数据科学与大数据分析学习笔记-6关联规则

•一种无监督学习方法
•描述性的，而不是预测性的
•发现有趣的、隐藏的关系 -表示为规则或频繁项目集
•通常用于挖掘数据库中的 transactions

Each transaction consists of one or more items
Itemset
– A collection of items or individual entities that contain some kind of relationship
k-itemset
– An itemset containing k items– {item1, item2, …, item k}
Apriori algorithm
– One of the earliest and the most fundamental algorithms for generating association rules.
Support
– Given an item X, the support of X is the percentage of transactions that contain X
– Denoted by support(X)
Frequent itemset
– Contains items that appear together often enough
– Formally, its support >= a minimum support
当最小支持度设置为 0.5时 ，如果至少 50%交易包含某个项集，那么该项集可以被认为是一个频繁项集。

Apriori property (downward closure property)

– If an itemset is frequent, then any subset