def setUpClass(cls):
metamap = MetaMap(
metamap_path=
"/home/share/programs/metamap/2016/public_mm/bin/metamap",
cache_output=False)
cls.pipeline = ClinicalPipeline(
metamap) # Will fail as MetaMap isn't installed
def test_with_metamap(self):
"""
Constructs a model that memorizes an entity, predicts it on same file, writes to ann
:return:
"""
train_loader = DataLoader(self.train_dir)
test_loader = DataLoader(self.test_dir)
metamap = MetaMap(metamap_path="/home/share/programs/metamap/2016/public_mm/bin/metamap",
cache_output=False)
train_loader.metamap(metamap)
test_loader.metamap(metamap)
pipeline = ClinicalPipeline(metamap, entities=['Strength'])
learner = Learner(pipeline, train_loader)
model = learner.train()
predictor = Predictor(pipeline, test_loader, model=model)
predictor.predict()
with open(predictor.prediction_directory+"predict_test.ann") as f:
self.assertEqual(f.read(), "T1 Strength 7 11 5 mg\n")
def test_with_metamap(self):
loader = DataLoader(self.test_dir)
metamap = MetaMap(
metamap_path=
"/home/share/programs/metamap/2016/public_mm/bin/metamap")
loader.metamap(metamap) #pre-cache metamap files
pipeline = ClinicalPipeline(metamap, entities=['Strength'])
learner = Learner(pipeline, loader)
model = learner.train()
self.assertIsInstance(learner, Learner)
def test_fit_with_clinical_pipeline(self):
"""
Loads in training data and uses it to fit a model using the Clinical Pipeline
:return:
"""
train_loader = DataLoader(self.train_dir)
metamap = MetaMap(
metamap_path=
"/home/share/programs/metamap/2016/public_mm/bin/metamap",
cache_output=False)
train_loader.metamap(metamap)
pipeline = ClinicalPipeline(metamap, entities=['Strength'])
model = Model(pipeline)
model.fit(train_loader)
self.assertIsInstance(model, Model)
self.assertIsNot(model.model, None)
def test_metamapping(self):
with open(os.path.join(self.test_dir, 'test.txt'), 'w') as f:
f.write("Contents of test file")
with open(os.path.join(self.test_dir, 'test.ann'), 'w') as f:
f.write("Example Ann File")
loader = DataLoader(self.test_dir)
metamap = MetaMap(
metamap_path=
"/home/share/programs/metamap/2016/public_mm/bin/metamap",
cache_output=False)
loader.metamap(metamap)
"""
Metamap output cannot be tested through this wrapper due to how unit tests work (they override input/output
streams which the wrapper relies on for calling the Metamap server). Instead we test that metamap works
correctly and throws no errors - it will however output a null body for the metamapped contents in this test.
"""
with open(self.test_dir + "/metamapped/test.metamapped", 'r') as f:
self.assertEqual("{\"metamap\": null}", f.read())
def test_prediction_with_clinical_pipeline(self):
"""
Constructs a model that memorizes an entity, predicts it on same file, writes to ann
:return:
"""
train_loader = DataLoader(self.train_dir)
test_loader = DataLoader(self.test_dir)
metamap = MetaMap(
metamap_path=
"/home/share/programs/metamap/2016/public_mm/bin/metamap",
cache_output=False)
train_loader.metamap(metamap)
test_loader.metamap(metamap)
pipeline = ClinicalPipeline(metamap, entities=['Strength'])
model = Model(pipeline)
model.fit(train_loader)
model.predict(test_loader)
with open(self.test_dir + "/predictions/" + "predict_test.ann") as f:
self.assertEqual(f.read(), "T1 Strength 7 11 5 mg\n")
import logging, sys
# print logs
logging.basicConfig(
stream=sys.stdout,
level=logging.DEBUG) #set level=logging.DEBUG for more information
#entity types
entities = ['Reason', 'ADE', 'Drug']
# entities = ['Symptom', 'Form', 'Route', 'Frequency', 'Duration', 'Dosage', 'Strength', 'Drug']
# dirPred = '/home/mahendrand/VE/Predictions/CV/N2C2'
training_dataset = Dataset('/home/mahendrand/VE/Data/N2C2/data')
#set metamap path
metamap = MetaMap(
metamap_path="/home/share/programs/metamap/2016/public_mm/bin/metamap",
convert_ascii=True)
training_dataset.metamap(metamap)
# pipeline = ClinicalPipeline(metamap=metamap, entities=entities)
pipeline = SystematicReviewPipeline(metamap=metamap, entities=entities)
model = Model(
pipeline, n_jobs=1
) #distribute documents between 30 processes during training and prediction
model.fit(training_dataset)
#cross validation
# model.cross_validate(num_folds = 5, training_dataset = training_dataset, prediction_directory=dirPred, groundtruth_directory=True)
#location to store the clinical model
def setUpClass(cls):
cls.metamap = MetaMap(
metamap_path=
"/home/share/programs/metamap/2016/public_mm/bin/metamap")
from medacy.pipeline_components import MetaMap metamap = MetaMap(metamap_path="/home/share/programs/metamap/2016/public_mm/bin/metamap", cache_output=True) file_to_map = "/home/aymulyar/development/medaCy/medacy/tests/pipeline_components/metamap/test.txt" file = metamap.map_file(file_to_map) print(file)
