{{ message }}
forked from TheAlgorithms/Python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathhash_table.py
More file actions
283 lines (243 loc) · 7.85 KB
/
Copy pathhash_table.py
File metadata and controls
283 lines (243 loc) · 7.85 KB
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
#!/usr/bin/env python3
from abc import abstractmethod
from .number_theory.prime_numbers import next_prime
class HashTable:
"""
Basic Hash Table example with open addressing and linear probing
"""
def __init__(
self,
size_table: int,
charge_factor: int | None = None,
lim_charge: float | None = None,
) -> None:
self.size_table = size_table
self.values = [None] * self.size_table
self.lim_charge = 0.75 if lim_charge is None else lim_charge
self.charge_factor = 1 if charge_factor is None else charge_factor
self.__aux_list: list = []
self._keys: dict = {}
def keys(self):
"""
The keys function returns a dictionary containing the key value pairs.
key being the index number in hash table and value being the data value.
Examples:
1. creating HashTable with size 10 and inserting 3 elements
>>> ht = HashTable(10)
>>> ht.insert_data(10)
>>> ht.insert_data(20)
>>> ht.insert_data(30)
>>> ht.keys()
{0: 10, 1: 20, 2: 30}
2. creating HashTable with size 5 and inserting 5 elements
>>> ht = HashTable(5)
>>> ht.insert_data(5)
>>> ht.insert_data(4)
>>> ht.insert_data(3)
>>> ht.insert_data(2)
>>> ht.insert_data(1)
>>> ht.keys()
{0: 5, 4: 4, 3: 3, 2: 2, 1: 1}
"""
return self._keys
def balanced_factor(self):
return sum(1 for slot in self.values if slot is not None) / (
self.size_table * self.charge_factor
)
def hash_function(self, key):
"""
Generates hash for the given key value
Examples:
Creating HashTable with size 5
>>> ht = HashTable(5)
>>> ht.hash_function(10)
0
>>> ht.hash_function(20)
0
>>> ht.hash_function(4)
4
>>> ht.hash_function(18)
3
>>> ht.hash_function(-18)
2
>>> ht.hash_function(18.5)
3.5
>>> ht.hash_function(0)
0
>>> ht.hash_function(-0)
0
"""
return key % self.size_table
def _step_by_step(self, step_ord):
print(f"step {step_ord}")
print(list(range(len(self.values))))
print(self.values)
def bulk_insert(self, values):
"""
bulk_insert is used for entering more than one element at a time
in the HashTable.
Examples:
1.
>>> ht = HashTable(5)
>>> ht.bulk_insert((10,20,30))
step 1
[0, 1, 2, 3, 4]
[10, None, None, None, None]
step 2
[0, 1, 2, 3, 4]
[10, 20, None, None, None]
step 3
[0, 1, 2, 3, 4]
[10, 20, 30, None, None]
2.
>>> ht = HashTable(5)
>>> ht.bulk_insert([5,4,3,2,1])
step 1
[0, 1, 2, 3, 4]
[5, None, None, None, None]
step 2
[0, 1, 2, 3, 4]
[5, None, None, None, 4]
step 3
[0, 1, 2, 3, 4]
[5, None, None, 3, 4]
step 4
[0, 1, 2, 3, 4]
[5, None, 2, 3, 4]
step 5
[0, 1, 2, 3, 4]
[5, 1, 2, 3, 4]
"""
i = 1
self.__aux_list = values
for value in values:
self.insert_data(value)
self._step_by_step(i)
i += 1
def _set_value(self, key, data):
"""
_set_value functions allows to update value at a particular hash
Examples:
1. _set_value in HashTable of size 5
>>> ht = HashTable(5)
>>> ht.insert_data(10)
>>> ht.insert_data(20)
>>> ht.insert_data(30)
>>> ht._set_value(0,15)
>>> ht.keys()
{0: 15, 1: 20, 2: 30}
2. _set_value in HashTable of size 2
>>> ht = HashTable(2)
>>> ht.insert_data(17)
>>> ht.insert_data(18)
>>> ht.insert_data(99)
>>> ht._set_value(3,15)
>>> ht.keys()
{3: 15, 2: 17, 4: 99}
3. _set_value in HashTable when hash is not present
>>> ht = HashTable(2)
>>> ht.insert_data(17)
>>> ht.insert_data(18)
>>> ht.insert_data(99)
>>> ht._set_value(0,15)
>>> ht.keys()
{3: 18, 2: 17, 4: 99, 0: 15}
4. _set_value in HashTable when multiple hash are not present
>>> ht = HashTable(2)
>>> ht.insert_data(17)
>>> ht.insert_data(18)
>>> ht.insert_data(99)
>>> ht._set_value(0,15)
>>> ht._set_value(1,20)
>>> ht.keys()
{3: 18, 2: 17, 4: 99, 0: 15, 1: 20}
"""
self.values[key] = data
self._keys[key] = data
@abstractmethod
def _collision_resolution(self, key, data=None):
"""
This method is a type of open addressing which is used for handling collision.
In this implementation the concept of linear probing has been used.
The hash table is searched sequentially from the original location of the
hash, if the new hash/location we get is already occupied we check for the next
hash/location.
references:
- https://en.wikipedia.org/wiki/Linear_probing
Examples:
1. The collision will be with keys 18 & 99, so new hash will be created for 99
>>> ht = HashTable(3)
>>> ht.insert_data(17)
>>> ht.insert_data(18)
>>> ht.insert_data(99)
>>> ht.keys()
{2: 17, 0: 18, 1: 99}
2. The collision will be with keys 17 & 101, so new hash
will be created for 101
>>> ht = HashTable(4)
>>> ht.insert_data(17)
>>> ht.insert_data(18)
>>> ht.insert_data(99)
>>> ht.insert_data(101)
>>> ht.keys()
{1: 17, 2: 18, 3: 99, 0: 101}
2. The collision will be with all keys, so new hash will be created for all
>>> ht = HashTable(1)
>>> ht.insert_data(17)
>>> ht.insert_data(18)
>>> ht.insert_data(99)
>>> ht.keys()
{2: 17, 3: 18, 4: 99}
3. Trying to insert float key in hash
>>> ht = HashTable(1)
>>> ht.insert_data(17)
>>> ht.insert_data(18)
>>> ht.insert_data(99.99)
Traceback (most recent call last):
...
TypeError: list indices must be integers or slices, not float
"""
new_key = self.hash_function(key + 1)
while self.values[new_key] is not None and self.values[new_key] != key:
if self.values.count(None) > 0:
new_key = self.hash_function(new_key + 1)
else:
new_key = None
break
return new_key
def rehashing(self):
survivor_values = [value for value in self.values if value is not None]
self.size_table = next_prime(self.size_table, factor=2)
self._keys.clear()
self.values = [None] * self.size_table # hell's pointers D: don't DRY ;/
for value in survivor_values:
self.insert_data(value)
def insert_data(self, data):
"""
insert_data is used for inserting a single element at a time in the HashTable.
Examples:
>>> ht = HashTable(3)
>>> ht.insert_data(5)
>>> ht.keys()
{2: 5}
>>> ht = HashTable(5)
>>> ht.insert_data(30)
>>> ht.insert_data(50)
>>> ht.keys()
{0: 30, 1: 50}
"""
key = self.hash_function(data)
if self.values[key] is None:
self._set_value(key, data)
elif self.values[key] == data:
pass
else:
collision_resolution = self._collision_resolution(key, data)
if collision_resolution is not None:
self._set_value(collision_resolution, data)
else:
self.rehashing()
self.insert_data(data)
if __name__ == "__main__":
import doctest
doctest.testmod()
You can’t perform that action at this time.