使用FP-growth算法来高效发现频繁项集

FP-growth算法是一种用于发现数据集中频繁模式的有效方法。可以使用FP-growth算法在多种文本档中查找频繁单词。FP-growth算法能够更加高效地发现频繁项集，但不能用于发现关联规则。

       FP-growth算法的一般流程

     (1)收集数据:使用任意方法。

     (2)准备数据:需要离散的数据

     (3)分析数据: 使用任意的方法

     (4)训练算法: 构建一个FP树，并对树进行挖掘

     (5)测试算法:没有测试过程

     (6)使用算法:可用于识别经常出现的元素项，从而用于制定决策、推荐元素或进行预测等应用中。

    FP-growth算法的实现代码如下：

'''
FP-Growth FP means frequent pattern
the FP-Growth algorithm needs: 
1. FP-tree (class treeNode)
2. header table (use dict)

This finds frequent itemsets similar to apriori but does not 
find association rules.  
'''
class treeNode:
    def __init__(self, nameValue, numOccur, parentNode):
        self.name = nameValue
        self.count = numOccur
        self.nodeLink = None
        self.parent = parentNode      #needs to be updated
        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 createTree(dataSet, minSup=1): #create FP-tree from dataset but don't mine
    headerTable = {}
    #go over dataSet twice
    for trans in dataSet:#first pass counts frequency of occurance
        for item in trans:
            headerTable[item] = headerTable.get(item, 0) + dataSet[trans]
    for k in headerTable.keys():  #remove items not meeting minSup
        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():  #go through dataset 2nd time
        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

import twitter
from time import sleep
import re

def textParse(bigString):
    urlsRemoved = re.sub('(http:[/][/]|www.)([a-z]|[A-Z]|[0-9]|[/.]|[~])*', '', bigString)    
    listOfTokens = re.split(r'\W*', urlsRemoved)
    return [tok.lower() for tok in listOfTokens if len(tok) > 2]

def getLotsOfTweets(searchStr):
    CONSUMER_KEY = ''
    CONSUMER_SECRET = ''
    ACCESS_TOKEN_KEY = ''
    ACCESS_TOKEN_SECRET = ''
    api = twitter.Api(consumer_key=CONSUMER_KEY, consumer_secret=CONSUMER_SECRET,
                      access_token_key=ACCESS_TOKEN_KEY, 
                      access_token_secret=ACCESS_TOKEN_SECRET)
    #you can get 1500 results 15 pages * 100 per page
    resultsPages = []
    for i in range(1,15):
        print "fetching page %d" % i
        searchResults = api.GetSearch(searchStr, per_page=100, page=i)
        resultsPages.append(searchResults)
        sleep(6)
    return resultsPages

def mineTweets(tweetArr, minSup=5):
    parsedList = []
    for i in range(14):
        for j in range(100):
            parsedList.append(textParse(tweetArr[i][j].text))
    initSet = createInitSet(parsedList)
    myFPtree, myHeaderTab = createTree(initSet, minSup)
    myFreqList = []
    mineTree(myFPtree, myHeaderTab, minSup, set([]), myFreqList)
    return myFreqList

#minSup = 3
#simpDat = loadSimpDat()
#initSet = createInitSet(simpDat)
#myFPtree, myHeaderTab = createTree(initSet, minSup)
#myFPtree.disp()
#myFreqList = []
#mineTree(myFPtree, myHeaderTab, minSup, set([]), myFreqList)