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

kmeans_init_dense_batch.cpp

/* file: kmeans_init_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 dense K-Means clustering with different initialization methods
! in the batch processing mode
!******************************************************************************/
#include "daal.h"
#include "service.h"
using namespace std;
using namespace daal;
using namespace daal::algorithms;
/* Input data set parameters */
const string datasetFileName = "../data/batch/kmeans_init_dense.csv";
/* K-Means algorithm parameters */
const size_t nMaxIterations = 1000;
const double cAccuracyThreshold = 0.01;
const size_t nClusters = 20;
template <typename Type>
Type getSingleValue(const NumericTablePtr& pTbl)
{
BlockDescriptor<Type> block;
pTbl->getBlockOfRows(0, 1, readOnly, block);
Type value = block.getBlockPtr()[0];
pTbl->releaseBlockOfRows(block);
return value;
}
template <kmeans::init::Method method>
static void runKmeans(const NumericTablePtr& inputData, size_t nClusters, const char* methodName, double oversamplingFactor = -1.0)
{
/* Get initial clusters for the K-Means algorithm */
kmeans::init::Batch<float, method> init(nClusters);
init.input.set(kmeans::init::data, inputData);
if(oversamplingFactor > 0)
init.parameter.oversamplingFactor = oversamplingFactor;
std::cout << "K-means init parameters: method = " << methodName;
if(method == kmeans::init::parallelPlusDense)
std::cout << ", oversamplingFactor = " << init.parameter.oversamplingFactor << ", nRounds = " << init.parameter.nRounds;
std::cout << std::endl;
init.compute();
NumericTablePtr centroids = init.getResult()->get(kmeans::init::centroids);
/* Create an algorithm object for the K-Means algorithm */
kmeans::Batch<> algorithm(nClusters, nMaxIterations);
algorithm.input.set(kmeans::data, inputData);
algorithm.input.set(kmeans::inputCentroids, centroids);
algorithm.parameter.accuracyThreshold = cAccuracyThreshold;
std::cout << "K-means algorithm parameters: maxIterations = " << algorithm.parameter.maxIterations
<< ", accuracyThreshold = " << algorithm.parameter.accuracyThreshold << std::endl;
algorithm.compute();
/* Print the results */
const float goalFunc = getSingleValue<float>(algorithm.getResult()->get(kmeans::objectiveFunction));
const int nIterations = getSingleValue<int>(algorithm.getResult()->get(kmeans::nIterations));
std::cout << "K-means algorithm results: Objective function value = " << goalFunc*1e-6
<< "*1E+6, number of iterations = " << nIterations << std::endl << std::endl;
}
int main(int argc, char *argv[])
{
/* Initialize FileDataSource to retrieve the input data from a .csv file */
FileDataSource<CSVFeatureManager> dataSource(datasetFileName, DataSource::doAllocateNumericTable, DataSource::doDictionaryFromContext);
/* Retrieve the data from the input file */
dataSource.loadDataBlock();
NumericTablePtr inputData = dataSource.getNumericTable();
runKmeans<kmeans::init::deterministicDense>(inputData, nClusters, "deterministicDense");
runKmeans<kmeans::init::randomDense>(inputData, nClusters, "randomDense");
runKmeans<kmeans::init::plusPlusDense>(inputData, nClusters, "plusPlusDense");
runKmeans<kmeans::init::parallelPlusDense>(inputData, nClusters, "parallelPlusDense", 0.5);
runKmeans<kmeans::init::parallelPlusDense>(inputData, nClusters, "parallelPlusDense", 2.0);
return 0;
}

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