def predict(self, cas: Cas, layer: str, feature: str, project_id: str,
document_id: str, user_id: str):
result = jieba.tokenize(cas.sofa_string)
for tk in result:
prediction = self.create_prediction(cas, layer, feature, tk[1],
tk[2], tk[0])
cas.add_annotation(prediction)
def write_sentence_documents(sentences: List[str],
labels: List[str],
path: Path,
labeled=True):
typesystem = TypeSystem()
cas = Cas(typesystem=typesystem)
SentenceType = typesystem.create_type(
"de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Sentence")
SentimentType = typesystem.create_type("webanno.custom.Sentiment")
typesystem.add_feature(type_=SentimentType,
name="value",
rangeTypeName="uima.cas.String")
cas.sofa_string = " ".join(sentences)
begin = 0
for sentence, label in zip(sentences, labels):
end = begin + len(sentence)
cas_sentence = SentenceType(begin=begin, end=end)
sentiment_annotation = SentimentType(begin=begin, end=end, value=label)
begin = end + 1
cas.add_annotation(cas_sentence)
if labeled:
cas.add_annotation(sentiment_annotation)
cas.to_xmi(path, pretty_print=True)
for sentence in cas.select(SENTENCE_TYPE):
print(cas.get_covered_text(sentence))
def predict(self, cas: Cas, layer: str, feature: str, project_id: str, document_id: str, user_id: str):
stemmer = nltk.PorterStemmer()
# For every token, steam it and create an annotation in the CAS
for cas_token in self.iter_tokens(cas):
stem = stemmer.stem(cas_token.get_covered_text())
begin = cas_token.begin
end = begin + len(stem)
prediction = self.create_prediction(cas, layer, feature, begin, end, stem)
cas.add_annotation(prediction)
def predict(self, cas: Cas, layer: str, feature: str, project_id: str, document_id: str, user_id: str):
for i, sentence in enumerate(cas.select(SENTENCE_TYPE)):
token_ids = self._tokenizer.convert_tokens_to_ids(self._tokenizer.tokenize(sentence.get_covered_text()))
input_tensor = torch.tensor([token_ids])
# predict output tensor
outputs = self._model(input_tensor, adapter_names=[self._adapter_internal_name])
# retrieve the predicted class label
label_id = torch.argmax(outputs[0]).item()
label = self._label_map[label_id]
prediction = self.create_prediction(cas, layer, feature, sentence.begin, sentence.end, label)
cas.add_annotation(prediction)
def predict(self, cas: Cas, layer: str, feature: str, project_id: str,
document_id: str, user_id: str):
model: Optional[Pipeline] = self._load_model(user_id)
if model is None:
logger.debug("No trained model ready yet!")
return
for sentence in cas.select(SENTENCE_TYPE):
predicted = model.predict([sentence.get_covered_text()])[0]
prediction = create_prediction(cas, layer, feature, sentence.begin,
sentence.end, predicted)
cas.add_annotation(prediction)
def rebuilt2xmi(ci,
output_dir,
typesystem_path,
iiif_mappings,
pct_coordinates=False) -> str:
"""
Converts a rebuilt ContentItem into Apache UIMA/XMI format.
The resulting file will be named after the content item's ID, adding
the `.xmi` extension.
:param ci: the content item to be converted
:type ci: `impresso_commons.classes.ContentItem`
:param output_dir: the path to the output directory
:type output_dir: str
:param typesystem_path: TypeSystem file containing defitions of annotation
layers.
:type typesystem_path: str
"""
with open(typesystem_path, "rb") as f:
typesystem = load_typesystem(f)
cas = Cas(typesystem=typesystem)
cas.sofa_string = ci.fulltext
cas.sofa_mime = 'text/plain'
sentType = 'de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Sentence'
imgLinkType = 'webanno.custom.ImpressoImages'
Sentence = typesystem.get_type(sentType)
ImageLink = typesystem.get_type(imgLinkType)
# create sentence-level annotations
start_offset = 0
for break_offset in ci.lines:
start = start_offset
end = break_offset
start_offset = break_offset
cas.add_annotation(Sentence(begin=start, end=end))
iiif_links = compute_image_links(ci,
iiif_links=iiif_mappings,
pct=pct_coordinates)
# inject the IIIF links into
for iiif_link, start, end in iiif_links:
cas.add_annotation(ImageLink(begin=start, end=end, link=iiif_link))
outfile_path = os.path.join(output_dir, f'{ci.id}.xmi')
cas.to_xmi(outfile_path, pretty_print=True)
return outfile_path
def predict(self, cas: Cas, layer: str, feature: str, project_id: str, document_id: str, user_id: str):
model = self._load_model(user_id)
if model is None:
logger.debug("No trained model ready yet!")
return
featurizer = self._get_featurizer()
sentences = cas.select(SENTENCE_TYPE)
featurized_sentences = featurizer.featurize([s.get_covered_text() for s in sentences])
predictions = model.predict(featurized_sentences)
for sentence, featurized_sentence, label in zip(sentences, featurized_sentences, predictions):
prediction = create_prediction(cas, layer, feature, sentence.begin, sentence.end, label)
cas.add_annotation(prediction)
def predict(self, cas: Cas, layer: str, feature: str, project_id: str, document_id: str, user_id: str):
for sentence in cas.select(SENTENCE_TYPE):
cas_tokens = list(cas.select_covered(TOKEN_TYPE, sentence))
tokens = [t.get_covered_text() for t in cas_tokens]
grouped_bert_tokens = self._tokenize_bert(tokens)
predictions = self._predict(grouped_bert_tokens)
grouped_predictions = self._align_tokens(tokens, grouped_bert_tokens, predictions)
for token, grouped_prediction in zip(cas_tokens, grouped_predictions):
begin = token.begin
end = token.end
label = Counter([self._label_map[pred] for pred in grouped_prediction]).most_common(1)[0][0]
prediction = self.create_prediction(cas, layer, feature, begin, end, label)
cas.add_annotation(prediction)
def predict(self, cas: Cas, layer: str, feature: str, project_id: str,
document_id: str, user_id: str):
model: Optional[sklearn_crfsuite.CRF] = self._load_model(user_id)
if model is None:
logger.debug("No trained model ready yet!")
return
all_tokens = []
featurized_sentences = []
for sentence in cas.select(SENTENCE_TYPE):
tokens = list(cas.select_covered(TOKEN_TYPE, sentence))
words = [token.get_covered_text() for token in tokens]
all_tokens.append(tokens)
featurized_sentences.append(self._sent2features(words))
all_predictions = model.predict(featurized_sentences)
assert len(all_predictions) == len(all_tokens)
for predictions, tokens in zip(all_predictions, all_tokens):
assert len(predictions) == len(tokens)
begin = None
end = None
prev_tag = "O"
for tag, token in zip(predictions, tokens):
if begin is not None and end is not None:
if tag == "O" or (tag.startswith("B")
and prev_tag.startswith("I")):
prediction = create_prediction(cas, layer, feature,
begin, end, "X")
cas.add_annotation(prediction)
if tag.startswith("B"):
begin = token.begin
end = token.end
elif tag.startswith("I"):
end = token.end
else:
begin = None
end = None
prev_tag = tag
def load_newsgroup_test_data() -> List[Cas]:
twenty_test = fetch_20newsgroups(subset="test", categories=NEWSGROUP_CATEGORIES, shuffle=True, random_state=42)
typesystem = build_typesystem()
SentenceType = typesystem.get_type(SENTENCE_TYPE)
result = []
for text in twenty_test.data[:5]:
cas = Cas(typesystem=typesystem)
cas.sofa_string = text
begin = 0
end = len(text)
cas.add_annotation(SentenceType(begin=begin, end=end))
result.append(cas)
return result
def predict(self, cas: Cas, layer: str, feature: str, project_id: str, document_id: str, user_id: str):
model = self._load_model(user_id)
if model is None:
return
le, items = model
m = Map.from_iter(items)
# We iterate over the all candidates and check whether they match
for (begin, end, term) in chain(
self._generate_candidates(cas, 3), self._generate_candidates(cas, 2), self._generate_candidates(cas, 1)
):
for mention, label_id in m.search(term=term, max_dist=2):
label = le.inverse_transform([label_id])[0]
prediction = create_prediction(cas, layer, feature, begin, end, label)
cas.add_annotation(prediction)
def predict(self, cas: Cas, layer: str, feature: str, project_id: str,
document_id: str, user_id: str):
# Extract the tokens from the CAS and create a spacy doc from it
cas_tokens = cas.select(TOKEN_TYPE)
words = [cas.get_covered_text(cas_token) for cas_token in cas_tokens]
doc = Doc(self._model.vocab, words=words)
# Find the named entities
self._model.get_pipe("ner")(doc)
# For every entity returned by spacy, create an annotation in the CAS
for named_entity in doc.ents:
begin = cas_tokens[named_entity.start].begin
end = cas_tokens[named_entity.end - 1].end
label = named_entity.label_
prediction = create_prediction(cas, layer, feature, begin, end,
label)
cas.add_annotation(prediction)
def predict(self, cas: Cas, layer: str, feature: str, project_id: str,
document_id: str, user_id: str):
# Extract the tokens from the CAS and create a spacy doc from it
words = [
cas.get_covered_text(cas_token)
for cas_token in self.iter_tokens(cas)
]
doc = Doc(self._model.vocab, words=words)
# Find the named entities
self._model.tagger(doc)
# For every token, extract the POS tag and create an annotation in the CAS
for cas_token, spacy_token in zip(self.iter_tokens(cas), doc):
prediction = self.create_prediction(cas, layer, feature,
cas_token.begin, cas_token.end,
spacy_token.pos_)
cas.add_annotation(prediction)
def predict(self, cas: Cas, layer: str, feature: str, project_id: str,
document_id: str, user_id: str):
# Extract the tokens from the CAS and create a spacy doc from it
words = [
cas.get_covered_text(cas_token)
for cas_token in cas.select(TOKEN_TYPE)
]
doc = Doc(self._model.vocab, words=words)
# Get the pos tags
self._model.get_pipe("tok2vec")(doc)
self._model.get_pipe("tagger")(doc)
# For every token, extract the POS tag and create an annotation in the CAS
for cas_token, spacy_token in zip(cas.select(TOKEN_TYPE), doc):
prediction = create_prediction(cas, layer, feature,
cas_token.begin, cas_token.end,
spacy_token.tag_)
cas.add_annotation(prediction)
def load_newsgroup_training_data() -> List[TrainingDocument]:
twenty_train = fetch_20newsgroups(subset="train", categories=NEWSGROUP_CATEGORIES, shuffle=True, random_state=42)
target_names = twenty_train.target_names
typesystem = build_typesystem()
SentenceType = typesystem.get_type(SENTENCE_TYPE)
PredictedType = typesystem.get_type(PREDICTED_TYPE)
docs = []
for i, (text, target) in enumerate(zip(twenty_train.data, twenty_train.target)):
cas = Cas(typesystem=typesystem)
cas.sofa_string = text
begin = 0
end = len(text)
cas.add_annotation(SentenceType(begin=begin, end=end))
cas.add_annotation(PredictedType(begin=begin, end=end, value=target_names[target]))
doc = TrainingDocument(cas, f"doc_{i}", USER)
docs.append(doc)
return docs
def predict(self, cas: Cas, layer: str, feature: str, project_id: str,
document_id: str, user_id: str):
sentences = cas.select(SENTENCE_TYPE)
src_tokens = cas.select_covered("webanno.custom.Base", sentences[0])
trg_tokens = cas.select_covered("webanno.custom.Base", sentences[1])
src_sentence = [e.get_covered_text() for e in src_tokens]
trg_sentence = [e.get_covered_text() for e in trg_tokens]
print(src_sentence)
print(trg_sentence)
alignments = self._aligner.get_word_aligns(src_sentence, trg_sentence)
Relation = cas.typesystem.get_type(layer)
print(list(Relation.all_features))
for matching_method in alignments:
for source_idx, target_idx in alignments[matching_method]:
src = src_tokens[source_idx]
target = trg_tokens[target_idx]
prediction = Relation(
Governor=src,
Dependent=target,
begin=target.begin,
end=target.end,
inception_internal_predicted=True,
)
# setattr(prediction, feature, f"{src.get_covered_text()} -> {target.get_covered_text()}")
setattr(prediction, feature, "")
print(source_idx, target_idx, prediction)
cas.add_annotation(prediction)
break
def convert_single_file(input_paragraph_list: List[str],
output_xmi_file: str) -> None:
document_text = '\n'.join(input_paragraph_list)
cas = Cas(typesystem=cassis.load_dkpro_core_typesystem())
cas.sofa_string = document_text
print("----")
print(document_text)
print("----")
token_type: Type = cas.typesystem.get_type(
'de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Token')
paragraph_type: Type = cas.typesystem.get_type(
'de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Paragraph')
sentence_type: Type = cas.typesystem.get_type(
'de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Sentence')
total_doc_offset: int = 0
for paragraph_str in input_paragraph_list:
this_paragraph_total_offset = total_doc_offset
doc: Doc = nlp(paragraph_str)
for token in doc:
assert isinstance(token, Token)
# print(token.text, token.idx, len(token), token.idx + len(token), token.is_space)
begin: int = total_doc_offset + token.idx
end: int = total_doc_offset + token.idx + len(token)
# annotate token -- only if it is not a space!
if not token.is_space:
cas.add_annotation(token_type.__call__(begin=begin, end=end))
total_doc_offset += len(paragraph_str)
# annotate paragraph
this_paragraph_annotation = paragraph_type.__call__(
begin=this_paragraph_total_offset, end=total_doc_offset)
cas.add_annotation(this_paragraph_annotation)
# and for paragraph too; but how about the '\n' char? maybe +1?
total_doc_offset += 1
# add sentences aligned exactly to paragraphs
cas.add_annotation(
sentence_type.__call__(begin=this_paragraph_annotation.begin,
end=this_paragraph_annotation.end))
print([x.get_covered_text() for x in cas.select(paragraph_type.name)])
print([x.get_covered_text() for x in cas.select(sentence_type.name)])
print([x.get_covered_text() for x in cas.select(token_type.name)])
# create parent folder if not exists
Path(output_xmi_file).parent.mkdir(parents=True, exist_ok=True)
cas.to_xmi(output_xmi_file)
def export_annotated_texts_to_xmi(annotated_texts: List[AnnotatedText],
type_system,
file: str,
xmi_file=None):
cas = Cas(typesystem=type_system)
current_start = 0
starts = []
sofa_string = ''
# Create sofa string
for annotated_text in annotated_texts:
starts.append(current_start)
text = annotated_text.text
if not text.endswith('\n'):
text += '\n'
sofa_string += text
current_start += len(text)
cas.sofa_string = sofa_string
# Tokens
for annotated_text, start in zip(annotated_texts, starts):
for token in annotated_text.tokens:
annotation = cas.typesystem.get_type(TOKEN_NS)(
begin=start + token.start, end=start + token.stop)
cas.add_annotation(annotation)
# Sentences
for annotated_text, start in zip(annotated_texts, starts):
annotation = cas.typesystem.get_type(SENTENCE_NS)(
begin=start, end=start + len(annotated_text.text))
cas.add_annotation(annotation)
# Annotations
for annotated_text, start in zip(annotated_texts, starts):
for annotation in annotated_text.annotations:
annotation = cas.typesystem.get_type(NAMED_ENTITY_NS)(
value=annotation.label,
begin=start + annotation.start,
end=start + annotation.stop)
cas.add_annotation(annotation)
# write
with open(file, 'wb') as f:
dump_cas_to_zip_file(cas, f, xmi_file=xmi_file)
