C++ API Reference for Intel® Data Analytics Acceleration Library 2019

gbt_reg_dense_batch.cpp

/* file: gbt_reg_dense_batch.cpp */
/*******************************************************************************
* Copyright 2014-2018 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 gradient boosted trees regression in the batch processing mode.
!
! The program trains the gradient boosted trees regression model on a training
! datasetFileName and computes regression for the test data.
!******************************************************************************/
#include "daal.h"
#include "service.h"
using namespace std;
using namespace daal;
using namespace daal::algorithms::gbt::regression;
/* Input data set parameters */
const string trainDatasetFileName = "../data/batch/df_regression_train.csv";
const string testDatasetFileName = "../data/batch/df_regression_test.csv";
const size_t categoricalFeaturesIndices[] = { 3 };
const size_t nFeatures = 13; /* Number of features in training and testing data sets */
/* Gradient boosted trees training parameters */
const size_t maxIterations = 40;
training::ResultPtr trainModel();
void testModel(const training::ResultPtr& res);
void loadData(const std::string& fileName, NumericTablePtr& pData, NumericTablePtr& pDependentVar);
int main(int argc, char *argv[])
{
checkArguments(argc, argv, 2, &trainDatasetFileName, &testDatasetFileName);
training::ResultPtr trainingResult = trainModel();
testModel(trainingResult);
return 0;
}
training::ResultPtr trainModel()
{
/* Create Numeric Tables for training data and dependent variables */
NumericTablePtr trainData;
NumericTablePtr trainDependentVariable;
loadData(trainDatasetFileName, trainData, trainDependentVariable);
/* Create an algorithm object to train the gradient boosted trees regression model with the default method */
training::Batch<> algorithm;
/* Pass a training data set and dependent values to the algorithm */
algorithm.input.set(training::data, trainData);
algorithm.input.set(training::dependentVariable, trainDependentVariable);
algorithm.parameter().maxIterations = maxIterations;
/* Build the gradient boosted trees regression model */
algorithm.compute();
/* Retrieve the algorithm results */
return algorithm.getResult();
}
void testModel(const training::ResultPtr& trainingResult)
{
/* 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 gradient boosted trees regression */
prediction::Batch<> algorithm;
/* Pass a testing data set and the trained model to the algorithm */
algorithm.input.set(prediction::data, testData);
algorithm.input.set(prediction::model, trainingResult->get(training::model));
/* Predict values of gradient boosted trees regression */
algorithm.compute();
/* Retrieve the algorithm results */
prediction::ResultPtr predictionResult = algorithm.getResult();
printNumericTable(predictionResult->get(prediction::prediction),
"Gragient boosted trees 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.