explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-31 07:57:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add efficiency note to new get_lca_matrix() method

Browse Source
This commit is contained in:
Matthew Honnibal 2017-09-04 15:43:52 +02:00 committed by GitHub
parent d61c117081
commit e8a26ebfab
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
spacy/tokens/doc.pyx
View File

@ -626,7 +626,14 @@ cdef class Doc:
impact on performance is negligible given impact on performance is negligible given
the natural limitations on the depth of a typical human sentence. the natural limitations on the depth of a typical human sentence.
''' '''
# Efficiency notes:
#
# We can easily improve the performance here by iterating in Cython.
# To loop over the tokens in Cython, the easiest way is:
# for token in doc.c[:doc.c.length]:
# head = token + token.head
# Both token and head will be TokenC* here. The token.head attribute
# is an integer offset.
def __pairwise_lca(token_j, token_k, lca_matrix): def __pairwise_lca(token_j, token_k, lca_matrix):
if lca_matrix[token_j.i][token_k.i] != -2: if lca_matrix[token_j.i][token_k.i] != -2:
return lca_matrix[token_j.i][token_k.i] return lca_matrix[token_j.i][token_k.i]
@ -649,7 +656,7 @@ cdef class Doc:
lca_matrix.fill(-2) lca_matrix.fill(-2)
for j in range(len(self)): for j in range(len(self)):
token_j = self[j] token_j = self[j]
for k in range(len(self)): for k in range(j, len(self)):
token_k = self[k] token_k = self[k]
lca_matrix[j][k] = __pairwise_lca(token_j, token_k, lca_matrix) lca_matrix[j][k] = __pairwise_lca(token_j, token_k, lca_matrix)
lca_matrix[k][j] = lca_matrix[j][k] lca_matrix[k][j] = lca_matrix[j][k]