Bloom Filter (#8615)

* Bloom filter with tests

* has functions constant

* fix type

* isort

* passing ruff

* type hints

* type hints

* from fail to erro

* captital leter

* type hints requested by boot

* descriptive name for m

* more descriptibe arguments II

* moved movies_test to doctest

* commented doctest

* removed test_probability

* estimated error

* added types

* again hash_

* Update data_structures/hashing/bloom_filter.py

Co-authored-by: Christian Clauss <cclauss@me.com>

* from b to bloom

* Update data_structures/hashing/bloom_filter.py

Co-authored-by: Christian Clauss <cclauss@me.com>

* Update data_structures/hashing/bloom_filter.py

Co-authored-by: Christian Clauss <cclauss@me.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* syntax error in dict comprehension

* from goodfather to godfather

* removed Interestellar

* forgot the last Godfather

* Revert "removed Interestellar"

This reverts commit 35fa5f5c4bf101d073aad43c37b0a423d8975071.

* pretty dict

* Apply suggestions from code review

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update bloom_filter.py

---------

Co-authored-by: Christian Clauss <cclauss@me.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

DIRECTORY.md

@@ -232,6 +232,7 @@
     * [Double Ended Queue](data_structures/queue/double_ended_queue.py)
     * [Linked Queue](data_structures/queue/linked_queue.py)
     * [Priority Queue Using List](data_structures/queue/priority_queue_using_list.py)
+    * [Queue By Two Stacks](data_structures/queue/queue_by_two_stacks.py)
     * [Queue On List](data_structures/queue/queue_on_list.py)
     * [Queue On Pseudo Stack](data_structures/queue/queue_on_pseudo_stack.py)
   * Stacks

data_structures/hashing/bloom_filter.py

@@ -0,0 +1,105 @@
+"""
+See https://en.wikipedia.org/wiki/Bloom_filter
+
+The use of this data structure is to test membership in a set.
+Compared to Python's built-in set() it is more space-efficient.
+In the following example, only 8 bits of memory will be used:
+>>> bloom = Bloom(size=8)
+
+Initially, the filter contains all zeros:
+>>> bloom.bitstring
+'00000000'
+
+When an element is added, two bits are set to 1
+since there are 2 hash functions in this implementation:
+>>> "Titanic" in bloom
+False
+>>> bloom.add("Titanic")
+>>> bloom.bitstring
+'01100000'
+>>> "Titanic" in bloom
+True
+
+However, sometimes only one bit is added
+because both hash functions return the same value
+>>> bloom.add("Avatar")
+>>> "Avatar" in bloom
+True
+>>> bloom.format_hash("Avatar")
+'00000100'
+>>> bloom.bitstring
+'01100100'
+
+Not added elements should return False ...
+>>> not_present_films = ("The Godfather", "Interstellar", "Parasite", "Pulp Fiction")
+>>> {
+...   film: bloom.format_hash(film) for film in not_present_films
+... } # doctest: +NORMALIZE_WHITESPACE
+{'The Godfather': '00000101',
+ 'Interstellar': '00000011',
+ 'Parasite': '00010010',
+ 'Pulp Fiction': '10000100'}
+>>> any(film in bloom for film in not_present_films)
+False
+
+but sometimes there are false positives:
+>>> "Ratatouille" in bloom
+True
+>>> bloom.format_hash("Ratatouille")
+'01100000'
+
+The probability increases with the number of elements added.
+The probability decreases with the number of bits in the bitarray.
+>>> bloom.estimated_error_rate
+0.140625
+>>> bloom.add("The Godfather")
+>>> bloom.estimated_error_rate
+0.25
+>>> bloom.bitstring
+'01100101'
+"""
+from hashlib import md5, sha256
+
+HASH_FUNCTIONS = (sha256, md5)
+
+
+class Bloom:
+    def __init__(self, size: int = 8) -> None:
+        self.bitarray = 0b0
+        self.size = size
+
+    def add(self, value: str) -> None:
+        h = self.hash_(value)
+        self.bitarray |= h
+
+    def exists(self, value: str) -> bool:
+        h = self.hash_(value)
+        return (h & self.bitarray) == h
+
+    def __contains__(self, other: str) -> bool:
+        return self.exists(other)
+
+    def format_bin(self, bitarray: int) -> str:
+        res = bin(bitarray)[2:]
+        return res.zfill(self.size)
+
+    @property
+    def bitstring(self) -> str:
+        return self.format_bin(self.bitarray)
+
+    def hash_(self, value: str) -> int:
+        res = 0b0
+        for func in HASH_FUNCTIONS:
+            position = (
+                int.from_bytes(func(value.encode()).digest(), "little") % self.size
+            )
+            res |= 2**position
+        return res
+
+    def format_hash(self, value: str) -> str:
+        return self.format_bin(self.hash_(value))
+
+    @property
+    def estimated_error_rate(self) -> float:
+        n_ones = bin(self.bitarray).count("1")
+        return (n_ones / self.size) ** len(HASH_FUNCTIONS)

data_structures/queue/queue_by_two_stacks.py

@@ -0,0 +1,115 @@
+"""Queue implementation using two stacks"""
+
+from collections.abc import Iterable
+from typing import Generic, TypeVar
+
+_T = TypeVar("_T")
+
+
+class QueueByTwoStacks(Generic[_T]):
+    def __init__(self, iterable: Iterable[_T] | None = None) -> None:
+        """
+        >>> QueueByTwoStacks()
+        Queue(())
+        >>> QueueByTwoStacks([10, 20, 30])
+        Queue((10, 20, 30))
+        >>> QueueByTwoStacks((i**2 for i in range(1, 4)))
+        Queue((1, 4, 9))
+        """
+        self._stack1: list[_T] = list(iterable or [])
+        self._stack2: list[_T] = []
+
+    def __len__(self) -> int:
+        """
+        >>> len(QueueByTwoStacks())
+        0
+        >>> from string import ascii_lowercase
+        >>> len(QueueByTwoStacks(ascii_lowercase))
+        26
+        >>> queue = QueueByTwoStacks()
+        >>> for i in range(1, 11):
+        ...     queue.put(i)
+        ...
+        >>> len(queue)
+        10
+        >>> for i in range(2):
+        ...   queue.get()
+        1
+        2
+        >>> len(queue)
+        8
+        """
+
+        return len(self._stack1) + len(self._stack2)
+
+    def __repr__(self) -> str:
+        """
+        >>> queue = QueueByTwoStacks()
+        >>> queue
+        Queue(())
+        >>> str(queue)
+        'Queue(())'
+        >>> queue.put(10)
+        >>> queue
+        Queue((10,))
+        >>> queue.put(20)
+        >>> queue.put(30)
+        >>> queue
+        Queue((10, 20, 30))
+        """
+        return f"Queue({tuple(self._stack2[::-1] + self._stack1)})"
+
+    def put(self, item: _T) -> None:
+        """
+        Put `item` into the Queue
+
+        >>> queue = QueueByTwoStacks()
+        >>> queue.put(10)
+        >>> queue.put(20)
+        >>> len(queue)
+        2
+        >>> queue
+        Queue((10, 20))
+        """
+
+        self._stack1.append(item)
+
+    def get(self) -> _T:
+        """
+        Get `item` from the Queue
+
+        >>> queue = QueueByTwoStacks((10, 20, 30))
+        >>> queue.get()
+        10
+        >>> queue.put(40)
+        >>> queue.get()
+        20
+        >>> queue.get()
+        30
+        >>> len(queue)
+        1
+        >>> queue.get()
+        40
+        >>> queue.get()
+        Traceback (most recent call last):
+            ...
+        IndexError: Queue is empty
+        """
+
+        # To reduce number of attribute look-ups in `while` loop.
+        stack1_pop = self._stack1.pop
+        stack2_append = self._stack2.append
+
+        if not self._stack2:
+            while self._stack1:
+                stack2_append(stack1_pop())
+
+        if not self._stack2:
+            raise IndexError("Queue is empty")
+        return self._stack2.pop()
+
+
+if __name__ == "__main__":
+    from doctest import testmod
+
+    testmod()