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

import com.imsl.datamining.decisionTree.*;

/**
 * 
 * <p>Fits a decision tree to the Kyphosis data using QUEST.</p>
 * <p>
 * This example uses the dataset Kyphosis. The 81 cases represent 81 children
 * who have undergone surgery to correct a type of spinal deformity known as
 * Kyphosis. The response variable is the presence or absence of Kyphosis after the
 * surgery. Three predictors are Age of the patient in months, Start, the number of
 * the vertebra where the surgery started, and Number, the number of vertebra
 * involved in the surgery. This example uses the method 
 * <a href="../../../datamining/decisionTree/QUEST.html">QUEST</a>to
 * produce a maximal tree. It also requests predictions for a test-data set
 * consisting of 10 "new" cases.
 * </p>
 * 
 * 
 * 
 * @see <a href="DecisionTreeEx4.java">Code</a>
 * @see <a href="doc-files/DecisionTreeEx4.out">Output</a>
 */
public class DecisionTreeEx4 {

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

        double[][] xy = {
            {0, 71, 3, 5}, {0, 158, 3, 14}, {1, 128, 4, 5}, {0, 2, 5, 1},
            {0, 1, 4, 15}, {0, 1, 2, 16}, {0, 61, 2, 17}, {0, 37, 3, 16},
            {0, 113, 2, 16}, {1, 59, 6, 12}, {1, 82, 5, 14}, {0, 148, 3, 16},
            {0, 18, 5, 2}, {0, 1, 4, 12}, {0, 168, 3, 18}, {0, 1, 3, 16},
            {0, 78, 6, 15}, {0, 175, 5, 13}, {0, 80, 5, 16},
            {0, 27, 4, 9}, {0, 22, 2, 16}, {1, 105, 6, 5}, {1, 96, 3, 12},
            {0, 131, 2, 3}, {1, 15, 7, 2}, {0, 9, 5, 13}, {0, 8, 3, 6},
            {0, 100, 3, 14}, {0, 4, 3, 16}, {0, 151, 2, 16}, {0, 31, 3, 16},
            {0, 125, 2, 11}, {0, 130, 5, 13}, {0, 112, 3, 16}, {0, 140, 5, 11},
            {0, 93, 3, 16}, {0, 1, 3, 9}, {1, 52, 5, 6}, {0, 20, 6, 9},
            {1, 91, 5, 12}, {1, 73, 5, 1}, {0, 35, 3, 13}, {0, 143, 9, 3},
            {0, 61, 4, 1}, {0, 97, 3, 16}, {1, 139, 3, 10}, {0, 136, 4, 15},
            {0, 131, 5, 13}, {1, 121, 3, 3}, {0, 177, 2, 14}, {0, 68, 5, 10},
            {0, 9, 2, 17}, {1, 139, 10, 6}, {0, 2, 2, 17}, {0, 140, 4, 15},
            {0, 72, 5, 15}, {0, 2, 3, 13}, {1, 120, 5, 8}, {0, 51, 7, 9},
            {0, 102, 3, 13}, {1, 130, 4, 1}, {1, 114, 7, 8}, {0, 81, 4, 1},
            {0, 118, 3, 16}, {0, 118, 4, 16}, {0, 17, 4, 10}, {0, 195, 2, 17},
            {0, 159, 4, 13}, {0, 18, 4, 11}, {0, 15, 5, 16}, {0, 158, 5, 14},
            {0, 127, 4, 12}, {0, 87, 4, 16}, {0, 206, 4, 10}, {0, 11, 3, 15},
            {0, 178, 4, 15}, {1, 157, 3, 13}, {0, 26, 7, 13}, {0, 120, 2, 13},
            {1, 42, 7, 6}, {0, 36, 4, 13}
        };

        double[][] xyTest = {
            {0, 71, 3, 5}, {1, 128, 4, 5}, {0, 1, 4, 15}, {0, 61, 6, 10},
            {0, 113, 2, 16}, {1, 82, 5, 14}, {0, 148, 3, 16}, {0, 1, 4, 12},
            {0, 1, 3, 16}, {0, 175, 5, 13}
        };

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

        String[] names = {"Age", "Number", "Start"};
        String[] classNames = {"Absent", "Present"};
        String responseName = "Kyphosis";

        QUEST dt = new QUEST(xy, 0, varType);
        dt.setMinObsPerChildNode(5);
        dt.setMinObsPerNode(10);
        dt.setMaxNodes(50);
        dt.setPrintLevel(2);
        dt.fitModel();

        double[] predictions = dt.predict(xyTest);
        double predErrSS = dt.getMeanSquaredPredictionError();

        dt.printDecisionTree(responseName, names,
                classNames, null, true);

        System.out.println("\nPredictions for test data:");
        System.out.printf("%5s%8s%7s%10s\n", names[0], names[1], names[2],
                responseName);

        for (int i = 0; i < xyTest.length; i++) {
            System.out.printf("%5.0f%8.0f%7.0f", xyTest[i][1], xyTest[i][2],
                    xyTest[i][3]);
            int idx = (int) predictions[i];
            System.out.printf("%10s\n", classNames[idx]);
        }
        System.out.printf("\nMean squared prediction error: %f\n", predErrSS);
    }
}