def main():
# Create input HTML string
input_html = (
"<body><p>"
"she does not have SVS syndrome from an axillary vein thrombosis."
"</p></body>"
)
# Assemble the pipeline:
# A pipeline is consisted of a set of Components (readers and processors).
# The data flows in the pipeline as data packs, and each component will
# use or add information to the data packs.
pipeline = Pipeline[DataPack]()
# Set HTMLReader as pipeline reader:
# HTMLReader takes in list of html strings, cleans the HTML tags and
# stores the cleaned text in pack.
pipeline.set_reader(HTMLReader())
# Add SpacyProcessor to process the datapack:
# SpacyProcessor provides functions including sentence parsing, tokenize,
# POS tagging, lemmatization, NER, and medical entity linking. This
# processor will do user defined tasks according to configs.
pipeline.add(SpacyProcessor(), config={
"processors": ["sentence", "tokenize", "pos", "ner", "dep", "umls_link"]
})
# Add StaveProcessor to visualize the processing results：
# StaveProcessor provides easy visualization for forte users. We can
# visualize datapack with annotations by inserting it into the forte
# pipeline.
pipeline.add(StaveProcessor())
# Initialize and run the pipeline
pipeline.initialize()
for datapack in pipeline.process_dataset(input_html):
# Get the results of dependency parsing
for link in datapack.get(Dependency):
parent = link.get_parent()
child = link.get_child()
# Print out the dependency between parent and child
print(
f"'{child.text}' has dependency '{link.dep_label}'"
f" of parent '{parent.text}'"
)
# Retrieve all the MedicalEntityMention in datapack
for medical_entity in datapack.get(MedicalEntityMention):
# Get and print out the UMLS links
for umls_link in medical_entity.umls_entities:
print(umls_link)
def setUp(self):
self._port: int = 8880
_file_dir_path: str = os.path.dirname(__file__)
self._project_name: str = "serialization_pipeline_test"
self._dataset_dir: str = os.path.abspath(
os.path.join(_file_dir_path, "../../../",
"data_samples/ontonotes/00/"))
self._test_specs_dir: str = os.path.abspath(
os.path.join(_file_dir_path, "../data/ontology/test_specs/"))
self._stave_processor = StaveProcessor()
self.pl = Pipeline[DataPack](ontology_file=os.path.join(
self._test_specs_dir, "test_stave_ontology.json"))
self.pl.set_reader(OntonotesReader())
from forte.huggingface import ZeroShotClassifier
from forte.stanza import StandfordNLPProcessor
from forte import Pipeline
from forte.data.readers import TerminalReader
from forte.processors.stave import StaveProcessor
nlp = Pipeline()
nlp.set_reader(TerminalReader())
nlp.add(StandfordNLPProcessor())
nlp.add(
ZeroShotClassifier(),
config={
"candidate_labels": [
"travel",
"cooking",
"dancing",
"exploration",
],
},
)
nlp.add(StaveProcessor())
nlp.initialize()
nlp.run()
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
Example code for pytorch blog post, a "one-liner" version.
"""
from forte.data.data_pack import DataPack
from forte.data.readers import HTMLReader
from forte.pipeline import Pipeline
from forte.processors.stave import StaveProcessor
from fortex.spacy import SpacyProcessor
Pipeline[DataPack](
).set_reader(
HTMLReader()
).add(
SpacyProcessor(), config={
"processors": ["sentence", "tokenize", "pos", "ner", "dep", "umls_link"]
}
).add(
StaveProcessor()
).run(
"<body><p>"
"she does not have SVS syndrome from an axillary vein thrombosis."
"</p></body>"
)