explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-26 01:04:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

Cast to uint64 for all array-based doc representations (#11933)

Browse Source 
* Convert all individual values explicitly to uint64 for array-based doc representations

* Temporarily test with latest numpy v1.24.0rc

* Remove unnecessary conversion from attr_t

* Reduce number of individual casts

* Convert specifically from int32 to uint64

* Revert "Temporarily test with latest numpy v1.24.0rc"

This reverts commit eb0e3c5006.

* Also use int32 in tests
This commit is contained in:
Adriane Boyd 2022-12-12 08:45:35 +01:00 committed by GitHub
parent 8c291ace0c
commit 0591e67265
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 14 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/tests/doc/test_array.py
View File

@ -123,14 +123,14 @@ def test_doc_from_array_heads_in_bounds(en_vocab):
# head before start # head before start
arr = doc.to_array(["HEAD"]) arr = doc.to_array(["HEAD"])
arr[0] = -1 arr[0] = numpy.int32(-1).astype(numpy.uint64)
doc_from_array = Doc(en_vocab, words=words) doc_from_array = Doc(en_vocab, words=words)
with pytest.raises(ValueError): with pytest.raises(ValueError):
doc_from_array.from_array(["HEAD"], arr) doc_from_array.from_array(["HEAD"], arr)
# head after end # head after end
arr = doc.to_array(["HEAD"]) arr = doc.to_array(["HEAD"])
arr[0] = 5 arr[0] = numpy.int32(5).astype(numpy.uint64)
doc_from_array = Doc(en_vocab, words=words) doc_from_array = Doc(en_vocab, words=words)
with pytest.raises(ValueError): with pytest.raises(ValueError):
doc_from_array.from_array(["HEAD"], arr) doc_from_array.from_array(["HEAD"], arr)

2
spacy/tokens/doc.pyx
View File

@ -359,6 +359,7 @@ cdef class Doc:
for annot in annotations: for annot in annotations:
if annot: if annot:
if annot is heads or annot is sent_starts or annot is ent_iobs: if annot is heads or annot is sent_starts or annot is ent_iobs:
annot = numpy.array(annot, dtype=numpy.int32).astype(numpy.uint64)
for i in range(len(words)): for i in range(len(words)):
if attrs.ndim == 1: if attrs.ndim == 1:
attrs[i] = annot[i] attrs[i] = annot[i]
@ -1558,6 +1559,7 @@ cdef class Doc:
for j, (attr, annot) in enumerate(token_annotations.items()): for j, (attr, annot) in enumerate(token_annotations.items()):
if attr is HEAD: if attr is HEAD:
annot = numpy.array(annot, dtype=numpy.int32).astype(numpy.uint64)
for i in range(len(words)): for i in range(len(words)):
array[i, j] = annot[i] array[i, j] = annot[i]
elif attr is MORPH: elif attr is MORPH:

4
spacy/tokens/span.pyx
View File

@ -299,7 +299,7 @@ cdef class Span:
for ancestor in ancestors: for ancestor in ancestors:
ancestor_i = ancestor.i - self.c.start ancestor_i = ancestor.i - self.c.start
if ancestor_i in range(length): if ancestor_i in range(length):
array[i, head_col] = ancestor_i - i array[i, head_col] = numpy.int32(ancestor_i - i).astype(numpy.uint64)
# if there is no appropriate ancestor, define a new artificial root # if there is no appropriate ancestor, define a new artificial root
value = array[i, head_col] value = array[i, head_col]
@ -307,7 +307,7 @@ cdef class Span:
new_root = old_to_new_root.get(ancestor_i, None) new_root = old_to_new_root.get(ancestor_i, None)
if new_root is not None: if new_root is not None:
# take the same artificial root as a previous token from the same sentence # take the same artificial root as a previous token from the same sentence
array[i, head_col] = new_root - i array[i, head_col] = numpy.int32(new_root - i).astype(numpy.uint64)
else: else:
# set this token as the new artificial root # set this token as the new artificial root
array[i, head_col] = 0 array[i, head_col] = 0

15
spacy/training/example.pyx
View File

@ -443,26 +443,27 @@ def _annot2array(vocab, tok_annot, doc_annot):
if key not in IDS: if key not in IDS:
raise ValueError(Errors.E974.format(obj="token", key=key)) raise ValueError(Errors.E974.format(obj="token", key=key))
elif key in ["ORTH", "SPACY"]: elif key in ["ORTH", "SPACY"]:
pass continue
elif key == "HEAD": elif key == "HEAD":
attrs.append(key) attrs.append(key)
values.append([h-i if h is not None else 0 for i, h in enumerate(value)]) row = [h-i if h is not None else 0 for i, h in enumerate(value)]
elif key == "DEP": elif key == "DEP":
attrs.append(key) attrs.append(key)
values.append([vocab.strings.add(h) if h is not None else MISSING_DEP for h in value]) row = [vocab.strings.add(h) if h is not None else MISSING_DEP for h in value]
elif key == "SENT_START": elif key == "SENT_START":
attrs.append(key) attrs.append(key)
values.append([to_ternary_int(v) for v in value]) row = [to_ternary_int(v) for v in value]
elif key == "MORPH": elif key == "MORPH":
attrs.append(key) attrs.append(key)
values.append([vocab.morphology.add(v) for v in value]) row = [vocab.morphology.add(v) for v in value]
else: else:
attrs.append(key) attrs.append(key)
if not all(isinstance(v, str) for v in value): if not all(isinstance(v, str) for v in value):
types = set([type(v) for v in value]) types = set([type(v) for v in value])
raise TypeError(Errors.E969.format(field=key, types=types)) from None raise TypeError(Errors.E969.format(field=key, types=types)) from None
values.append([vocab.strings.add(v) for v in value]) row = [vocab.strings.add(v) for v in value]
array = numpy.asarray(values, dtype="uint64") values.append([numpy.array(v, dtype=numpy.int32).astype(numpy.uint64) if v < 0 else v for v in row])
array = numpy.array(values, dtype=numpy.uint64)
return attrs, array.T return attrs, array.T