FP-growth算法（一）——通过构建FP树发现频繁项集

 1 def loadSimpDat():
 2     simpDat = [[‘r‘, ‘z‘, ‘h‘, ‘j‘, ‘p‘],
 3                [‘z‘, ‘y‘, ‘x‘, ‘w‘, ‘v‘, ‘u‘, ‘t‘, ‘s‘],
 4                [‘z‘],
 5                [‘r‘, ‘x‘, ‘n‘, ‘o‘, ‘s‘],
 6                [‘y‘, ‘r‘, ‘x‘, ‘z‘, ‘q‘, ‘t‘, ‘p‘],
 7                [‘y‘, ‘z‘, ‘x‘, ‘e‘, ‘q‘, ‘s‘, ‘t‘, ‘m‘]]
 8     return simpDat
 9 
10 def createInitSet(dataSet):
11     retDict = {}
12     for trans in dataSet:
13         fset = frozenset(trans)
14         retDict.setdefault(fset, 0)
15         retDict[fset] += 1
16     return retDict
17 
18 class treeNode:
19     def __init__(self, nameValue, numOccur, parentNode):
20         self.name = nameValue
21         self.count = numOccur
22         self.nodeLink = None
23         self.parent = parentNode
24         self.children = {}
25 
26     def inc(self, numOccur):
27         self.count += numOccur
28 
29     def disp(self, ind=1):
30         print(‘   ‘ * ind, self.name, ‘ ‘, self.count)
31         for child in self.children.values():
32             child.disp(ind + 1)
33 
34 
35 def createTree(dataSet, minSup=1):
36     headerTable = {}
37     #此一次遍历数据集， 记录每个数据项的支持度
38     for trans in dataSet:
39         for item in trans:
40             headerTable[item] = headerTable.get(item, 0) + 1
41 
42     #根据最小支持度过滤
43     lessThanMinsup = list(filter(lambda k:headerTable[k] < minSup, headerTable.keys()))
44     for k in lessThanMinsup: del(headerTable[k])
45 
46     freqItemSet = set(headerTable.keys())
47     #如果所有数据都不满足最小支持度，返回None, None
48     if len(freqItemSet) == 0:
49         return None, None
50 
51     for k in headerTable:
52         headerTable[k] = [headerTable[k], None]
53 
54     retTree = treeNode(‘φ‘, 1, None)
55     #第二次遍历数据集，构建fp-tree
56     for tranSet, count in dataSet.items():
57         #根据最小支持度处理一条训练样本，key:样本中的一个样例，value:该样例的的全局支持度
58         localD = {}
59         for item in tranSet:
60             if item in freqItemSet:
61                 localD[item] = headerTable[item][0]
62 
63         if len(localD) > 0:
64             #根据全局频繁项对每个事务中的数据进行排序,等价于 order by p[1] desc, p[0] desc
65             orderedItems = [v[0] for v in sorted(localD.items(), key=lambda p: (p[1],p[0]), reverse=True)]
66             updateTree(orderedItems, retTree, headerTable, count)
67     return retTree, headerTable
68 
69 
70 def updateTree(items, inTree, headerTable, count):
71     if items[0] in inTree.children:  # check if orderedItems[0] in retTree.children
72         inTree.children[items[0]].inc(count)  # incrament count
73     else:  # add items[0] to inTree.children
74         inTree.children[items[0]] = treeNode(items[0], count, inTree)
75         if headerTable[items[0]][1] == None:  # update header table
76             headerTable[items[0]][1] = inTree.children[items[0]]
77         else:
78             updateHeader(headerTable[items[0]][1], inTree.children[items[0]])
79 
80     if len(items) > 1:  # call updateTree() with remaining ordered items
81         updateTree(items[1:], inTree.children[items[0]], headerTable, count)
82 
83 
84 def updateHeader(nodeToTest, targetNode):  # this version does not use recursion
85     while (nodeToTest.nodeLink != None):  # Do not use recursion to traverse a linked list!
86         nodeToTest = nodeToTest.nodeLink
87     nodeToTest.nodeLink = targetNode
88 
89 simpDat = loadSimpDat()
90 dictDat = createInitSet(simpDat)
91 myFPTree,myheader = createTree(dictDat, 3)
92 myFPTree.disp()