def test_contains_key_2(self):
"""
Test contains_key with a hash map of 1 bucket.
:passed: yes
"""
# Make a linked list
ll_1 = LinkedList()
ll_1.add_front("cot", 3)
ll_1.add_front("box", 2)
ll_1.add_front("axe", 1)
# print("ll_1:", ll_1)
# Make a hash map
hash_m = HashMap(7, hash_function_2)
hash_m._buckets[6] = ll_1
# Make calls to contains_key
self.assertTrue(hash_m.contains_key("axe"))
self.assertTrue(hash_m.contains_key("box"))
self.assertTrue(hash_m.contains_key("cot"))
self.assertFalse(hash_m.contains_key("Axe"))
self.assertFalse(hash_m.contains_key("aXe"))
self.assertFalse(hash_m.contains_key("axE"))
self.assertFalse(hash_m.contains_key("AXE"))
self.assertFalse(hash_m.contains_key("boxx"))
self.assertFalse(hash_m.contains_key("cat"))
self.assertFalse(hash_m.contains_key("verb"))
def test_all():
hash_map = HashMap()
el_count = EL_COUNT
for x in range(el_count):
hash_map.put(str(x), str(x))
for x in range(el_count):
assert hash_map.get(str(x)) == str(x)
class TestHashMap(unittest.TestCase):
def setUp(self):
self.hash_map = HashMap()
self.item = Item('key', 'value')
def test_resize(self):
self.assertEqual(len(self.hash_map.buckets), 1)
self.hash_map._resize()
self.assertEqual(len(self.hash_map.buckets), 2)
self.hash_map._resize()
self.assertEqual(len(self.hash_map.buckets), 4)
def test_insert(self):
self.hash_map.insert(self.item)
self.assertEqual(len(self.hash_map), 1)
self.assertEqual(len(self.hash_map.buckets), 1)
self.assertIn(self.item, self.hash_map)
new_item_1 = Item('new key', 'new value')
self.hash_map.insert(new_item_1)
self.assertEqual(len(self.hash_map), 2)
self.assertEqual(len(self.hash_map.buckets), 2)
self.assertIn(self.item, self.hash_map)
self.assertIn(new_item_1, self.hash_map)
new_item_2 = Item('newer key', 'newer value')
self.hash_map.insert(new_item_2)
self.assertEqual(len(self.hash_map), 3)
self.assertEqual(len(self.hash_map.buckets), 4)
self.assertIn(self.item, self.hash_map)
self.assertIn(new_item_1, self.hash_map)
self.assertIn(new_item_2, self.hash_map)
def test_remove_2(self):
"""
Test remove() on a HashMap of capacity 0.
:passed: yes
"""
hash_m = HashMap(0, hash_function_1)
print(hash_m.remove("key1"))
def test_remove_3(self):
"""
Test remove() on an empty HashMap.
:passed: yes
"""
hash_m = HashMap(6, hash_function_1)
print(hash_m.remove("cat"))
def test_generate_hash_index_1(self):
"""
Test generate_hash_index.
:passed: yes
"""
hash_m = HashMap(6, hash_function_1)
print(hash_m.generate_hash_index("dog"))
self.assertEqual(2, hash_m.generate_hash_index("dog"))
def test_compressor():
hash_map = HashMap(3)
hash_code = hash_map.hash("test")
compressed = hash_map.compressor(hash_code)
result = (hash_code % 3)
assert compressed == result
def final_test(self):
map = HashMap()
map[1] = 100
map[5] = 500
map[20] = 5
map["Hello"] = "Goodbye"
assert (map.exists("Hello"))
assert (map["Hello"]) == "Goodbye"
map.delete("Hello")
assert (map["Hello"]) == None
def test_get(self):
"""Tests the HashMap get method"""
test_values = [("test_5", 5), ("test_-5", -5), ("test_5_", 5),
("diff_word", 15), ("another_word", 20), ("set", 10),
("anotha_one", -7), ("completely_different", 5),
("getting_there", -1)]
collision_values = [("completely_different", 5), ("anotha_one", -7),
("set", 10), ("another_word", 20)]
head_node = collision_values[0]
tail_node = collision_values[3]
student_map = HashMap(10, hash_function_1)
# add all key value pairs to the table
for key, val in test_values:
student_map.put(key, val)
# test get at linked_list head
self.assertEqual(student_map.get(head_node[0]), head_node[1])
# test get at linked_list tail
self.assertEqual(student_map.get(tail_node[0]), tail_node[1])
# test get at > 2 collision bucket
for node in collision_values:
self.assertEqual(student_map.get(node[0]), node[1])
# test get with no collision
self.assertEqual(student_map.get("getting_there"), -1)
# test that all values are in the list
for node in test_values:
self.assertEqual(student_map.get(node[0]), node[1])
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set() # Variable representing empty set.
ht = HashMap(
2500, hash_function_2
) # Variable to represent hash map construct utilizing above function.
# This block of code will read a file one word as a time and
# put the word in `w`. It should be left as starter code.
with open(source
) as f: # Opens file to be used declaring it as variable 'f'.
for line in f: # Loops through each line within file (f).
words = rgx.findall(
line) # Variable utilized to represent words within each line.
for w in words: # Loops through each word within each line.
lw = w.lower(
) # Turns words lowercase to remove case sensitivity.
keys.add(
lw
) # Adds lowercase word to set represented by variable 'key'.
if ht.contains_key(
lw): # Checks if word is already present in hash map.
new_value = (
ht.get(lw) + 1
) # Variable represents word count increased by one.
ht.put(
lw, new_value
) # Inserts word into hash map to have word count be updated.
else:
ht.put(
lw, 1
) # Inserts word into hash map with initial count of one.
keys_list = [] # Variable represents an empty list.
for values in keys: # Loops through words present in set represented by variable 'keys'.
ind = ht._hash_function(values) % ht.capacity
# Variable to represent number established by chosen function and available capacity.
temp = ht._buckets[
ind] # Variable to represent position within hash map containing linked list.
node = temp.contains(
values
) # Variable to represent node containing key if already present.
keys_list.append(
(node.key,
node.value)) # Adds tuple to list containing word, word count.
keys_list.sort(
key=lambda tup: tup[1],
reverse=True) # Sorts list in descending order based on word count.
return keys_list[
0:
number] # Returns list of top words within given range provided by user.
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500,hash_function_2)
# This block of code will read a file one word as a time and
# put the word in `w`. It should be left as starter code.
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
if ht.contains_key(w.lower()):
ht.put(w.lower(), ht.get(w.lower()) + 1)
else:
ht.put(w.lower(), 1)
tup = ht.sorted_tup()
return tup[:number]
def test_empty_buckets_2(self):
"""
Test empty_buckets() with Example #2 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 2 ---")
m = HashMap(50, hash_function_1)
for i in range(150):
m.put('key' + str(i), i * 100)
if i % 30 == 0:
print(m.empty_buckets(), m.size, m.capacity)
def test_resize_table_1(self):
"""
Test resize_table() with Example #1 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 1 ---")
m = HashMap(20, hash_function_1)
m.put('key1', 10)
print(m.size, m.capacity, m.get('key1'), m.contains_key('key1'))
m.resize_table(30)
print(m.size, m.capacity, m.get('key1'), m.contains_key('key1'))
def test_contains_key_3(self):
"""
Test contains_key with an empty hash map.
:passed: yes
"""
# Make an empty hash map
hash_m = HashMap(3, hash_function_2)
print(hash_m)
self.assertFalse(hash_m.contains_key("cat"))
self.assertFalse(hash_m.contains_key(" "))
def test_keys(self):
hash = HashMap()
hash[1] = [100]
hash[2] = [200]
hash[3] = [300]
hash["Hello"] = "Goodbye"
keys = hash.keys()
assert ("Hello" in keys)
assert (1 in keys)
assert (2 in keys)
assert (3 in keys)
def test_values(self):
hash = HashMap()
hash[1] = [100]
hash[2] = [200]
hash[3] = [300]
hash["Hello"] = "Goodbye"
values = hash.values()
assert ([100] in values)
assert ([200] in values)
assert ([300] in values)
assert ("Goodbye" in values)
def test_table_load_2(self):
"""
Test table_load() with Example #2 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 2 ---")
m = HashMap(50, hash_function_1)
for i in range(50):
m.put('key' + str(i), i * 100)
if i % 10 == 0:
print(m.table_load(), m.size, m.capacity)
def test_get(self):
h = HashMap(100)
h.set('1', SampleObject('A'))
b_obj = SampleObject('B')
h.set('2', b_obj)
h.set('3', SampleObject('C'))
self.assertEqual(h.get('2'), b_obj)
self.assertEqual(h.get('4'), None)
def test_put_1(self):
"""
Test put() on a hash map of capacity 0.
:passed: yes
"""
hash_m = HashMap(0, hash_function_1)
print("map before put():", hash_m)
hash_m.put("key1", 10)
print("put('key1', 10):", hash_m)
print(hash_m.put("key1", 10))
class Account(object):
# Initialize Account object with cash and hash map of stocks, where
# stock name points to number of shares
def __init__(self):
self.cash = 0
self.stocks = HashMap()
# Compare account's cash and stocks with that of another account
# Used in TransactionParser's reconcile() method
def compare(self, other_acct):
diffs = []
other_stocks = other_acct.stocks
all_keys = list(set(self.stocks.keys() + other_stocks.keys()))
for key in all_keys:
diff = self.stock_diff(key, other_stocks)
if diff and diff != 0:
diffs.append(key + " " + str(int(diff)))
diffs.insert(0, "Cash " + str(self.cash_diff(other_acct.cash)))
return "\n".join(diffs)
def cash_diff(self, other_cash):
return int(other_cash) - self.cash
# Calculates differences in shares of stocks between two accounts
def stock_diff(self, key, declared_results):
if self.stocks[key] and declared_results[key]:
return float(declared_results[key]) - self.stocks[key]
elif self.stocks[key]:
return -1 * self.stocks[key]
elif declared_results[key] and key != "Cash":
return float(declared_results[key])
else:
return None
# Wrapper for setting a stock into self.stocks
def set_stock(self, name, value):
self.stocks[name] = value
# Wrapper for getting a stock
def get_stock(self, stock):
return self.stocks.get(stock, 0)
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# Reads a file one word as a time and
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
w = w.lower(
) # covert word to lowercase for case-insensitive comparisons
if ht.contains_key(
w
): # if word already exists as key in ht, add 1 to value to track count
value = ht.get(w)
ht.put(w, value + 1)
else:
ht.put(
w, 1
) # if word does not exist in ht as key, add word as key and initialize value as 1
keys.add(w) # add word to set of keys
count_dict = {} # initialize empty dictionary
count_array = [] # initialize empty array
for key in keys: # for each key, get it's value from ht and then add key/value pair to count_dict
value = ht.get(key)
count_dict[key] = value
for key in keys: # for each key, add value/key pair to array for sorting
count_array.append((count_dict[key], key))
count_array = sorted(
count_array, reverse=True
) # reverse sort count_array from largest to smallest value
for i in range(
len(count_array)
): # reswap key/value pairs to get (word, count) for each tuple in count_array
count_array[i] = (count_array[i][1], count_array[i][0])
return count_array[:
number] # return only the requested number of top words
def test_contains_key_4(self):
"""
Test contains_key with an empty hash map.
:passed: yes
"""
# Make an empty hash map
hash_m = HashMap(0, hash_function_2)
print("hash_m:", hash_m)
self.assertFalse(hash_m.contains_key("blue"))
self.assertFalse(hash_m.contains_key("a"))
self.assertFalse(hash_m.contains_key(" "))
print(hash_m.contains_key("a"))
def test_assign():
hash_map = HashMap(1)
hash_map.assign("key_1", "value_1")
hash_map.assign("key_2", "value_2")
index_1 = hash_map.compressor(hash_map.hash("key_1"))
assert hash_map.array[index_1].get_head_node().get_next_node().get_value(
) == ("key_1", "value_1")
hash_map.assign("key_1", "test")
assert hash_map.array[index_1].get_head_node().get_next_node().get_value(
) == ("key_1", "test")
index_2 = hash_map.compressor(hash_map.hash("key_2"))
assert hash_map.array[index_2].get_head_node().get_value() == ("key_2",
"value_2")
def test_clear_2(self):
"""
Test clear() with Example #2 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 2 ---")
m = HashMap(50, hash_function_1)
print(m.size, m.capacity)
m.put('key1', 10)
print(m.size, m.capacity)
m.put('key2', 20)
print(m.size, m.capacity)
m.resize_table(100)
print(m.size, m.capacity)
m.clear()
print(m.size, m.capacity)
def test_init(self):
"""Checks that the hash_table initializes correctly, if __init__ is provided, ignore"""
student_map = HashMap(10, hash_function_1)
self.assertEqual(10, student_map.capacity)
self.assertEqual(0, student_map.size)
self.assertEqual(hash_function_1, student_map._hash_function)
for bucket in student_map._buckets:
self.assertIsNone(bucket.head)
def test_contains_key(self):
"""Tests the HashMap contains_key method"""
test_values = [("test_5", 5), ("test_-5", -5), ("test_5_", 5),
("diff_word", 15), ("another_word", 20), ("set", 10),
("anotha_one", -7), ("completely_different", 5),
("getting_there", -1)]
student_map = HashMap(10, hash_function_1)
# simple check to test that all values are in the list
for key, val in test_values:
student_map.put(key, val)
found = False
for bucket in student_map._buckets:
if bucket.contains(key):
found = True
self.assertEqual(found, student_map.contains_key(key))
def test_put_and_get(self):
hash = HashMap()
hash[1] = [100]
hash["Hello"] = "Goodbye"
hash[1.7] = 45
assert (hash[1]) == [100]
assert (hash["Hello"]) == "Goodbye"
assert (hash[1.7]) == 45
def add_words_to_hash_map(self, current_hash_map: HashMap,
current_line: str):
if self.line_count >= 50:
self.line_count = 0
self.hash_maps.append(current_hash_map)
current_hash_map = HashMap()
split_line = current_line.split(' ')
if '\n' in split_line:
split_line.remove('\n')
if '' in split_line:
split_line.remove('')
for word in self.strip_punctuation(split_line):
if word in self.punctuation:
continue
map_index = current_hash_map.hash_string(word)
current_hash_map.add_to_hash_table(map_index, (word, 1))
return current_hash_map
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# This block of code will read a file one word at a time and
# put the word in `w`. It should be left as starter code.
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
# Convert all words to lowercase prior to insertion
w = w.lower()
# If the word is already in the hash map, pass the value with a new updated count
if ht.contains_key(w):
count = ht.get(w) + 1
ht.put(w, count)
else:
# Otherwise, create a new entry in the hashmap
ht.put(w, 1)
# Add all of the words to the keys set
for bucket in ht.get_buckets():
# Iterate through each bucket/linked list
curr = bucket.head
while curr is not None:
# Add the keys as a tuple
keys.add((curr.key, curr.value))
curr = curr.next
# Cast the set as a list
all_words = list(keys)
# Sort the words according to their value in the tuple
all_words.sort(key=lambda word: word[1])
slice_val = (number * -1 - 1)
top_wds = all_words[:slice_val:-1]
return top_wds
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# This block of code will read a file one word as a time and
# put the word in `w`. It should be left as starter code.
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words: # Iterate through all the words in the line.
# Place lowercased version of words.
if ht.contains_key(
w.lower()): # If the word is in the hashmap.
ht.put(w.lower(),
ht.get(w.lower()) +
1) # Update the word count by 1.
else: # If the word does not exist in the hashmap.
ht.put(w.lower(),
1) # Place the key in the map with the value of 1.
keys.add(w.lower()) # Add the new keys into the keys set.
list_of_occurences = [
] # Create an empty list to hold the tuples of keys and values.
for key in keys: # Iterate through all the keys.
list_of_occurences.append(
(key, ht.get(key))) # Add the key and value tuple into the list.
# Source to help me find a way to implement this:
# stackoverflow.com/questions/10695139/sort-a-list-of-tuples-by-2nd-item-integer-value
# We use lambda here to sort the list of tuples by its second value.
# The sorting is also reversed to make it in descending order.
sorted_list = sorted(list_of_occurences, key=lambda x: x[1], reverse=True)
return sorted_list[:
number] # Using list slice, return the top numbers of the list depending on what the user inputs
# print(top_words("alice.txt",10)) # COMMENT THIS OUT WHEN SUBMITTING TO GRADESCOPE
def setUp(self):
self.uut = HashMap()
class HashMapTests(unittest.TestCase, DictTestCases):
def setUp(self):
self.uut = HashMap()
def mock_hashes_to(self, index=0):
class Mock(object):
def __hash__(self):
return index
def __str__(self):
return "mock(%s)" % index
__repr__ = __str__
return Mock()
def test_initial_current_capacity_is_16(self):
self.assertEqual(16, self.uut.capacity())
def test_initial_doubling_size_is_12(self):
self.assertEqual(12, self.uut.doubling_size())
def test_when_inialized_with_one_half_then_doubling_size_is_8(self):
uut = HashMap(0.5)
self.assertEqual(8, uut.doubling_size())
def test_initial_len_is_0(self):
self.assertEqual(0, len(self.uut))
def test_insertion_increses_size_to_1(self):
self.uut.insert(self.mock_hashes_to(), 42)
def test_collisions_are_handled(self):
first = self.mock_hashes_to(1)
second = self.mock_hashes_to(1)
self.uut.insert(first, "spam")
self.uut.insert(second, "eggs")
self.assertEqual("spam", self.uut.get(first))
self.assertEqual("eggs", self.uut.get(second))
def test_inserting_items_with_a_higher_value_works(self):
item = self.mock_hashes_to(99)
self.uut.insert(item, 42)
self.assertEqual(42, self.uut.get(item))
def test_when_at_doubling_size_then_the_capacity_doubles(self):
for i in xrange(11):
self.uut.insert(i, "_")
self.assertEqual(16, self.uut.capacity())
self.uut.insert(12, "_")
self.assertEqual(32, self.uut.capacity())
self.assertEqual(12, len(self.uut))
def test_len_is_0_after_delete_of_empty(self):
self.uut.delete("foo")
self.assertEqual(0, len(self.uut))
def test_len_is_0_after_delete_of_only_item(self):
self.uut.insert("foo", "_")
self.uut.delete("foo")
self.assertEqual(0, len(self.uut))
def test_len_is_0_after_delete_of_only_item_twice(self):
self.uut.insert("foo", "_")
self.uut.delete("foo")
self.uut.delete("foo")
self.assertEqual(0, len(self.uut))
def test_when_inialized_with_one_half_then_doubling_size_is_8(self):
uut = HashMap(0.5)
self.assertEqual(8, uut.doubling_size())
def test_hash_map(self):
test_map = HashMap()
for i in range(0,1000):
if i%2 is 0:
test_map.put((i,), i)
else: # i%2 is 1
test_map.put(str(i), [i])
# initialize the map with 1001 kv pairs
self.assertEquals(test_map.size(), 1000)
for i in range(0,1000):
if i%2 is 0:
self.assertEquals(test_map.get((i,)), i)
else: # i%2 is 1
self.assertEquals(test_map.get(str(i)), [i])
with self.assertRaises(KeyNotFound):
test_map.get("8")
with self.assertRaises(KeyNotFound):
test_map.get((991,))
with self.assertRaises(KeyNotFound):
test_map.get("test_key")
with self.assertRaises(KeyNotFound):
test_map.get((1002,))
# remove 700 elements
for i in range(100,800):
if i%2 is 0:
test_map.remove((i,))
else: # i%2 is 1
test_map.remove(str(i))
self.assertEquals(test_map.size(), 300)
self.assertTrue(test_map.contains((80,)))
self.assertFalse(test_map.contains((120,)))
# insert 9000 more values
for i in range(1000,10000):
if i%2 is 1:
test_map.put((i,), i)
else: # i%2 is 0
test_map.put(str(i), [i])
self.assertEquals(test_map.size(), 9300)
for i in range(1000,10000):
if i%2 is 1:
self.assertEquals(test_map.get((i,)), i)
else: # i%2 is 0
self.assertEquals(test_map.get(str(i)), [i])
