def get_scores(self, terms):
"""creates a list of scores for each file in corpus
The score = weighted frequency / the total word count in the file.
Compute this score for each term in a query and sum all the scores.
Args:
terms (list) : a list of str
Returns:
list : a list of tuples, each containing the filename and its relevancy score
"""
scores = HashTableLinear()
for term in terms:
if self.term_freqs.contains(term):
hashtable = self.term_freqs[term]
for file1 in hashtable.slots:
if file1 != None and hashtable.contains(file1[0]):
if scores.contains(file1[0]):
key, val = scores.remove(file1[0])
scores.put(file1[0], val + self.get_wf(file1[1]))
else:
scores.put(file1[0], self.get_wf(file1[1]))
for file1 in scores.slots:
if file1 is not None:
key, val = scores.remove(file1[0])
val /= self.doc_length.get(file1[0])
scores.put(file1[0], val)
return scores
def test_linear4(self):
ht = HashTableLinear()
for i in range(22):
ht.put(chr(i), i)
self.assertEqual(ht.size(), 22)
self.assertTrue(ht.load_factor() <= 0.75)
self.assertEqual(ht[chr(0)], 0)
self.assertEqual(ht[chr(1)], 1)
self.assertEqual(ht[chr(19)], 19)
for i in range(22):
ht.remove(chr(i))
self.assertFalse(ht.contains(chr(0)))
self.assertFalse(ht.contains(chr(1)))
self.assertFalse(ht.contains(chr(19)))
def test_HashTableLinear(self):
t = HashTableLinear()
self.assertEqual(t.size(), 0)
self.assertFalse(t.contains('us'))
self.assertRaises(KeyError, t.get, 'us')
t.put('us', 'us')
self.assertEqual(t.get('us'), 'us')
self.assertEqual(t['us'], 'us')
self.assertTrue(t.contains('us'))
self.assertFalse(t.contains('say'))
self.assertEqual(t.size(), 1)
self.assertEqual(t.collisions(), 0)
t.put('say', 'say')
self.assertEqual(t.get('say'), 'say')
self.assertTrue(t.contains('say'))
self.assertEqual(t.size(), 2)
self.assertEqual(t.collisions(), 1)
t.remove('say')
self.assertFalse(t.contains('say'))
self.assertTrue(t.contains('us'))
t.remove('us')
self.assertEqual(t.size(), 0)
# print(hash_string('the', 11)) # 'the' = 5
t.put('us', 'us')
t.put('say', 'say')
# self.assertEqual(t.load_factor(), 0.18181818181818182)
t.put('the', 'the')
# t.put(chr(0), chr(0))
# t.put('0', '0')
# print('chr 0', chr(0))
# print('just 0', '0')
# print(type(chr(0)))
# print(type('0'))
# print(hash_string('us', 23)) # 'the' = 5
# print(hash_string('say', 23)) # 'the' = 5
# print(hash_string('the', 23)) # 'the' = 5
# print('from tests', t)
self.assertTrue(t.contains('us'))
self.assertTrue(t.contains('the'))
def test_whole_functionality(self):
""" Tests the Separate Chain Hash Table Functionality"""
filename = 'stop_words.txt'
hash_table = HashTableLinear()
hash_table = import_stopwords(filename, hash_table)
self.assertRaises(KeyError, hash_table.get, 'BubbleGum')
self.assertTrue('to' in hash_table)
second_hash = HashTableLinear()
second_hash.put('three', 'three')
third_hash = HashTableLinear()
third_hash.put('three', 'three')
self.assertEqual(second_hash, third_hash)
self.assertNotEqual(hash_table, second_hash)
self.assertNotEqual(hash_table, 5)
expected = "Hash_val = 0: None\n" \
"Hash_val = 1: None\n" \
"Hash_val = 2: None\n" \
"Hash_val = 3: None\n" \
"Hash_val = 4: ('three', 'three')\n" \
"Hash_val = 5: None\n" \
"Hash_val = 6: None\n" \
"Hash_val = 7: None\n" \
"Hash_val = 8: None\n" \
"Hash_val = 9: None\n" \
"Hash_val = 10: None\n"
self.assertEqual(expected, repr(second_hash))
second_hash['four'] = 'four'
self.assertEqual(second_hash['four'], 'four')
second_hash['five'] = 'five'
self.assertEqual(0, hash_table.get('from'))
self.assertFalse(second_hash.contains('p'))
self.assertTrue(second_hash.contains('five'))
second_hash.remove('five')
self.assertFalse(second_hash.contains('five'))
self.assertRaises(KeyError, second_hash.remove, 'p')
self.assertEqual(1, third_hash.size())
self.assertEqual(0, third_hash.collisions())
def test_hash_linear(self):
table = HashTableLinear()
self.assertEqual(table.table_size, 11)
table["3"] = "3"
table["2"] = "2"
table["4"] = "4"
table["5"] = "5"
self.assertEqual("5" in table, True)
self.assertEqual("6" in table, False)
self.assertRaises(KeyError, table.get, "6")
table["3"] = "6"
self.assertEqual(table["3"], "6")
table[chr(40)] = "20"
self.assertEqual(table["3"], "6")
self.assertEqual(table.num_collisions, 1)
table.remove("3")
table.remove("4")
self.assertRaises(KeyError, table.get, "4")
self.assertRaises(KeyError, table.remove, "4")