def stream(self, data):
print('\nThe following request in RDF format was passed:')
print(data)
identification, theDate, suri, puri, ouri = extract.getValues(data)
print('\nSURI, PURI and OURI are:')
print(suri)
print(puri)
print(ouri)
print('\n')
# sid, pid, oid = self.uriToId(suri, puri, ouri)
sid, pid, oid = mapping.convert(suri, puri, ouri)
# required for passing it to compute_mincostflow
sid, pid, oid = np.array([sid]), np.array([pid]), np.array([oid])
t1 = time()
print('\nTheir corresponding IDs are:')
print(sid)
print(pid)
print(oid)
print('\n')
log.info('Computing KL for triple')
with warnings.catch_warnings():
try:
warnings.simplefilter("ignore")
# compute klinker
scores, paths, rpaths, times = self.compute_klinker(
self.G, sid, pid, oid)
normalizedScore = normalization.score(scores[0])
log.info(
'KLinker computation complete. Time taken: {:.2f} secs.\n'.
format(time() - t1))
result = '<http://swc2017.aksw.org/task2/dataset/s-' + str(
identification
) + '> <http://swc2017.aksw.org/hasTruthValue>\"' + str(
normalizedScore
) + '\"<http://www.w3.org/2001/XMLSchema#double> .'
print('The result in RDF format is:')
print(result)
except MemoryError:
print('\nA MemoryError is successfully caught.')
result = 'MemoryError'
return result
def stream(self, data, args=None):
print('\nThe following request in RDF format was passed:')
print(data)
identification, theDate, suri, puri, ouri = extract.getValues(data)
print('\nSURI, PURI and OURI are:')
print(suri)
print(puri)
print(ouri)
print('\n')
# sid, pid, oid = self.uriToId(suri, puri, ouri)
sid, pid, oid = mapping.convert(suri, puri, ouri)
# required for passing it to compute_mincostflow
sid, pid, oid = np.array([sid]), np.array([pid]), np.array([oid])
t1 = time()
print('\nTheir corresponding IDs are:')
print(sid)
print(pid)
print(oid)
print('\n')
log.info('Computing Predpath for triple')
int_sid = int(sid)
int_pid = int(pid)
int_oid = int(oid)
print("The subject id is: %s " % int_sid)
print("The predicate id is: %s" % int_pid)
print("The object id is: %s" % int_oid)
# Creating a dataframe
data = {
'sid': [int_sid],
'pid': [int_pid],
'oid': [int_oid],
'class': [0]
}
#__________________test________________________
dfObj = pd.DataFrame(data)
test_spo_df = dfObj.dropna(axis=0,
subset=['sid', 'pid', 'oid', 'class'])
test_model_pkl = open("./output/trained_pra_model.pkl", "rb")
test_model = pkl.load(test_model_pkl)
test_features_pkl = open("./output/pra_features_file.pkl", "rb")
test_features = pkl.load(test_features_pkl)
with warnings.catch_warnings():
try:
warnings.simplefilter("ignore")
# pra_predict() function is used to predict the triple's veracity
array_value = pra_predict(self.G, test_features, test_model,
test_spo_df) # test
val = str(array_value)[1:-1]
log.info(
'Predpath computation complete. Time taken: {:.2f} secs.\n'
.format(time() - t1))
result = '<http://swc2017.aksw.org/task2/dataset/s-' + str(
identification
) + '> <http://swc2017.aksw.org/hasTruthValue>\"' + str(
val) + '\"<http://www.w3.org/2001/XMLSchema#double> .'
print('The result in RDF format is:')
print(result)
except MemoryError:
print('\nA MemoryError is successfully caught.')
result = 'MemoryError'
return result
