explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-10 16:22:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

avoid two for loops over all docs by not precomputing

Browse Source
This commit is contained in:
kadarakos 2023-05-03 13:08:44 +00:00
parent fe4c094d86
commit 6b2e8363fc
1 changed files with 2 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/pipeline/span_finder.py
View File

@ -226,20 +226,12 @@ class SpanFinder(TrainablePipe):
docs (Iterable[Doc]): The documents to modify. docs (Iterable[Doc]): The documents to modify.
scores: The scores to set, produced by SpanFinder predict method. scores: The scores to set, produced by SpanFinder predict method.
""" """
lengths = [len(doc) for doc in docs]
offset = 0 offset = 0
scores_per_doc = [] for i, doc in enumerate(docs):
# XXX Isn't this really inefficient that we are creating these
# slices ahead of time? Couldn't we just do this in the next loop?
for length in lengths:
scores_per_doc.append(scores[offset : offset + length])
offset += length
for doc, doc_scores in zip(docs, scores_per_doc):
doc.spans[self.predicted_key] = [] doc.spans[self.predicted_key] = []
starts = [] starts = []
ends = [] ends = []
doc_scores = scores[offset:offset + len(doc)]
for token, token_score in zip(doc, doc_scores): for token, token_score in zip(doc, doc_scores):
if token_score[0] >= self.threshold: if token_score[0] >= self.threshold: