def to_input_samples(self,
fold: Optional[str] = None) -> List[InputSample]:
files_found = False
input_samples = []
for i, file_path in enumerate(self.files_path.glob(self.glob_pattern)):
if fold and fold not in file_path.name:
continue
files_found = True
with open(file_path, "r", encoding="utf-8") as file:
text = file.readlines()
text = "".join(text)
output_docs = conll_ner_to_docs(input_data=text,
n_sents=None,
no_print=True)
for doc in tqdm(output_docs,
f"Processing doc for file {file_path.name}"):
input_samples.append(InputSample.from_spacy_doc(doc=doc))
if not files_found:
raise FileNotFoundError(
f"No files found for pattern {self.glob_pattern} and fold {fold}"
)
return input_samples
def test_cli_converters_conll_ner_to_docs():
lines = [
"-DOCSTART- -X- O O",
"",
"I\tO",
"like\tO",
"London\tB-GPE",
"and\tO",
"New\tB-GPE",
"York\tI-GPE",
"City\tI-GPE",
".\tO",
"",
"I O",
"like O",
"London B-GPE",
"and O",
"New B-GPE",
"York I-GPE",
"City I-GPE",
". O",
"",
"I PRP O",
"like VBP O",
"London NNP B-GPE",
"and CC O",
"New NNP B-GPE",
"York NNP I-GPE",
"City NNP I-GPE",
". . O",
"",
"I PRP _ O",
"like VBP _ O",
"London NNP _ B-GPE",
"and CC _ O",
"New NNP _ B-GPE",
"York NNP _ I-GPE",
"City NNP _ I-GPE",
". . _ O",
"",
"I\tPRP\t_\tO",
"like\tVBP\t_\tO",
"London\tNNP\t_\tB-GPE",
"and\tCC\t_\tO",
"New\tNNP\t_\tB-GPE",
"York\tNNP\t_\tI-GPE",
"City\tNNP\t_\tI-GPE",
".\t.\t_\tO",
]
input_data = "\n".join(lines)
converted_docs = list(conll_ner_to_docs(input_data, n_sents=10))
assert len(converted_docs) == 1
converted = docs_to_json(converted_docs)
assert converted["id"] == 0
assert len(converted["paragraphs"]) == 1
assert len(converted["paragraphs"][0]["sentences"]) == 5
for i in range(0, 5):
sent = converted["paragraphs"][0]["sentences"][i]
assert len(sent["tokens"]) == 8
tokens = sent["tokens"]
# fmt: off
assert [t["orth"] for t in tokens] == [
"I", "like", "London", "and", "New", "York", "City", "."
]
# fmt: on
assert len(converted_docs[0].ents) == 10
for ent in converted_docs[0].ents:
assert ent.text in ["New York City", "London"]