使用FP-growth算法来高效发现频繁项集

fpTree.py

#!/usr/bin/python  
# -*- coding: utf-8 -*-  
#coding=utf-8

from numpy import *

class treeNode:
    def __init__(self, nameValue, numOccur, parentNode):
        self.name = nameValue     #变量名
        self.count = numOccur     #计数值
        self.nodeLink = None      #链接相似元素项
        self.parent = parentNode  #指向父节点
        self.children = {}  #子节点

    #对count增加给定值
    def inc(self, numOccur):
        self.count += numOccur

    #将树以文本形式显示
    def disp(self, ind = 1):
        print ' '* ind, self.name, ' ', self.count
        for child in self.children.values():
            child.disp(ind+1)

#FP树构建函数
def createTree(dataSet, minSup=1):
    headerTable = {}
    for trans in dataSet:
        for item in trans:
            #get(item, 0) 如果key中不包含item，返回0，否则返回value
            headerTable[item] = headerTable.get(item, 0) + dataSet[trans]
    for k in headerTable.keys():  #只保留频繁项
        if headerTable[k] < minSup:
            del(headerTable[k])
    freqItemSet = set(headerTable.keys())
    if len(freqItemSet) == 0:  #如果没有元素项满足要求，则退出
        return None, None
    for k in headerTable:  #扩展头指针表，以便可以保存计数值以及指向每种类型第一个元素项的指针
        headerTable[k] = [headerTable[k], None]
    retTree = treeNode('Null Set', 1, None)
    for tranSet, count in dataSet.items():
        localD = {}
        for item in tranSet:
            if item in freqItemSet:  #只考虑频繁项
                localD[item] = headerTable[item][0]
        if len(localD) > 0:
            orderedItem = [v[0] for v in sorted(localD.items(), key=lambda p:p[1], reverse=True)]
            updateTree(orderedItem, retTree, headerTable, count) #使用排序后的频繁项集进行填充
    return retTree, headerTable

#为了让FP树生长
def updateTree(items, inTree, headerTable, count):
    if items[0] in inTree.children:   #测试事务中的第一个元素项是否作为子节点存在。
       inTree.children[items[0]].inc(count)   #存在，则更新该元素项的计数
    else:   #否则，创建一个新的treeNode并将其作为一个子节点添加到树中
        inTree.children[items[0]] = treeNode(items[0], count, inTree)
        #头指针表也要更新以指向新的节点
        if headerTable[items[0]][1] == None:  
            headerTable[items[0]][1] = inTree.children[items[0]]
        else:
            updateHeader(headerTable[items[0]][1], inTree.children[items[0]])
    #不断迭代调用自身，每次调用时去掉列表中第一个元素
    if len(items) > 1:
        updateTree(items[1::], inTree.children[items[0]], headerTable, count)

#确保节点链接指向树中给元素向的每一个实例
def updateHeader(nodeToTest, targetNode):
    while(nodeToTest.nodeLink != None):    #从头指针表的nodeLink开始，直到链表末尾
        nodeToTest = nodeToTest.nodeLink
    nodeToTest.nodeLink = targetNode

#简单的数据集及数据包装器
def loadSimpData():
    simpDat = [['r', 'z', 'h', 'j', 'p'],
               ['z', 'y', 'x', 'w', 'v', 'u', 't', 's'],
               ['z'],
               ['r', 'x', 'n', 'o', 's'],
               ['y', 'r', 'x', 'z', 'q', 't', 'p'],
               ['y', 'z', 'x', 'e', 'q', 's', 't', 'm']]
    return simpDat

def createInitSet(dataSet):
    retDict = {}
    for trans in dataSet:
        retDict[frozenset(trans)] = 1
    return retDict

#迭代上溯整棵树
def ascendTree(leafNode, prefixPath):
    if leafNode.parent != None:
        prefixPath.append(leafNode.name)
        ascendTree(leafNode.parent, prefixPath)

#发现以给定元素项结尾的所有路径的函数
def findPrefixPath(basePat, treeNode):
    condPats = {}
    while treeNode != None:
        prefixPath = []
        ascendTree(treeNode, prefixPath)  #每遇到一个元素项都上溯FP树，并收集所有遇到的元素项的名称
        if len(prefixPath) > 1: 
            condPats[frozenset(prefixPath[1:])] = treeNode.count #添加到条件模式基字典中
        treeNode = treeNode.nodeLink
    return condPats

#创建条件FP树。递归查找频繁项集
def minTree(inTree, headerTable, minSup, preFix, freqItemList):
    #对头指针表中的元素项按其出现频率进行排序
    bigL = [v[0] for v in sorted(headerTable.items(), key=lambda p:p[1])]
    for basePat in bigL:
        newFreqSet = preFix.copy()
        newFreqSet.add(basePat)
        freqItemList.append(newFreqSet)  #将每一个频繁项添加到频繁项集列表中
        condPattBases = findPrefixPath(basePat, headerTable[basePat][1])  #创建条件基
        myCondTree, myHead = createTree(condPattBases, minSup)  #从条件模式基构建条件FP树
        if myHead != None:  #挖掘条件FP树
            print 'conditional tree for: ',newFreqSet
            myCondTree.disp(1) 
            minTree(myCondTree, myHead, minSup, newFreqSet, freqItemList)

测试：

#导入数据
>>> import fpTree
>>> simpDat = loadSimpData()
>>> simpDat
[['r', 'z', 'h', 'j', 'p'], ['z', 'y', 'x', 'w', 'v', 'u', 't', 's'], 
['z'], ['r', 'x', 'n', 'o', 's'], 
['y', 'r', 'x', 'z', 'q', 't', 'p'], 
['y', 'z', 'x', 'e', 'q', 's', 't', 'm']]
#格式化处理
>>> initSet = createInitSet(simpDat)
>>> initSet
{frozenset(['e', 'm', 'q', 's', 't', 'y', 'x', 'z']): 1, 
frozenset(['x', 's', 'r', 'o', 'n']): 1,
frozenset(['s', 'u', 't', 'w', 'v', 'y', 'x', 'z']): 1,
frozenset(['q', 'p', 'r', 't', 'y', 'x', 'z']): 1,
frozenset(['h', 'r', 'z', 'p', 'j']): 1,
frozenset(['z']): 1}
#创建FP树
>>> myFPtree, myHeaderTab = createTree(initSet, 3)
#以文本形式显示树
>>> myFPtree.disp()
  Null Set   1
   x   1
    s   1
     r   1
   z   5
    x   3
     y   3
      s   2
       t   2
      r   1
       t   1
    r   1
#以特定元素结尾的路径
>>> findPrefixPath('x', myHeaderTab['x'][1])
{frozenset(['z']): 3}
>>> findPrefixPath('z', myHeaderTab['z'][1])
{}
>>> findPrefixPath('r', myHeaderTab['r'][1])
{frozenset(['x', 's']): 1, frozenset(['z']): 1, frozenset(['y', 'x', 'z']): 1}
#创建条件FP树
>>> freqItems = []  #存储所有频繁项集
>>> mineTree(myFPtree, myHeaderTab, 3, set([]), freqItems)
#显示所有的条件树
>>> minTree(myFPtree, myHeaderTab, 3, set([]), freqItems)
conditional tree for:  set(['y'])
  Null Set   1
   x   3
    z   3
conditional tree for:  set(['y', 'z'])
  Null Set   1
   x   3
conditional tree for:  set(['s'])
  Null Set   1
   x   3
conditional tree for:  set(['t'])
  Null Set   1
   y   3
    x   3
     z   3
conditional tree for:  set(['x', 't'])
  Null Set   1
   y   3
conditional tree for:  set(['z', 't'])
  Null Set   1
   y   3
    x   3
conditional tree for:  set(['x', 'z', 't'])
  Null Set   1
   y   3
conditional tree for:  set(['x'])
  Null Set   1
   z   3
 #频繁项集
 >>> freqItems
[set(['y']),set(['y','z']),set(['y','x','z']),set(['y', 'x']), 
set(['t']), set(['y', 't']), set(['x', 't']), set(['y', 'x', 't']), 
set(['z', 't']), set(['y', 'z', 't']), set(['x', 'z', 't']), set(['y', 'x', 'z', 't']),
set(['s']), set(['x', 's']), set(['r']), set(['x']),
set(['x', 'z']), set(['z'])]