spaCy/spacy/tests/lang/en/test_noun_chunks.py

45 lines
1.4 KiB
Python
Raw Normal View History

2017-01-11 20:54:56 +03:00
import numpy
💫 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.attrs import HEAD, DEP
from spacy.symbols import nsubj, dobj, amod, nmod, conj, cc, root
from spacy.lang.en.syntax_iterators import noun_chunks
2020-09-21 21:43:54 +03:00
from spacy.tokens import Doc
import pytest
def test_noun_chunks_is_parsed(en_tokenizer):
2020-05-21 15:14:01 +03:00
"""Test that noun_chunks raises Value Error for 'en' language if Doc is not parsed.
"""
doc = en_tokenizer("This is a sentence")
with pytest.raises(ValueError):
list(doc.noun_chunks)
2018-11-30 19:43:08 +03:00
def test_en_noun_chunks_not_nested(en_vocab):
words = ["Peter", "has", "chronic", "command", "and", "control", "issues"]
2020-09-21 21:43:54 +03:00
heads = [1, 1, 6, 6, 3, 3, 1]
deps = ["nsubj", "ROOT", "amod", "nmod", "cc", "conj", "dobj"]
2020-09-21 21:43:54 +03:00
doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
2018-11-30 19:43:08 +03:00
doc.from_array(
[HEAD, DEP],
numpy.asarray(
[
[1, nsubj],
[0, root],
[4, amod],
[3, nmod],
[-1, cc],
[-2, conj],
[-5, dobj],
],
dtype="uint64",
),
)
doc.noun_chunks_iterator = noun_chunks
word_occurred = {}
2018-11-30 19:43:08 +03:00
for chunk in doc.noun_chunks:
for word in chunk:
word_occurred.setdefault(word.text, 0)
word_occurred[word.text] += 1
for word, freq in word_occurred.items():
2018-11-30 19:43:08 +03:00
assert freq == 1, (word, [chunk.text for chunk in doc.noun_chunks])