forked from TheAlgorithms/Python
- Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathhash_map.py
More file actions
Latest commit
162 lines (128 loc) · 4.53 KB
/
Copy pathhash_map.py
File metadata and controls
162 lines (128 loc) · 4.53 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
"""
Hash map with open addressing.
https://en.wikipedia.org/wiki/Hash_table
Another hash map implementation, with a good explanation.
Modern Dictionaries by Raymond Hettinger
https://www.youtube.com/watch?v=p33CVV29OG8
"""
fromcollections.abcimportIterator, MutableMapping
fromdataclassesimportdataclass
fromtypingimportGeneric, TypeVar
KEY=TypeVar("KEY")
VAL=TypeVar("VAL")
@dataclass(frozen=True, slots=True)
class_Item(Generic[KEY, VAL]):
key: KEY
val: VAL
class_DeletedItem(_Item):
def__init__(self) ->None:
super().__init__(None, None)
def__bool__(self) ->bool:
returnFalse
_deleted=_DeletedItem()
classHashMap(MutableMapping[KEY, VAL]):
"""
Hash map with open addressing.
"""
def__init__(
self, initial_block_size: int=8, capacity_factor: float=0.75
) ->None:
self._initial_block_size=initial_block_size
self._buckets: list[_Item|None] = [None] *initial_block_size
assert0.0<capacity_factor<1.0
self._capacity_factor=capacity_factor
self._len=0
def_get_bucket_index(self, key: KEY) ->int:
returnhash(key) %len(self._buckets)
def_get_next_ind(self, ind: int) ->int:
"""
Get next index.
Implements linear open addressing.
"""
return (ind+1) %len(self._buckets)
def_try_set(self, ind: int, key: KEY, val: VAL) ->bool:
"""
Try to add value to the bucket.
If bucket is empty or key is the same, does insert and return True.
If bucket has another key or deleted placeholder,
that means that we need to check next bucket.
"""
stored=self._buckets[ind]
ifnotstored:
self._buckets[ind] =_Item(key, val)
self._len+=1
returnTrue
elifstored.key==key:
self._buckets[ind] =_Item(key, val)
returnTrue
else:
returnFalse
def_is_full(self) ->bool:
"""
Return true if we have reached safe capacity.
So we need to increase the number of buckets to avoid collisions.
"""
limit=len(self._buckets) *self._capacity_factor
returnlen(self) >=int(limit)
def_is_sparse(self) ->bool:
"""Return true if we need twice fewer buckets when we have now."""
iflen(self._buckets) <=self._initial_block_size:
returnFalse
limit=len(self._buckets) *self._capacity_factor/2
returnlen(self) <limit
def_resize(self, new_size: int) ->None:
old_buckets=self._buckets
self._buckets= [None] *new_size
self._len=0
foriteminold_buckets:
ifitem:
self._add_item(item.key, item.val)
def_size_up(self) ->None:
self._resize(len(self._buckets) *2)
def_size_down(self) ->None:
self._resize(len(self._buckets) //2)
def_iterate_buckets(self, key: KEY) ->Iterator[int]:
ind=self._get_bucket_index(key)
for_inrange(len(self._buckets)):
yieldind
ind=self._get_next_ind(ind)
def_add_item(self, key: KEY, val: VAL) ->None:
forindinself._iterate_buckets(key):
ifself._try_set(ind, key, val):
break
def__setitem__(self, key: KEY, val: VAL) ->None:
ifself._is_full():
self._size_up()
self._add_item(key, val)
def__delitem__(self, key: KEY) ->None:
forindinself._iterate_buckets(key):
item=self._buckets[ind]
ifitemisNone:
raiseKeyError(key)
ifitemis_deleted:
continue
ifitem.key==key:
self._buckets[ind] =_deleted
self._len-=1
break
ifself._is_sparse():
self._size_down()
def__getitem__(self, key: KEY) ->VAL:
forindinself._iterate_buckets(key):
item=self._buckets[ind]
ifitemisNone:
break
ifitemis_deleted:
continue
ifitem.key==key:
returnitem.val
raiseKeyError(key)
def__len__(self) ->int:
returnself._len
def__iter__(self) ->Iterator[KEY]:
yieldfrom (item.keyforiteminself._bucketsifitem)
def__repr__(self) ->str:
val_string=" ,".join(
f"{item.key}: {item.val}"foriteminself._bucketsifitem
)
returnf"HashMap({val_string})"