def test_saveStandoffFile_noArgNames():
text = "The colorectal cancer was caused by mutations in APC"
e1 = kindred.Entity(entityType="disease",text="colorectal cancer",position=[(4, 21)],sourceEntityID="T1")
e2 = kindred.Entity(entityType="gene",text="APC",position=[(49, 52)],sourceEntityID="T2")
rel = kindred.Relation(relationType="causes",entityIDs=[e1.entityID,e2.entityID])
doc = kindred.Document(text,[e1,e2],[rel],relationsUseSourceIDs=False)
corpus = kindred.Corpus()
corpus.addDocument(doc)
tempDir = tempfile.mkdtemp()
kindred.save(corpus,'standoff',tempDir)
loadedCorpus = kindred.loadDir('standoff',tempDir)
assert isinstance(loadedCorpus,kindred.Corpus)
assert len(loadedCorpus.documents) == 1
loadedDoc = loadedCorpus.documents[0]
assert isinstance(loadedDoc,kindred.Document)
entities = loadedDoc.getEntities()
relations = loadedDoc.getRelations()
sourceEntityIDsToEntityIDs = loadedDoc.getSourceEntityIDsToEntityIDs()
assertEntity(entities[0],expectedType='disease',expectedText='colorectal cancer',expectedPos=[(4,21)],expectedSourceEntityID="T1")
assertEntity(entities[1],expectedType='gene',expectedText='APC',expectedPos=[(49,52)],expectedSourceEntityID="T2")
assert relations == [kindred.Relation('causes',[sourceEntityIDsToEntityIDs["T1"],sourceEntityIDsToEntityIDs["T2"]],['arg1','arg2'])], "(%s) not as expected" % relations
shutil.rmtree(tempDir)
def load(taskName,ignoreEntities=[]):
"""
Download and load the corresponding corpus from the BioNLP Shared Task
:param taskName: The name of the shared task to download (e.g. 'BioNLP-ST-2016_BB-event_train'). Use kindred.bionlpst.listTasks() to get a list of valid options
:param ignoreEntities: A list of any entities that should be ignored during loading
:type taskName: str
:type ignoreEntities: list of str
:return: The loaded corpus
:rtype: kindred.Corpus
"""
global taskOptions
tempDir = tempfile.mkdtemp()
assert taskName in taskOptions.keys(), "%s not a valid option in %s" % (taskName, taskOptions.keys())
url,expectedFile,expectedSHA256 = taskOptions[taskName]
filesToDownload = [(url,expectedFile,expectedSHA256)]
expectedDir = expectedFile.replace('.zip','')
try:
kindred.utils._downloadFiles(filesToDownload,tempDir)
except:
exc_info = sys.exc_info()
shutil.rmtree(tempDir)
six.reraise(*exc_info)
mainDir = kindred.utils._findDir(expectedDir,tempDir)
corpus = kindred.loadDir(dataFormat='standoff',directory=mainDir,ignoreEntities=ignoreEntities)
shutil.rmtree(tempDir)
return corpus
def test_saveStandoffFile_fromSimpleTag():
text = 'The <disease id="T1">colorectal cancer</disease> was caused by mutations in <gene id="T2">APC</gene><relation type="causes" subj="T2" obj="T1" />'
corpus = kindred.Corpus()
doc = kindred.Document(text)
corpus.addDocument(doc)
tempDir = tempfile.mkdtemp()
kindred.save(corpus,'standoff',tempDir)
loadedCorpus = kindred.loadDir('standoff',tempDir)
assert isinstance(loadedCorpus,kindred.Corpus)
assert len(loadedCorpus.documents) == 1
loadedDoc = loadedCorpus.documents[0]
assert isinstance(loadedDoc,kindred.Document)
entities = loadedDoc.getEntities()
relations = loadedDoc.getRelations()
sourceEntityIDsToEntityIDs = loadedDoc.getSourceEntityIDsToEntityIDs()
assertEntity(entities[0],expectedType='disease',expectedText='colorectal cancer',expectedPos=[(4,21)],expectedSourceEntityID="T1")
assertEntity(entities[1],expectedType='gene',expectedText='APC',expectedPos=[(49,52)],expectedSourceEntityID="T2")
assert relations == [kindred.Relation('causes',[sourceEntityIDsToEntityIDs["T1"],sourceEntityIDsToEntityIDs["T2"]],['obj','subj'])], "(%s) not as expected" % relations
shutil.rmtree(tempDir)
def test_saveStandoffFile_SeparateSentences():
texts = ['The <disease id="T1">colorectal cancer</disease> was caused by mutations in <gene id="T2">APC</gene><relation type="causes" subj="T2" obj="T1" />','<disease id="T1">Li-Fraumeni</disease> was caused by mutations in <gene id="T2">P53</gene><relation type="causes" subj="T2" obj="T1" />']
corpus = kindred.Corpus()
for t in texts:
doc = kindred.Document(t)
corpus.addDocument(doc)
tempDir = tempfile.mkdtemp()
kindred.save(corpus,'standoff',tempDir)
loadedCorpus = kindred.loadDir('standoff',tempDir)
assert isinstance(loadedCorpus,kindred.Corpus)
assert len(loadedCorpus.documents) == 2
data = loadedCorpus.documents[0]
assert isinstance(data,kindred.Document)
entities = data.getEntities()
relations = data.getRelations()
sourceEntityIDsToEntityIDs = data.getSourceEntityIDsToEntityIDs()
assertEntity(entities[0],expectedType='disease',expectedText='colorectal cancer',expectedPos=[(4,21)],expectedSourceEntityID="T1")
assertEntity(entities[1],expectedType='gene',expectedText='APC',expectedPos=[(49,52)],expectedSourceEntityID="T2")
assert relations == [kindred.Relation('causes',[sourceEntityIDsToEntityIDs["T1"],sourceEntityIDsToEntityIDs["T2"]],['obj','subj'])], "(%s) not as expected" % relations
data = loadedCorpus.documents[1]
assert isinstance(data,kindred.Document)
entities = data.getEntities()
relations = data.getRelations()
sourceEntityIDsToEntityIDs = data.getSourceEntityIDsToEntityIDs()
assertEntity(entities[0],expectedType='disease',expectedText='Li-Fraumeni',expectedPos=[(0,11)],expectedSourceEntityID="T1")
assertEntity(entities[1],expectedType='gene',expectedText='P53',expectedPos=[(39,42)],expectedSourceEntityID="T2")
assert relations == [kindred.Relation('causes',[sourceEntityIDsToEntityIDs["T1"],sourceEntityIDsToEntityIDs["T2"]],['obj','subj'])], "(%s) not as expected" % relations
shutil.rmtree(tempDir)
def test_loadBiocFile_dir():
scriptDir = os.path.dirname(__file__)
dataPath = os.path.join(scriptDir, 'data')
corpus = kindred.loadDir(dataFormat='bioc', directory=dataPath)
assert isinstance(corpus, kindred.Corpus)
assert len(corpus.documents) == 1
data = corpus.documents[0]
assert isinstance(data, kindred.Document)
entities = data.getEntities()
relations = data.getRelations()
sourceEntityIDsToEntityIDs = data.getSourceEntityIDsToEntityIDs()
assertEntity(entities[0],
expectedType='disease',
expectedText='colorectal cancer',
expectedPos=[(4, 21)],
expectedSourceEntityID="T1")
assertEntity(entities[1],
expectedType='gene',
expectedText='APC',
expectedPos=[(49, 52)],
expectedSourceEntityID="T2")
assert relations == [
kindred.Relation('causes', [
sourceEntityIDsToEntityIDs["T1"], sourceEntityIDsToEntityIDs["T2"]
], ['obj', 'subj'])
], "(%s) not as expected" % relations
def test_loadEmptyDirectory():
tempDir = tempfile.mkdtemp()
for dataformat in ['standoff','simpletag','json','bioc']:
with pytest.raises(RuntimeError) as excinfo:
corpus = kindred.loadDir(dataformat,tempDir)
expectedError = 'No documents loaded from directory (%s/). Are you sure this directory contains the corpus (format: %s)' % (tempDir.rstrip('/'),dataformat)
assert excinfo.value.args == (expectedError ,)
shutil.rmtree(tempDir)
def test_saveBB3Data():
corpus = kindred.bionlpst.load('2016-BB3-event-train')
assert isinstance(corpus,kindred.Corpus)
tempDir = tempfile.mkdtemp()
kindred.save(corpus,'standoff',tempDir)
loadedCorpus = kindred.loadDir('standoff',tempDir)
assert len(corpus.documents) == len(loadedCorpus.documents)
shutil.rmtree(tempDir)
def test_saveStandoffFile_fromSimpleTag_triple():
text = '<drug id="T1">Erlotinib</drug>, a <gene id="T2">EGFR</gene> inhibitor is commonly used for <disease id="T3">NSCLC</disease> patients. <relation type="druginfo" drug="T1" gene="T2" disease="T3" />'
corpus = kindred.Corpus(text, loadFromSimpleTag=True)
tempDir = tempfile.mkdtemp()
kindred.save(corpus, 'standoff', tempDir)
loadedCorpus = kindred.loadDir('standoff', tempDir)
shutil.rmtree(tempDir)
assert isinstance(loadedCorpus, kindred.Corpus)
assert len(loadedCorpus.documents) == 1
loadedDoc = loadedCorpus.documents[0]
assert isinstance(loadedDoc, kindred.Document)
entities = loadedDoc.getEntities()
relations = loadedDoc.getRelations()
sourceEntityIDsToEntityIDs = loadedDoc.getSourceEntityIDsToEntityIDs()
assertEntity(entities[0],
expectedType='drug',
expectedText='Erlotinib',
expectedPos=[(0, 9)],
expectedSourceEntityID="T1")
assertEntity(entities[1],
expectedType='gene',
expectedText='EGFR',
expectedPos=[(13, 17)],
expectedSourceEntityID="T2")
assertEntity(entities[2],
expectedType='disease',
expectedText='NSCLC',
expectedPos=[(49, 54)],
expectedSourceEntityID="T3")
assert relations == [
kindred.Relation('druginfo', [
sourceEntityIDsToEntityIDs["T3"], sourceEntityIDsToEntityIDs["T1"],
sourceEntityIDsToEntityIDs["T2"]
], ['disease', 'drug', 'gene'])
], "(%s) not as expected" % relations
)
parser.add_argument('--reltype',
type=str,
required=True,
help='Relation type to analyze. Must be one of %s' %
reltypes)
parser.add_argument('--outCurve',
type=str,
required=True,
help='File to output curve data to')
args = parser.parse_args()
with open(args.outCurve, 'w') as outF:
outF.write("%s\t%s\t%s\n" % ('threshold', 'precision', 'recall'))
for threshold in [-0.1] + list(np.arange(0, 1, 0.01)) + [1.0]:
train = kindred.loadDir('standoff', args.trainDir)
gold = kindred.loadDir('standoff', args.testDir)
# Trim back to relation type of choice
for doc in train.documents:
doc.relations = [
r for r in doc.relations if r.relationType == args.reltype
]
for doc in gold.documents:
doc.relations = [
r for r in doc.relations if r.relationType == args.reltype
]
entityType = entityTypes[args.reltype]
entityCount = len(entityType)
classifier = kindred.RelationClassifier(
