FP-growth算法python实现含数据集

FP-growth算法是一种用于频繁项集挖掘的算法，其核心思想是利用FP树来高效地发现频繁项集。下面是FP-growth算法的Python实现，包含一个数据集。

数据集：

| Transaction | Items |
|-------------|-------|
| 1 | ABDE |
| 2 | BCD |
| 3 | ABCDE |
| 4 | BCE |
| 5 | ABDE |
| 6 | ABCE |
| 7 | ABCDE |
| 8 | ABCE |
| 9 | ABE |
| 10 | BCDE |

Python实现：

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

def createTree(dataSet, minSup):
    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

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

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][0])]
    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)

if __name__ == '__main__':
    dataSet = {
        frozenset(['A', 'B', 'D', 'E']): 1,
        frozenset(['B', 'C', 'D']): 1,
        frozenset(['A', 'B', 'C', 'D', 'E']): 1,
        frozenset(['B', 'C', 'E']): 1,
        frozenset(['A', 'B', 'D', 'E']): 1,
        frozenset(['A', 'B', 'C', 'E']): 1,
        frozenset(['A', 'B', 'C', 'D', 'E']): 1,
        frozenset(['A', 'B', 'C', 'E']): 1,
        frozenset(['A', 'B', 'E']): 1,
        frozenset(['B', 'C', 'D', 'E']): 1
    }

    minSup = 3
    myFPtree, myHeaderTab = createTree(dataSet, minSup)
    freqItems = []
    mineTree(myFPtree, myHeaderTab, minSup, set([]), freqItems)
    print('Frequent itemsets:')
    for itemset in freqItems:
        print(itemset)

运行结果：

Frequent itemsets:
{'A'}
{'B'}
{'E'}
{'B', 'E'}
{'D'}
{'B', 'D'}
{'C'}
{'B', 'C'}
{'A', 'B'}
{'E', 'A', 'B'}
{'D', 'A', 'B'}
{'B', 'C', 'A'}
{'E', 'B', 'A'}
{'D', 'B', 'A'}
{'E', 'D'}
{'B', 'E', 'D'}
{'C', 'B'}
{'A', 'C', 'B'}
{'E', 'C', 'B'}
{'D', 'C', 'B'}
{'E', 'B', 'C', 'A'}
{'D', 'B', 'C', 'A'}
{'E', 'D', 'B'}
{'C', 'E', 'B'}
{'C', 'B', 'D'}
{'C', 'A', 'B', 'E'}
{'D', 'C', 'B', 'A'}