explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-06 06:30:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

additional tests for new get_aligned function

Browse Source
This commit is contained in:
svlandeg 2020-06-15 17:42:40 +02:00
parent 41d29983a7
commit 68986a252e
2 changed files with 30 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/gold/example.pyx
View File

@ -23,7 +23,6 @@ cpdef Doc annotations2doc(vocab, tok_annot, doc_annot):
cdef class Example: cdef class Example:
def __init__(self, Doc predicted, Doc reference, *, Alignment alignment=None): def __init__(self, Doc predicted, Doc reference, *, Alignment alignment=None):
""" Doc can either be text, or an actual Doc """ """ Doc can either be text, or an actual Doc """
assert predicted.vocab is reference.vocab
msg = "Example.__init__ got None for '{arg}'. Requires Doc." msg = "Example.__init__ got None for '{arg}'. Requires Doc."
if predicted is None: if predicted is None:
raise TypeError(msg.format(arg="predicted")) raise TypeError(msg.format(arg="predicted"))
@ -89,11 +88,12 @@ cdef class Example:
output.append(None) output.append(None)
elif gold_i is None: elif gold_i is None:
if i in i2j_multi: if i in i2j_multi:
output.append(vocab.strings[gold_values[i2j_multi[i]]]) output.append(gold_values[i2j_multi[i]])
else: else:
output.append(None) output.append(None)
else: else:
output.append(vocab.strings[gold_values[gold_i]]) output.append([gold_values[gold_i]])
output = [vocab.strings[o] for o in output]
return output return output
def to_dict(self): def to_dict(self):

30
spacy/tests/test_new_example.py
View File

@ -32,11 +32,11 @@ def test_Example_from_dict_invalid(annots):
Example.from_dict(predicted, annots) Example.from_dict(predicted, annots)
@pytest.mark.parametrize("gold_words", [["ice", "cream"], ["icecream"], ["i", "ce", "cream"]]) @pytest.mark.parametrize("pred_words", [["ice", "cream"], ["icecream"], ["i", "ce", "cream"]])
@pytest.mark.parametrize("annots", [{"words": ["icecream"], "tags": ["NN"]}]) @pytest.mark.parametrize("annots", [{"words": ["icecream"], "tags": ["NN"]}])
def test_Example_from_dict_with_tags(gold_words, annots): def test_Example_from_dict_with_tags(pred_words, annots):
vocab = Vocab() vocab = Vocab()
predicted = Doc(vocab, words=gold_words) predicted = Doc(vocab, words=pred_words)
example = Example.from_dict(predicted, annots) example = Example.from_dict(predicted, annots)
for i, token in enumerate(example.reference): for i, token in enumerate(example.reference):
assert token.tag_ == annots["tags"][i] assert token.tag_ == annots["tags"][i]
@ -44,6 +44,30 @@ def test_Example_from_dict_with_tags(gold_words, annots):
assert aligned_tags == ["NN" for _ in predicted] assert aligned_tags == ["NN" for _ in predicted]
def test_aligned_tags():
pred_words = ["Apply", "some", "sunscreen", "unless", "you", "can", "not"]
gold_words = ["Apply", "some", "sun", "screen", "unless", "you", "cannot"]
gold_tags = ["VERB", "DET", "NOUN", "NOUN", "SCONJ", "PRON", "VERB"]
annots = {"words": gold_words, "tags": gold_tags}
vocab = Vocab()
predicted = Doc(vocab, words=pred_words)
example = Example.from_dict(predicted, annots)
aligned_tags = example.get_aligned("tag")
assert aligned_tags == ["VERB", "DET", None, "SCONJ", "PRON", "VERB", "VERB"]
def test_aligned_tags_multi():
pred_words = ["Applysome", "sunscreen", "unless", "you", "can", "not"]
gold_words = ["Apply", "somesun", "screen", "unless", "you", "cannot"]
gold_tags = ["VERB", "DET", "NOUN", "SCONJ", "PRON", "VERB"]
annots = {"words": gold_words, "tags": gold_tags}
vocab = Vocab()
predicted = Doc(vocab, words=pred_words)
example = Example.from_dict(predicted, annots)
aligned_tags = example.get_aligned("tag")
assert aligned_tags == [None, None, "SCONJ", "PRON", "VERB", "VERB"]
@pytest.mark.parametrize( @pytest.mark.parametrize(
"annots", "annots",
[ [