KMeansDenseBatch.java

/* file: KMeansDenseBatch.java */
/*******************************************************************************
* Copyright 2014-2016 Intel Corporation All Rights Reserved.
*
* The source code,  information  and material  ("Material") contained  herein is
* owned by Intel Corporation or its  suppliers or licensors,  and  title to such
* Material remains with Intel  Corporation or its  suppliers or  licensors.  The
* Material  contains  proprietary  information  of  Intel or  its suppliers  and
* licensors.  The Material is protected by  worldwide copyright  laws and treaty
* provisions.  No part  of  the  Material   may  be  used,  copied,  reproduced,
* modified, published,  uploaded, posted, transmitted,  distributed or disclosed
* in any way without Intel's prior express written permission.  No license under
* any patent,  copyright or other  intellectual property rights  in the Material
* is granted to  or  conferred  upon  you,  either   expressly,  by implication,
* inducement,  estoppel  or  otherwise.  Any  license   under such  intellectual
* property rights must be express and approved by Intel in writing.
*
* Unless otherwise agreed by Intel in writing,  you may not remove or alter this
* notice or  any  other  notice   embedded  in  Materials  by  Intel  or Intel's
* suppliers or licensors in any way.
*******************************************************************************/

/*
 //  Content:
 //     Java example of dense K-Means clustering in the batch processing mode
 */

package com.intel.daal.examples.kmeans;

import com.intel.daal.algorithms.kmeans.*;
import com.intel.daal.algorithms.kmeans.init.*;
import com.intel.daal.data_management.data.NumericTable;
import com.intel.daal.data_management.data_source.DataSource;
import com.intel.daal.data_management.data_source.FileDataSource;
import com.intel.daal.examples.utils.Service;
import com.intel.daal.services.DaalContext;

class KMeansDenseBatch {
    /* Input data set parameters */
    private static final String dataset       = "../data/batch/kmeans_dense.csv";
    private static final int    nClusters     = 20;

    /* K-Means algorithm parameters */
    private static final int maxIterations = 5;

    private static DaalContext context = new DaalContext();

    public static void main(String[] args) throws java.io.FileNotFoundException, java.io.IOException {
        /* Retrieve the input data */
        FileDataSource dataSource = new FileDataSource(context, dataset,
                DataSource.DictionaryCreationFlag.DoDictionaryFromContext,
                DataSource.NumericTableAllocationFlag.DoAllocateNumericTable);
        dataSource.loadDataBlock();
        NumericTable input = dataSource.getNumericTable();

        /* Calculate initial clusters for K-Means clustering */
        InitBatch init = new InitBatch(context, Double.class, InitMethod.randomDense, nClusters);
        init.input.set(InitInputId.data, input);
        InitResult initResult = init.compute();
        NumericTable inputCentroids = initResult.get(InitResultId.centroids);

        /* Create an algorithm for K-Means clustering */
        Batch algorithm = new Batch(context, Double.class, Method.lloydDense, nClusters, maxIterations);

        /* Set an input object for the algorithm */
        algorithm.input.set(InputId.data, input);
        algorithm.input.set(InputId.inputCentroids, inputCentroids);

        /* Clusterize the data */
        Result result = algorithm.compute();

        /* Print the results */
        Service.printNumericTable("First 20 cluster assignments:", result.get(ResultId.assignments), 20);
        Service.printNumericTable("First 10 dimensions of centroids:", result.get(ResultId.centroids), 20, 10);
        Service.printNumericTable("Goal function value:", result.get(ResultId.goalFunction));

        context.dispose();
    }
}