df_cls_dense_batch_model_build.cpp

/* file: df_cls_dense_batch_model_build.cpp */
/*******************************************************************************
* Copyright 2014-2019 Intel Corporation.
*
* This software and the related documents are Intel copyrighted  materials,  and
* your use of  them is  governed by the  express license  under which  they were
* provided to you (License).  Unless the License provides otherwise, you may not
* use, modify, copy, publish, distribute,  disclose or transmit this software or
* the related documents without Intel's prior written permission.
*
* This software and the related documents  are provided as  is,  with no express
* or implied  warranties,  other  than those  that are  expressly stated  in the
* License.
*******************************************************************************/

/*
!  Content:
!    C++ example of decision forest classification model building.
!
!    The program builds the decision forest classification model
!     via Model Builder and computes classification for the test data.
!******************************************************************************/

#include "daal.h"
#include "service.h"

using namespace std;
using namespace daal;
using namespace daal::algorithms;
using namespace daal::algorithms::decision_forest::classification;

/* Input data set parameters */
const string testDatasetFileName  = "../data/batch/df_classification_model_builder_test.csv";
const size_t categoricalFeaturesIndices[] = { 2 };
const size_t nFeatures  = 3;  /* Number of features in training and testing data sets */

/* Decision forest parameters */
const size_t nTrees = 3;
const size_t nClasses = 5;  /* Number of classes */


void testModel(decision_forest::classification::ModelPtr& model);
decision_forest::classification::ModelPtr buildModel();
void loadData(const std::string& fileName, NumericTablePtr& pData, NumericTablePtr& pDependentVar);

int main(int argc, char *argv[])
{
    checkArguments(argc, argv, 1, &testDatasetFileName);

    decision_forest::classification::ModelPtr model = buildModel();
    testModel(model);

    return 0;
}

decision_forest::classification::ModelPtr buildModel()
{
    const size_t nNodes = 3;

    ModelBuilder modelBuilder(nClasses, nTrees);
    ModelBuilder::TreeId tree1 =  modelBuilder.createTree(nNodes);
    ModelBuilder::NodeId root1   = modelBuilder.addSplitNode(tree1, ModelBuilder::noParent, 0, 0, 0.174108);
    ModelBuilder::NodeId child12 = modelBuilder.addLeafNode(tree1, root1, 1, 4);
    ModelBuilder::NodeId child11 = modelBuilder.addLeafNode(tree1, root1, 0, 0);

    ModelBuilder::TreeId tree2 = modelBuilder.createTree(nNodes);
    ModelBuilder::NodeId root2 = modelBuilder.addSplitNode(tree2, ModelBuilder::noParent, 0, 1, 0.571184);
    ModelBuilder::NodeId child22 = modelBuilder.addLeafNode(tree2, root2, 1, 4);
    ModelBuilder::NodeId child21 = modelBuilder.addLeafNode(tree2, root2, 0, 2);

    ModelBuilder::TreeId tree3 = modelBuilder.createTree(nNodes);
    ModelBuilder::NodeId root3 = modelBuilder.addSplitNode(tree3, ModelBuilder::noParent, 0, 0, 0.303995);
    ModelBuilder::NodeId child32 = modelBuilder.addLeafNode(tree3, root3, 1, 4);
    ModelBuilder::NodeId child31 = modelBuilder.addLeafNode(tree3, root3, 0, 2);

    return modelBuilder.getModel();
}

void testModel(decision_forest::classification::ModelPtr& model)
{

    /* Create Numeric Tables for testing data and ground truth values */
    NumericTablePtr testData;
    NumericTablePtr testGroundTruth;

    loadData(testDatasetFileName, testData, testGroundTruth);

    /* Create an algorithm object to predict values of decision forest classification */
    prediction::Batch<> algorithm(nClasses);

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

    /* set model obtained by builder */
    algorithm.input.set(classifier::prediction::model, model);

    /* Predict values of decision forest classification */
    algorithm.compute();

    /* Retrieve the algorithm results */
    classifier::prediction::ResultPtr predictionResult = algorithm.getResult();
    printNumericTable(predictionResult->get(classifier::prediction::prediction),
        "Decision forest prediction results (first 10 rows):", 10);
    printNumericTable(testGroundTruth, "Ground truth (first 10 rows):", 10);
}

void loadData(const std::string& fileName, NumericTablePtr& pData, NumericTablePtr& pDependentVar)
{
    /* Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file */
    FileDataSource<CSVFeatureManager> trainDataSource(fileName,
        DataSource::notAllocateNumericTable,
        DataSource::doDictionaryFromContext);

    /* Create Numeric Tables for training data and dependent variables */
    pData.reset(new HomogenNumericTable<>(nFeatures, 0, NumericTable::notAllocate));
    pDependentVar.reset(new HomogenNumericTable<>(1, 0, NumericTable::notAllocate));
    NumericTablePtr mergedData(new MergedNumericTable(pData, pDependentVar));

    /* Retrieve the data from input file */
    trainDataSource.loadDataBlock(mergedData.get());

    NumericTableDictionaryPtr pDictionary = pData->getDictionarySharedPtr();
    for(size_t i = 0, n = sizeof(categoricalFeaturesIndices) / sizeof(categoricalFeaturesIndices[0]); i < n; ++i)
        (*pDictionary)[categoricalFeaturesIndices[i]].featureType = data_feature_utils::DAAL_CATEGORICAL;
}
For more complete information about compiler optimizations, see our Optimization Notice.
Select sticky button color: 
Orange (only for download buttons)