/**
* This method applies a stacked autoencoders model to a given dataset and make predictions
*
* @param ctxt JavaSparkContext
* @param deeplearningModel Stacked Autoencoders model
* @param test Testing dataset as a JavaRDD of labeled points
* @return
*/
public JavaPairRDD<Double, Double> test(
JavaSparkContext ctxt,
final DeepLearningModel deeplearningModel,
JavaRDD<LabeledPoint> test,
MLModel mlModel)
throws MLModelBuilderException {
Scope.enter();
if (deeplearningModel == null) {
throw new MLModelBuilderException("DeeplearningModel is Null");
}
int numberOfFeatures = mlModel.getFeatures().size();
List<Feature> features = mlModel.getFeatures();
String[] names = new String[numberOfFeatures + 1];
for (int i = 0; i < numberOfFeatures; i++) {
names[i] = features.get(i).getName();
}
names[numberOfFeatures] = mlModel.getResponseVariable();
Frame testData = DeeplearningModelUtils.javaRDDToFrame(names, test);
Frame testDataWithoutLabels = testData.subframe(0, testData.numCols() - 1);
int numRows = (int) testDataWithoutLabels.numRows();
Vec predictionsVector = deeplearningModel.score(testDataWithoutLabels).vec(0);
double[] predictionValues = new double[numRows];
for (int i = 0; i < numRows; i++) {
predictionValues[i] = predictionsVector.at(i);
}
Vec labelsVector = testData.vec(testData.numCols() - 1);
double[] labels = new double[numRows];
for (int i = 0; i < numRows; i++) {
labels[i] = labelsVector.at(i);
}
Scope.exit();
ArrayList<Tuple2<Double, Double>> tupleList = new ArrayList<Tuple2<Double, Double>>();
for (int i = 0; i < labels.length; i++) {
tupleList.add(new Tuple2<Double, Double>(predictionValues[i], labels[i]));
}
return ctxt.parallelizePairs(tupleList);
}
