关联分析--FP-growth（12）

相较于Apriori，FP-growth可以加快速度，其过程主要分为：

1.构建FP树；2.利用FP树挖掘频繁项集；

#FP树构架设置
class treeNode:
    def __init__(self, nameValue, numOccur, parentNode):
        self.name = nameValue
        self.count = numOccur
        self.nodeLink = None
        self.parent = parentNode
        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)

def createTree(dataSet, minSup=1):
    #输入：数据集、最小支持度
    headerTable = {}
    for trans in dataSet:
        for item in trans:
            headerTable[item] = headerTable.get(item, 0) + dataSet[trans]
    for k in headerTable.keys():
        if headerTable[k] < minSup: 
            del(headerTable[k])
    freqItemSet = set(headerTable.keys())
    if len(freqItemSet) == 0: return None, None
    for k in headerTable:
        headerTable[k] = [headerTable[k], None]  
    retTree = treeNode('Null Set', 1, None)    #新建FP树
    for tranSet, count in dataSet.items():
        localD = {}
        for item in tranSet:
            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

寻找频繁项集

def ascendTree(leafNode, prefixPath):
    if leafNode.parent != None:
        prefixPath.append(leafNode.name)
        ascendTree(leafNode.parent, prefixPath)
    
def findPrefixPath(basePat, treeNode):
    condPats = {}
    while treeNode != None:
        prefixPath = []
        ascendTree(treeNode, prefixPath)
        if len(prefixPath) > 1: 
            condPats[frozenset(prefixPath[1:])] = treeNode.count
        treeNode = treeNode.nodeLink
    return condPats

def mineTree(inTree, headerTable, minSup, preFix, freqItemList):
    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)
        condPattBases = findPrefixPath(basePat, headerTable[basePat][1])
        myCondTree, myHead = createTree(condPattBases, minSup)
        if myHead != None: #3. mine cond. FP-tree            
            mineTree(myCondTree, myHead, minSup, newFreqSet, freqItemList)