package com.imsl.test.example.datamining.decisionTree;

import com.imsl.datamining.decisionTree.*;

/**
 * <p>
 * Fits a decision tree to the golf data using C45 and ALACART.</p>
 *
 * <p>
 * In this example, we use a small data set with response variable, Play, which
 * indicates whether a golfer plays (1) or does not play (0) golf under weather
 * conditions measured by Temperature, Humidity, Outlook (Sunny (0), Overcast
 * (1), Rainy (2)), and Wind (True (0), False (1)). A decision tree is generated
 * by <a href="../../../../datamining/decisionTree/C45.html">C45</a>
 * and the <a href="../../../../datamining/decisionTree/ALACART.html">ALACART</a>
 * class. The control parameters are adjusted because of the small data size and
 * no cross-validation or pruning is performed. The maximal trees are printed
 * out using the method, <code>DecisionTree.printDecisionTree</code>
 * Notice that <code>C45</code> splits on Outlook, then Humidity and Wind, while
 * <code>ALACART</code> splits on Outlook, then Temperature.</p>
 *
 * @see <a href="DecisionTreeEx1.java">Code</a>
 * @see <a href="doc-files/DecisionTreeEx1.out">Output</a>
 *
 */
public class DecisionTreeEx1 {

    public static void main(String[] args) throws Exception {

        int golfResponseIdx = 4;
        double[][] golfXY = {
            {0, 85, 85, 0, 0}, {0, 80, 90, 1, 0}, {1, 83, 78, 0, 1},
            {2, 70, 96, 0, 1}, {2, 68, 80, 0, 1}, {2, 65, 70, 1, 0},
            {1, 64, 65, 1, 1}, {0, 72, 95, 0, 0}, {0, 69, 70, 0, 1},
            {2, 75, 80, 0, 1}, {0, 75, 70, 1, 1}, {1, 72, 90, 1, 1},
            {1, 81, 75, 0, 1}, {2, 71, 80, 1, 0}
        };

        DecisionTree.VariableType[] golfVarType = {
            DecisionTree.VariableType.CATEGORICAL,
            DecisionTree.VariableType.QUANTITATIVE_CONTINUOUS,
            DecisionTree.VariableType.QUANTITATIVE_CONTINUOUS,
            DecisionTree.VariableType.CATEGORICAL,
            DecisionTree.VariableType.CATEGORICAL
        };

        String[] names = {
            "Outlook", "Temperature", "Humidity", "Wind", "Play"
        };
        String[] classNames = {"Don't Play", "Play"};
        String[] varLevels = {"Sunny", "Overcast", "Rainy", "False", "True"};

        C45 dt = new C45(golfXY, golfResponseIdx, golfVarType);
        dt.setMinObsPerChildNode(2);
        dt.setMinObsPerNode(3);
        dt.setMaxNodes(50);
        dt.fitModel();

        System.out.println("\n\nDecision Tree using Method C4.5:");
        dt.printDecisionTree(null, names, classNames,
                varLevels, true);

        ALACART adt = new ALACART(golfXY, golfResponseIdx, golfVarType);
        adt.setMinObsPerChildNode(2);
        adt.setMinObsPerNode(3);
        adt.setMaxNodes(50);
        adt.fitModel();

        System.out.println("\n\nDecision Tree using Method ALACART:");
        adt.printDecisionTree(null, names, classNames,
                varLevels, true);
    }
}