FpGrowth算法python实现

FP-Growth算法是一种用于挖掘频繁模式的算法，它基于一种称为FP树的数据结构，能够在挖掘频繁项集时避免生成大量的候选项集。下面是FP-Growth算法的Python实现。

首先，我们需要定义一个类来表示FP树的节点：

class TreeNode:
    def __init__(self, name, count, parent):
        self.name = name
        self.count = count
        self.parent = parent
        self.children = {}
        self.nodeLink = None

    def inc(self, count):
        self.count += count

    def display(self, ind=1):
        print(' ' * ind, self.name, ' ', self.count)
        for child in self.children.values():
            child.display(ind + 1)

然后，我们需要定义函数来构建FP树：

def createTree(dataSet, minSup=1):
    headerTable = {}
    for trans in dataSet:
        for item in trans:
            headerTable[item] = headerTable.get(item, 0) + dataSet[trans]

    for k in list(headerTable):
        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

接下来，我们需要定义函数来更新FP树：

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 updateHeader(nodeToTest, targetNode):
    while (nodeToTest.nodeLink != None):
        nodeToTest = nodeToTest.nodeLink
    nodeToTest.nodeLink = targetNode

最后，我们需要定义函数来挖掘频繁模式：

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:
            mineTree(myCondTree, myHead, minSup, newFreqSet, freqItemList)

使用FP-Growth算法挖掘频繁模式的代码如下：

# 导入所需的库
from collections import defaultdict

# 构造数据集
def loadDataSet():
    return [[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]]

# 将数据集转换为字典格式
def createInitSet(dataSet):
    retDict = defaultdict(int)
    for trans in dataSet:
        retDict[frozenset(trans)] += 1
    return retDict

# FP-Growth算法
def fpGrowth(dataSet, minSup=1):
    initSet = createInitSet(dataSet)
    myFPtree, myHeaderTab = createTree(initSet, minSup)
    freqItems = []
    mineTree(myFPtree, myHeaderTab, minSup, set([]), freqItems)
    return freqItems

# 测试
dataSet = loadDataSet()
minSup = 2
freqItems = fpGrowth(dataSet, minSup)
print(freqItems)

输出结果为：

[frozenset({5}), frozenset({2, 5}), frozenset({2}), frozenset({3}), frozenset({2, 3}), frozenset({1}), frozenset({1, 3}), frozenset({3, 5}), frozenset({1, 5}), frozenset({1, 2}), frozenset({2, 3, 5}), frozenset({1, 2, 3}), frozenset({1, 2, 5}), frozenset({1, 3, 5})]

这些频繁模式表示项集{1}、{2}、{3}、{5}以及它们的组合。