R语言聚类与关联规则挖掘Apriori算法的频繁项集产生实例及FP-Growth算法的应用实例

> install.packages("arules")   #下载安装arules包
> library(arules)                        #加载arules软件包
> data("Groceries")                     #获取数据集Groceries
> summary(Groceries)                 #获取Groceries数据集的概括信息

> inspect(Groceries[1:10])           #观测Groceries数据集的前10行数据

> rules0 = apriori(Groceries, parameter = list ( support=0.001, confidence=0.5 ))                     #生成关联规则rule0

> rules0                                 #显示rule0中生成关连规则的条数
> inspect ( rules0 [ 1:10 ] )  #观测rule0中前10条规则及10条规则展示

> rulesl =apriori(Groceries,parameter=list(support=0.005,confidence=0.5))
#将支持度调整为0.005，记为rule1
> rulesl                                    #显示rule1生成关连规则的条数
set of 120 rules
> rules2=apriori(Groceries,parameter=list(support=0.005,confidence=0.60))
#将置信度调整为0.60，记为rule2
> rules2                                    #显示rule2成关连规则的条数
set of 22 rules
> rules3=apriori(Groceries,parameter=list(support=0.005,confidence=0.64))
#将置信度调整为0.64，记为rule3
> rules3                                    #显示rule2成关连规则的条数
set of 4 rules

>inspect(rules3)

> rules.sorted_sup = sort ( rules0, by="support")
#给定置信度阈值为0.5，按支持度排序记为rules.sorted_sup
> inspect(rules.sorted_sup [1:5] )         
#输出rules.sorted_sup前5条强关联规则

> rules.sorted_con = sort ( rules0, by="confidence")
#给定支持度阈值为0.001，按置信度排序，记为rules.sorted_con
> inspect ( rules.sorted_con [1:5] )            
#输出rules.sorted_con前5条强关联规则

> rules.sorted_lift=sort(rules0, by="lift")
#给定支持度阈值为0.001，置信度阈值为0.5，按提升度排序，记为rules.sorted_lift
> inspect ( rules.sorted_lift [1:5] )            
#输出rules.sorted_lift前5条强关联规则

>itemsets_apr=apriori(Groceries,parameter=list(supp=0.001,target="frequent itemsets"),control=list(sort=-1))              
#将apriori()中的目标参数取设为频繁项集

> itemsets_apr                        #显示所生成频繁项集的个数
> inspect(itemsets_apr[1:5])    #观测前5个频繁项集

> library(arulesViz)                            #加载程序包aruleViz
> rules5<-apriori(Groceries,parameter = list(support=0.002,confidence=0.5))
#生成关联规则rule5

>rules5                             #显示rules5生成关联规则的条数
set of 1098 rules
> plot(rules5)                                 #对rule5作散点图

#coding:utf-8
from numpy import *

class treeNode:#定义节点类，创建一个类来保存树的每一个节点
    def __init__(self, nameValue, numOccur, parentNode):
        self.name = nameValue#值
        self.count = numOccur#数量
        self.nodeLink = None#节点链接
        self.parent = parentNode  #父节点
        self.children = {} #孩子
        
    def inc(self, numOccur):#count计算
        self.count += numOccur

    def disp(self, ind=1):#按照等级打印出每个节点
        print ' '*ind, self.name, ' ', self.count
        for child in self.children.values():
            child.disp(ind+1)

rootNode = treeNode('pyramid', 9, None)#节点
rootNode.children['eye'] = treeNode('eye', 13, None)#子节点
a = rootNode.disp()
print a


def createTree(dataSet,minSup = 1):#FP表示的是频繁模式，其通过链接来连接相似元素，被连起来的元素可以看成是一个链表。将事务数据表中的各个事务对应的数据项按照支持度排序后，把每个事务中的数据项按降序依次插入到一棵以 NULL为根节点的树中，同时在每个结点处记录该结点出现的支持度。
headerTable = {}
    for trans in dataSet:
        for item in trans:
            headerTable[item] = headerTable.get(item, 0) + dataSet[trans]#记录每个元素项出现的频度，计数
    for k in headerTable.keys():#key中
        if headerTable[k] < minSup:
            del(headerTable[k])#删除键值
    freqItemSet = set(headerTable.keys())#建立集合
    if len(freqItemSet) == 0:#不满足最小值支持度要求的除去
        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):#更新树
    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):#更新每个节点的链接
    while (nodeToTest.nodeLink != None):
        nodeToTest = nodeToTest.nodeLink
    nodeToTest.nodeLink = targetNode
def loadSimpDat():#自定义数据集
    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']]
    return simpDat

def createInitSet(dataSet):#建立字典
    retDict = {}
    for trans in dataSet:
        retDict[frozenset(trans)] = 1
    return retDict

simpDat = loadSimpDat()
initSet = createInitSet(simpDat)
myFPtree, myHeaderTab = createTree(initSet, 3)
a = myFPtree.disp()
print a

def ascendTree(leafNode, prefixPath):  # 从叶节点到根节点的提升
    if leafNode.parent != None:
        prefixPath.append(leafNode.name)
        ascendTree(leafNode.parent, prefixPath)

def findPrefixPath(basePat, treeNode):  # 树节点来自树的表
    condPats = {}
    while treeNode != None:
        prefixPath = []
        ascendTree(treeNode, prefixPath)
        if len(prefixPath) > 1:
            condPats[frozenset(prefixPath[1:])] = treeNode.count
        treeNode = treeNode.nodeLink
    return condPats

simpDat = loadSimpDat()
initSet = createInitSet(simpDat)
myFPtree, myHeaderTab = createTree(initSet, 3)
a = myFPtree.disp()
b = findPrefixPath('x', myHeaderTab['x'][1])
print b


#首先构造FP树，然后利用它来挖掘频繁项集。在构造FP树时，需要对数据集扫描两边，第一遍扫描用来统计频率，第二遍扫描至考虑频繁项集。下面举例对FP树加以说明。def mineTree(inTree, headerTable, minSup, preFix, freqItemList):    bigL = [v[0] for v in sorted(headerTable.items(), key=lambda p: p[1])]#(排序表)    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)#(1)构建FP树；#(2)从FP树中挖掘频繁项集parsedData = [line.split() for line in open('kosarak.dat').readlines()]#读取数据initSet = createInitSet(parsedData)#建立初始数据集合myFPtree, myHeaderTab = createTree(initSet, 100000)#载入FP结构树myFreqList = []#新建列表a = mineTree(myFPtree,myHeaderTab,100000,set([]),myFreqList)b = len(myFreqList)print bprint myFreqList