explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-27 09:44:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

Auto-format [ci skip]

Browse Source
This commit is contained in:
Ines Montani 2019-10-24 16:21:08 +02:00
parent 73dc63d3bf
commit cc05d9dad6
4 changed files with 11 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/cli/convert.py
View File

@ -57,7 +57,7 @@ def convert(
is written to stdout, so you can pipe them forward to a JSON file: is written to stdout, so you can pipe them forward to a JSON file:
$ spacy convert some_file.conllu > some_file.json $ spacy convert some_file.conllu > some_file.json
""" """
no_print = (output_dir == "-") no_print = output_dir == "-"
msg = Printer(no_print=no_print) msg = Printer(no_print=no_print)
input_path = Path(input_file) input_path = Path(input_file)
if file_type not in FILE_TYPES: if file_type not in FILE_TYPES:

4
spacy/cli/converters/conll_ner2json.py
View File

@ -9,7 +9,9 @@ from ...tokens.doc import Doc
from ...util import load_model from ...util import load_model
def conll_ner2json(input_data, n_sents=10, seg_sents=False, model=None, no_print=False, **kwargs): def conll_ner2json(
input_data, n_sents=10, seg_sents=False, model=None, no_print=False, **kwargs
):
""" """
Convert files in the CoNLL-2003 NER format and similar Convert files in the CoNLL-2003 NER format and similar
whitespace-separated columns into JSON format for use with train cli. whitespace-separated columns into JSON format for use with train cli.

6
spacy/tests/regression/test_issue3001-3500.py
View File

@ -297,8 +297,10 @@ def test_issue3410():
def test_issue3412(): def test_issue3412():
data = numpy.asarray([[0, 0, 0], [1, 2, 3], [9, 8, 7]], dtype="f") data = numpy.asarray([[0, 0, 0], [1, 2, 3], [9, 8, 7]], dtype="f")
vectors = Vectors(data=data) vectors = Vectors(data=data)
keys, best_rows, scores = vectors.most_similar(numpy.asarray([[9, 8, 7], [0, 0, 0]], dtype="f")) keys, best_rows, scores = vectors.most_similar(
assert(best_rows[0] == 2) numpy.asarray([[9, 8, 7], [0, 0, 0]], dtype="f")
)
assert best_rows[0] == 2
def test_issue3447(): def test_issue3447():

6
spacy/tests/test_gold.py
View File

@ -90,7 +90,7 @@ def test_gold_ner_missing_tags(en_tokenizer):
def test_iob_to_biluo(): def test_iob_to_biluo():
good_iob = ["O", "O", "B-LOC", "I-LOC", "O", "B-PERSON"] good_iob = ["O", "O", "B-LOC", "I-LOC", "O", "B-PERSON"]
good_biluo = ["O", "O", "B-LOC", "L-LOC", "O", "U-PERSON"] good_biluo = ["O", "O", "B-LOC", "L-LOC", "O", "U-PERSON"]
bad_iob = ["O", "O", "\"", "B-LOC", "I-LOC"] bad_iob = ["O", "O", '"', "B-LOC", "I-LOC"]
converted_biluo = iob_to_biluo(good_iob) converted_biluo = iob_to_biluo(good_iob)
assert good_biluo == converted_biluo assert good_biluo == converted_biluo
with pytest.raises(ValueError): with pytest.raises(ValueError):
@ -99,9 +99,9 @@ def test_iob_to_biluo():
def test_roundtrip_docs_to_json(): def test_roundtrip_docs_to_json():
text = "I flew to Silicon Valley via London." text = "I flew to Silicon Valley via London."
tags = ['PRP', 'VBD', 'IN', 'NNP', 'NNP', 'IN', 'NNP', '.'] tags = ["PRP", "VBD", "IN", "NNP", "NNP", "IN", "NNP", "."]
heads = [1, 1, 1, 4, 2, 1, 5, 1] heads = [1, 1, 1, 4, 2, 1, 5, 1]
deps = ['nsubj', 'ROOT', 'prep', 'compound', 'pobj', 'prep', 'pobj', 'punct'] deps = ["nsubj", "ROOT", "prep", "compound", "pobj", "prep", "pobj", "punct"]
biluo_tags = ["O", "O", "O", "B-LOC", "L-LOC", "O", "U-GPE", "O"] biluo_tags = ["O", "O", "O", "B-LOC", "L-LOC", "O", "U-GPE", "O"]
cats = {"TRAVEL": 1.0, "BAKING": 0.0} cats = {"TRAVEL": 1.0, "BAKING": 0.0}
nlp = English() nlp = English()