Python常用數據結構之heapq模塊

Python數據結構常用模塊：collections、heapq、operator、itertools

heapq

　　堆是一種特殊的樹形結構，通常我們所說的堆的數據結構指的是完全二叉樹，並且根節點的值小於等於該節點所有子節點的值

　                                                     　

常用方法

heappush(heap,item)	往堆中插入一條新的值
heappop(heap)	從堆中彈出最小值
heapreplace(heap,item)	從堆中彈出最小值，並往堆中插入item
heappushpop(heap,item)	Python3中的heappushpop更高級
heapify(x)	以線性時間將一個列表轉化為堆
merge(*iterables,key=None,reverse=False)	合並對個堆，然后輸出
nlargest(n,iterable,key=None)	返回可枚舉對象中的n個最大值並返回一個結果集list
nsmallest(n,iterable,key=None)	返回可枚舉對象中的n個最小值並返回一個結果集list

常用方法示例　

#coding=utf-8

import heapq
import random

def test():
    li = list(random.sample(range(100),6))
    print (li)

    n = len(li)
    #nlargest
    print ("nlargest:",heapq.nlargest(n, li))
    #nsmallest
    print ("nsmallest:", heapq.nsmallest(n, li)) 
    #heapify
    print('original list is', li) 
    heapq.heapify(li) 
    print('heapify  list is', li)  
    # heappush & heappop  
    heapq.heappush(li, 105)  
    print('pushed heap is', li)  
    heapq.heappop(li)  
    print('popped heap is', li)  
    # heappushpop & heapreplace  
    heapq.heappushpop(li, 130)    # heappush -> heappop  
    print('heappushpop', li)  
    heapq.heapreplace(li, 2)    # heappop -> heappush  
    print('heapreplace', li) 

　　>>> [15, 2, 50, 34, 37, 55]
　　>>> nlargest: [55, 50, 37, 34, 15, 2]
　　>>> nsmallest: [2, 15, 34, 37, 50, 55]
　　>>> original list is [15, 2, 50, 34, 37, 55]
　　>>> heapify  list is [2, 15, 50, 34, 37, 55]
　　>>> pushed heap is [2, 15, 50, 34, 37, 55, 105]
　　>>> popped heap is [15, 34, 50, 105, 37, 55]
　　>>> heappushpop [34, 37, 50, 105, 130, 55]
　　>>> heapreplace [2, 37, 50, 105, 130, 55]

堆排序示例　

　　heapq模塊中有幾張方法進行排序：

　　方法一：

#coding=utf-8

import heapq

def heapsort(iterable):
    heap = []
    for i in iterable:
        heapq.heappush(heap, i)

    return [heapq.heappop(heap) for j in range(len(heap))]
        
if __name__ == "__main__":
    li = [30,40,60,10,20,50]
    print(heapsort(li))

　　>>>> [10, 20, 30, 40, 50, 60]

　　方法二（使用nlargest或nsmallest）：

li = [30,40,60,10,20,50]
#nlargest
n = len(li)
print ("nlargest:",heapq.nlargest(n, li))
#nsmallest
print ("nsmallest:", heapq.nsmallest(n, li))

　　>>> nlargest: [60, 50, 40, 30, 20, 10]
　　>>> nsmallest: [10, 20, 30, 40, 50, 60]

　　方法三（使用heapify）：

def heapsort(list):
    heapq.heapify(list)
    heap = []

    while(list):
        heap.append(heapq.heappop(list))
        
    li[:] = heap
    print (li)
        
if __name__ == "__main__":
    li = [30,40,60,10,20,50]
    heapsort(li)

　　>>> [10, 20, 30, 40, 50, 60]

堆在優先級隊列中的應用

　　需求：實現任務的添加，刪除(相當於任務的執行)，修改任務優先級

pq = []                         # list of entries arranged in a heap
entry_finder = {}               # mapping of tasks to entries
REMOVED = '<removed-task>'      # placeholder for a removed task
counter = itertools.count()     # unique sequence count

def add_task(task, priority=0):
    'Add a new task or update the priority of an existing task'
    if task in entry_finder:
        remove_task(task)
    count = next(counter)
    entry = [priority, count, task]
    entry_finder[task] = entry
    heappush(pq, entry)

def remove_task(task):
    'Mark an existing task as REMOVED.  Raise KeyError if not found.'
    entry = entry_finder.pop(task)
    entry[-1] = REMOVED

def pop_task():
    'Remove and return the lowest priority task. Raise KeyError if empty.'
    while pq:
        priority, count, task = heappop(pq)
        if task is not REMOVED:
            del entry_finder[task]
            return task
    raise KeyError('pop from an empty priority queue')