C++ API Reference for Intel® Data Analytics Acceleration Library 2018 Update 1

df_reg_dense_batch.cpp

/* file: df_reg_dense_batch.cpp */
/*******************************************************************************
* Copyright 2014-2017 Intel Corporation
* All Rights Reserved.
*
* If this software was obtained under the Intel Simplified Software License,
* the following terms apply:
*
* 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.
*
*
* If this software was obtained under the Apache License, Version 2.0 (the
* "License"), the following terms apply:
*
* You may not use this file except in compliance with the License. You may
* obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0
*
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
*
* See the License for the specific language governing permissions and
* limitations under the License.
*******************************************************************************/
/*
! Content:
! C++ example of decision forest regression in the batch processing mode.
!
! The program trains the decision forest 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::decision_forest::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 */
/* Decision forest parameters */
const size_t nTrees = 100;
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 decision forest 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.nTrees = nTrees;
algorithm.parameter.varImportance = algorithms::decision_forest::training::MDA_Raw;
algorithm.parameter.resultsToCompute = algorithms::decision_forest::training::computeOutOfBagError;
/* Build the decision forest regression model */
algorithm.compute();
/* Retrieve the algorithm results */
training::ResultPtr trainingResult = algorithm.getResult();
printNumericTable(trainingResult->get(training::variableImportance), "Variable importance results: ");
printNumericTable(trainingResult->get(training::outOfBagError), "OOB error: ");
return trainingResult;
}
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 decision forest 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 decision forest regression */
algorithm.compute();
/* Retrieve the algorithm results */
prediction::ResultPtr predictionResult = algorithm.getResult();
printNumericTable(predictionResult->get(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.