关联分析算法Apriori和FP-Growth

参考文献：

https://www.cnblogs.com/zhengxingpeng/p/6679280.html

https://www.kdnuggets.com/2016/04/association-rules-apriori-algorithm-tutorial.html

代码:

Apriori:

import pandas as pd
from mlxtend.preprocessing import TransactionEncoder
from mlxtend.frequent_patterns import apriori
from Mine import C24_get_flaw_list
from Mine import C13_get_flaw_list
from mlxtend.frequent_patterns import association_rules


pd.set_option('display.max_columns', None)
# dataset = [['Milk', 'Onion', 'Nutmeg', 'Kidney Beans', 'Eggs', 'Yogurt'],
#            ['Dill', 'Onion', 'Nutmeg', 'Kidney Beans', 'Eggs', 'Yogurt'],
#            ['Milk', 'Apple', 'Kidney Beans', 'Eggs'],
#            ['Milk', 'Unicorn', 'Corn', 'Kidney Beans', 'Yogurt'],
#            ['Corn', 'Onion', 'Onion', 'Kidney Beans', 'Ice cream', 'Eggs']]


dataset = C24_get_flaw_list()
te = TransactionEncoder()
te_ary = te.fit(dataset).transform(dataset)
df = pd.DataFrame(te_ary, columns=te.columns_)
frequent_itemsets = apriori(df, min_support=0.1, use_colnames=True)
print(association_rules(frequent_itemsets, metric="confidence", min_threshold=0.1))

FP-Growth:

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


def updateTree(items, inTree, headerTable, count):
    if items[0] in inTree.children:
        # 有该元素项时计数值+1
        inTree.children[items[0]].inc(count)
    else:
        # 没有这个元素项时创建一个新节点
        inTree.children[items[0]] = treeNode(items[0], count, inTree)
        # 更新头指针表或前一个相似元素项节点的指针指向新节点
        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:
        # 对剩下的元素项迭代调用updateTree函数
        updateTree(items[1::], inTree.children[items[0]], headerTable, count)


def createTree(dataSet, minSup=1):
    ''' 创建FP树 '''
    # 第一次遍历数据集，创建头指针表
    headerTable = {}
    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元素项
    for k in list(headerTable.keys()):
        if headerTable[k] < minSup:
            del(headerTable[k])
    # 空元素集，返回空
    freqItemSet = set(headerTable.keys())
    if len(freqItemSet) == 0:
        return None, None
    # 增加一个数据项，用于存放指向相似元素项指针
    for k in headerTable:
        headerTable[k] = [headerTable[k], None]
    retTree = treeNode('Null Set', 1, None) # 根节点
    # 第二次遍历数据集，创建FP树
    print("dataset = ", dataSet)
    for tranSet, count in dataSet.items():
        localD = {} # 对一个项集tranSet，记录其中每个元素项的全局频率，用于排序
        for item in tranSet:
            if item in freqItemSet:
                localD[item] = headerTable[item][0] # 注意这个[0]，因为之前加过一个数据项
        if len(localD) > 0:
            orderedItems = [v[0] for v in sorted(localD.items(), key=lambda p: p[1], reverse=True)] # 排序
            updateTree(orderedItems, retTree, headerTable, count) # 更新FP树
    return retTree, headerTable


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']]
    simpDat = [["a", "b"],
               ["a", "b"],
               ["a", "b"],
               ["b", "c", "d"],
               ["b", "c"]]
    return simpDat


def createInitSet(dataSet):
    retDict = {}
    for trans in dataSet:
        if frozenset(trans) in retDict.keys():
            retDict[frozenset(trans)] += 1
        else:
            retDict[frozenset(trans)] = 1
    return retDict


def ascendTree(leafNode, prefixPath):
    if leafNode.parent != None:
        prefixPath.append(leafNode.name)
        ascendTree(leafNode.parent, prefixPath)


def findPrefixPath(basePat, treeNode):
    ''' 创建前缀路径 '''
    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])]#(sort header table)
    print("header.items = ", headerTable.items())
    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)


def main(simDat, minSup):
    initSet = createInitSet(simDat)
    myFPtree, myHeaderTab = createTree(initSet, minSup)
    treeNode.disp(myFPtree)
    freqItems = []
    mineTree(myFPtree, myHeaderTab, minSup, set([]), freqItems)
    for x in freqItems:
        print(x)


if __name__ == "__main__":
    simDat = loadSimpDat()
    main(simDat, 3)