久久精品免费,欧美日韩成人一区二区,欧美黄色一区二区

栈操作实例－�Q�整理SUMO分类数据

SunRise_at — Wed, 10 Oct 2012 02:24:00 GMT

tree_map.py提取原理�Q?/div>

树的�l�构如下

,实体

, , , , , , ,物质�?/div>

, , , , , , , , , , , ,物体

, , , , , , , , , , , , , , , , ,自��n�q�箋物体

, , , , , , , , , , , , , , , , , , , , , ,物质

, , , , , , , , , , , , , , , , , , , , , , , , , , ,�U�物�?/div>

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,基本物质

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,金属

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,原子

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,�ơ原子粒�?/div>

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,原子�?/div>

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,电子

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,质子

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,中子

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,化合�?/div>

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,�?/div>

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,��M��

1.��Z��个列表，��所有的节点存入treenodeList中；

2.逗号表示树的深度�Q�当深度与大于前一个的时候，��当前层�ơ数和当前所在的ID压入到栈中，�q�将栈顶元素和当前比较元素添加到tupleList中；

3.当下一个进栈的层次数大于或�{�于栈顶元素�Q�弹出栈��元素，直到栈顶元素��于当前层次数时�Q�将当前层次数和当前所在的ID压入到栈中，�q�将栈顶元素和当前比较元素添加到tupleList中；

4.输出树的最底两层数据即为self.tupleList[i][len(self.tupleList[i])-1][0]�Q�self.tupleList[i][len(self.tupleList[i])-1][1]�?br />

#!/usr/bin/env python
#coding:utf8

#
# Finename: tree_map.py
# Function: ��大分类树中的底层数�?/span>
#
# Current version: 1.0
# author: Chen Yu
# Date: 25/9/2012
#

#栈操作类
class Stack(object):
  def __init__(self):
    self.stack = []
  def push(self,object):
    self.stack.append(object)
  def top(self):
    return self.stack[len(self.stack)-1]
  def pop(self):
    return self.stack.pop()
  def length(self):
    return len(self.stack)

class ExtractTreeunder:
  def __init__(self):
    self.treedataList = []
    self.undertreeDir = {}
    self.treenodeList = []
    self.spacenumList = []
    self.tupleList = [[]]

#数据的加载和预处�?/span>
  def load(self,infile,nodefile):
    try:
      #加蝲整棵层次�?/span>
      rfile = open(infile,'r')
      self.treedataList = rfile.read().split('\n')
      rfile.close()
      for i in range(len(self.treedataList)):
        self.treedataList[i] = self.treedataList[i].split(',')
        self.tupleList.append([[]])
      #加蝲所有的叶子节点
      rfile = open(nodefile,'r')
      self.treenodeList = rfile.read().split('\n')
      rfile.close()

    except IOError:
      return None

  def extract_tree(self):
    #�l�计�I�格数目
    i = 0
    lens = len(self.treenodeList)
    while(1):
      if i == lens:
        break
      nowflag = 0
      for j in range(len(self.treedataList[i])):
        if self.treedataList[i][j] == ' ':
          nowflag += 1
        else:
          break
      self.spacenumList.append(nowflag)
      i+=1
    #获取的二元组
    s = Stack()
    i = 1
    #标记层次
    tuplenum = 0
    s.push([self.spacenumList[0],0])
    while(1):
      if i == lens:
        break
      if i + 2 < lens and self.spacenumList[i-1] < self.spacenumList[i]:
        topdata = s.top()
      #  print self.treenodeList[topdata[1]],'i =',i,self.treenodeList[i]
        s.push([self.spacenumList[i],i])
        self.tupleList[tuplenum].append([self.treenodeList[topdata[1]],self.treenodeList[i]])
      elif i + 2 < lens and self.spacenumList[i-1] >= self.spacenumList[i]:
        tuplenum += 1
        while(1):
          print '2'
          s.pop()
          topdata = s.top()
          if topdata[0] < self.spacenumList[i]:
            s.push([self.spacenumList[i],i])
            print self.treenodeList[topdata[1]],'i =',i,self.treenodeList[i]
            self.tupleList[tuplenum].append([self.treenodeList[topdata[1]],self.treenodeList[i]])
            break
      i+=1

  #分别生成所有的�l�合�Q�叶子节点，最底两层的数据
  def output(self,outfile,outfile2,outfile3):
    #取出最低层两层节点
    wfile = open(outfile,'wa+')
    wfile2 = open(outfile2,'wa+')
    wfile3 = open(outfile3,'wa+')
    for i in range(len(self.tupleList)):
      if len(self.tupleList[i][len(self.tupleList[i])-1]) >= 2:
        wfile2.write(self.tupleList[i][len(self.tupleList[i])-1][1] + '\n')
        wfile3.write(self.tupleList[i][len(self.tupleList[i])-1][0]+' ' + self.tupleList[i][len(self.tupleList[i])-1][1] + '\n')
      for j in range(len(self.tupleList[i])):
        print self.tupleList[i][j]
        if len(self.tupleList[i][j])>=2:
          wfile.write(self.tupleList[i][j][0] + ' ' + self.tupleList[i][j][1] + '\n')
    wfile.close()
    wfile2.close()

if __name__ == '__main__':
  t = ExtractTreeunder()
  t.load('chinatree.txt','chinatreenode.txt')
  t.extract_tree()
  t.output('all_chinanode.txt','treeunder.txt','treeundertuple.txt')

SunRise_at 2012-10-10 10:24 发表评论

SunRise_at — Fri, 24 Aug 2012 02:15:00 GMT

�l�于该好了，该字典树能够实现对于数据的模�p�匹配。代码如下：

#!/usr/bin/env python
#-*- coding: UTF-8 -*-

class Node:
  def __init__(self):
    self.map = {}
    self.indexnum = 0
    self.endflag = False
  def contain(self,key):
    return self.map.__contains__(key)
  def __getitem__(self,key):
    return self.map[key]
  def __setitem__(self,key,value):
    self.map[key] =value

class TrieTree:
  def  __init__(self):
    self.subNum = 0
    self.indexNum = 0
    self.subNode = Node()
  def add(self,key,trieTree):
    self.subNum += 1
    self.subNode[key] = trieTree

  def __chinese(self,char):
    char = unicode(char,"utf8")
    buf = []
    for word in char:
        if word >= u'\u4e00'and word <= u'\u9fa5':
          buf.append(word.encode('utf-8'))
        elif word == '\n':
          #在这里对索引�q�行标记
          self.indexNum+=1
    return buf

  def search(self,buf):
    buf = self.__chinese(buf)
    current = self
    for i in range(len(buf)):
      #转化成每个汉�?/span>
      #print buf[i]
      if current.subNode.contain(buf[i]):
        if current.subNode[buf[i]].subNode.endflag == True:
          return current.subNode.contain(buf[i])
        else:
          current = current.subNode[buf[i]]
      else:
         #如果没有匚w��上，直接�q�入下一�?/span>
        continue

  def load(self,filename):
    try:
      sock = open(filename,'r')
      buf = sock.read().split('\n')
      sock.close()
    except IOError:
      return None

    #��d��每个词语
    for i  in range(len(buf)):
      buftmp = self.__chinese(buf[i])
      tree = self
      #��d��每个汉字
      current = tree
      for j in range(len(buftmp)):
        if current.subNode.contain(buftmp[j]):
          current = current.subNode[buftmp[j]]
        else:
          sub = TrieTree()
          current.add(buftmp[j],sub)
          current = sub
        if j  == len(buftmp) - 1:
          current.subNode.endflag = True
          current.subNode.indexnum = self.indexNum

if __name__=='__main__':
  s = TrieTree()
  s.load('citynames')
  print s.search('我你')
#  s.printSelf()

SunRise_at 2012-08-24 10:15 发表评论

数据�l�构之快排（递归版）

SunRise_at — Tue, 26 Jun 2012 09:23:00 GMT

大学毕业了，之前说把数据�l�构书里的算法都写一遍，最后也不了了之。�?br /> 从学会用STL中的sort的后�Q�再也没有写�q�快排。在以后的时间中��x��慢的��L��q�些再写写。。一步一步慢慢的��C��厅R�?div style="font-size: 13px; border-top-width: 1px; border-right-width: 1px; border-bottom-width: 1px; border-left-width: 1px; border-top-style: solid; border-right-style: solid; border-bottom-style: solid; border-left-style: solid; border-top-color: #cccccc; border-right-color: #cccccc; border-bottom-color: #cccccc; border-left-color: #cccccc; border-image: initial; padding-right: 5px; padding-bottom: 4px; padding-left: 4px; padding-top: 4px; width: 98%; word-break: break-all; background-color: #eeeeee; ">
#include

/*快速排序采用分��L��想�Q�设两个指针left和right�Q?br /> * 一个从左往��x��描，一个从叛_��左扫描；
* 对于左指针，如果左指针所指的元素的值小于或者等于基准��|��
* 那么指针往右移一位，如果大于基准��|��则和基准��g��换；
* 同理�Q�对于右指针�Q�如果右指针所指的元素的值大于或者等于基准��|��
* 那么指针往左移一位，如果��于基准��|��则和基准��g��换�?/span>*/

//对序列进行分�?/span>
int Part(int array[],int left,int right)
{
    int flag = array[left];  //基准
    while(right > left)
    {
        while(right > left && array[right] >= flag)
        {
            right--;
        }
        array[left] = array[right];
        while(right > left && array[left] <= flag)
        {
            left++;
        }
        array[right] = array[left];
    }
    array[left] = flag;
    return left;
}

//�q�用递归�q�行排序
int quicksort(int array[],int low,int high)
{
    int flag;
    if (low < high)
    {
        flag = Part(array,low,high);
        quicksort(array,low,flag - 1);
        quicksort(array,flag + 1,high);
    }
}

SunRise_at 2012-06-26 17:23 发表评论

用python实现的字典树

SunRise_at — Thu, 05 Apr 2012 03:04:00 GMT

1 #!/usr/bin/env python
2 # -*-coding: UTF-8-*-
3
4 #构徏节点
5 class Node:
6   def __init__(self):
7     self.map = {}
8   def contain(self,key):
9     return self.map.__contains__(key)
10   def __getitem__(self,key):
11     return self.map[key]
12   def __setitem__(self,key,value):
13     self.map[key]=value
14
15 class Item:
16   def __init__(self,key):
17     self.key=key
18     self.subNum=0
19     self.subNode=Node()
20   def add(self,key,item):
21     self.subNum += 1
22     self.subNode[key] = item
23
24 #建树
25 def build_tree(input):
26   """build a tree"""
27   sock = open(input,"r")
28   buf = sock.read()
29   buf = chinese(buf)
30   tree = Item(" ")
31   for word in buf:
32     current = tree
33     for x in word:
34       if current.subNode.contain(x):
35         current = current.subNode[x]
36       else:
37         item = Item(x)
38         current.add(x,item)
39         current = item
40   print tree
41   return tree
42
43 def search(buf,thefile):
44   "search."
45   buf = chinese(buf)
46   tree = build_tree(thefile)
47   havefind = ""
48   for word in buf:
49     current = tree
50     for x in word:
51       if current.subNode.contain(x):
52         current = current.subNode[x]
53         if  current.subNum == 0:
54           havefind += "".join(word)
55       else:
56         break
57   return havefind
58
59 #判断��d��的是否�ؓ汉字
60 def chinese(input):
61   "remove the not chinese"
62   input = unicode(input,"utf8")
63   buf = []
64   for word in input:
65     if word >= u'\u4e00' and word <= u'\u9fa5':
66       buf = buf+[word.encode('utf-8')]
67   return buf
68
69
70 def run():
71   fileName = "test"
72   textChar = "�?/span>"
73   buf = search(textChar,fileName)
74   print buf
75
76 if __name__ == "__main__":
77   run()

有关字典树的理论和概念可以参�?a >http://blog.csdn.net/v_july_v/article/details/6897097
有关python的徏树过�E?a >http://bytes.com/topic/python/answers/827476-dictionary-tree-format-hopefully-simple

SunRise_at 2012-04-05 11:04 发表评论