algorithm/Python
1
0
Fork 0
mirror of https://github.com/TheAlgorithms/Python.git synced 2025-07-06 02:13:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

Improve hash map (#12678)

Browse Source 
* Mutable _Item

* document falsy item

* resize_down: expected test result

* resize_down: actual result

This is a problem since it causes rapid cycling

* improve comment about falsy item

Co-authored-by: Andrey <Cjkjvfnby@gmail.com>

* fix long line

* Update hash_map.py

* Update hash_map.py

---------

Co-authored-by: Andrey <Cjkjvfnby@gmail.com>
Co-authored-by: Maxim Smolskiy <mithridatus@mail.ru>
This commit is contained in:
Isidro
2025-05-22 22:44:25 +02:00
committed by GitHub
parent ca445f5296
commit c81cc26996
1 changed files with 26 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
data_structures/hashing/hash_map.py
View File

@ -16,7 +16,7 @@ KEY = TypeVar("KEY")
VAL = TypeVar("VAL") VAL = TypeVar("VAL")
@dataclass(frozen=True, slots=True) @dataclass(slots=True)
class _Item(Generic[KEY, VAL]): class _Item(Generic[KEY, VAL]):
key: KEY key: KEY
val: VAL val: VAL
@ -72,16 +72,17 @@ class HashMap(MutableMapping[KEY, VAL]):
If bucket is empty or key is the same, does insert and return True. If bucket is empty or key is the same, does insert and return True.
If bucket has another key or deleted placeholder, If bucket has another key that means that we need to check next bucket.
that means that we need to check next bucket.
""" """
stored = self._buckets[ind] stored = self._buckets[ind]
if not stored: if not stored:
# A falsy item means that bucket was never used (None)
# or was deleted (_deleted).
self._buckets[ind] = _Item(key, val) self._buckets[ind] = _Item(key, val)
self._len += 1 self._len += 1
return True return True
elif stored.key == key: elif stored.key == key:
self._buckets[ind] = _Item(key, val) stored.val = val
return True return True
else: else:
return False return False
@ -228,6 +229,27 @@ class HashMap(MutableMapping[KEY, VAL]):
Traceback (most recent call last): Traceback (most recent call last):
... ...
KeyError: 4 KeyError: 4
# Test resize down when sparse
## Setup: resize up
>>> hm = HashMap(initial_block_size=100, capacity_factor=0.75)
>>> len(hm._buckets)
100
>>> for i in range(75):
... hm[i] = i
>>> len(hm._buckets)
100
>>> hm[75] = 75
>>> len(hm._buckets)
200
## Resize down
>>> del hm[75]
>>> len(hm._buckets)
200
>>> del hm[74]
>>> len(hm._buckets)
100
""" """
for ind in self._iterate_buckets(key): for ind in self._iterate_buckets(key):
item = self._buckets[ind] item = self._buckets[ind]