Apriori Algorithm

Overview

---

• Apriori is an algorithm mining frequent item sets and association rules in transactional databases.
• Apriori uses Breadth-First Search and a Hash Tree Structure to count candidate item sets efficiently.
• if {X} is a frequent item set, so all subsets of {X} are frequent item sets.
• if {X} is a infrequent item set, so all supersets of {X} are infrequent item sets.

Preliminary

---

Breadth-First Search

Hash Tree Structure

Pseudo Code

---

• $T$ means a tansactional database, $\epsilon$ is the support threshold, which means the minimum times of occurrence of a item set. （$T$ 表示我们的数据集， $\epsilon$ 表示的支持阈值，它表示在一个项集（item set）可以被称为频繁项集的最小出现次数）.
• $L_1\leftarrow \{\textrm{large 1} - \textrm{itemsets}\}$ means the frequent item sets with only one item.
• $C_k\leftarrow\{a \cup \{ b \} \mid a \in L_{k-1} \wedge b \notin a \} - \{ c \mid \{s \mid s \subseteq c \wedge |s| = k-1 \} \nsubseteq L_{k-1}\}$ means the candidate set for level $k$.（$\{a \cup \{ b \} \mid a \in L_{k-1} \wedge b \notin a \}$ 表示的是在$L_{k-1}$这个频繁项集中，$a$和不包含$a$的$b$的合集，$\{ c \mid \{s \mid s \subseteq c \wedge |s| = k-1 \} \nsubseteq L_{k-1}\}$表示$C_k$中某些$c$包含有一些$s$，这些$s$在$C_{k-1}$中但是不在$F_{k-1}$中，减去这些集合意味着他们不可能是频繁项集，这是根据Overview中的第四条得到的）
• $C_t \leftarrow \{c \ |\ c \in C_k \wedge c \subseteq t, \textrm{transactions}\ t \in T \}$ means the item sets exist in the database indeed.
• The following step is counting the time of occurrence for a certain item set and keep iteration.

Example

---

Itemsets
{1,2,3,4}
{1,2,4}
{1,2}
{2,3,4}
{2,3}
{3,4}
{2,4}

Step 1

$L_1\leftarrow \{\textrm{large 1} - \textrm{itemsets}\}$, so we can obtain the following table:

Item	Support
{1}	3
{2}	6
{3}	4
{4}	5

Step 2

$C_k\leftarrow\{a \cup \{ b \} \mid a \in L_{k-1} \wedge b \notin a \} - \{ c \mid \{s \mid s \subseteq c \wedge |s| = k-1 \} \nsubseteq L_{k-1}\}\ \ \ \ \ k=2$

Item	Support
{1,2}	3
{1,3}	1
{1,4}	2
{2,3}	3
{2,4}	4
{3,4}	3

So the frequent item sets ($L_k\ \ k=2$) are:

Item	Support
{1,2}	3
{2,3}	3
{2,4}	4
{3,4}	3

And the Prune sets which means any lager set that contains the prune sets cannot be frequent are :

Item	Support
{1,3}	1
{1,4}	2

Step 3

$C_k\leftarrow\{a \cup \{ b \} \mid a \in L_{k-1} \wedge b \notin a \} - \{ c \mid \{s \mid s \subseteq c \wedge |s| = k-1 \} \nsubseteq L_{k-1}\}\ \ \ \ \ k=3$

First, $\{a \cup \{ b \} \mid a \in L_{k-1} \wedge b \notin a \}$ is :

Item
{1,2,3}
{2,3,4}
{1,2,4}
{1,2,3,4}

And then, we need to cancel the items contain the Prune sets, we got:

Item	Support
{2,3,4}	2

Finally, there is no frequent item in the $L_k\ \ k=3$, the calculation is over.