package com.imsl.test.example.datamining;

import com.imsl.datamining.*;

/**
 * <h4>Applies the Apriori algorithm to separate sets of
 * transactions. </h4>
 *
 * <p>
 * This example demonstrates how to apply {@link Apriori} to separate chunks of
 * data and then combine the results. This is a strategy for using
 * <code>Apriori</code> on distributed data. The data are two separate blocks of
 * 50 transactions involving five different products. Recall that in the data,
 * transaction ID appears first, and then the product ID. The minimum support
 * percentage is set to 0.30, giving a minimum required support of 30
 * transactions overall.
 * </p>
 *
 * @see <a href="AprioriEx2.java">Code</a>
 * @see <a href="doc-files/AprioriEx2.out">Output</a>
 *
 */
public class AprioriEx2 {

    public static void main(String[] args) {
        int numProducts = 5;
        int[][] x1 = {
            {1, 3}, {1, 2}, {1, 1}, {2, 1}, {2, 2}, {2, 4}, {2, 5},
            {3, 3}, {4, 4}, {4, 3}, {4, 5}, {4, 1}, {5, 5}, {6, 1}, {6, 2},
            {6, 3}, {7, 5}, {7, 3}, {7, 2}, {8, 3}, {8, 4}, {8, 1}, {8, 5},
            {8, 2}, {9, 4}, {10, 5}, {10, 3}, {11, 2}, {11, 3}, {12, 4},
            {13, 4}, {14, 2}, {14, 3}, {14, 1}, {15, 3}, {15, 5}, {15, 1},
            {16, 2}, {17, 3}, {17, 5}, {17, 1}, {18, 5}, {18, 1}, {18, 2},
            {18, 3}, {19, 2}, {20, 4}, {21, 1}, {21, 4}, {21, 2}, {21, 5},
            {22, 5}, {22, 4}, {23, 2}, {23, 5}, {23, 3}, {23, 1}, {23, 4},
            {24, 3}, {24, 1}, {24, 5}, {25, 3}, {25, 5}, {26, 1}, {26, 4},
            {26, 2}, {26, 3}, {27, 2}, {27, 3}, {27, 1}, {27, 5}, {28, 5},
            {28, 3}, {28, 4}, {28, 1}, {28, 2}, {29, 4}, {29, 5}, {29, 2},
            {30, 2}, {30, 4}, {30, 3}, {31, 2}, {32, 5}, {32, 1}, {32, 4},
            {33, 4}, {33, 1}, {33, 5}, {33, 3}, {33, 2}, {34, 3}, {35, 5},
            {35, 3}, {36, 3}, {36, 5}, {36, 4}, {36, 1}, {36, 2}, {37, 1},
            {37, 3}, {37, 2}, {38, 4}, {38, 2}, {38, 3}, {39, 3}, {39, 2},
            {39, 1}, {40, 2}, {40, 1}, {41, 3}, {41, 5}, {41, 1}, {41, 4},
            {41, 2}, {42, 5}, {42, 1}, {42, 4}, {43, 3}, {43, 2}, {43, 4},
            {44, 4}, {44, 5}, {44, 2}, {44, 3}, {44, 1}, {45, 4}, {45, 5},
            {45, 3}, {45, 2}, {45, 1}, {46, 2}, {46, 4}, {46, 5}, {46, 3},
            {46, 1}, {47, 4}, {47, 5}, {48, 2}, {49, 1}, {49, 4}, {49, 3},
            {50, 3}, {50, 4}
        };

        int[][] x2 = {
            {1, 2}, {1, 1}, {1, 4}, {1, 3}, {2, 2}, {2, 5}, {2, 3}, {2, 1},
            {2, 4}, {3, 5}, {3, 4}, {4, 2}, {5, 4}, {5, 2}, {5, 3}, {5, 5},
            {6, 3}, {6, 5}, {7, 2}, {7, 5}, {7, 4}, {7, 1}, {7, 3}, {8, 2},
            {9, 2}, {9, 4}, {10, 4}, {10, 2}, {11, 4}, {11, 1}, {12, 3},
            {12, 1}, {12, 5}, {12, 2}, {13, 2}, {14, 3}, {14, 4}, {14, 2},
            {15, 2}, {16, 5}, {16, 2}, {16, 4}, {17, 1}, {18, 2}, {18, 3},
            {18, 4}, {19, 3}, {19, 1}, {19, 2}, {19, 4}, {20, 5}, {20, 1},
            {21, 5}, {21, 4}, {21, 1}, {21, 3}, {22, 4}, {22, 1}, {22, 5},
            {23, 1}, {23, 2}, {24, 4}, {25, 4}, {25, 3}, {26, 5}, {26, 2},
            {26, 3}, {26, 4}, {26, 1}, {27, 2}, {27, 1}, {27, 5}, {27, 3},
            {28, 1}, {28, 2}, {28, 3}, {28, 4}, {29, 5}, {29, 2}, {29, 1},
            {30, 5}, {30, 3}, {30, 2}, {30, 4}, {31, 4}, {31, 1}, {32, 1},
            {32, 2}, {32, 3}, {32, 4}, {32, 5}, {33, 3}, {33, 2}, {33, 4},
            {33, 5}, {33, 1}, {34, 3}, {34, 4}, {34, 5}, {34, 2}, {35, 2},
            {35, 3}, {36, 3}, {36, 5}, {36, 4}, {37, 1}, {37, 4}, {37, 2},
            {37, 3}, {37, 5}, {38, 5}, {38, 3}, {38, 1}, {38, 2}, {39, 2},
            {39, 5}, {40, 4}, {40, 2}, {41, 4}, {42, 4}, {43, 5}, {43, 4},
            {44, 5}, {44, 4}, {44, 3}, {44, 2}, {44, 1}, {45, 1}, {45, 2},
            {45, 3}, {45, 5}, {45, 4}, {46, 3}, {46, 4}, {47, 4}, {47, 5},
            {47, 2}, {47, 3}, {48, 5}, {48, 3}, {48, 2}, {48, 1}, {48, 4},
            {49, 4}, {49, 5}, {50, 4}, {50, 1}
        };

        // Find frequent itemsets in x1 and x2.
        Itemsets fis1
                = Apriori.getFrequentItemsets(x1, numProducts, 4, 0.30);
        Itemsets fis2
                = Apriori.getFrequentItemsets(x2, numProducts, 4, 0.30);

        // Get the union of fis1 and fis2.
        Itemsets cis = Apriori.getUnion(fis1, fis2);

        // Count the frequencies of the itemsets in the union in
        // each of the data sets.
        int[] freq1 = Apriori.countFrequency(cis, x1);
        int[] freq2 = Apriori.countFrequency(cis, x2);
        int[] freq = Apriori.sum(freq1, freq2);

        // Get the frequent itemset of the union.
        Itemsets itemsets = Apriori.updateFrequentItemsets(cis, freq);
        itemsets.print();

        // Generate and print the association rules.
        AssociationRule.print(Apriori.getAssociationRules(itemsets, 0.80, 2.0));
    }
}