def test_positive(self):
container = []
maxelements = 7
library.create(container, maxelements)
# Test remove positive cases
self.assertEqual(library.size(container), 0)
for n in range(maxelements):
self.assertEqual(library.inList(n, container), 0)
self.assertEqual(library.add(n, container), 1)
self.assertEqual(library.inList(n, container), 1)
self.assertEqual(library.size(container), n + 1)
for n in range(maxelements):
self.assertEqual(library.inList(n, container), 1)
self.assertEqual(library.remove(n, container), 1)
self.assertEqual(library.inList(n, container), 0)
self.assertEqual(library.size(container), maxelements - (n + 1))
self.assertEqual(library.size(container), 0)
# Test removeAll positive cases
self.assertEqual(library.size(container), 0)
self.assertEqual(library.inList(9, container), 0)
for n in range(maxelements):
self.assertEqual(library.add(9, container), 1)
self.assertEqual(library.inList(9, container), 1)
self.assertEqual(library.size(container), n + 1)
for n in range(maxelements, 10):
self.assertEqual(library.inList(9, container), 1)
self.assertEqual(library.add(9, container), 0)
self.assertEqual(library.inList(9, container), 1)
self.assertEqual(library.size(container), maxelements)
self.assertEqual(library.removeAll(9, container), maxelements)
self.assertEqual(library.size(container), 0)
def test_boundary(self):
container = []
maxelements = 7
library.create(container, maxelements)
# Test remove boundary cases
self.assertEqual(library.inList(0, container), 0)
self.assertEqual(library.remove(0, container), 0)
for n in range(maxelements):
library.add(n, container)
for n in range(maxelements, 10):
self.assertEqual(library.inList(n, container), 0)
self.assertEqual(library.add(n, container), 0)
self.assertEqual(library.inList(n, container), 0)
self.assertEqual(library.size(container), maxelements)
for n in range(maxelements, 10):
self.assertEqual(library.inList(n, container), 0)
self.assertEqual(library.remove(n, container), 0)
self.assertEqual(library.inList(n, container), 0)
self.assertEqual(library.size(container), maxelements)
for n in range(maxelements):
library.remove(n, container)
self.assertEqual(library.remove(0, container), 0)
self.assertEqual(library.inList(9, container), 0)
# Test removeAll boundary cases
self.assertEqual(library.inList(9, container), 0)
self.assertEqual(library.removeAll(9, container), 0)
for n in range(maxelements):
self.assertEqual(library.add(9, container), 1)
self.assertEqual(library.inList(9, container), 1)
self.assertEqual(library.size(container), n + 1)
for n in range(maxelements, 10):
self.assertEqual(library.inList(9, container), 1)
self.assertEqual(library.add(9, container), 0)
self.assertEqual(library.inList(9, container), 1)
self.assertEqual(library.size(container), maxelements)
self.assertEqual(library.removeAll(9, container), maxelements)
self.assertEqual(library.size(container), 0)
self.assertEqual(library.removeAll(9, container), 0)
self.assertEqual(library.inList(9, container), 0)
def test_random(self):
container = []
maxelements = 7
library.create(container, maxelements)
random_numbers = [random.randint(1, 9) for i in range(maxelements)]
# Test random cases
self.assertEqual(library.size(container), 0)
size = 0
for n in random_numbers:
self.assertEqual(library.size(container), size)
self.assertEqual(library.add(n, container), 1)
size += 1
self.assertEqual(library.inList(n, container), 1)
self.assertEqual(library.size(container), size)
for n in random_numbers:
self.assertEqual(library.size(container), size)
self.assertEqual(library.inList(n, container), 1)
self.assertEqual(library.remove(n, container), 1)
size -= 1
self.assertEqual(library.size(container), size)
self.assertEqual(library.size(container), 0)
from library import read_data, remove, tokenize, stem, stopwords, write_inverted_index, write_most_word
files = {}
word_count = {}
for data in read_data():
data['body'] = remove(data['body'])
data['body'] = tokenize(data['body'])
for token in data['body']:
token = stem(token)
if token not in stopwords() and len(token) > 1:
if data['id'] not in word_count.keys():
word_count[data['id']] = {}
elif token not in word_count[data['id']].keys():
word_count[data['id']][token] = 1
else:
word_count[data['id']][token] += 1
if token not in files.keys():
files[token] = {data['id']: 1}
elif token in files and data['id'] not in files[token]:
files[token][data['id']] = 1
else:
files[token][data['id']] += 1
most_word = {}
for words, counter in word_count.items():
word_counts = 0
for word, value in counter.items():
if word_counts < value:
word_counts = value
most_word[words] = word_counts
def run():
print("Proyek Mesin Pencarian Sederhana dengan Cranfield Collection")
term = read_inverted_index()
for query in read_query():
print(str(query['query number']) + '. ', query['query'])
choice = input("Masukan id dari query yang ingin dicari = ")
a("cls")
print("Proyek Mesin Pencarian Sederhana dengan Cranfield Collection")
for query in read_query():
if query['query number'] == int(choice):
selected_query = query['query']
selected_query = remove(selected_query)
selected_query = tokenize(selected_query)
tf = {}
term_doc = {}
for token in selected_query:
token = stem(token)
if token not in stopwords() and len(token) > 1:
if token not in tf.keys():
tf[token] = {}
tf[token]['query'] = 1
term_doc[token] = term.get(token)
else:
tf[token]['query'] += 1
max_idf = {}
ranked_doc = {}
for term, doc in term_doc.items():
max_idf[term] = len(term_doc[term])
for id, total in doc.items():
if id not in ranked_doc:
ranked_doc[id] = 0
if id not in tf[term]:
tf[term][id] = total
for word, data in tf.items():
for id, sum in data.items():
if id != "query":
tf[word][id] = 0.5 + (0.5 *
(tf[word][id] / read_most_word()[id]))
idf = {}
for term in tf.keys():
idf[term] = math.log2(1400 / max_idf[term])
for word, data in tf.items():
for id, sum in data.items():
if id != "query":
ranked_doc[id] += tf[word][id] * idf[word]
sorted_doc = sorted(ranked_doc.items(), key=lambda x: x[1], reverse=True)
doc = read_data()
sum = int(input("Masukan banyak dokumen relevan yang ini di tampilkan = "))
for i in range(sum):
print(
str(i + 1) + ". " + str(doc[int(sorted_doc[i][0]) - 1]['title']) +
" | similarity coefficient = " + str(sorted_doc[i][1]))
a("pause")
a("cls")
start()