NAME

Data::Mining::Apriori - Perl extension for implement the apriori algorithm of data mining.

SYNOPSIS

use strict;
use warnings;
use Data::Mining::Apriori;

# TRANSACTION 103:CEREAL 101:MILK 102:BREAD
#        1101          1        1         0
#        1102          1        0         1
#        1103          1        1         1
#        1104          1        1         1
#        1105          0        1         1
#        1106          1        1         1
#        1107          1        1         1
#        1108          1        0         1
#        1109          1        1         1
#        1110          1        1         1

my $apriori = Data::Mining::Apriori->new(1); # A value boolean to display the messages(optional)
 
$apriori->{totalTransactions}=10; # The total number of transactions

$apriori->{minSupport}=1.55; # The minimum support

$apriori->{minConfidence}=1.55; # The minimum confidence

$apriori->{output}=1; # The output type (1 - Export to file; 2 - Export to excel)(optional)

$apriori->{itemsKeyDescription}{'101'}='MILK'; # Hash table to add items by key and description
$apriori->{itemsKeyDescription}{102}='BREAD';
$apriori->{itemsKeyDescription}{'103'}='CEREAL';

@{$apriori->{itemsKeyTransactions}{'101'}}=('1101',1103,'1104',1105,'1106',1107,'1109',1110);
# Reference to array, to add the transactions of each item per key
@{$apriori->{itemsKeyTransactions}{102}}=('1102',1103,'1104',1105,'1106',1107,1108,'1109',1110);
@{$apriori->{itemsKeyTransactions}{'103'}}=('1101',1102,1103,'1104','1106',1107,1108,'1109',1110);

$apriori->generate_rules; # Generate association rules to no longer meet the minimum support and confidence
# or
# $apriori->association_rules_itemset_size(3); # Generate rules from a set of items size 3, for example

print "\n@{$apriori->{frequentItemset}}\n"; # Show frequent items

# or from a database

# CREATE TABLE dimension_product(
# 	product_key INTEGER NOT NULL PRIMARY KEY,
# 	product_alternate_key INTEGER NOT NULL,
# 	product_name TEXT NOT NULL,
# 	price REAL NOT NULL
#  // ...
# );
#
# INSERT INTO dimension_product VALUES(1,101,'MILK',10.00);
# INSERT INTO dimension_product VALUES(2,102,'BREAD',10.00);
# INSERT INTO dimension_product VALUES(3,103,'CEREAL',10.00);
# 
# // ...
# 
# CREATE TABLE fact_sales(
# 	sales_order_number INTEGER NOT NULL,
# 	sales_order_line_number INTEGER NOT NULL,
# 	product_key INTEGER NOT NULL,
# 	quantity INTEGER NOT NULL,
#  // ...
# 	PRIMARY KEY(sales_order_number, sales_order_line_number),
# 	FOREIGN KEY(product_key) REFERENCES dimension_product(product_key)
# );
#
# INSERT INTO fact_sales VALUES(1101,1,3,1);
# INSERT INTO fact_sales VALUES(1101,2,1,1);
# INSERT INTO fact_sales VALUES(1102,1,3,1);
# INSERT INTO fact_sales VALUES(1102,2,2,1);
# INSERT INTO fact_sales VALUES(1103,1,1,1);
# INSERT INTO fact_sales VALUES(1103,2,2,1);
# INSERT INTO fact_sales VALUES(1103,3,3,1);
# INSERT INTO fact_sales VALUES(1104,1,1,1);
# INSERT INTO fact_sales VALUES(1104,2,2,1);
# INSERT INTO fact_sales VALUES(1104,3,3,1);
# INSERT INTO fact_sales VALUES(1105,1,1,1);
# INSERT INTO fact_sales VALUES(1105,2,2,1);
# INSERT INTO fact_sales VALUES(1106,1,1,1);
# INSERT INTO fact_sales VALUES(1106,2,2,1);
# INSERT INTO fact_sales VALUES(1106,3,3,1);
# INSERT INTO fact_sales VALUES(1107,1,1,1);
# INSERT INTO fact_sales VALUES(1107,2,2,1);
# INSERT INTO fact_sales VALUES(1107,3,3,1);
# INSERT INTO fact_sales VALUES(1108,1,3,1);
# INSERT INTO fact_sales VALUES(1108,2,2,1);
# INSERT INTO fact_sales VALUES(1109,1,1,1);
# INSERT INTO fact_sales VALUES(1109,2,2,1);
# INSERT INTO fact_sales VALUES(1109,3,3,1);
# INSERT INTO fact_sales VALUES(1110,1,1,1);
# INSERT INTO fact_sales VALUES(1110,2,2,1);
# INSERT INTO fact_sales VALUES(1110,3,3,1);

use DBD::SQLite;
use Data::Mining::Apriori;

my $db = DBI->connect('dbi:SQLite:dbname=DW.db','','');

my $sql = q~
SELECT COUNT(DISTINCT(sales_order_number)) FROM fact_sales
/* WHERE ... */
~;

my $query = $db->prepare($sql);
$query->execute;
my $totalTransactions = $query->fetchrow;

$apriori = Data::Mining::Apriori->new(1);

$apriori->{totalTransactions}=$totalTransactions;

$apriori->{minSupport}=1.55;

$apriori->{minConfidence}=1.55;

$apriori->{output}=1;

my $support = int((($apriori->{totalTransactions}/100)*$apriori->{minSupport}));

$sql = qq~
SELECT dp.product_alternate_key, dp.product_name, COUNT(*)
FROM dimension_product dp
JOIN fact_sales fs ON
dp.product_key = fs.product_key
/* WHERE ... */
GROUP BY dp.product_alternate_key, dp.product_name
HAVING COUNT(*) >= $support
~;

$query = $db->prepare($sql);
$query->execute;
while(my($key,$description)=$query->fetchrow_array){
	$apriori->{itemsKeyDescription}{$key}=$description;
}

foreach my$key(keys(%{$apriori->{itemsKeyDescription}})){
	$sql = qq~
	SELECT DISTINCT(fs.sales_order_number)
	FROM dimension_product dp
	JOIN fact_sales fs ON
	dp.product_key = fs.product_key
	WHERE dp.product_alternate_key = $key
	/* AND ... */
	~;
	$query = $db->prepare($sql);
	$query->execute;
	while(my$transaction=$query->fetchrow){
		push @{$apriori->{itemsKeyTransactions}{$key}},$transaction;
	}
}

$apriori->generate_rules;
# or
# $apriori->association_rules_itemset_size(3);

print "\n@{$apriori->{frequentItemset}}\n";

DESCRIPTION

This module implements the apriori algorithm of data mining.

ATTRIBUTES

totalTransactions

The total number of transactions.

minSupport

The minimum support.

minConfidence

The minimum confidence.

output

The output type (optional):

1 - Export to file;
- 2 - Export to excel.

itemsKeyDescription

Hash table to add items by key and description.

itemsKeyTransactions

Reference to array, to add the transactions of each item per key.

quantityPossibleRules

Quantity of possible rules.

frequentItemset

Frequent itemset.

recursively

A value boolean to generate association rules until no set of items meets the minimum support or minimum confidence.

METHODS

new

Creates a new instance of Data::Mining::Apriori.

Expected a value boolean to display the messages(optional).

generate_rules

Generate association rules until no set of items meets the minimum support or minimum confidence.

association_rules_itemset_size

Generates association rules by size set of items. Accepts the following argument:

An integer

Representing the size of the set of items.

AUTHOR

Alex Graciano, <agraciano@cpan.org>

COPYRIGHT AND LICENSE

This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself, either Perl version 5.12.4 or, at your option, any later version of Perl 5 you may have available.

2 POD Errors

The following errors were encountered while parsing the POD:

Around line 521:

You forgot a '=back' before '=head2'

Around line 553: