explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-11 00:32:40 +03:00
Code Issues Packages Projects Releases Wiki Activity

Whitespace

Browse Source
This commit is contained in:
Matthew Honnibal 2017-03-15 09:29:42 -05:00
parent 7769bc31e3
commit 3d4e389d23
1 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
spacy/gold.pyx
View File

@ -1,3 +1,4 @@
# cython: profile=True
from __future__ import unicode_literals, print_function from __future__ import unicode_literals, print_function
import numpy import numpy
@ -90,9 +91,9 @@ def _min_edit_path(cand_words, gold_words):
# TODO: Fix this --- just do it properly, make the full edit matrix and # TODO: Fix this --- just do it properly, make the full edit matrix and
# then walk back over it... # then walk back over it...
# Preprocess inputs # Preprocess inputs
cand_words = [punct_re.sub('', w) for w in cand_words] cand_words = [punct_re.sub('', w) for w in cand_words]
gold_words = [punct_re.sub('', w) for w in gold_words] gold_words = [punct_re.sub('', w) for w in gold_words]
if cand_words == gold_words: if cand_words == gold_words:
return 0, ''.join(['M' for _ in gold_words]) return 0, ''.join(['M' for _ in gold_words])
mem = Pool() mem = Pool()
@ -132,7 +133,7 @@ def _min_edit_path(cand_words, gold_words):
else: else:
best_cost = d_cost best_cost = d_cost
best_hist = previous_row[j + 1] + 'D' best_hist = previous_row[j + 1] + 'D'
current_row.append(best_hist) current_row.append(best_hist)
curr_costs[j+1] = best_cost curr_costs[j+1] = best_cost
previous_row = current_row previous_row = current_row
@ -306,7 +307,7 @@ cdef class GoldParse:
def __len__(self): def __len__(self):
"""Get the number of gold-standard tokens. """Get the number of gold-standard tokens.
Returns (int): The number of gold-standard tokens. Returns (int): The number of gold-standard tokens.
""" """
return self.length return self.length
@ -330,7 +331,7 @@ def biluo_tags_from_offsets(doc, entities):
entities (sequence): entities (sequence):
A sequence of (start, end, label) triples. start and end should be A sequence of (start, end, label) triples. start and end should be
character-offset integers denoting the slice into the original string. character-offset integers denoting the slice into the original string.
Returns: Returns:
tags (list): tags (list):
A list of unicode strings, describing the tags. Each tag string will A list of unicode strings, describing the tags. Each tag string will
@ -348,7 +349,7 @@ def biluo_tags_from_offsets(doc, entities):
doc = nlp.tokenizer(text) doc = nlp.tokenizer(text)
tags = biluo_tags_from_offsets(doc, entities) tags = biluo_tags_from_offsets(doc, entities)
assert tags == ['O', 'O', 'U-LOC', 'O'] assert tags == ['O', 'O', 'U-LOC', 'O']
''' '''
starts = {token.idx: token.i for token in doc} starts = {token.idx: token.i for token in doc}