|
i2j_multi, j2i_multi = multi_align(i2j, j2i, lengths1, lengths2)
|
|
assert i2j_multi[0] == 0
|
|
assert i2j_multi[1] == 0
|
|
assert i2j_multi[2] == 1
|
|
assert i2j_multi[3] == 1
|
|
assert i2j_multi[3] == 1
|
|
assert i2j_multi[5] == 3
|
|
assert i2j_multi[6] == 3
|
|
|
|
assert j2i_multi[0] == 1
|
|
assert j2i_multi[1] == 3
|