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

dt_reg_traverse_model.cpp

/* file: dt_reg_traverse_model.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 tree classification model traversal.
!
! The program trains the decision tree classification model on a training
! datasetFileName and prints the trained model by its depth-first traversing.
!******************************************************************************/
#include "daal.h"
#include "service.h"
#include <cstdio>
using namespace std;
using namespace daal;
using namespace daal::algorithms;
/* Input data set parameters */
string trainDatasetFileName = "../data/batch/decision_tree_train.csv";
string pruneDatasetFileName = "../data/batch/decision_tree_prune.csv";
const size_t nFeatures = 5; /* Number of features in training and testing data sets */
decision_tree::regression::training::ResultPtr trainModel();
void printModel(const daal::algorithms::decision_tree::regression::Model& m);
int main(int argc, char *argv[])
{
checkArguments(argc, argv, 2, &trainDatasetFileName, &pruneDatasetFileName);
decision_tree::regression::training::ResultPtr trainingResult = trainModel();
printModel(*trainingResult->get(decision_tree::regression::training::model));
return 0;
}
decision_tree::regression::training::ResultPtr trainModel()
{
/* Initialize FileDataSource<CSVFeatureManager> to retrieve the input data from a .csv file */
FileDataSource<CSVFeatureManager> trainDataSource(trainDatasetFileName,
DataSource::notAllocateNumericTable,
DataSource::doDictionaryFromContext);
/* Create Numeric Tables for training data and dependent variables */
NumericTablePtr trainData(new HomogenNumericTable<>(nFeatures, 0, NumericTable::notAllocate));
NumericTablePtr trainGroundTruth(new HomogenNumericTable<>(1, 0, NumericTable::notAllocate));
NumericTablePtr mergedData(new MergedNumericTable(trainData, trainGroundTruth));
/* Retrieve the data from the input file */
trainDataSource.loadDataBlock(mergedData.get());
/* Initialize FileDataSource<CSVFeatureManager> to retrieve the pruning input data from a .csv file */
FileDataSource<CSVFeatureManager> pruneDataSource(pruneDatasetFileName,
DataSource::notAllocateNumericTable,
DataSource::doDictionaryFromContext);
/* Create Numeric Tables for pruning data and dependent variables */
NumericTablePtr pruneData(new HomogenNumericTable<>(nFeatures, 0, NumericTable::notAllocate));
NumericTablePtr pruneGroundTruth(new HomogenNumericTable<>(1, 0, NumericTable::notAllocate));
NumericTablePtr pruneMergedData(new MergedNumericTable(pruneData, pruneGroundTruth));
/* Retrieve the data from the pruning input file */
pruneDataSource.loadDataBlock(pruneMergedData.get());
/* Create an algorithm object to train the Decision tree model */
decision_tree::regression::training::Batch<> algorithm;
/* Pass the training data set, dependent variables, and pruning dataset with dependent variables to the algorithm */
algorithm.input.set(decision_tree::regression::training::data, trainData);
algorithm.input.set(decision_tree::regression::training::dependentVariables, trainGroundTruth);
algorithm.input.set(decision_tree::regression::training::dataForPruning, pruneData);
algorithm.input.set(decision_tree::regression::training::dependentVariablesForPruning, pruneGroundTruth);
/* Train the Decision tree model */
algorithm.compute();
/* Retrieve the results of the training algorithm */
return algorithm.getResult();
}
class PrintNodeVisitor : public daal::algorithms::regression::TreeNodeVisitor
{
public:
virtual bool onLeafNode(size_t level, double response)
{
for(size_t i = 0; i < level; ++i)
std::cout << " ";
std::cout << "Level " << level << ", leaf node. Response value = " << response << std::endl;
return true;
}
virtual bool onSplitNode(size_t level, size_t featureIndex, double featureValue)
{
for(size_t i = 0; i < level; ++i)
std::cout << " ";
std::cout << "Level " << level << ", split node. Feature index = " << featureIndex <<
", feature value = " << featureValue << std::endl;
return true;
}
};
void printModel(const daal::algorithms::decision_tree::regression::Model& m)
{
PrintNodeVisitor visitor;
m.traverseDF(visitor);
}

For more complete information about compiler optimizations, see our Optimization Notice.