一般的に使用される検索データ構造とアルゴリズムの詳細な説明 (Python 実装)

# 最基础的遍历无序列表的查找算法
# 时间复杂度O(n)
 
def sequential_search(lis, key):
  length = len(lis)
  for i in range(length):
    if lis[i] == key:
      return i
    else:
      return False
 
 
if __name__ == '__main__':
  LIST = [1, 5, 8, 123, 22, 54, 7, 99, 300, 222]
  result = sequential_search(LIST, 123)
  print(result)

# 针对有序查找表的二分查找算法
# 时间复杂度O(log(n))
 
def binary_search(lis, key):
  low = 0
  high = len(lis) - 1
  time = 0
  while low < high:
    time += 1
    mid = int((low + high) / 2)
    if key < lis[mid]:
      high = mid - 1
    elif key > lis[mid]:
      low = mid + 1
    else:
      # 打印折半的次数
      print("times: %s" % time)
      return mid
  print("times: %s" % time)
  return False
 
if __name__ == &#39;__main__&#39;:
  LIST = [1, 5, 7, 8, 22, 54, 99, 123, 200, 222, 444]
  result = binary_search(LIST, 99)
  print(result)

# 插值查找算法
# 时间复杂度O(log(n))
 
def binary_search(lis, key):
  low = 0
  high = len(lis) - 1
  time = 0
  while low < high:
    time += 1
    # 计算mid值是插值算法的核心代码
    mid = low + int((high - low) * (key - lis[low])/(lis[high] - lis[low]))
    print("mid=%s, low=%s, high=%s" % (mid, low, high))
    if key < lis[mid]:
      high = mid - 1
    elif key > lis[mid]:
      low = mid + 1
    else:
      # 打印查找的次数
      print("times: %s" % time)
      return mid
  print("times: %s" % time)
  return False
 
if __name__ == &#39;__main__&#39;:
  LIST = [1, 5, 7, 8, 22, 54, 99, 123, 200, 222, 444]
  result = binary_search(LIST, 444)
  print(result)

# 斐波那契查找算法
# 时间复杂度O(log(n))
 
def fibonacci_search(lis, key):
  # 需要一个现成的斐波那契列表。其最大元素的值必须超过查找表中元素个数的数值。
  F = [1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89, 144,
     233, 377, 610, 987, 1597, 2584, 4181, 6765,
     10946, 17711, 28657, 46368]
  low = 0
  high = len(lis) - 1
   
  # 为了使得查找表满足斐波那契特性，在表的最后添加几个同样的值
  # 这个值是原查找表的最后那个元素的值
  # 添加的个数由F[k]-1-high决定
  k = 0
  while high > F[k]-1:
    k += 1
  print(k)
  i = high
  while F[k]-1 > i:
    lis.append(lis[high])
    i += 1
  print(lis)
   
  # 算法主逻辑。time用于展示循环的次数。
  time = 0
  while low <= high:
    time += 1
    # 为了防止F列表下标溢出，设置if和else
    if k < 2:
      mid = low
    else:
      mid = low + F[k-1]-1
     
    print("low=%s, mid=%s, high=%s" % (low, mid, high))
    if key < lis[mid]:
      high = mid - 1
      k -= 1
    elif key > lis[mid]:
      low = mid + 1
      k -= 2
    else:
      if mid <= high:
        # 打印查找的次数
        print("times: %s" % time)
        return mid
      else:
        print("times: %s" % time)
        return high
  print("times: %s" % time)
  return False
 
if __name__ == &#39;__main__&#39;:
  LIST = [1, 5, 7, 8, 22, 54, 99, 123, 200, 222, 444]
  result = fibonacci_search(LIST, 444)
  print(result)

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# Author: Liu Jiang
# Python 3.5
 
 
class BSTNode:
  """
  定义一个二叉树节点类。
  以讨论算法为主，忽略了一些诸如对数据类型进行判断的问题。
  """
  def __init__(self, data, left=None, right=None):
    """
    初始化
    :param data: 节点储存的数据
    :param left: 节点左子树
    :param right: 节点右子树
    """
    self.data = data
    self.left = left
    self.right = right
 
 
class BinarySortTree:
  """
  基于BSTNode类的二叉排序树。维护一个根节点的指针。
  """
  def __init__(self):
    self._root = None
 
  def is_empty(self):
    return self._root is None
 
  def search(self, key):
    """
    关键码检索
    :param key: 关键码
    :return: 查询节点或None
    """
    bt = self._root
    while bt:
      entry = bt.data
      if key < entry:
        bt = bt.left
      elif key > entry:
        bt = bt.right
      else:
        return entry
    return None
 
  def insert(self, key):
    """
    插入操作
    :param key:关键码
    :return: 布尔值
    """
    bt = self._root
    if not bt:
      self._root = BSTNode(key)
      return
    while True:
      entry = bt.data
      if key < entry:
        if bt.left is None:
          bt.left = BSTNode(key)
          return
        bt = bt.left
      elif key > entry:
        if bt.right is None:
          bt.right = BSTNode(key)
          return
        bt = bt.right
      else:
        bt.data = key
        return
 
  def delete(self, key):
    """
    二叉排序树最复杂的方法
    :param key: 关键码
    :return: 布尔值
    """
    p, q = None, self._root   # 维持p为q的父节点，用于后面的链接操作
    if not q:
      print("空树！")
      return
    while q and q.data != key:
      p = q
      if key < q.data:
        q = q.left
      else:
        q = q.right
      if not q:        # 当树中没有关键码key时，结束退出。
        return
    # 上面已将找到了要删除的节点，用q引用。而p则是q的父节点或者None（q为根节点时）。
    if not q.left:
      if p is None:
        self._root = q.right
      elif q is p.left:
        p.left = q.right
      else:
        p.right = q.right
      return
    # 查找节点q的左子树的最右节点，将q的右子树链接为该节点的右子树
    # 该方法可能会增大树的深度，效率并不算高。可以设计其它的方法。
    r = q.left
    while r.right:
      r = r.right
    r.right = q.right
    if p is None:
      self._root = q.left
    elif p.left is q:
      p.left = q.left
    else:
      p.right = q.left
 
  def __iter__(self):
    """
    实现二叉树的中序遍历算法,
    展示我们创建的二叉排序树.
    直接使用python内置的列表作为一个栈。
    :return: data
    """
    stack = []
    node = self._root
    while node or stack:
      while node:
        stack.append(node)
        node = node.left
      node = stack.pop()
      yield node.data
      node = node.right
 
 
if __name__ == &#39;__main__&#39;:
  lis = [62, 58, 88, 48, 73, 99, 35, 51, 93, 29, 37, 49, 56, 36, 50]
  bs_tree = BinarySortTree()
  for i in range(len(lis)):
    bs_tree.insert(lis[i])
  # bs_tree.insert(100)
  bs_tree.delete(58)
  for i in bs_tree:
    print(i, end=" ")
  # print("\n", bs_tree.search(4))

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# Author: Liu Jiang
# Python 3.5
# 忽略了对数据类型，元素溢出等问题的判断。
 
 
class HashTable:
  def __init__(self, size):
    self.elem = [None for i in range(size)] # 使用list数据结构作为哈希表元素保存方法
    self.count = size # 最大表长
 
  def hash(self, key):
    return key % self.count # 散列函数采用除留余数法
 
  def insert_hash(self, key):
    """插入关键字到哈希表内"""
    address = self.hash(key) # 求散列地址
    while self.elem[address]: # 当前位置已经有数据了，发生冲突。
      address = (address+1) % self.count # 线性探测下一地址是否可用
    self.elem[address] = key # 没有冲突则直接保存。
 
  def search_hash(self, key):
    """查找关键字，返回布尔值"""
    star = address = self.hash(key)
    while self.elem[address] != key:
      address = (address + 1) % self.count
      if not self.elem[address] or address == star: # 说明没找到或者循环到了开始的位置
        return False
    return True
 
 
if __name__ == '__main__':
  list_a = [12, 67, 56, 16, 25, 37, 22, 29, 15, 47, 48, 34]
  hash_table = HashTable(12)
  for i in list_a:
    hash_table.insert_hash(i)
 
  for i in hash_table.elem:
    if i:
      print((i, hash_table.elem.index(i)), end=" ")
  print("\n")
 
  print(hash_table.search_hash(15))
  print(hash_table.search_hash(33))