explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Replace deepcopy

Browse Source
This commit is contained in:
ines 2017-05-13 12:32:37 +02:00
parent df68bf45ce
commit 6129016e15
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/tokens/printers.py
View File

@ -1,7 +1,10 @@
from copy import deepcopy
# coding: utf8
from __future__ import unicode_literals
from .doc import Doc
from ..symbols import HEAD, TAG, DEP, ENT_IOB, ENT_TYPE
def merge_ents(doc):
"""
Helper: merge adjacent entities into single tokens; modifies the doc.
@ -61,6 +64,8 @@ def parse_tree(doc, light=False, flat=False):
>>> trees = doc.print_tree()
[{'modifiers': [{'modifiers': [], 'NE': 'PERSON', 'word': 'Bob', 'arc': 'nsubj', 'POS_coarse': 'PROPN', 'POS_fine': 'NNP', 'lemma': 'Bob'}, {'modifiers': [], 'NE': 'PERSON', 'word': 'Alice', 'arc': 'dobj', 'POS_coarse': 'PROPN', 'POS_fine': 'NNP', 'lemma': 'Alice'}, {'modifiers': [{'modifiers': [], 'NE': '', 'word': 'the', 'arc': 'det', 'POS_coarse': 'DET', 'POS_fine': 'DT', 'lemma': 'the'}], 'NE': '', 'word': 'pizza', 'arc': 'dobj', 'POS_coarse': 'NOUN', 'POS_fine': 'NN', 'lemma': 'pizza'}, {'modifiers': [], 'NE': '', 'word': '.', 'arc': 'punct', 'POS_coarse': 'PUNCT', 'POS_fine': '.', 'lemma': '.'}], 'NE': '', 'word': 'brought', 'arc': 'ROOT', 'POS_coarse': 'VERB', 'POS_fine': 'VBD', 'lemma': 'bring'}, {'modifiers': [{'modifiers': [], 'NE': 'PERSON', 'word': 'Alice', 'arc': 'nsubj', 'POS_coarse': 'PROPN', 'POS_fine': 'NNP', 'lemma': 'Alice'}, {'modifiers': [{'modifiers': [], 'NE': '', 'word': 'the', 'arc': 'det', 'POS_coarse': 'DET', 'POS_fine': 'DT', 'lemma': 'the'}], 'NE': '', 'word': 'pizza', 'arc': 'dobj', 'POS_coarse': 'NOUN', 'POS_fine': 'NN', 'lemma': 'pizza'}, {'modifiers': [], 'NE': '', 'word': '.', 'arc': 'punct', 'POS_coarse': 'PUNCT', 'POS_fine': '.', 'lemma': '.'}], 'NE': '', 'word': 'ate', 'arc': 'ROOT', 'POS_coarse': 'VERB', 'POS_fine': 'VBD', 'lemma': 'eat'}]
"""
doc_clone = deepcopy(doc)
doc_clone = Doc(doc.vocab, words=[w.text for w in doc])
doc_clone.from_array([HEAD, TAG, DEP, ENT_IOB, ENT_TYPE],
doc.to_array([HEAD, TAG, DEP, ENT_IOB, ENT_TYPE]))
merge_ents(doc_clone) # merge the entities into single tokens first
return [POS_tree(sent.root, light=light, flat=flat) for sent in doc_clone.sents]