def proses(test_str):
kata_pengganti = ""
katadasar = tampil.Tampil_KataDasar()
#katadasar = json.JSONDecoder().decode(katadasar)
katadasar = [i[0] for i in katadasar]
query = preprocessing.PreProcess(test_str)
query = query.split()
hasil = []
for i in range(len(query)):
if query[i] in katadasar:
hasil.append(query[i])
else:
word = bigram.urut(query[i])
nilai = 0
for j in range(len(katadasar)):
kata_urut = bigram.urut(katadasar[j])
nilai_tertinggi = jaccard.compute_jaccard_similarity_score(
word, kata_urut)
if nilai_tertinggi > nilai:
print(kata_urut)
print(nilai_tertinggi)
nilai = nilai_tertinggi
kata_pengganti = katadasar[j]
hasil.append(kata_pengganti)
#print(katadasar[2])
#hasil.append(bigram.urut(query[i]))
spasi = " "
hasil = spasi.join(hasil)
return hasil
def createDictionary():
wordsAdded = {}
cwd = os.getcwd()
data = tampil.Tampil_Hadis()
folder = "Hadits Bukhari-Muslim/"
fileList = []
for i in range(len(data)):
fileList.append(data[i][2])
for file in fileList:
with open(folder+file, 'r') as f:
words = f.read()
words = preprocessing.PreProcess(words)
words = urut(words)
words = urut2(words)
for word in words:
if word not in wordsAdded.keys():
wordsAdded[word] = [f.name]
else:
if file not in wordsAdded[word]:
wordsAdded[word] += [f.name]
#return wordsAdded
with open('indexing.txt', 'w') as json_file:
json.dump(wordsAdded, json_file)
def proses_Pencarian(value):
waktu_awal = time.time()
waktu_prepro_a = time.time()
query = preprocessing.PreProcess(value) #Preprocessing query
waktu_prepro_b = time.time()
waktu_proses_pre = waktu_prepro_b - waktu_prepro_a
print("Waktu Proses PrePro query "+str(waktu_proses_pre))
waktu_bigram_a = time.time()
value = bigram.proses(query) #Bigram query
waktu_bigram_b = time.time()
waktu_proses_bigram = waktu_bigram_b - waktu_bigram_a
print("Waktu Proses bigram query "+str(waktu_proses_bigram))
typo = ''
if value != query:
typo = value
value = value.split() #Bagi perkata hasil typo/query
f = open('indexing.json',)
indexing = json.load(f)
#Mengecek query di indexing
hasil = []
for i in range(len(value)):
if value[i] in indexing:
hasil = hasil + indexing[value[i]]
f.close()
doc = []
for x in range(len(hasil)):
if hasil[x] not in doc:
doc.append(hasil[x])
#Ambil Data dari Database sesuai dengan dokumen yang cocok dengan query
data = []
dokumen = tampil.Tampil_Hadis()
for k in range(len(doc)):
for l in range(len(dokumen)):
init = "Hadits Bukhari-Muslim/"+dokumen[l][2]
#print(init)
if doc[k] == init:
data.append(dokumen[l])
#Menghitung nilai jaccard similarity tiap dokumen terhadap query
waktu_jaccard_a = time.time()
rank = []
folder = "Hadits Bukhari-Muslim/"
for j in range(len(data)):
alamat = folder+data[j][2]
words = jaccard.urut(data[j][3])
nilai = jaccard.compute_jaccard_similarity_score(value, words)
result = [alamat, nilai]
rank.append(result)
waktu_jaccard_b = time.time()
waktu_proses_jaccard = waktu_jaccard_b - waktu_jaccard_a
print("Waktu Proses jaccard "+str(waktu_proses_jaccard))
#sorting dokumen
rank = sorted(rank, key=lambda x: x[1], reverse=True)
waktu_akhir = time.time()
waktu_proses1 = waktu_akhir - waktu_awal
return typo, rank, waktu_proses1