-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathhash_map_oa.py
495 lines (424 loc) · 16.4 KB
/
hash_map_oa.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
# Name: Kristin Eberman
# OSU Email: [email protected]
# Course: CS261 - Data Structures (section 404)
# Assignment: 6 - HashMap Implementation - Open Addressing
# Due Date: December 2, 2022
# Description: This assignment implements 10 methods within the HashMap class
# using a DynamicArray to store the hash table and implements
# Open Addressing with Quadratic Probing for collision resolution
from a6_include import (DynamicArray, DynamicArrayException, HashEntry,
hash_function_1, hash_function_2)
class HashMap:
def __init__(self, capacity: int, function) -> None:
"""
Initialize new HashMap that uses
quadratic probing for collision resolution
DO NOT CHANGE THIS METHOD IN ANY WAY
"""
self._buckets = DynamicArray()
# capacity must be a prime number
self._capacity = self._next_prime(capacity)
for _ in range(self._capacity):
self._buckets.append(None)
self._hash_function = function
self._size = 0
def __str__(self) -> str:
"""
Override string method to provide more readable output
DO NOT CHANGE THIS METHOD IN ANY WAY
"""
out = ''
for i in range(self._buckets.length()):
out += str(i) + ': ' + str(self._buckets[i]) + '\n'
return out
def _next_prime(self, capacity: int) -> int:
"""
Increment from given number to find the closest prime number
DO NOT CHANGE THIS METHOD IN ANY WAY
"""
if capacity % 2 == 0:
capacity += 1
while not self._is_prime(capacity):
capacity += 2
return capacity
@staticmethod
def _is_prime(capacity: int) -> bool:
"""
Determine if given integer is a prime number and return boolean
DO NOT CHANGE THIS METHOD IN ANY WAY
"""
if capacity == 2 or capacity == 3:
return True
if capacity == 1 or capacity % 2 == 0:
return False
factor = 3
while factor ** 2 <= capacity:
if capacity % factor == 0:
return False
factor += 2
return True
def get_size(self) -> int:
"""
Return size of map
DO NOT CHANGE THIS METHOD IN ANY WAY
"""
return self._size
def get_capacity(self) -> int:
"""
Return capacity of map
DO NOT CHANGE THIS METHOD IN ANY WAY
"""
return self._capacity
# ------------------------------------------------------------------ #
def put(self, key: str, value: object) -> None:
"""
Adds or updates a key/value pair in the hash map
:param key: Unique key associated with value
:param value: Value associated with key
:return: None
"""
# Resize the array if load factor >= 0.5
if self.table_load() >= 0.5:
self.resize_table(self._capacity * 2)
# Use hash function to generate hash value and associated index
hash = self._hash_function(key)
index = hash % self._capacity
# Initialize new HashEntry
new_entry = HashEntry(key, value)
# Initialize boolean to control loop & quadratic probing variables
filled = False
probe_count = 1
probe_index = index
while not filled:
# If index is empty, fill with new_entry
if not self._buckets[probe_index]:
self._buckets[probe_index] = new_entry
self._size += 1
filled = True
# If array element is a tombstone, overwrite it
elif self._buckets[probe_index].is_tombstone:
self._buckets[probe_index] = new_entry
self._size += 1
filled = True
# If key already exists, update its value (do not increment size)
elif self._buckets[probe_index].key == key:
self._buckets[probe_index].value = value
filled = True
# Use quadratic probing formula to find next possible index
else:
probe_index = (index + probe_count ** 2) % self._capacity
probe_count += 1
def table_load(self) -> float:
"""
Returns the current hash table load factor
:return: Number of elements (size) / number of buckets (capacity)
"""
return self._size / self._capacity
def empty_buckets(self) -> int:
"""
Returns the number of empty buckets in the hash table
:return: Integer value that represents number of empty buckets
"""
# Empty buckets = the array's capacity minus size of HashMap
return self._capacity - self._size
def resize_table(self, new_capacity: int) -> None:
"""
Changes capacity of the hash table; rehashes all key/value pairs
:param new_capacity: New value for capacity of underlying array
:return: None
"""
# Don't resize if new_capacity < current number of elements
if new_capacity < self._size:
return
# Initialize HashMap with new capacity
resized_hash = HashMap(new_capacity, self._hash_function)
# Iterate over all elements in the original array
for i in range(self._capacity):
# Only re-hash elements that exist and are not tombstone values
if self._buckets[i] and not self._buckets[i].is_tombstone:
resized_hash.put(self._buckets[i].key, self._buckets[i].value)
# Update/re-point the original buckets and capacity variables
self._capacity = resized_hash._capacity
self._buckets = resized_hash._buckets
def get(self, key: str) -> object:
"""
Returns the value associated with a given key
:param key: Key to search for in the HashMap
:return: Value of given key if it exists, otherwise None
"""
# Use hash function to find index of key & set up probing variables
hash = self._hash_function(key)
index = hash % self._capacity
probe_count = 1
probe_index = index
# Iterate over array to search for key value
while self._buckets[probe_index]:
if self._buckets[probe_index].key == key and not self._buckets[probe_index].is_tombstone:
return self._buckets[probe_index].value
else:
# Use quadratic probing formula to find next possible index
probe_index = (index + probe_count ** 2) % self._capacity
probe_count += 1
# If the key is not found, return None
return None
def contains_key(self, key: str) -> bool:
"""
Searches for a given key within the HashMap (using get method)
:param key: Key to search for
:return: True if the key is found, otherwise False
"""
if self.get(key) is None:
return False
return True
def remove(self, key: str) -> None:
"""
Removes key/value pair if key exists in the HashMap
:param key: Key to search for and remove
:return: None
"""
# Use hash function to find index of key & set up probing variables
hash = self._hash_function(key)
index = hash % self._capacity
probe_count = 1
probe_index = index
# Iterate over array to search for key value
while self._buckets[probe_index]:
if self._buckets[probe_index].key == key and not self._buckets[probe_index].is_tombstone:
# If key is found, set tombstone to True and decrement size
self._buckets[probe_index].is_tombstone = True
self._size -= 1
else:
# Use quadratic probing formula to find next possible index
probe_index = (index + probe_count ** 2) % self._capacity
probe_count += 1
def clear(self) -> None:
"""
Clears the contents of the HashMap without changing its capacity
:return: None
"""
# Override _buckets with an empty DynamicArray and reset size to 0
self._buckets = DynamicArray()
for _ in range(self._capacity):
self._buckets.append(None)
self._size = 0
def get_keys_and_values(self) -> DynamicArray:
"""
Creates a dynamic array that contains tuples of all key/value pairs
stored in the HashMap
:return: Dynamic array of key/value tuples
"""
# Initialize an empty dynamic array to fill with tuples
key_value_arr = DynamicArray()
# Iterate over the HashMap
for i in range(self._capacity):
# Only add tuples for existing elements that are not tombstones
if self._buckets[i] and not self._buckets[i].is_tombstone:
key_value_arr.append((self._buckets[i].key, self._buckets[i].value))
return key_value_arr
def __iter__(self):
"""
Method enables the HashMap to iterate across itself
:return: None
"""
# Initialize index variable to track progress of iterator
self._index = 0
return self
def __next__(self):
"""
Returns value of the next active element in the HashMap based on the
current iterator location, then increments index/iterator position
"""
try:
element = self._buckets.get_at_index(self._index)
self._index += 1
# Skip elements that are empty or are tombstones
while not element or element.is_tombstone:
element = self._buckets.get_at_index(self._index)
self._index += 1
# StopIteration exception is raised when there are no more items
except DynamicArrayException:
raise StopIteration
return element
# ------------------- BASIC TESTING ---------------------------------------- #
if __name__ == "__main__":
print("\nPDF - put example 1")
print("-------------------")
m = HashMap(53, hash_function_1)
for i in range(150):
m.put('str' + str(i), i * 100)
if i % 25 == 24:
print(m.empty_buckets(), round(m.table_load(), 2), m.get_size(), m.get_capacity())
print("\nPDF - put example 2")
print("-------------------")
m = HashMap(41, hash_function_2)
for i in range(50):
m.put('str' + str(i // 3), i * 100)
if i % 10 == 9:
print(m.empty_buckets(), round(m.table_load(), 2), m.get_size(), m.get_capacity())
print("\nPDF - table_load example 1")
print("--------------------------")
m = HashMap(101, hash_function_1)
print(round(m.table_load(), 2))
m.put('key1', 10)
print(round(m.table_load(), 2))
m.put('key2', 20)
print(round(m.table_load(), 2))
m.put('key1', 30)
print(round(m.table_load(), 2))
print("\nPDF - table_load example 2")
print("--------------------------")
m = HashMap(53, hash_function_1)
for i in range(50):
m.put('key' + str(i), i * 100)
if i % 10 == 0:
print(round(m.table_load(), 2), m.get_size(), m.get_capacity())
print("\nPDF - empty_buckets example 1")
print("-----------------------------")
m = HashMap(101, hash_function_1)
print(m.empty_buckets(), m.get_size(), m.get_capacity())
m.put('key1', 10)
print(m.empty_buckets(), m.get_size(), m.get_capacity())
m.put('key2', 20)
print(m.empty_buckets(), m.get_size(), m.get_capacity())
m.put('key1', 30)
print(m.empty_buckets(), m.get_size(), m.get_capacity())
m.put('key4', 40)
print(m.empty_buckets(), m.get_size(), m.get_capacity())
print("\nPDF - empty_buckets example 2")
print("-----------------------------")
m = HashMap(53, hash_function_1)
for i in range(150):
m.put('key' + str(i), i * 100)
if i % 30 == 0:
print(m.empty_buckets(), m.get_size(), m.get_capacity())
print("\nPDF - resize example 1")
print("----------------------")
m = HashMap(23, hash_function_1)
m.put('key1', 10)
print(m.get_size(), m.get_capacity(), m.get('key1'), m.contains_key('key1'))
m.resize_table(30)
print(m.get_size(), m.get_capacity(), m.get('key1'), m.contains_key('key1'))
print("\nPDF - resize example 2")
print("----------------------")
m = HashMap(79, hash_function_2)
keys = [i for i in range(1, 1000, 13)]
for key in keys:
m.put(str(key), key * 42)
print(m.get_size(), m.get_capacity())
for capacity in range(111, 1000, 117):
m.resize_table(capacity)
if m.table_load() > 0.5:
print(f"Check that the load factor is acceptable after the call to resize_table().\n"
f"Your load factor is {round(m.table_load(), 2)} and should be less than or equal to 0.5")
m.put('some key', 'some value')
result = m.contains_key('some key')
m.remove('some key')
for key in keys:
# all inserted keys must be present
result &= m.contains_key(str(key))
# NOT inserted keys must be absent
result &= not m.contains_key(str(key + 1))
print(capacity, result, m.get_size(), m.get_capacity(), round(m.table_load(), 2))
print("\nPDF - get example 1")
print("-------------------")
m = HashMap(31, hash_function_1)
print(m.get('key'))
m.put('key1', 10)
print(m.get('key1'))
print("\nPDF - get example 2")
print("-------------------")
m = HashMap(151, hash_function_2)
for i in range(200, 300, 7):
m.put(str(i), i * 10)
print(m.get_size(), m.get_capacity())
for i in range(200, 300, 21):
print(i, m.get(str(i)), m.get(str(i)) == i * 10)
print(i + 1, m.get(str(i + 1)), m.get(str(i + 1)) == (i + 1) * 10)
print("\nPDF - contains_key example 1")
print("----------------------------")
m = HashMap(11, hash_function_1)
print(m.contains_key('key1'))
m.put('key1', 10)
m.put('key2', 20)
m.put('key3', 30)
print(m.contains_key('key1'))
print(m.contains_key('key4'))
print(m.contains_key('key2'))
print(m.contains_key('key3'))
m.remove('key3')
print(m.contains_key('key3'))
print("\nPDF - contains_key example 2")
print("----------------------------")
m = HashMap(79, hash_function_2)
keys = [i for i in range(1, 1000, 20)]
for key in keys:
m.put(str(key), key * 42)
print(m.get_size(), m.get_capacity())
result = True
for key in keys:
# all inserted keys must be present
result &= m.contains_key(str(key))
# NOT inserted keys must be absent
result &= not m.contains_key(str(key + 1))
print(result)
print("\nPDF - remove example 1")
print("----------------------")
m = HashMap(53, hash_function_1)
print(m.get('key1'))
m.put('key1', 10)
print(m.get('key1'))
m.remove('key1')
print(m.get('key1'))
m.remove('key4')
print("\nPDF - clear example 1")
print("---------------------")
m = HashMap(101, hash_function_1)
print(m.get_size(), m.get_capacity())
m.put('key1', 10)
m.put('key2', 20)
m.put('key1', 30)
print(m.get_size(), m.get_capacity())
m.clear()
print(m.get_size(), m.get_capacity())
print("\nPDF - clear example 2")
print("---------------------")
m = HashMap(53, hash_function_1)
print(m.get_size(), m.get_capacity())
m.put('key1', 10)
print(m.get_size(), m.get_capacity())
m.put('key2', 20)
print(m.get_size(), m.get_capacity())
m.resize_table(100)
print(m.get_size(), m.get_capacity())
m.clear()
print(m.get_size(), m.get_capacity())
print("\nPDF - get_keys_and_values example 1")
print("------------------------")
m = HashMap(11, hash_function_2)
for i in range(1, 6):
m.put(str(i), str(i * 10))
print(m.get_keys_and_values())
m.resize_table(2)
print(m.get_keys_and_values())
m.put('20', '200')
m.remove('1')
m.resize_table(12)
print(m.get_keys_and_values())
print("\nPDF - __iter__(), __next__() example 1")
print("---------------------")
m = HashMap(10, hash_function_1)
for i in range(5):
m.put(str(i), str(i * 10))
print(m)
for item in m:
print('K:', item.key, 'V:', item.value)
print("\nPDF - __iter__(), __next__() example 2")
print("---------------------")
m = HashMap(10, hash_function_2)
for i in range(5):
m.put(str(i), str(i * 24))
m.remove('0')
m.remove('4')
print(m)
for item in m:
print('K:', item.key, 'V:', item.value)