数据挖掘实验一关联规则挖掘.docVIP

关联规则挖掘 Association Rule Mining 【一】题目要求 Data Description: The marketing department of a financial firm keeps records on customers, including demographic information and, number of type of accounts. When launching a new product, such as a Personal Equity Plan (PEP), a direct mail piece, advertising the product, is sent to existing customers, and a record kept as to whether that customer responded and bought the product. Based on this store of prior experience, the managers decide to use data mining techniques to build customer profile models. In this particular problem we are interested only in deriving (quantitative) association rules from the data (in a future assignment we will consider the use of classification. Your goal: perform Association Rule discovery on the data set. 具体的实验数据在bank-data.txt文件中 【二】实现思路 某财务公司生产了一种新产品，本题提供了600个客户的记录，对这些客户的不同属性进行数据挖掘。根据题目要求，首先应该对数据进行全面分析。有些属性可以忽略不计，因此，需要识别出哪些是特殊属性，哪些是可忽略属性。然后对非离散数据进行离散化，最后通过aprior算法进行关联规则和相关性分析，来挖掘出频繁项集。 【三】解题过程详细分析 采用Apriori算法发现频繁项集。Apriori算法是发现频繁项集的基本算法。Apriori算法该算法使用逐层搜索的迭代方法，k项集用于探索（k+1）项集。首先，通过扫描数据库，累积每个项的计数，并收集满足最小支持度的项，找出频繁1项集的集合。记作L1，然后L1用于找频繁2项集的集合L2，如此循环下去，直到再找不到频繁项集。找每个LK需要一次数据库扫描。 Apriori算法思想如下： 1) = find_frequent_1_itemsets(D); 2) for (k = 2;; k++) { 3) = aproiri_gen(,min_sup); 4) for each transaction t∈D{ //scan D for count 5) = subset(,t); //get subsets of t that are candidates 6) for each candidate c∈ 7) c.count++; 8) } 9) ={|c.count ≥ min_sup} 10) } 11) return L = ； procedure apriori_gen(Lk-1: frequent (k-1)-itemset; min_sup: support) 1) for each itemset ∈ 2) for each itemset ∈ 3) if ( [1]= [1])∧...∧([k-2]=[k-2])∧([k-1] [k-2]) then { 4) c = ; //join step: generate candidates 5) if has_infrequent_subset(c, ) then 6) delete c; // prune step: remove unfrequent cadidate 7) else add c to ; 8) } 9) return; procedure has_infrequent_subset(c:candidate k-itemset; :frequent (k-1)-itemset) // use apriori knowledge 1) for each (k-1)-subset s of c 2) if then 3) return TRUE; 4) return FALSE; 【四】实现步骤 在weka