FP-growth算法是一种用于发现数据集中频繁模式的有效方法。FP-growth算法利用apriori原理,执行更快。Apriori算法产生候选项集,然后扫描数据集来检查它们是否频繁。由于只对数据集扫描两次,因此FP-growth算法执行的更快。在FP-growth算法中,数据集存储在一个称为FP树的结构中。FP树构建完成后,可以通过查找元素项的条件基及构建条件FP树来发现频繁项集。该过程不断以更多元素作为条件重复执行,直到FP树只包含一个元素为止。
我们可以使用FP-growth算法在多种文本文档中查找频繁单词。FP-growth算法的工作流程如下。首先构建FP树,然后利用它来挖掘频繁项集。为构建FP树,需要对原始数据集扫面两遍。第一遍对所有元素项的出现次数进行计数。第二遍扫描中只考虑那些频繁项集。
#FP树节点的定义 class treeNode: def __init__(self, nameValue, numOccur, parentNode): self.name = nameValue self.count = numOccur self.nodeLink = None #nodelink用于链接相同的元素像 self.parent = parentNode #指向当前节点的父节点 self.children = {} #存放当前节点的子节点 def inc(self, numOccur): #对count变量增加给定值 self.count += numOccur def disp(self, ind=1): #用于将树以文本形式显示,有点类似于深度优先搜素 print (' '*ind, self.name, ' ', self.count) for child in self.children.values(): child.disp(ind+1) #函数createTree使用数据集以及最小支持度作为参数来构建FP树。 def createTree(dataSet, minSup=1): headerTable = {} #遍历数据集两次 for trans in dataSet: #第一次扫描数据集并统计每个元素项出现的频度,这些信息被存储在头指针表中 for item in trans: headerTable[item] = headerTable.get(item, 0) + dataSet[trans] for k in headerTable.keys(): #删除那些出现次数少于minSup的项 if headerTable[k] < minSup: del(headerTable[k]) freqItemSet = set(headerTable.keys()) #print 'freqItemSet: ',freqItemSet if len(freqItemSet) == 0: return None, None #if no items meet min support -->get out for k in headerTable: headerTable[k] = [headerTable[k], None] #reformat headerTable to use Node link #print 'headerTable: ',headerTable retTree = treeNode('Null Set', 1, None) #create tree for tranSet, count in dataSet.items(): #第二次遍历数据集,根据全局频度对每个事物中的元素进行排序 localD = {} for item in tranSet: #put transaction items in order 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)#populate tree with ordered freq itemset return retTree, headerTable #return tree and header table def updateTree(items, inTree, headerTable, count): if items[0] in inTree.children:#check if orderedItems[0] in retTree.children inTree.children[items[0]].inc(count) #incrament count else: #add items[0] to inTree.children inTree.children[items[0]] = treeNode(items[0], count, inTree) if headerTable[items[0]][1] == None: #update header table headerTable[items[0]][1] = inTree.children[items[0]] else: updateHeader(headerTable[items[0]][1], inTree.children[items[0]]) if len(items) > 1:#call updateTree() with remaining ordered items updateTree(items[1::], inTree.children[items[0]], headerTable, count) def updateHeader(nodeToTest, targetNode): #this version does not use recursion while (nodeToTest.nodeLink != None): #Do not use recursion to traverse a linked list! nodeToTest = nodeToTest.nodeLink nodeToTest.nodeLink = targetNode def ascendTree(leafNode, prefixPath): #ascends from leaf node to root if leafNode.parent != None: prefixPath.append(leafNode.name) ascendTree(leafNode.parent, prefixPath) def findPrefixPath(basePat, treeNode): #treeNode comes from header table 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])]#(sort header table) for basePat in bigL: #start from bottom of header table newFreqSet = preFix.copy() newFreqSet.add(basePat) #print 'finalFrequent Item: ',newFreqSet #append to set freqItemList.append(newFreqSet) condPattBases = findPrefixPath(basePat, headerTable[basePat][1]) #print 'condPattBases :',basePat, condPattBases #2. construct cond FP-tree from cond. pattern base myCondTree, myHead = createTree(condPattBases, minSup) #print 'head from conditional tree: ', myHead if myHead != None: #3. mine cond. FP-tree #print 'conditional tree for: ',newFreqSet #myCondTree.disp(1) mineTree(myCondTree, myHead, minSup, newFreqSet, freqItemList) 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']] return simpDat def createInitSet(dataSet): retDict = {} for trans in dataSet: retDict[frozenset(trans)] = 1 return retDict