Uji similaritas, this file only works on project dir with activated working environment

ujisimilarity.py

from lsirina.lsi.similarity import calc_similarity

d1 = "Shipment of gold damaged in a fire"
d2 = "Delivery of silver arrived in a silver truck"
d3 = "Shipment of gold arrived in a truck"
query = "gold silver truck"

docs = [d1,d2,d3]
tokenized_doc = [d.split() for d in docs]

sim = calc_similarity(query, tokenized_doc)
sort_by_most_valid = filter(lambda x: x[1] > 0, sorted(enumerate(sim), key=lambda item: -item[1]))

for index, sim in sort_by_most_valid:
  print "dokumen %s: %s, nilai similaritas: %s" % (index+1, docs[index], sim)