mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-24 12:59:21 +03:00
32 lines
911 B
Python
32 lines
911 B
Python
|
import numpy as np
|
||
|
|
|
||
|
|
from spacy.attrs import HEAD, DEP
|
||
|
|
from spacy.symbols import nsubj, dobj, punct, amod, nmod, conj, cc, root
|
||
|
|
from spacy.en import English
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
def test_not_nested():
|
||
|
|
nlp = English(parser=False)
|
||
|
|
sent = u'''Peter has chronic command and control issues'''.strip()
|
||
|
|
tokens = nlp(sent)
|
||
|
|
tokens.from_array(
|
||
|
|
[HEAD, DEP],
|
||
|
|
np.asarray(
|
||
|
|
[
|
||
|
|
[1, nsubj],
|
||
|
|
[0, root],
|
||
|
|
[4, amod],
|
||
|
|
[3, nmod],
|
||
|
|
[-1, cc],
|
||
|
|
[-2, conj],
|
||
|
|
[-5, dobj]
|
||
|
|
], dtype='int32'))
|
||
|
|
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])
|