Can LRU be implemented in code?

Can you explain what LRU caching is?

LRU stands for Least Recently Used. It's a caching algorithm that removes the least recently accessed items when the cache reaches its limit.

How can I implement LRU caching in Python?

You can use a combination of a dictionary and a doubly linked list to implement LRU caching efficiently.

Can you show me a sample code for LRU caching?

Sure! Here's a simple implementation:

class Node:
    def __init__(self, key, value):
        self.key = key
        self.value = value
        self.prev = None
        self.next = None

class LRUCache:
    def __init__(self, capacity):
        self.capacity = capacity
        self.cache = {}  # key -> Node
        self.head = Node(0, 0)  # dummy head
        self.tail = Node(0, 0)  # dummy tail
        self.head.next = self.tail
        self.tail.prev = self.head

    def _remove(self, node):
        prev_node = node.prev
        next_node = node.next
        prev_node.next = next_node
        next_node.prev = prev_node

    def _add(self, node):
        prev_node = self.tail.prev
        prev_node.next = node
        node.prev = prev_node
        node.next = self.tail
        self.tail.prev = node

    def get(self, key):
        if key in self.cache:
            node = self.cache[key]
            self._remove(node)
            self._add(node)
            return node.value
        return -1

    def put(self, key, value):
        if key in self.cache:
            self._remove(self.cache[key])
        node = Node(key, value)
        self.cache[key] = node
        self._add(node)
        if len(self.cache) > self.capacity:
            lru = self.head.next
            self._remove(lru)
            del self.cache[lru.key]

What are the time complexities for the operations in this implementation?

The time complexities are:

• get: O(1)
• put: O(1) This is because both operations involve constant time operations on the dictionary and the linked list.