def test_doc_from_array_heads_in_bounds(en_vocab):
"""Test that Doc.from_array doesn't set heads that are out of bounds."""
words = ["This", "is", "a", "sentence", "."]
doc = Doc(en_vocab, words=words)
for token in doc:
token.head = doc[0]
# correct
arr = doc.to_array(["HEAD"])
doc_from_array = Doc(en_vocab, words=words)
doc_from_array.from_array(["HEAD"], arr)
# head before start
arr = doc.to_array(["HEAD"])
arr[0] = -1
doc_from_array = Doc(en_vocab, words=words)
with pytest.raises(ValueError):
doc_from_array.from_array(["HEAD"], arr)
# head after end
arr = doc.to_array(["HEAD"])
arr[0] = 5
doc_from_array = Doc(en_vocab, words=words)
with pytest.raises(ValueError):
doc_from_array.from_array(["HEAD"], arr)
def test_doc_from_array_sent_starts(en_vocab):
# fmt: off
words = ["I", "live", "in", "New", "York", ".", "I", "like", "cats", "."]
heads = [0, 0, 0, 0, 0, 0, 6, 6, 6, 6]
deps = ["ROOT", "dep", "dep", "dep", "dep", "dep", "ROOT", "dep", "dep", "dep"]
# fmt: on
doc = Doc(en_vocab, words=words, heads=heads, deps=deps)
# HEAD overrides SENT_START without warning
attrs = [SENT_START, HEAD]
arr = doc.to_array(attrs)
new_doc = Doc(en_vocab, words=words)
new_doc.from_array(attrs, arr)
# no warning using default attrs
attrs = doc._get_array_attrs()
arr = doc.to_array(attrs)
with pytest.warns(None) as record:
new_doc.from_array(attrs, arr)
assert len(record) == 0
# only SENT_START uses SENT_START
attrs = [SENT_START]
arr = doc.to_array(attrs)
new_doc = Doc(en_vocab, words=words)
new_doc.from_array(attrs, arr)
assert [t.is_sent_start for t in doc] == [t.is_sent_start for t in new_doc]
assert not new_doc.has_annotation("DEP")
# only HEAD uses HEAD
attrs = [HEAD, DEP]
arr = doc.to_array(attrs)
new_doc = Doc(en_vocab, words=words)
new_doc.from_array(attrs, arr)
assert [t.is_sent_start for t in doc] == [t.is_sent_start for t in new_doc]
assert new_doc.has_annotation("DEP")
def test_doc_from_array_sent_starts(en_vocab):
words = ["I", "live", "in", "New", "York", ".", "I", "like", "cats", "."]
heads = [0, 0, 0, 0, 0, 0, 6, 6, 6, 6]
# fmt: off
deps = ["ROOT", "dep", "dep", "dep", "dep", "dep", "ROOT", "dep", "dep", "dep", "dep"]
# fmt: on
doc = Doc(en_vocab, words=words)
for i, (dep, head) in enumerate(zip(deps, heads)):
doc[i].dep_ = dep
doc[i].head = doc[head]
if head == i:
doc[i].is_sent_start = True
doc.is_parsed
attrs = [SENT_START, HEAD]
arr = doc.to_array(attrs)
new_doc = Doc(en_vocab, words=words)
with pytest.raises(ValueError):
new_doc.from_array(attrs, arr)
attrs = [SENT_START, DEP]
arr = doc.to_array(attrs)
new_doc = Doc(en_vocab, words=words)
new_doc.from_array(attrs, arr)
assert [t.is_sent_start for t in doc] == [t.is_sent_start for t in new_doc]
assert not new_doc.is_parsed
attrs = [HEAD, DEP]
arr = doc.to_array(attrs)
new_doc = Doc(en_vocab, words=words)
new_doc.from_array(attrs, arr)
assert [t.is_sent_start for t in doc] == [t.is_sent_start for t in new_doc]
assert new_doc.is_parsed
def test_doc_stringy_array_attr_of_token(en_vocab):
doc = Doc(en_vocab, words=["An", "example", "sentence"])
example = doc.vocab["example"]
assert example.orth != example.shape
feats_array = doc.to_array((ORTH, SHAPE))
feats_array_stringy = doc.to_array(("ORTH", "SHAPE"))
assert feats_array_stringy[0][0] == feats_array[0][0]
assert feats_array_stringy[0][1] == feats_array[0][1]
def test_doc_stringy_array_attr_of_token(en_vocab):
doc = Doc(en_vocab, words=["An", "example", "sentence"])
example = doc.vocab["example"]
assert example.orth != example.shape
feats_array = doc.to_array((ORTH, SHAPE))
feats_array_stringy = doc.to_array(("ORTH", "SHAPE"))
assert feats_array_stringy[0][0] == feats_array[0][0]
assert feats_array_stringy[0][1] == feats_array[0][1]
def test_doc_array_to_from_string_attrs(en_vocab, attrs):
"""Test that both Doc.to_array and Doc.from_array accept string attrs,
as well as single attrs and sequences of attrs.
"""
words = ["An", "example", "sentence"]
doc = Doc(en_vocab, words=words)
Doc(en_vocab, words=words).from_array(attrs, doc.to_array(attrs))
def get_doc(vocab, words, pos, heads, deps):
assert len(pos) == len(words)
assert len(heads) == len(words)
assert len(deps) == len(words)
headings = []
values = []
annotations = [pos, heads, deps]
possible_headings = [POS, HEAD, DEP]
for a, annot in enumerate(annotations):
headings.append(possible_headings[a])
if annot is not heads:
values.extend(annot)
for value in values:
vocab.strings.add(value)
doc = Doc(vocab, words=words)
attrs = doc.to_array(headings)
j = 0
for annot in annotations:
if annot is heads:
for i in range(len(words)):
attrs[i, j] = heads[i]
else:
for i in range(len(words)):
attrs[i, j] = doc.vocab.strings[annot[i]]
j += 1
doc.from_array(headings, attrs)
return doc
def get_doc(vocab, words=[], pos=None, heads=None, deps=None, tags=None, ents=None):
"""Create Doc object from given vocab, words and annotations."""
pos = pos or [""] * len(words)
tags = tags or [""] * len(words)
heads = heads or [0] * len(words)
deps = deps or [""] * len(words)
for value in deps + tags + pos:
vocab.strings.add(value)
doc = Doc(vocab, words=words)
attrs = doc.to_array([POS, HEAD, DEP])
for i, (p, head, dep) in enumerate(zip(pos, heads, deps)):
attrs[i, 0] = doc.vocab.strings[p]
attrs[i, 1] = head
attrs[i, 2] = doc.vocab.strings[dep]
doc.from_array([POS, HEAD, DEP], attrs)
if ents:
doc.ents = [
Span(doc, start, end, label=doc.vocab.strings[label])
for start, end, label in ents
]
if tags:
for token in doc:
token.tag_ = tags[token.i]
return doc
def test_doc_array_to_from_string_attrs(en_vocab, attrs):
"""Test that both Doc.to_array and Doc.from_array accept string attrs,
as well as single attrs and sequences of attrs.
"""
words = ["An", "example", "sentence"]
doc = Doc(en_vocab, words=words)
Doc(en_vocab, words=words).from_array(attrs, doc.to_array(attrs))
def get_doc(self,
words=[],
pos=None,
heads=None,
deps=None,
tags=None,
ents=None):
"""Create Doc object from given vocab, words and annotations."""
vocab = Vocab()
pos = pos or [""] * len(words)
tags = tags or [""] * len(words)
heads = heads or [0] * len(words)
deps = deps or [""] * len(words)
for value in deps + tags + pos:
vocab.strings.add(value)
doc = Doc(vocab, words=words)
attrs = doc.to_array([POS, HEAD, DEP])
for i, (p, head, dep) in enumerate(zip(pos, heads, deps)):
attrs[i, 0] = doc.vocab.strings[p]
attrs[i, 1] = head
attrs[i, 2] = doc.vocab.strings[dep]
doc.from_array([POS, HEAD, DEP], attrs)
if ents:
doc.ents = [
Span(doc, start, end, label=doc.vocab.strings[label])
for start, end, label in ents
]
if tags:
for token in doc:
token.tag_ = tags[token.i]
return doc
def test_doc_array_dep(en_vocab):
words = ["A", "nice", "sentence", "."]
deps = ["det", "amod", "ROOT", "punct"]
doc = Doc(en_vocab, words=words, deps=deps)
feats_array = doc.to_array((ORTH, DEP))
assert feats_array[0][1] == doc[0].dep
assert feats_array[1][1] == doc[1].dep
assert feats_array[2][1] == doc[2].dep
assert feats_array[3][1] == doc[3].dep
def get_doc(vocab,
words=[],
pos=None,
heads=None,
deps=None,
tags=None,
ents=None,
lemmas=None):
"""Create Doc object from given vocab, words and annotations."""
if deps and not heads:
heads = [0] * len(deps)
headings = []
values = []
annotations = [pos, heads, deps, lemmas, tags]
possible_headings = [POS, HEAD, DEP, LEMMA, TAG]
for a, annot in enumerate(annotations):
if annot is not None:
if len(annot) != len(words):
raise ValueError(Errors.E189)
headings.append(possible_headings[a])
if annot is not heads:
values.extend(annot)
for value in values:
vocab.strings.add(value)
doc = Doc(vocab, words=words)
# if there are any other annotations, set them
if headings:
attrs = doc.to_array(headings)
j = 0
for annot in annotations:
if annot:
if annot is heads:
for i in range(len(words)):
if attrs.ndim == 1:
attrs[i] = heads[i]
else:
attrs[i, j] = heads[i]
else:
for i in range(len(words)):
if attrs.ndim == 1:
attrs[i] = doc.vocab.strings[annot[i]]
else:
attrs[i, j] = doc.vocab.strings[annot[i]]
j += 1
doc.from_array(headings, attrs)
# finally, set the entities
if ents:
doc.ents = [
Span(doc, start, end, label=doc.vocab.strings[label])
for start, end, label in ents
]
return doc
def test_doc_array_tag(en_vocab):
words = ["A", "nice", "sentence", "."]
pos = ["DET", "ADJ", "NOUN", "PUNCT"]
doc = Doc(en_vocab, words=words, pos=pos)
assert doc[0].pos != doc[1].pos != doc[2].pos != doc[3].pos
feats_array = doc.to_array((ORTH, POS))
assert feats_array[0][1] == doc[0].pos
assert feats_array[1][1] == doc[1].pos
assert feats_array[2][1] == doc[2].pos
assert feats_array[3][1] == doc[3].pos
def test_doc_from_array_morph(en_vocab):
# fmt: off
words = ["I", "live", "in", "New", "York", "."]
morphs = ["Feat1=A", "Feat1=B", "Feat1=C", "Feat1=A|Feat2=D", "Feat2=E", "Feat3=F"]
# fmt: on
doc = Doc(en_vocab, words=words, morphs=morphs)
attrs = [MORPH]
arr = doc.to_array(attrs)
new_doc = Doc(en_vocab, words=words)
new_doc.from_array(attrs, arr)
assert [str(t.morph) for t in new_doc] == morphs
assert [str(t.morph) for t in doc] == [str(t.morph) for t in new_doc]
def test_doc_array_morph(en_vocab):
words = ["Eat", "blue", "ham"]
morph = ["Feat=V", "Feat=J", "Feat=N"]
doc = Doc(en_vocab, words=words, morphs=morph)
assert morph[0] == str(doc[0].morph)
assert morph[1] == str(doc[1].morph)
assert morph[2] == str(doc[2].morph)
feats_array = doc.to_array((ORTH, MORPH))
assert feats_array[0][1] == doc[0].morph.key
assert feats_array[1][1] == doc[1].morph.key
assert feats_array[2][1] == doc[2].morph.key
def doc_cleaning(doc: Doc):
np_array = doc.to_array(
[LEMMA, LOWER, POS, TAG, ENT_TYPE, IS_ALPHA, DEP, HEAD, SPACY])
words = [t.text for i, t in enumerate(doc)]
cleaned_words = list()
for w in words:
if w != 'PairDrug1' and w != 'PairDrug2':
w = number_substitution(w)
if w == '%':
w = ' '
cleaned_words.append(w)
doc2 = Doc(doc.vocab, words=cleaned_words)
doc2.from_array(
[LEMMA, LOWER, POS, TAG, ENT_TYPE, IS_ALPHA, DEP, HEAD, SPACY],
np_array)
return doc2
def test_issue2203(en_vocab):
"""Test that lemmas are set correctly in doc.from_array."""
words = ["I", "'ll", "survive"]
tags = ["PRP", "MD", "VB"]
lemmas = ["-PRON-", "will", "survive"]
tag_ids = [en_vocab.strings.add(tag) for tag in tags]
lemma_ids = [en_vocab.strings.add(lemma) for lemma in lemmas]
doc = Doc(en_vocab, words=words)
# Work around lemma corrpution problem and set lemmas after tags
doc.from_array("TAG", numpy.array(tag_ids, dtype="uint64"))
doc.from_array("LEMMA", numpy.array(lemma_ids, dtype="uint64"))
assert [t.tag_ for t in doc] == tags
assert [t.lemma_ for t in doc] == lemmas
# We need to serialize both tag and lemma, since this is what causes the bug
doc_array = doc.to_array(["TAG", "LEMMA"])
new_doc = Doc(doc.vocab, words=words).from_array(["TAG", "LEMMA"], doc_array)
assert [t.tag_ for t in new_doc] == tags
assert [t.lemma_ for t in new_doc] == lemmas
def test_issue2203(en_vocab):
"""Test that lemmas are set correctly in doc.from_array."""
words = ["I", "'ll", "survive"]
tags = ["PRP", "MD", "VB"]
lemmas = ["-PRON-", "will", "survive"]
tag_ids = [en_vocab.strings.add(tag) for tag in tags]
lemma_ids = [en_vocab.strings.add(lemma) for lemma in lemmas]
doc = Doc(en_vocab, words=words)
# Work around lemma corrpution problem and set lemmas after tags
doc.from_array("TAG", numpy.array(tag_ids, dtype="uint64"))
doc.from_array("LEMMA", numpy.array(lemma_ids, dtype="uint64"))
assert [t.tag_ for t in doc] == tags
assert [t.lemma_ for t in doc] == lemmas
# We need to serialize both tag and lemma, since this is what causes the bug
doc_array = doc.to_array(["TAG", "LEMMA"])
new_doc = Doc(doc.vocab, words=words).from_array(["TAG", "LEMMA"], doc_array)
assert [t.tag_ for t in new_doc] == tags
assert [t.lemma_ for t in new_doc] == lemmas
def substitution(doc: Doc, index: int, value: int) -> Doc:
np_array = doc.to_array(
[LEMMA, LOWER, POS, TAG, ENT_TYPE, IS_ALPHA, DEP, HEAD, SPACY])
words = [t.text for i, t in enumerate(doc)]
#print(words[index])
if value == -1:
item = 'NoPair'
if value == 0:
item = "Drug"
if value == 1:
item = "PairDrug1"
if value == 2:
item = "PairDrug2"
words.__setitem__(index, item)
doc2 = Doc(doc.vocab, words=words)
doc2.from_array(
[LEMMA, LOWER, POS, TAG, ENT_TYPE, IS_ALPHA, DEP, HEAD, SPACY],
np_array)
return doc2
def test_issue3012(en_vocab):
"""Test that the is_tagged attribute doesn't get overwritten when we from_array
without tag information."""
words = ["This", "is", "10", "%", "."]
tags = ["DT", "VBZ", "CD", "NN", "."]
pos = ["DET", "VERB", "NUM", "NOUN", "PUNCT"]
ents = ["O", "O", "B-PERCENT", "I-PERCENT", "O"]
doc = Doc(en_vocab, words=words, tags=tags, pos=pos, ents=ents)
assert doc.has_annotation("TAG")
expected = ("10", "NUM", "CD", "PERCENT")
assert (doc[2].text, doc[2].pos_, doc[2].tag_,
doc[2].ent_type_) == expected
header = [ENT_IOB, ENT_TYPE]
ent_array = doc.to_array(header)
doc.from_array(header, ent_array)
assert (doc[2].text, doc[2].pos_, doc[2].tag_,
doc[2].ent_type_) == expected
# Serializing then deserializing
doc_bytes = doc.to_bytes()
doc2 = Doc(en_vocab).from_bytes(doc_bytes)
assert (doc2[2].text, doc2[2].pos_, doc2[2].tag_,
doc2[2].ent_type_) == expected
def test_doc_scalar_attr_of_token(en_vocab):
doc = Doc(en_vocab, words=["An", "example", "sentence"])
example = doc.vocab["example"]
assert example.orth != example.shape
feats_array = doc.to_array(ORTH)
assert feats_array.shape == (3,)
def test_doc_scalar_attr_of_token(en_vocab):
doc = Doc(en_vocab, words=["An", "example", "sentence"])
example = doc.vocab["example"]
assert example.orth != example.shape
feats_array = doc.to_array(ORTH)
assert feats_array.shape == (3,)
