def test_empty_buckets(self):
"""Checks the empty_buckets 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)]
empty_buckets = initial_capacity = 10
student_map = HashMap(initial_capacity, hash_function_1)
self.assertEqual(empty_buckets, student_map.empty_buckets())
empty_buckets = initial_capacity = 20
student_map = HashMap(initial_capacity, hash_function_1)
self.assertEqual(empty_buckets, student_map.empty_buckets())
student_map.put("first_value", 5)
self.assertEqual(empty_buckets - 1, student_map.empty_buckets())
student_map = HashMap(10, hash_function_1)
student_map_hf2 = HashMap(10, hash_function_2)
for key, val in test_values:
student_map.put(key, val)
student_map_hf2.put(key, val)
# should have 5 empty buckets with hash_function_1
self.assertEqual(5, student_map.empty_buckets())
# 4 with hash_function_2
self.assertEqual(4, student_map_hf2.empty_buckets())
def test_empty_buckets_1(self):
"""
Test empty_buckets() with Example #1 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 1 ---")
m = HashMap(100, hash_function_1)
print(m.empty_buckets(), m.size, m.capacity)
m.put('key1', 10)
print(m.empty_buckets(), m.size, m.capacity)
m.put('key2', 20)
print(m.empty_buckets(), m.size, m.capacity)
m.put('key1', 30)
print(m.empty_buckets(), m.size, m.capacity)
m.put('key4', 40)
print(m.empty_buckets(), m.size, m.capacity)
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_put_5(self):
"""
Test put() with Example #2 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 2 ---")
m = HashMap(40, hash_function_2)
for i in range(50):
m.put('str' + str(i // 3), i * 100)
if i % 10 == 9:
print(m.empty_buckets(), m.table_load(), m.size, m.capacity)
def test_put_4(self):
"""
Test put() with Example #1 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 1 ---")
m = HashMap(50, hash_function_1)
for i in range(150):
m.put('str' + str(i), i * 100)
if i % 25 == 24:
print(m.empty_buckets(), m.table_load(), m.size, m.capacity)
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)])
"""
result = []
ht = HashMap(2500, hash_function_2)
# This block of code will read a file one word at a time
# and add it to the hash map
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
lw = w.lower()
# If the word is not in the hash map, add it with a value of 1
if not ht.contains_key(lw):
ht.put(lw, 1)
else:
# Otherwise, update the value by increasing it by 1
ht.put(lw, ht.get(lw) + 1)
for bucket in ht._buckets:
cur = bucket.head
while cur is not None:
result.append((cur.key, cur.value))
cur = cur.next
print(ht.table_load())
print(ht.empty_buckets())
sort_words(result)
return result[:number]
# Author: Leon Samuel
# Date: May 28, 2020
# Description: Testing for hash map program
from hash_map import SLNode, LinkedList, HashMap, hash_function_1, hash_function_2
""" EMPTY BUCKETS """
print("\n\n******** EMPTY_BUCKETS() ********")
print("--- EXAMPLE 1 ---")
m = HashMap(100, hash_function_1)
print(m.empty_buckets(), m.size, m.capacity)
m.put('key1', 10)
print(m.empty_buckets(), m.size, m.capacity)
m.put('key2', 20)
print(m.empty_buckets(), m.size, m.capacity)
m.put('key1', 30)
print(m.empty_buckets(), m.size, m.capacity)
m.put('key4', 40)
print(m.empty_buckets(), m.size, m.capacity)
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)
""" TABLE LOAD """
print("\n\n******** TABLE_LOAD() ********")
print("--- EXAMPLE 1 ---")
m = HashMap(100, hash_function_1)
print(m.table_load())
m.put('key1', 10)
