@Override
public double evaluate(
JavaSparkContext sparkContext, PMML model, Path modelParentPath, JavaRDD<String> testData) {
log.info("Evaluating model");
JavaRDD<Rating> testRatingData = parsedToRatingRDD(toParsedRDD(testData));
testRatingData = aggregateScores(testRatingData);
MatrixFactorizationModel mfModel = pmmlToMFModel(sparkContext, model, modelParentPath);
double eval;
if (implicit) {
double auc = AUC.areaUnderCurve(sparkContext, mfModel, testRatingData);
log.info("AUC: {}", auc);
eval = auc;
} else {
double rmse = RMSE.rmse(mfModel, testRatingData);
log.info("RMSE: {}", rmse);
eval = 1.0 / rmse;
}
return eval;
}
@Override
public OutputOracle forecast(InputOracle io) throws OracleException {
double AVGrmse = Double.MAX_VALUE;
Oracle best = null;
try {
SelectInstancesRP(io);
KNN.setInstances(m_Training);
m_TestSet = DataConverter.FromInputOracleToInstance(io);
logger.info("PREDICT TARGET VALUE FOR : " + m_TestSet.toStringNoWeight());
System.out.println(m_TestSet);
Neighbourshood =
KNN.kNearestNeighbours(
m_TestSet,
NumNeighbours); // >k neighbours are returned if there are more than one neighbours at
// the kth boundary.
distances = KNN.getDistances();
RMSE = RMSE(this.ConsideredOutOracle);
double actual;
for (Map.Entry<Oracle, Double[]> entry : RMSE.entrySet()) {
// actual=(entry.getValue()[0]*VarianceRMSE(entry.getValue())[0]+entry.getValue()[1]*VarianceRMSE(entry.getValue())[1])/2;
actual = (entry.getValue()[0] + entry.getValue()[1]) / 2;
if (actual <= AVGrmse) {
AVGrmse = actual;
best = entry.getKey();
}
}
logger.info("ORACLE SELECTED FOR PREDICTION : " + best.toString().split("@")[0]);
return best.forecast(io);
} catch (Exception ex) {
logger.error("forecast error " + ex);
throw new OracleException(ex);
}
}
