clusteringapply.java

一个数据挖掘软件ALPHAMINERR的整个过程的JAVA版源代码

/*
 *    This program is free software; you can redistribute it and/or modify
 *    it under the terms of the GNU General Public License as published by
 *    the Free Software Foundation; either version 2 of the License, or
 *    (at your option) any later version.
 *
 *    This program is distributed in the hope that it will be useful,
 *    but WITHOUT ANY WARRANTY; without even the implied warranty of
 *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *    GNU General Public License for more details.
 *
 *    You should have received a copy of the GNU General Public License
 *    along with this program; if not, write to the Free Software
 *    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

 /**
  * Title: XELOPES Data Mining Library
  * Description: The XELOPES library is an open platform-independent and data-source-independent library for Embedded Data Mining.
  * Copyright: Copyright (c) 2002 Prudential Systems Software GmbH
  * Company: ZSoft (www.zsoft.ru), Prudsys (www.prudsys.com)
  * @author Carsten Weisse
  * @author Michael Thess
  * @version 1.0
  */

package com.prudsys.pdm.Examples;

import java.io.FileReader;

import com.prudsys.pdm.Core.MiningDataSpecification;
import com.prudsys.pdm.Core.MiningModel;
import com.prudsys.pdm.Input.MiningFilterStream;
import com.prudsys.pdm.Input.MiningInputStream;
import com.prudsys.pdm.Input.MiningVector;
import com.prudsys.pdm.Input.Records.Csv.MiningCsvStream;
import com.prudsys.pdm.Models.Clustering.CDBased.CDBasedClusteringMiningModel;

/**
 * Applies a clustering model which is read from the PMML file 'ClusteringModel.xml'
 * to a data set.
 */
public class ClusteringApply extends BasisExample {

  /**
   * Empty constructor.
   */
  public ClusteringApply() {
  }

  /**
   * Run the example of this class.
   *
   * @throws Exception error while example is running
   */
  public void runExample() throws Exception {

    // Read from PMML:
    MiningModel model = new CDBasedClusteringMiningModel();
    FileReader reader = new FileReader("data/pmml/ClusteringModel.xml");
    model.readPmml(reader);
    MiningDataSpecification modelMetaData = model.getMiningSettings().getDataSpecification();
    System.out.println("-------------> PMML model read successfully");

    // Open data source and get metadata:
    MiningInputStream inputData0 = new MiningCsvStream( "data/csv/iris.csv");
    inputData0.open();

    // Transform input data (dynamically) if required:
    MiningInputStream inputData = inputData0;
    if ( modelMetaData.isTransformed() )
      inputData = new MiningFilterStream(inputData0, modelMetaData.getMiningTransformationActivity());

    MiningDataSpecification inputMetaData = inputData.getMetaData();

    // Show relation header:
    System.out.println("Prediction:");
    for (int i = 0; i < inputMetaData.getAttributesNumber(); i++) {
      System.out.print(inputMetaData.getMiningAttribute(i).getName() + " ");
    };

    // Show clustering results:
    System.out.println();
    int i = 0;
    while (inputData.next()) {
      // Make prediction:
      MiningVector vector = inputData.read();
      int predicted       = (int) model.applyModelFunction(vector);

      // Output and stats:
      System.out.println(" " + ++i +": " + vector + " -> " + predicted);
    };
  }


  /**
   * Example of applying a cluster model to a data set.
   *
   * @param args arguments (ignored)
   */
  public static void main(String[] args) {

    try {
      new ClusteringApply().runExample();
    }
    catch (Exception ex) {
      ex.printStackTrace();
    }
  }
}