无监督学习-apriori算法
来源:互联网 发布:ubuntu install opera 编辑:程序博客网 时间:2024/06/05 14:30
from numpy import *def loadDataSet(): return [[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]]def createC1(dataSet): C1 = [] for transaction in dataSet: for item in transaction: if not [item] in C1: C1.append([item]) C1.sort() return map(frozenset, C1)#use frozen set so we #can use it as a key in a dict def scanD(D, Ck, minSupport): ssCnt = {} for tid in D: for can in Ck: if can.issubset(tid): if not ssCnt.has_key(can): ssCnt[can]=1 else: ssCnt[can] += 1 numItems = float(len(D)) retList = [] supportData = {} for key in ssCnt: support = ssCnt[key]/numItems if support >= minSupport: retList.insert(0,key) supportData[key] = support return retList, supportDatadef aprioriGen(Lk, k): #creates Ck retList = [] lenLk = len(Lk) for i in range(lenLk): for j in range(i+1, lenLk): L1 = list(Lk[i])[:k-2]; L2 = list(Lk[j])[:k-2] L1.sort(); L2.sort() if L1==L2: #if first k-2 elements are equal retList.append(Lk[i] | Lk[j]) #set union return retListdef apriori(dataSet, minSupport = 0.5): C1 = createC1(dataSet) D = map(set, dataSet) L1, supportData = scanD(D, C1, minSupport) L = [L1] k = 2 while (len(L[k-2]) > 0): Ck = aprioriGen(L[k-2], k) Lk, supK = scanD(D, Ck, minSupport)#scan DB to get Lk supportData.update(supK) L.append(Lk) k += 1 return L, supportDatadef generateRules(L, supportData, minConf=0.7): #supportData is a dict coming from scanD bigRuleList = [] for i in range(1, len(L)):#only get the sets with two or more items for freqSet in L[i]: H1 = [frozenset([item]) for item in freqSet] if (i > 1): rulesFromConseq(freqSet, H1, supportData, bigRuleList, minConf) else: calcConf(freqSet, H1, supportData, bigRuleList, minConf) return bigRuleList def calcConf(freqSet, H, supportData, brl, minConf=0.7): prunedH = [] #create new list to return for conseq in H: conf = supportData[freqSet]/supportData[freqSet-conseq] #calc confidence if conf >= minConf: print freqSet-conseq,'-->',conseq,'conf:',conf brl.append((freqSet-conseq, conseq, conf)) prunedH.append(conseq) return prunedHdef rulesFromConseq(freqSet, H, supportData, brl, minConf=0.7): m = len(H[0]) if (len(freqSet) > (m + 1)): #try further merging Hmp1 = aprioriGen(H, m+1)#create Hm+1 new candidates Hmp1 = calcConf(freqSet, Hmp1, supportData, brl, minConf) if (len(Hmp1) > 1): #need at least two sets to merge rulesFromConseq(freqSet, Hmp1, supportData, brl, minConf)def pntRules(ruleList, itemMeaning): for ruleTup in ruleList: for item in ruleTup[0]: print itemMeaning[item] print " -------->" for item in ruleTup[1]: print itemMeaning[item] print "confidence: %f" % ruleTup[2] print #print a blank linefrom time import sleepfrom votesmart import votesmartvotesmart.apikey = 'a7fa40adec6f4a77178799fae4441030'#votesmart.apikey = 'get your api key first'def getActionIds(): actionIdList = []; billTitleList = [] fr = open('recent20bills.txt') for line in fr.readlines(): billNum = int(line.split('\t')[0]) try: billDetail = votesmart.votes.getBill(billNum) #api call for action in billDetail.actions: if action.level == 'House' and \ (action.stage == 'Passage' or action.stage == 'Amendment Vote'): actionId = int(action.actionId) print 'bill: %d has actionId: %d' % (billNum, actionId) actionIdList.append(actionId) billTitleList.append(line.strip().split('\t')[1]) except: print "problem getting bill %d" % billNum sleep(1) #delay to be polite return actionIdList, billTitleListdef getTransList(actionIdList, billTitleList): #this will return a list of lists containing ints itemMeaning = ['Republican', 'Democratic']#list of what each item stands for for billTitle in billTitleList:#fill up itemMeaning list itemMeaning.append('%s -- Nay' % billTitle) itemMeaning.append('%s -- Yea' % billTitle) transDict = {}#list of items in each transaction (politician) voteCount = 2 for actionId in actionIdList: sleep(3) print 'getting votes for actionId: %d' % actionId try: voteList = votesmart.votes.getBillActionVotes(actionId) for vote in voteList: if not transDict.has_key(vote.candidateName): transDict[vote.candidateName] = [] if vote.officeParties == 'Democratic': transDict[vote.candidateName].append(1) elif vote.officeParties == 'Republican': transDict[vote.candidateName].append(0) if vote.action == 'Nay': transDict[vote.candidateName].append(voteCount) elif vote.action == 'Yea': transDict[vote.candidateName].append(voteCount + 1) except: print "problem getting actionId: %d" % actionId voteCount += 2 return transDict, itemMeaning
0 0
- 无监督学习-apriori算法
- 无监督学习算法
- 无监督学习-FPgrowth算法
- 机器学习-->无监督学习-->EM算法
- 《机器学习实战》学习笔记-[15]-无监督学习-利用Apriori进行关联分析
- 聚类算法---无监督学习
- 无监督学习之K-means算法
- 监督学习?无监督学习?
- 监督学习&无监督学习
- 无监督学习:无监督降维
- K-means聚类算法(无监督学习算法)
- 机器学习入门—无监督学习、监督学习、强化学习概念及算法介绍
- 无监督学习
- 无监督特征学习
- 什么是无监督学习
- 无监督学习
- 无监督学习
- 4.无监督学习
- dedecms织梦安装后COMMON.INC.PHP 文件权限777属性修改无效的解决方法
- Android进阶系列-发布项目到Jcenter
- MapReduce进阶:多路径输入输出
- 【Java】java.util.Objects 源码学习
- 冒泡算法详解及与插入算法区别
- 无监督学习-apriori算法
- adb命令设置wifi上网
- Hadoop CDH四种安装方式总结及实例指导
- 题目1158:买房子
- ajaxfileupload源码
- SSM+EasyUI整合,简单实现后台增删改查操作
- C++容器中的函数
- SEMer必会:通过SEO思维为网站获取精准流量
- 数据结构实验之二叉树五:层序遍历