大型数据库的联想规则 Mining Association Rules in Large Databases.pptx

Mining Association Rules in Large Databases;Association rules ;An even simpler concept: frequent itemsets;Lecture outline;Definition: Frequent Itemset;Why do we want to find frequent itemsets?;Finding frequent sets;How many itemsets are there? ;When is the task sensible and feasible?;A simple algorithm for finding all frequent itemsets ??;Brute-force algorithm for finding all frequent itemsets?;Brute-force approach for finding all frequent itemsets;Speeding-up the brute-force algorithm;Reduce the number of candidates;Example;;Illustrating the Apriori principle;Exploiting the Apriori principle;The Apriori algorithm;GenerateCandidates;Example of Candidates Generation;GenerateCandidates;Example of Candidates Generation;The Apriori algorithm;How to Count Supports of Candidates?;Example of the hash-tree for C3;Example of the hash-tree for C3;Example of the hash-tree for C3;Discussion of the Apriori algorithm;Making a single pass over the data: the AprioriTid algorithm;The AprioriTID algorithm;AprioriTid Example (minsup=2)?;Discussion on the AprioriTID algorithm;Apriori vs. AprioriTID;Implementations;Lecture outline;Definition: Association Rule;Definition: Association Rule;Rule Measures: Support and Confidence;TID date items_bought 100 10/10/99 {F,A,D,B} 200 15/10/99 {D,A,C,E,B} 300 19/10/99 {C,A,B,E} 400 20/10/99 {B,A,D};Association-rule mining task;Brute-force algorithm for association-rule mining ;Computational Complexity;Mining Association Rules;Mining Association Rules;Rule Generation – Naive algorithm;Efficient rule generation;Rule Generation for Apriori Algorithm;Apriori algorithm for rule generation