fpgrowth算法伪代码

以下是fpgrowth算法的伪代码：

FP-Growth算法（D，minsup）

1. 扫描数据集D，统计每个项的支持度，并构造项头表。

2. 根据项头表，对D进行重构，只保留频繁项，并将它们按照支持度从大到小排序。

3. 初始化FP-树的根节点为空，遍历D的每个事务T，依次插入T到FP-树中。

4. 对于每个项头表中的项i，构建条件模式基ConditionalPatternBase，然后递归构建条件FP-树ConditionalFPTree_i，并输出频繁项集。

5. 对于每个条件FP-树ConditionalFPTree_i，重复步骤2到步骤4，直到不能再构建出更多的频繁项集。

6. 输出所有的频繁项集。

其中，D为数据集，minsup为最小支持度阈值。FP-树是一种紧凑的数据结构，它用于存储数据集中的频繁项集，并且能够高效地发现频繁项集。在FP-Growth算法中，通过构建FP-树和递归地构建条件FP-树，可以高效地挖掘出数据集中的频繁项集。

相关问题

fpgrowth算法python代码

FP-growth算法是一种用于频繁模式挖掘的快速和高效的算法。下面是FP-growth算法的Python代码：

# 定义FP树的节点类
class TreeNode:
    def __init__(self, name, count, parent):
        self.name = name # 节点名称
        self.count = count # 节点计数
        self.parent = parent # 父节点
        self.children = {} # 子节点

    # 增加节点计数
    def increment(self, count):
        self.count += count

# 构建FP树
def createFPtree(dataset, minSupport):
    headerTable = {}
    # 第一次遍历数据集，创建头指针表
    for trans in dataset:
        for item in trans:
            headerTable[item] = headerTable.get(item, 0) + dataset[trans]

    # 移除不满足最小支持度的项
    headerTable = {k: v for k, v in headerTable.items() if v >= minSupport}
    freqItemSet = set(headerTable.keys())
    if len(freqItemSet) == 0: # 如果没有项满足最小支持度，则退出
        return None, None

    # 更新头指针表
    for k in headerTable:
        headerTable[k] = [headerTable[k], None]

    # 创建根节点
    root = TreeNode('NULL', 1, None)

    # 第二次遍历数据集，构建FP树
    for trans, count in dataset.items():
        localD = {}
        for item in trans:
            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)]
            updateFPtree(orderedItems, root, headerTable, count)

    return root, headerTable

# 更新FP树
def updateFPtree(items, root, headerTable, count):
    if items[0] in root.children:
        root.children[items[0]].increment(count)
    else:
        root.children[items[0]] = TreeNode(items[0], count, root)

        if headerTable[items[0]][1] is None:
            headerTable[items[0]][1] = root.children[items[0]]
        else:
            updateHeader(headerTable[items[0]][1], root.children[items[0]])

    if len(items) > 1:
        updateFPtree(items[1:], root.children[items[0]], headerTable, count)

# 更新头指针表
def updateHeader(nodeToTest, targetNode):
    while nodeToTest.nodeLink is not None:
        nodeToTest = nodeToTest.nodeLink
    nodeToTest.nodeLink = targetNode

# 抽取条件模式基
def findPrefixPath(treeNode):
    conditionPatterns = {}
    while treeNode is not None:
        prefixPath = []
        ascendTree(treeNode, prefixPath)
        if len(prefixPath) > 1:
            conditionPatterns[frozenset(prefixPath[1:])] = treeNode.count
        treeNode = treeNode.nodeLink
    return conditionPatterns

# 递归上溯FP树
def ascendTree(treeNode, prefixPath):
    if treeNode.parent is not None:
        prefixPath.append(treeNode.name)
        ascendTree(treeNode.parent, prefixPath)

# 递归查找频繁项集
def mineFPtree(headerTable, minSupport, preFix, freqItemList):
    sortedItemList = [v[0] for v in sorted(headerTable.items(), key=lambda p: p[1][0])]
    for basePat in sortedItemList:
        newFreqSet = preFix.copy()
        newFreqSet.add(basePat)
        freqItemList.append(newFreqSet)
        conditionPatterns = findPrefixPath(headerTable[basePat][1])
        myCondTree, myHead = createFPtree(conditionPatterns, minSupport)

        if myHead is not None:
            mineFPtree(myHead, minSupport, newFreqSet, freqItemList)

# FP-growth算法
def fpGrowth(dataset, minSupport):
    headerTable = {}
    # 第一次遍历数据集，创建头指针表
    for trans in dataset:
        for item in trans:
            headerTable[item] = headerTable.get(item, 0) + dataset[trans]

    # 移除不满足最小支持度的项
    headerTable = {k: v for k, v in headerTable.items() if v >= minSupport}
    freqItemSet = set(headerTable.keys())
    if len(freqItemSet) == 0: # 如果没有项满足最小支持度，则退出
        return []

    for k in headerTable:
        headerTable[k] = [headerTable[k], None]

    freqItemList = []
    mineFPtree(headerTable, minSupport, set(), freqItemList)
    
    return freqItemList

# 使用示例
dataset = [['A', 'B', 'C', 'D'],
           ['B', 'D'],
           ['A', 'B', 'E'],
           ['A', 'B', 'C', 'D', 'E'],
           ['A', 'D', 'E'],
           ['A', 'B', 'C'],
           ['A', 'C', 'D', 'E'],
           ['B', 'C', 'E']]
minSupport = 2

freqItemSet = fpGrowth(dataset, minSupport)
print(freqItemSet)

以上是FP-growth算法的Python代码，通过构建FP树和递归查找频繁项集的方式进行频繁模式挖掘。

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。