spaCy/spacy/tests/lang/en/test_noun_chunks.py
Ines Montani 75f3234404
💫 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 23:38:44 +02:00

30 lines
1.1 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import numpy
from spacy.attrs import HEAD, DEP
from spacy.symbols import nsubj, dobj, amod, nmod, conj, cc, root
from spacy.lang.en.syntax_iterators import SYNTAX_ITERATORS
from ...util import get_doc
def test_en_noun_chunks_not_nested(en_tokenizer):
text = "Peter has chronic command and control issues"
heads = [1, 0, 4, 3, -1, -2, -5]
deps = ['nsubj', 'ROOT', 'amod', 'nmod', 'cc', 'conj', 'dobj']
tokens = en_tokenizer(text)
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
tokens.from_array(
[HEAD, DEP],
numpy.asarray([[1, nsubj], [0, root], [4, amod], [3, nmod], [-1, cc],
[-2, conj], [-5, dobj]], dtype='uint64'))
tokens.noun_chunks_iterator = SYNTAX_ITERATORS['noun_chunks']
word_occurred = {}
for chunk in tokens.noun_chunks:
for word in chunk:
word_occurred.setdefault(word.text, 0)
word_occurred[word.text] += 1
for word, freq in word_occurred.items():
assert freq == 1, (word, [chunk.text for chunk in tokens.noun_chunks])