def run(q, d1, d2_s):
d2 = convert_string_to_dict(d2_s)
dimensions = return_keys(d1, d2)
v1 = mk_vector(d1, dimensions)
v2 = mk_vector(d2, dimensions)
v1_bin = binarise(v1)
v2_bin = binarise(v2)
coverage = sum(v1_bin * v2_bin) / len(q.split())
d1_vec = normalise(v1)
d2_vec = normalise(v2)
return cosine_similarity(d1_vec, d2_vec), coverage
def compute_pod_summary(name):
'''This function is very similar to 'self' in PeARS-pod'''
DS_vector = np.zeros(400)
word_vector = ""
freqs = {}
for u in db.session.query(Urls).filter_by(pod=name).all():
DS_vector += convert_to_array(u.vector)
for k, v in convert_string_to_dict(u.freqs).items():
if k in freqs:
freqs[k] += int(v)
else:
freqs[k] = int(v)
DS_vector = convert_to_string(normalise(DS_vector))
c = 0
for w in sorted(freqs, key=freqs.get, reverse=True):
word_vector += w + ':' + str(freqs[w]) + ' '
c += 1
if c == 300:
break
return DS_vector, word_vector