mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 11:59:14 +03:00
7e4cd7575c
* Refactor Docs.is_ flags
* Add derived `Doc.has_annotation` method
* `Doc.has_annotation(attr)` returns `True` for partial annotation
* `Doc.has_annotation(attr, require_complete=True)` returns `True` for
complete annotation
* Add deprecation warnings to `is_tagged`, `is_parsed`, `is_sentenced`
and `is_nered`
* Add `Doc._get_array_attrs()`, which returns a full list of `Doc` attrs
for use with `Doc.to_array`, `Doc.to_bytes` and `Doc.from_docs`. The
list is the `DocBin` attributes list plus `SPACY` and `LENGTH`.
Notes on `Doc.has_annotation`:
* `HEAD` is converted to `DEP` because heads don't have an unset state
* Accept `IS_SENT_START` as a synonym of `SENT_START`
Additional changes:
* Add `NORM`, `ENT_ID` and `SENT_START` to default attributes for
`DocBin`
* In `Doc.from_array()` the presence of `DEP` causes `HEAD` to override
`SENT_START`
* In `Doc.from_array()` using `attrs` other than
`Doc._get_array_attrs()` (i.e., a user's custom list rather than our
default internal list) with both `HEAD` and `SENT_START` shows a warning
that `HEAD` will override `SENT_START`
* `set_children_from_heads` does not require dependency labels to set
sentence boundaries and sets `sent_start` for all non-sentence starts to
`-1`
* Fix call to set_children_form_heads
Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
48 lines
1.4 KiB
Python
48 lines
1.4 KiB
Python
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 noun_chunks
|
|
|
|
import pytest
|
|
|
|
|
|
from ...util import get_doc
|
|
|
|
|
|
def test_noun_chunks_is_parsed(en_tokenizer):
|
|
"""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)
|
|
|
|
|
|
def test_en_noun_chunks_not_nested(en_vocab):
|
|
words = ["Peter", "has", "chronic", "command", "and", "control", "issues"]
|
|
heads = [1, 0, 4, 3, -1, -2, -5]
|
|
deps = ["nsubj", "ROOT", "amod", "nmod", "cc", "conj", "dobj"]
|
|
doc = get_doc(en_vocab, words=words, heads=heads, deps=deps)
|
|
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 = {}
|
|
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():
|
|
assert freq == 1, (word, [chunk.text for chunk in doc.noun_chunks])
|