FP-growth算法發現頻繁項集——構建FP樹

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:
        fset = frozenset(trans)
        retDict.setdefault(fset, 0)
        retDict[fset] += 1
    return retDict
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):
    headerTable = {}
    #此一次遍歷數據集， 記錄每個數據項的支持度
    for trans in dataSet:
        for item in trans:
            headerTable[item] = headerTable.get(item, 0) + 1
    #根據最小支持度過濾
    lessThanMinsup = list(filter(lambda k:headerTable[k] < minSup, headerTable.keys()))
    for k in lessThanMinsup: del(headerTable[k])
    freqItemSet = set(headerTable.keys())
    #如果所有數據都不滿足最小支持度，返回None, None
    if len(freqItemSet) == 0:
        return None, None
    for k in headerTable:
        headerTable[k] = [headerTable[k], None]
    retTree = treeNode('φ', 1, None)
    #第二次遍歷數據集，構建fp-tree
    for tranSet, count in dataSet.items():
        #根據最小支持度處理一條訓練樣本，key:樣本中的一個樣例，value:該樣例的的全局支持度
        localD = {}
        for item in tranSet:
            if item in freqItemSet:
                localD[item] = headerTable[item][0]
        if len(localD) > 0:
            #根據全局頻繁項對每個事務中的數據進行排序,等價於 order by p[1] desc, p[0] desc
            orderedItems = [v[0] for v in sorted(localD.items(), key=lambda p: (p[1],p[0]), reverse=True)]
            updateTree(orderedItems, retTree, headerTable, count)
    return retTree, headerTable

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] == 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)

def updateHeader(nodeToTest, targetNode):  # this version does not use recursion
    while (nodeToTest.nodeLink != None):  # Do not use recursion to traverse a linked list!
        nodeToTest = nodeToTest.nodeLink
    nodeToTest.nodeLink = targetNode
simpDat = loadSimpDat()
dictDat = createInitSet(simpDat)
myFPTree,myheader = createTree(dictDat, 3)
myFPTree.disp()