fpgrowth算法代码

fpgrowth算法是一种用于频繁项集挖掘的常用算法，它的主要思想是基于Apriori算法的改进，通过构建FP树（频繁模式树）来高效地发现频繁项集。下面是fpgrowth算法的代码示例：

class TreeNode:
    def __init__(self, name, count, parent):
        self.name = name              # 项的名称
        self.count = count            # 计数
        self.nodeLink = None        # 指向相似节点的指针
        self.parent = parent         # 指向父节点
        self.children = {}             # 子节点

def createFPTree(dataSet, minSup):
    headerTable = {}
    for trans in dataSet:
        for item in trans:
            headerTable[item] = headerTable.get(item, 0) + dataSet[trans]
    for k in list(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)
    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)
    return retTree, headerTable

def updateTree(items, inTree, headerTable, count):
    if items[0] in inTree.children:
        inTree.children[items[0]].inc(count)
    else:
        inTree.children[items[0]] = TreeNode(items[0], count, inTree)
        if headerTable[items[0]][1] == None:
            headerTable[items[0]][1] = inTree.children[items[0]]
        else:
            updateHeader(headerTable[items[0]][1], inTree.children[items[0]])
    if len(items) > 1:
        updateTree(items[1:], inTree.children[items[0]], headerTable, count)

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 = createFPTree(condPattBases, minSup)
        if myHead != None:
            mineTree(myCondTree, myHead, minSup, newFreqSet, freqItemList)

dataSet = {frozenset(['e', 'a', 'c', 'd', 'f', 'g', 'm', 'p']): 1,
           frozenset(['a', 'b', 'c', 'f', 'l', 'm', 'o']): 1,
           frozenset(['b', 'f', 'h', 'j', 'o']): 1,
           frozenset(['b', 'c', 'k', 's', 'p']): 1,
           frozenset(['a', 'f', 'c', 'e', 'l', 'p', 'm', 'n']): 1}
tree, headerTable = createFPTree(dataSet, 3)
freqItems = []
mineTree(tree, headerTable, 3, set([]), freqItems)
print(freqItems)

上面是一个简单的Python实现的fpgrowth算法的代码示例，通过构建FP树来高效地发现频繁项集，并输出频繁项集。