def createTree(dataSet, minSup=1): #create FP-tree from dataset but don't mineheaderTable = {}#扫描两次数据集dataSetfor trans in dataSet:#第一次扫描，统计所有元素出现的频次for item in trans:headerTable[item] = headerTable.get(item, 0) + dataSet[trans]for k in headerTable.keys():  #移除不符合minSup的itemsif headerTable[k] < minSup:del(headerTable[k])freqItemSet = set(headerTable.keys())#print 'freqItemSet: ',freqItemSetif len(freqItemSet) == 0: return None, None  #没有items符合minSup，返回None退出for k in headerTable:headerTable[k] = [headerTable[k], None]  #结构化headerTable#print 'headerTable: ',headerTableretTree = treeNode('Null Set', 1, None)      #创建FP树根节点for tranSet, count in dataSet.items():       #第二次扫描，构建FP树retTreelocalD = {}for item in tranSet:                     #获取条数据中每个元素的全局频次，以便排序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)]      #排序updateTree(orderedItems, retTree, headerTable, count)  #更新FP树retTreereturn retTree, headerTable                  #返回FP树retTree，头指针表headerTable

#更新FP树retTree
def updateTree(items, inTree, headerTable, count):if items[0] in inTree.children:          #如果第一个元素orderedItems[0]在子节点中inTree.children[items[0]].inc(count) #增加计数else:                                    #不存在，增加子节点inTree.children[items[0]] = treeNode(items[0], count, inTree)if headerTable[items[0]][1] == None: #头指针表中items没有指向节点headerTable[items[0]][1] = inTree.children[items[0]]else:           #头指针表中items以指向某个相似节点，追加到后面updateHeader(headerTable[items[0]][1], inTree.children[items[0]])if len(items) > 1:  #items不止一个元素，去掉第一个元素，递归调用updateTree构建树updateTree(items[1::], inTree.children[items[0]], headerTable, count)

>>> import fpGrowth
>>> simpdata=fpGrowth.loadSimpDat()
>>> initset=fpGrowth.createInitSet(simpdata)
>>> simpdata
[['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']]
>>> initset
{frozenset(['e', 'm', 'q', 's', 't', 'y', 'x', 'z']): 1, frozenset(['x', 's', 'r', 'o', 'n']): 1, frozenset(['s', 'u', 't', 'w', 'v', 'y', 'x', 'z']): 1, frozenset(['q', 'p', 'r', 't', 'y', 'x', 'z']): 1, frozenset(['h', 'r', 'z', 'p', 'j']): 1, frozenset(['z']): 1}
>>> minSup = 3
>>> myFPtree, myHeaderTab = fpGrowth.createTree(initset, minSup)
>>> myFPtree.disp()Null Set   1x   1s   1r   1z   5x   3y   3s   2t   2r   1t   1r   1
>>> myHeaderTab
{'s': [3, <fpGrowth.treeNode instance at 0x00000000039FE608>], 'r': [3, <fpGrowth.treeNode instance at 0x00000000039FE788>], 't': [3, <fpGrowth.treeNode instance at 0x00000000039FE688>], 'y': [3, <fpGrowth.treeNode instance at 0x00000000039FE5C8>], 'x': [4, <fpGrowth.treeNode instance at 0x00000000039FE588>], 'z': [5, <fpGrowth.treeNode instance at 0x00000000039FE548>]}
>>>

#输入：inTree——输入FP树，递归调用时为此时的元素preFix条件FP树；headerTable——头指针表；minSup——最小支持数；preFix——初始化为set([])，递归调用时为条件FP树inTree对应的元素；freqItemList——初始化为[]，用来存储频繁项集。
#输出：freqItemList——用来存储频繁项集
def mineTree(inTree, headerTable, minSup, preFix, freqItemList):bigL = [v[0] for v in sorted(headerTable.items(), key=lambda p: p[1])]  #头指针表排序for basePat in bigL:                #从头指针表bigL（headerTable）底端开始遍历（从小到大）newFreqSet = preFix.copy()newFreqSet.add(basePat)         #递归前，newFreqSet为单元素频繁项；递归时preFix不为空，开始组合freqItemList.append(newFreqSet) #将每个频繁项加入到列表freqItemList中condPattBases = findPrefixPath(basePat,\        #抽取条件模式基condPattBases，去掉了元素本身headerTable[basePat][1])myCondTree, myHead = createTree(condPattBases,\ #根据条件模式基condPattBases构建条件频繁树myCondTree
                             minSup)if myHead != None:                              #挖掘FP条件树       #print 'conditional tree for: ',newFreqSet#myCondTree.disp(1)mineTree(myCondTree, myHead, minSup, \      #newFreqSet不为空set([]),递归调用mineTree函数newFreqSet, freqItemList)

>>> myFreqList = []
>>> reload(fpGrowth)
<module 'fpGrowth' from 'fpGrowth.py'>#遍历头指针表myHeaderTab，将其单元素频繁项加入myFreqList后，再找出每个元素的条件FP树。递归调用组合频繁项
>>> fpGrowth.mineTree(myFPtree, myHeaderTab, minSup, set([]), myFreqList)
conditional tree for:  set(['y'])Null Set   1x   3z   3
conditional tree for:  set(['y', 'z'])Null Set   1x   3
conditional tree for:  set(['s'])Null Set   1x   3
conditional tree for:  set(['t'])Null Set   1y   3x   3z   3
conditional tree for:  set(['x', 't'])Null Set   1y   3
conditional tree for:  set(['z', 't'])Null Set   1y   3x   3
conditional tree for:  set(['x', 'z', 't'])Null Set   1y   3
conditional tree for:  set(['x'])Null Set   1z   3
>>> myFreqList
[set(['y']), set(['y', 'z']), set(['y', 'x', 'z']), set(['y', 'x']), set(['s']), set(['x', 's']), set(['t']), set(['z', 't']), set(['x', 'z', 't']), set(['y', 'x', 'z', 't']), set(['y', 'z', 't']), set(['x', 't']), set(['y', 'x', 't']), set(['y', 't']), set(['r']), set(['x']), set(['x', 'z']), set(['z'])]
>>> len(myFreqList)
18
>>>

>>> parsedDat=[line.split() for line in open('kosarak.dat').readlines()]
>>> len(parsedDat)
990002
>>> initset=fpGrowth.createInitSet(parsedDat)#构建FP树，寻找阅读量10+的新闻报道
>>> myFPtree, myHeaderTab = fpGrowth.createTree(initset, 100000)#创建条件FP树
>>> myFreqList = []
>>> fpGrowth.mineTree(myFPtree, myHeaderTab, 100000, set([]), myFreqList)
>>> len(myFreqList)
9
>>> myFreqList
[set(['1']), set(['1', '6']), set(['3']), set(['11', '3']), set(['11', '3', '6']), set(['3', '6']), set(['11']), set(['11', '6']), set(['6'])]
>>>