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 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)

import pyfpgrowth

transactions = [[1, 2, 5],
                [2, 4],
                [2, 3],
                [1, 2, 4],
                [1, 3],
                [2, 3],
                [1, 3],
                [1, 2, 3, 5],
                [1, 2, 3]]
                
# find patterns in baskets that occur over the support threshold
patterns = pyfpgrowth.find_frequent_patterns(transactions, 2)

# find patterns that are associated with another with a certain minimum probability
# 所以这个是可以发掘规则的。。？
rules = pyfpgrowth.generate_association_rules(patterns, 0.7)

import fpGrowth

parsedData = [line.split() for line in open('kosarak.dat').readlines()]
parsedData[0:2]
# [['1', '2', '3'], ['1']]

initSet = fpGrowth.createInitSet(parsedData)
myFPtree, myHeaderTab = fpGrowth.createTree(initSet, 100000)

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'])]


import pyfpgrowth
patterns = pyfpgrowth.find_frequent_patterns(parsedData, 100000)
len(patterns)
# 8

patterns
# {('3', '6'): 265180, ('11', '3', '6'): 143682, ('6',): 601374, ('11', '3'): 161286, ('1', '6'): 132113, ('1',): 197522, ('3',): 450031, ('11', '6'): 324013}
# 这个相比上面的结果少了一个：set(['1'])