机器学习——Weak7.使用FP-growth算法来高效发现频繁项集

使用FP-growth算法来高效发现频繁项集

FP-growth算法
优点：一般要快于Apriori
缺点：实现比较困难，在某些数据集上性能会下降
适用数据类型：标称型数据

FP-growth的一般流程
①收集数据：使用任意方法
②准备数据：由于存储的是集合，所以需要离散数据。如果要处理连续数据，需要将它们量化为离散值
③分析数据：使用任意方法
④训练算法：构建一个FP树，并对树进行挖掘
⑤测试算法：没有测试过程
⑥使用算法：可用于识别经常出现的元素项，从而用于制定决策、推荐元素或进行预测等应用中

---

• FP树的类定义

class treeNode:
    def __init__(self, nameValue, numOccur, parentNode):
        self.name = nameValue
        self.count = numOccur
        self.nodeLink = None
        self.parent = parentNode      #needs to be updated
        self.children = {} 
    
    def inc(self, numOccur):
        self.count += numOccur
        
    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): #create FP-tree from dataset but don't mine
    headerTable = {}
    #go over dataSet twice
    for trans in dataSet:#first pass counts frequency of occurance
        for item in trans:
            headerTable[item] = headerTable.get(item, 0) + dataSet[trans]
    for k in headerTable.keys():  #remove items not meeting minSup
        if headerTable[k] < minSup: 
            del(headerTable[k])
    freqItemSet = set(headerTable.keys())
    #print 'freqItemSet: ',freqItemSet
    if len(freqItemSet) == 0: return None, None  #if no items meet min support -->get out
    for k in headerTable:
        headerTable[k] = [headerTable[k], None] #reformat headerTable to use Node link 
    #print 'headerTable: ',headerTable
    retTree = treeNode('Null Set', 1, None) #create tree
    for tranSet, count in dataSet.items():  #go through dataset 2nd time
        localD = {}
        for item in tranSet:  #put transaction items in order
            if item in freqItemSet:
                localD[item] = headerTable[item][0]
        if len(localD) > 0:
            orderedItems = [v[0] for v in sorted(localD.items(), key=lambda p: p[1], reverse=True)]
            updateTree(orderedItems, retTree, headerTable, count)#populate tree with ordered freq itemset
    return retTree, headerTable #return tree and header table

def updateTree(items, inTree, headerTable, count):
    if items[0] in inTree.children:#check if orderedItems[0] in retTree.children
        inTree.children[items[0]].inc(count) #incrament count
    else:   #add items[0] to inTree.children
        inTree.children[items[0]] = treeNode(items[0], count, inTree)
        if headerTable[items[0]][1] is None: #update header table
            headerTable[items[0]][1] = inTree.children[items[0]]
        else:
            updateHeader(headerTable[items[0]][1], inTree.children[items[0]])
    if len(items) > 1:#call updateTree() with remaining ordered items
        updateTree(items[1::], inTree.children[items[0]], headerTable, count)

• 简单数据集及数据包装器

def loadSimpDat():
    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

---

从一颗FP树中挖掘频繁项集

• 发现以给定元素项结尾的所有路径的函数

def ascendTree(leafNode, prefixPath): #ascends from leaf node to root
    if leafNode.parent is not None:
        prefixPath.append(leafNode.name)
        ascendTree(leafNode.parent, prefixPath)
    
def findPrefixPath(basePat, treeNode): #treeNode comes from header table
    condPats = {}
    while treeNode is not None:
        prefixPath = []
        ascendTree(treeNode, prefixPath)
        if len(prefixPath) > 1: 
            condPats[frozenset(prefixPath[1:])] = treeNode.count
        treeNode = treeNode.nodeLink
    return condPats

• 递归查找频繁项集的mineTree函数

def mineTree(inTree, headerTable, minSup, preFix, freqItemList):
    bigL = [v[0] for v in sorted(headerTable.items(), key=lambda p: p[1])]#(sort header table)
    for basePat in bigL:  #start from bottom of header table
        newFreqSet = preFix.copy()
        newFreqSet.add(basePat)
        #print 'finalFrequent Item: ',newFreqSet    #append to set
        freqItemList.append(newFreqSet)
        condPattBases = findPrefixPath(basePat, headerTable[basePat][1])
        #print 'condPattBases :',basePat, condPattBases
        #2. construct cond FP-tree from cond. pattern base
        myCondTree, myHead = createTree(condPattBases, minSup)
        #print 'head from conditional tree: ', myHead
        if myHead is not None: #3. mine cond. FP-tree
            #print 'conditional tree for: ',newFreqSet
            #myCondTree.disp(1)            
            mineTree(myCondTree, myHead, minSup, newFreqSet, freqItemList)