Java* API Reference for Intel® Data Analytics Acceleration Library 2018 Update 1

DfRegDenseBatch.java

/* file: DfRegDenseBatch.java */
/*******************************************************************************
* 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:
// Java example of decision forest regression.
//
// The program trains the decision forest regression model on a supplied
// training data set and then predicts previously unseen data.
*/
package com.intel.daal.examples.decision_forest;
import com.intel.daal.algorithms.decision_forest.regression.*;
import com.intel.daal.algorithms.decision_forest.regression.prediction.*;
import com.intel.daal.algorithms.decision_forest.regression.training.*;
import com.intel.daal.algorithms.decision_forest.*;
import com.intel.daal.data_management.data.NumericTable;
import com.intel.daal.data_management.data.HomogenNumericTable;
import com.intel.daal.data_management.data.MergedNumericTable;
import com.intel.daal.data_management.data_source.DataSource;
import com.intel.daal.data_management.data_source.FileDataSource;
import com.intel.daal.examples.utils.Service;
import com.intel.daal.services.DaalContext;
import com.intel.daal.data_management.data.*;
class DfRegDenseBatch {
/* Input data set parameters */
private static final String trainDataset = "../data/batch/df_regression_train.csv";
private static final String testDataset = "../data/batch/df_regression_test.csv";
private static final int nFeatures = 13;
/* Decision forest regression algorithm parameters */
private static final int nTrees = 100;
private static NumericTable testGroundTruth;
private static DaalContext context = new DaalContext();
public static void main(String[] args) throws java.io.FileNotFoundException, java.io.IOException {
TrainingResult trainingResult = trainModel();
PredictionResult predictionResult = testModel(trainingResult);
printResults(predictionResult);
context.dispose();
}
private static TrainingResult trainModel() {
/* Retrieve the data from the input data sets */
FileDataSource trainDataSource = new FileDataSource(context, trainDataset,
DataSource.DictionaryCreationFlag.DoDictionaryFromContext,
DataSource.NumericTableAllocationFlag.NotAllocateNumericTable);
/* Create Numeric Tables for training data and labels */
NumericTable trainData = new HomogenNumericTable(context, Float.class, nFeatures, 0, NumericTable.AllocationFlag.NotAllocate);
NumericTable trainGroundTruth = new HomogenNumericTable(context, Float.class, 1, 0, NumericTable.AllocationFlag.NotAllocate);
MergedNumericTable mergedData = new MergedNumericTable(context);
mergedData.addNumericTable(trainData);
mergedData.addNumericTable(trainGroundTruth);
/* Retrieve the data from an input file */
trainDataSource.loadDataBlock(mergedData);
/* Set feature as categorical */
DataFeature categoricalFeature = trainData.getDictionary().getFeature(3);
categoricalFeature.setFeatureType(DataFeatureUtils.FeatureType.DAAL_CATEGORICAL);
/* Create algorithm objects to train the decision forest regression model */
TrainingBatch algorithm = new TrainingBatch(context, Float.class, TrainingMethod.defaultDense);
algorithm.parameter.setNTrees(nTrees);
algorithm.parameter.setVariableImportanceMode(VariableImportanceModeId.MDA_Raw);
algorithm.parameter.setResultsToCompute(ResultsToComputeId.computeOutOfBagError);
/* Pass a training data set and dependent values to the algorithm */
algorithm.input.set(InputId.data, trainData);
algorithm.input.set(InputId.dependentVariable, trainGroundTruth);
/* Train the decision forest regression model */
TrainingResult trainingResult = algorithm.compute();
Service.printNumericTable("Variable importance results: ", trainingResult.get(ResultNumericTableId.variableImportance));
Service.printNumericTable("OOB error: ", trainingResult.get(ResultNumericTableId.outOfBagError));
return trainingResult;
}
private static PredictionResult testModel(TrainingResult trainingResult) {
FileDataSource testDataSource = new FileDataSource(context, testDataset,
DataSource.DictionaryCreationFlag.DoDictionaryFromContext,
DataSource.NumericTableAllocationFlag.NotAllocateNumericTable);
/* Create Numeric Tables for testing data and labels */
NumericTable testData = new HomogenNumericTable(context, Float.class, nFeatures, 0, NumericTable.AllocationFlag.NotAllocate);
testGroundTruth = new HomogenNumericTable(context, Float.class, 1, 0, NumericTable.AllocationFlag.NotAllocate);
MergedNumericTable mergedData = new MergedNumericTable(context);
mergedData.addNumericTable(testData);
mergedData.addNumericTable(testGroundTruth);
/* Retrieve the data from an input file */
testDataSource.loadDataBlock(mergedData);
/* Set feature as categorical */
DataFeature categoricalFeature = testData.getDictionary().getFeature(3);
categoricalFeature.setFeatureType(DataFeatureUtils.FeatureType.DAAL_CATEGORICAL);
/* Create algorithm objects for decision forest regression prediction with the fast method */
PredictionBatch algorithm = new PredictionBatch(context, Float.class, PredictionMethod.defaultDense);
/* Pass a testing data set and the trained model to the algorithm */
Model model = trainingResult.get(TrainingResultId.model);
algorithm.input.set(NumericTableInputId.data, testData);
algorithm.input.set(ModelInputId.model, model);
/* Compute prediction results */
return algorithm.compute();
}
private static void printResults(PredictionResult predictionResult) {
NumericTable predictionResults = predictionResult.get(PredictionResultId.prediction);
Service.printNumericTable("Decision forest prediction results (first 10 rows):", predictionResults, 10);
Service.printNumericTable("Ground truth (first 10 rows):", testGroundTruth, 10);
}
}

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