头歌平台第六章关联挖掘实验二：FP-growth
第一关：构建FP-tree
def loadSimpDat():
simpDat = [['beer', 'milk', 'chicken'], ['milk', 'bread'], ['milk', 'diaper'],
['beer', 'milk', 'bread'], ['beer', 'diaper'], ['milk', 'diaper'],
['beer', 'diaper'], ['beer', 'milk', 'diaper', 'chicken'], ['beer', 'milk', 'diaper']]
return simpDat
def createInitSet(dataSet):
retDict = {}
for trans in dataSet:
fset = frozenset(trans)
retDict.setdefault(fset, 0)
retDict[fset] += 1
return retDict
class treeNode:
def __init__(self, nameValue, numOccur, parentNode):
self.name = nameValue
self.count = numOccur
self.nodeLink = None
self.parent = parentNode
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):
headerTable = {}
for trans in dataSet:
for item in trans:
headerTable[item] = headerTable.get(item, 0) + 1
lessThanMinsup = list(filter(lambda k:headerTable[k] < minSup, headerTable.keys()))
for k in lessThanMinsup: del(headerTable[k])
freqItemSet = set(headerTable.keys())
if len(freqItemSet) == 0:
return None, None
for k in headerTable:
headerTable[k] = [headerTable[k], None]
retTree = treeNode('φ', 1, None)
for tranSet, count in dataSet.items():
localD = {}
for item in tranSet:
if item in freqItemSet:
localD[item]=headerTable[item]
if len(localD) > 0:
orderedItems = [v[0] for v in sorted(localD.items(), key=lambda p: (p[1],p[0]), reverse=True)]
updateTree(orderedItems, retTree, headerTable, count)
return retTree, headerTable
def updateTree(items, inTree, headerTable, count):
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):
while (nodeToTest.nodeLink != None):
nodeToTest = nodeToTest.nodeLink
nodeToTest.nodeLink = targetNode
simpDat = loadSimpDat()
dictDat = createInitSet(simpDat)
myFPTree,myheader = createTree(dictDat, 3)
myFPTree.disp()
第二关：从FP数中挖掘频繁项集
class treeNode:
def __init__(self, nameValue, numOccur, parentNode):
self.name = nameValue
self.count = numOccur
self.nodeLink = None
self.parent = parentNode
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 updateHeader(nodeToTest, targetNode):
while nodeToTest.nodeLink != None:
nodeToTest = nodeToTest.nodeLink
nodeToTest.nodeLink = targetNode
def updateFPtree(items, inTree, headerTable, count):
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:
updateFPtree(items[1::], inTree.children[items[0]], headerTable, count)
def createFPtree(dataSet, minSup=1):
headerTable = {}
for trans in dataSet:
for item in trans:
headerTable[item] = headerTable.get(item, 0) + dataSet[trans]
for k in list(headerTable):
if headerTable[k] < minSup:
del(headerTable[k])
freqItemSet = set(headerTable.keys())
if len(freqItemSet) == 0:
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:
orderedItem = [v[0] for v in sorted(localD.items(), key=lambda p: (p[1],p[0]), reverse=True)]
updateFPtree(orderedItem, retTree, headerTable, count)
return retTree, headerTable
def loadSimpDat():
simDat = [['beer', 'milk', 'chicken'], ['milk', 'bread'], ['milk', 'diaper'],
['beer', 'milk', 'bread'], ['beer', 'diaper'], ['milk', 'diaper'],
['beer', 'diaper'], ['beer', 'milk', 'diaper', 'chicken'], ['beer', 'milk', 'diaper']]
return simDat
def createInitSet(dataSet):
retDict={}
for trans in dataSet:
key = frozenset(trans)
if key in retDict:
retDict[frozenset(trans)] += 1
else:
retDict[frozenset(trans)] = 1
return retDict
def ascendFPtree(leafNode, prefixPath):
if leafNode.parent != None:
prefixPath.append(leafNode.name)
ascendFPtree(leafNode.parent, prefixPath)
def findPrefixPath(basePat, myHeaderTab):
treeNode = myHeaderTab[basePat][1]
condPats = {}
while treeNode != None:
prefixPath = []
ascendFPtree(treeNode, prefixPath)
if len(prefixPath) > 1:
condPats[frozenset(prefixPath[1:])] = treeNode.count
treeNode = treeNode.nodeLink
return condPats
def mineFPtree(inTree, headerTable, minSup, preFix, freqItemList):
bigL = [v[0] for v in sorted(headerTable.items(), key=lambda p:str(p[1]))]
for basePat in bigL:
newFreqSet = preFix.copy()
newFreqSet.add(basePat)
listFreqSet=sorted(list(newFreqSet),key= lambda i:i[0])
freqItemList.append(listFreqSet)
condPattBases=findPrefixPath(basePat,headerTable)
myCondTree,myHead=createFPtree(condPattBases,minSup)
if myHead!=None:
mineFPtree(myCondTree,myHead,minSup,newFreqSet,freqItemList)
simpDat=loadSimpDat()
initSet=createInitSet(simpDat)
retTree, headerTable=createFPtree(initSet,3)
retTree.disp()
freqItems=[]
mineFPtree(retTree,headerTable,3,set([]),freqItems)
print (freqItems)
