def runEngine(tokenizer_type, address):
print("RUNNING ENGINE ...")
inverted_index = load_obj("INVERTED INDEX " + tokenizer_type + "_" +
address)
tfidfs = load_obj("CHAMPIONS " + tokenize_type + "_" + address)
query = ""
while True:
query = input("QUERY :>")
if query == "!q": break
queryToken = query.split(" ")
queryw = tf_idf(queryToken, inverted_index, False)
h = Heap()
for i in range(len(tfidfs)):
if bool(set(queryToken) & set(tfidfs[i].keys())):
sim = querySimilarity(queryw, tfidfs[i])
if sim != 0:
h.addnSort([i, sim])
k = 10
result = h.getFirstK(k)
titles = fetch_column(address, 'title')
for i in range(k):
print(titles[result[i][0]][::-1])
def callback(self):
print("GOT TOKEN ", self.text.get("1.0", END))
queryToken = self.text.get("1.0", END).replace("\n", "").split(" ")
queryToken = normalize_query(queryToken)
print(queryToken)
queryw = tf_idf(queryToken, self.inverted_index, False)
h = Heap()
for i in range(len(self.tfidfs)):
if bool(set(queryToken) & set(self.tfidfs[i].keys())):
sim = querySimilarity(queryw, self.tfidfs[i])
if sim != 0:
h.addnSort([i, sim])
k = 10
result = h.getFirstK(k)
k = min(len(result), k)
print(k)
for i in range(k):
print(self.titles[result[i][0]])
self.mylist.delete(i)
self.mylist.insert(i, self.titles[result[i][0]])
