SVMTwoClassCSRBatch.java

/* file: SVMTwoClassCSRBatch.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 two-class support vector machine (SVM) classification
 //
 //     The program trains the SVM model on a supplied training data set
 //     in compressed sparse rows (CSR) format and then performs classification
 //     of previously unseen data.
 */

package com.intel.daal.examples.svm;

import com.intel.daal.algorithms.classifier.prediction.*;
import com.intel.daal.algorithms.classifier.training.InputId;
import com.intel.daal.algorithms.classifier.training.TrainingResultId;
import com.intel.daal.algorithms.svm.Model;
import com.intel.daal.algorithms.svm.prediction.PredictionBatch;
import com.intel.daal.algorithms.svm.prediction.PredictionMethod;
import com.intel.daal.algorithms.svm.training.*;
import com.intel.daal.data_management.data.NumericTable;
import com.intel.daal.data_management.data.HomogenNumericTable;
import com.intel.daal.data_management.data.CSRNumericTable;
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 SVMTwoClassCSRBatch {

    /* Input data set parameters */
    private static final String trainDatasetFileName     = "../data/batch/svm_two_class_train_csr.csv";
    private static final String trainGroundTruthFileName = "../data/batch/svm_two_class_train_labels.csv";

    private static final String testDatasetFileName     = "../data/batch/svm_two_class_test_csr.csv";
    private static final String testGroundTruthFileName = "../data/batch/svm_two_class_test_labels.csv";

    private static TrainingResult   trainingResult;
    private static PredictionResult predictionResult;

    private static DaalContext context = new DaalContext();

    public static void main(String[] args) throws java.io.FileNotFoundException, java.io.IOException {

        trainModel();

        testModel();

        printResults();

        context.dispose();
    }

    private static void trainModel() throws java.io.IOException {

        /* Retrieve the data from input data sets */
        FileDataSource trainGroundTruthSource = new FileDataSource(context, trainGroundTruthFileName,
                DataSource.DictionaryCreationFlag.DoDictionaryFromContext,
                DataSource.NumericTableAllocationFlag.DoAllocateNumericTable);

        /* Load the data from the data files */
        NumericTable trainData = Service.createSparseTable(context, trainDatasetFileName);
        trainGroundTruthSource.loadDataBlock();

        /* Create algorithm objects to train the two-class SVM model */
        TrainingBatch algorithm = new TrainingBatch(context, Double.class, TrainingMethod.boser);

        /* Set parameters for the two-class SVM algorithm */
        algorithm.parameter.setCacheSize(40000000);
        algorithm.parameter.setKernel(
            new com.intel.daal.algorithms.kernel_function.linear.Batch(
                context, Double.class, com.intel.daal.algorithms.kernel_function.linear.Method.fastCSR));

        /* Pass a training data set and dependent values to the algorithm */
        algorithm.input.set(InputId.data, trainData);
        algorithm.input.set(InputId.labels, trainGroundTruthSource.getNumericTable());

        /* Train the two-class SVM model */
        trainingResult = algorithm.compute();
    }

    private static void testModel() throws java.io.IOException {

        /* Create Numeric Tables for testing data and labels */
        NumericTable testData = Service.createSparseTable(context, testDatasetFileName);

        /* Create algorithm objects to predict two-class SVM values with the defaultDense method */
        PredictionBatch algorithm = new PredictionBatch(context, Double.class, PredictionMethod.defaultDense);

        algorithm.parameter.setKernel(
            new com.intel.daal.algorithms.kernel_function.linear.Batch(
                context, Double.class, com.intel.daal.algorithms.kernel_function.linear.Method.fastCSR));

        Model model = trainingResult.get(TrainingResultId.model);

        /* Pass a testing data set and the trained model to the algorithm */
        algorithm.input.set(NumericTableInputId.data, testData);
        algorithm.input.set(ModelInputId.model, model);

        /* Compute the prediction results */
        predictionResult = algorithm.compute();
    }

    private static void printResults() {

        FileDataSource testGroundTruthSource = new FileDataSource(context, testGroundTruthFileName,
                DataSource.DictionaryCreationFlag.DoDictionaryFromContext,
                DataSource.NumericTableAllocationFlag.DoAllocateNumericTable);
        testGroundTruthSource.loadDataBlock();

        NumericTable testGroundTruth = testGroundTruthSource.getNumericTable();
        NumericTable predictionResults = predictionResult.get(PredictionResultId.prediction);
        Service.printClassificationResult(testGroundTruth, predictionResults, "Ground truth", "Classification results",
                "SVM classification results (first 20 observations):", 20);
    }
}