堆与优先级队列
堆的定义
堆有最大堆以及最小堆之分,二叉堆结构类似于一颗完全二叉树,其中最大堆满足对于每一个节点其值大于左右孩子节点值。
可以用数组索引顺序按照完全二叉树的层序编号顺序来存储二叉堆,具体示意如下所示:
二叉树从1开始编号,分别对应数组索引从1位置处开始存储。对于k节点,其父节点为k/2,其左节点为2k,右节点为2k+1
堆的调整算法
向上调整:以最大堆为例,如果某一个节点值小于其父节点,则需要交换该节点与父节点值,继续比较交换,直到根节点一直是有序的。
代码如下:
private void swim(int k) {
while(k>1 && less(k/2, k)){
exch(k, k/2);
k = k /2;
}
}
其中less是小于判断,exch为交换操作
private void exch(int i, int j) {
Key swap = pq[i];
pq[i] = pq[j];
pq[j] = swap;
}
private boolean less(int i, int j) {
if(comparator==null){
return ((Comparable<Key>)pq[i]).compareTo((Key)pq[j])<0;
}else{
return comparator.compare(pq[i], pq[j])<0;
}
}
向下调整:最大堆,当某一个节点小于其左右孩子节点时,应该将该节点与左右孩子最大值节点交换,然后继续判断被交换孩子节点位置是否满足最大堆的定义。
代码如下:
private void sink(int k) {
while(2*k<=n){
int j=2*k;
if(j<n && less(j, j+1)) j++;
if(!less(k, j)) break;
exch(k, j);
k = j;
}
}
堆的建立过程
给定一个初始化数组来建立一个最大堆,假定数组长度为N,则从N/2到1位置处,对于每一个节点元素进行向下调整,则最终数组为一个最大堆。
public MaxPQ(Key[] keys){
n = keys.length;
pq = (Key[]) new Object[n+1];
for(int i=0; i<n; i++){
pq[i+1] = keys[i];
}
for(int k=n/2; k>=1; k--){
sink(k);
}
}
插入操作
首先判断当前元素数量与堆容量大小关系,判断是否需要扩容;如果不需要,则将新插入元素放置到数组最后位置。将最后位置元素执行向上调整操作,可以实现堆的平衡。
public void insert(Key x){
if(n==pq.length-1) resize(2*pq.length);
pq[++n] = x;
swim(n);
}
private void resize(int capacity) {
Key[] tmp = (Key[]) new Object[capacity];
for(int i=1; i<=n; i++){
tmp[i] = pq[i];
}
pq = tmp;
}
删除最大值
最大堆可以在O(1)内返回数组元素的最大值,在O(logN)内删除最大值并且调整堆有序。
删除最大值,即删除索引位置为1的元素,在此首先记录堆顶元素值,然后将数组最后一个元素与堆顶元素交换,对于堆顶新元素执行向下调整操作,以此保证堆有序。
public Key delMax(){
if(isEmpty()) return null;
Key max = pq[1];
exch(1, n--);
sink(1);
pq[n+1] = null;
if(n>0 && n==(pq.length-1)/4)
resize(pq.length/2);
return max;
}
最终用最大堆实现的优先级队列如下所示:
public class MaxPQ<Key> implements Iterable<Key>{
private Key[] pq;
private int n;
private Comparator<Key> comparator;
public MaxPQ(int initCapacity){
pq = (Key[]) new Object[initCapacity+1];
n = 0;
}
public MaxPQ(){
this(1);
}
public MaxPQ(int initCapacity, Comparator<Key> comparator){
this(initCapacity);
this.comparator = comparator;
}
public MaxPQ(Comparator<Key> comparator){
this(1, comparator);
}
public MaxPQ(Key[] keys){
n = keys.length;
pq = (Key[]) new Object[n+1];
for(int i=0; i<n; i++){
pq[i+1] = keys[i];
}
for(int k=n/2; k>=1; k--){
sink(k);
}
}
public void insert(Key x){
if(n==pq.length-1) resize(2*pq.length);
pq[++n] = x;
swim(n);
}
public Key delMax(){
if(isEmpty()) return null;
Key max = pq[1];
exch(1, n--);
sink(1);
pq[n+1] = null;
if(n>0 && n==(pq.length-1)/4)
resize(pq.length/2);
return max;
}
// is pq[1..N] a max heap?
private boolean isMaxHeap() {
return isMaxHeap(1);
}
// is subtree of pq[1..n] rooted at k a max heap?
private boolean isMaxHeap(int k) {
if (k > n) return true;
int left = 2*k;
int right = 2*k + 1;
if (left <= n && less(k, left)) return false;
if (right <= n && less(k, right)) return false;
return isMaxHeap(left) && isMaxHeap(right);
}
private boolean isEmpty() {
return n == 0;
}
private void swim(int k) {
while(k>1 && less(k/2, k)){
exch(k, k/2);
k = k /2;
}
}
private void resize(int capacity) {
Key[] tmp = (Key[]) new Object[capacity];
for(int i=1; i<=n; i++){
tmp[i] = pq[i];
}
pq = tmp;
}
private void sink(int k) {
while(2*k<=n){
int j=2*k;
if(j<n && less(j, j+1)) j++;
if(!less(k, j)) break;
exch(k, j);
k = j;
}
}
private void exch(int i, int j) {
Key swap = pq[i];
pq[i] = pq[j];
pq[j] = swap;
}
private boolean less(int i, int j) {
if(comparator==null){
return ((Comparable<Key>)pq[i]).compareTo((Key)pq[j])<0;
}else{
return comparator.compare(pq[i], pq[j])<0;
}
}
public int size() {
return n;
}
@Override
public Iterator<Key> iterator() {
return new HeapIterator();
}
//迭代访问首先将原堆数据复制一份,然后执行迭代访问
private class HeapIterator implements Iterator<Key> {
// create a new pq
private MaxPQ<Key> copy;
// add all items to copy of heap
// takes linear time since already in heap order so no keys move
public HeapIterator() {
if (comparator == null) copy = new MaxPQ<Key>(size());
else copy = new MaxPQ<Key>(size(), comparator);
for (int i = 1; i <= n; i++)
copy.insert(pq[i]);
}
public boolean hasNext() { return !copy.isEmpty(); }
public void remove() { throw new UnsupportedOperationException(); }
public Key next() {
if (!hasNext()) throw new NoSuchElementException();
return copy.delMax();
}
}
}
JDK中优先级队列PriorityQueue
核心变量:
private static final int DEFAULT_INITIAL_CAPACITY = 11;
/**
* Priority queue represented as a balanced binary heap: the two
* children of queue[n] are queue[2*n+1] and queue[2*(n+1)]. The
* priority queue is ordered by comparator, or by the elements'
* natural ordering, if comparator is null: For each node n in the
* heap and each descendant d of n, n <= d. The element with the
* lowest value is in queue[0], assuming the queue is nonempty.
*/
transient Object[] queue; // non-private to simplify nested class access
/**
* The number of elements in the priority queue.
*/
private int size = 0;
/**
* The comparator, or null if priority queue uses elements'
* natural ordering.
*/
private final Comparator<? super E> comparator;
/**
* The number of times this priority queue has been
* <i>structurally modified</i>. See AbstractList for gory details.
*/
transient int modCount = 0; // non-private to simplify nested class access
DEFAULT_INITIAL_CAPACITY为数组的默认初始化大小,size为已经存放元素数量,queue为数组。
优先级队列的构造函数 设置初始容量以及比较器,比较器用来决定最大堆以及最小堆
public PriorityQueue(int initialCapacity,
Comparator<? super E> comparator) {
// Note: This restriction of at least one is not actually needed,
// but continues for 1.5 compatibility
if (initialCapacity < 1)
throw new IllegalArgumentException();
this.queue = new Object[initialCapacity];
this.comparator = comparator;
}
基本调整算法
在k位置插入元素x,由于x插入会破坏堆序,因此需要对于k位置进行向下调整
/**
* Inserts item x at position k, maintaining heap invariant by
* demoting x down the tree repeatedly until it is less than or
* equal to its children or is a leaf.
*
* @param k the position to fill
* @param x the item to insert
*/
private void siftDown(int k, E x) {
if (comparator != null)
siftDownUsingComparator(k, x);
else
siftDownComparable(k, x);
}
具体的向下调整过程,k必定为非叶子节点,因此有k<size/2,获取k的左孩子2k+1(这里数组索引下标从0开始),右孩子2k+2,然后求出左孩子与右孩子较大值,比较较大值与k位置处元素值,如果k位置处元素较小,则需要交换较小值与k位置处元素值,然后继续对于较小值进行向下调整。
@SuppressWarnings("unchecked")
private void siftDownComparable(int k, E x) {
Comparable<? super E> key = (Comparable<? super E>)x;
int half = size >>> 1; // loop while a non-leaf
while (k < half) {
int child = (k << 1) + 1; // assume left child is least
Object c = queue[child];
int right = child + 1;
if (right < size &&
((Comparable<? super E>) c).compareTo((E) queue[right]) > 0)
c = queue[child = right];
if (key.compareTo((E) c) <= 0)
break;
queue[k] = c;
k = child;
}
queue[k] = key;
}
在k位置插入元素x,进行向上调整
private void siftUp(int k, E x) {
if (comparator != null)
siftUpUsingComparator(k, x);
else
siftUpComparable(k, x);
}
比较k与其父节点(k-1)/2大小关系,如果k位置处节点值大于其父节点,则将k与父节点交换,继续判断父节点与其父节点是否满足堆序。
@SuppressWarnings("unchecked")
private void siftUpComparable(int k, E x) {
Comparable<? super E> key = (Comparable<? super E>) x;
while (k > 0) {
int parent = (k - 1) >>> 1;
Object e = queue[parent];
if (key.compareTo((E) e) >= 0)
break;
queue[k] = e;
k = parent;
}
queue[k] = key;
}
堆的建立
private void heapify() {
for (int i = (size >>> 1) - 1; i >= 0; i--)
siftDown(i, (E) queue[i]);
}
插入元素
public boolean offer(E e) {
if (e == null)
throw new NullPointerException();
modCount++;
int i = size;
if (i >= queue.length)
grow(i + 1);
size = i + 1;
if (i == 0)
queue[0] = e;
else
siftUp(i, e);
return true;
}
删除堆顶元素
@SuppressWarnings("unchecked")
public E poll() {
if (size == 0)
return null;
int s = --size;
modCount++;
E result = (E) queue[0];
E x = (E) queue[s];
queue[s] = null;
if (s != 0)
siftDown(0, x);
return result;
}
删除任意元素
public boolean remove(Object o) {
int i = indexOf(o);
if (i == -1)
return false;
else {
removeAt(i);
return true;
}
}
首先找到待删除元素的位置,遍历查找
private int indexOf(Object o) {
if (o != null) {
for (int i = 0; i < size; i++)
if (o.equals(queue[i]))
return i;
}
return -1;
}
然后将待删除元素删除
private E removeAt(int i) {
// assert i >= 0 && i < size;
modCount++;
int s = --size;
if (s == i) // removed last element
queue[i] = null;
else {
E moved = (E) queue[s];
queue[s] = null;
siftDown(i, moved);
if (queue[i] == moved) {
siftUp(i, moved);
if (queue[i] != moved)
return moved;
}
}
return null;
}
可以用堆来实现优先级队列,利用堆可以实现堆排序,堆的调整操作时间复杂度均为O(logN)。
利用优先级队列可以每次取出集合的极值,不需要将所有元素都进行排序,可以在O(NlogK)时间内解决数组中前K个最大值问题。
下一篇: mysql5.6乱码