/// <summary>
/// Builds readout layer.
/// Prepares prediction clusters containing trained readout units.
/// </summary>
/// <param name="predictorsCollection">Collection of predictors</param>
/// <param name="idealOutputsCollection">Collection of desired outputs related to predictors</param>
/// <param name="regressionController">Regression controller delegate</param>
/// <param name="regressionControllerData">An user object</param>
/// <returns>Returned ValidationBundle is something like a protocol.
/// There is recorded fold by fold (unit by unit) predicted and corresponding ideal values.
/// This is the pesimistic approach. Real results on unseen data could be better due to the clustering synergy.
/// </returns>
public ValidationBundle Build(List <double[]> predictorsCollection,
List <double[]> idealOutputsCollection,
ReadoutUnit.RegressionCallbackDelegate regressionController,
Object regressionControllerData
)
{
//Random object
Random rand = new Random(0);
//Allocation of computed and ideal vectors for validation bundle
List <double[]> validationComputedVectorCollection = new List <double[]>(idealOutputsCollection.Count);
List <double[]> validationIdealVectorCollection = new List <double[]>(idealOutputsCollection.Count);
for (int i = 0; i < idealOutputsCollection.Count; i++)
{
validationComputedVectorCollection.Add(new double[idealOutputsCollection[0].Length]);
validationIdealVectorCollection.Add(new double[idealOutputsCollection[0].Length]);
}
//Test dataset size
if (_settings.TestDataRatio > MaxRatioOfTestData)
{
throw new ArgumentException($"Test dataset size is greater than {MaxRatioOfTestData.ToString(CultureInfo.InvariantCulture)}", "TestDataSetSize");
}
int testDataSetLength = (int)Math.Round(idealOutputsCollection.Count * _settings.TestDataRatio, 0);
if (testDataSetLength < MinLengthOfTestDataset)
{
throw new ArgumentException($"Num of test samples is less than {MinLengthOfTestDataset.ToString(CultureInfo.InvariantCulture)}", "TestDataSetSize");
}
//Number of folds
int numOfFolds = _settings.NumOfFolds;
if (numOfFolds <= 0)
{
//Auto setup
numOfFolds = idealOutputsCollection.Count / testDataSetLength;
if (numOfFolds > MaxNumOfFolds)
{
numOfFolds = MaxNumOfFolds;
}
}
//Create shuffled copy of the data
TimeSeriesBundle shuffledData = new TimeSeriesBundle(predictorsCollection, idealOutputsCollection);
shuffledData.Shuffle(rand);
//Data inspection, preparation of datasets and training of ReadoutUnits
//Clusters of readout units (one cluster for each output field)
for (int clusterIdx = 0; clusterIdx < _settings.ReadoutUnitCfgCollection.Count; clusterIdx++)
{
_clusterCollection[clusterIdx] = new ReadoutUnit[numOfFolds];
List <double[]> idealValueCollection = new List <double[]>(idealOutputsCollection.Count);
BinDistribution refBinDistr = null;
if (_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType == CommonEnums.TaskType.Classification)
{
//Reference binary distribution is relevant only for classification task
refBinDistr = new BinDistribution(_dataRange.Mid);
}
//Transformation to a single value vectors and data analysis
foreach (double[] idealVector in shuffledData.OutputVectorCollection)
{
double[] value = new double[1];
value[0] = idealVector[clusterIdx];
idealValueCollection.Add(value);
if (_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType == CommonEnums.TaskType.Classification)
{
//Reference binary distribution is relevant only for classification task
refBinDistr.Update(value);
}
}
List <TimeSeriesBundle> subBundleCollection = null;
//Datasets preparation is depending on the task type
if (_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType == CommonEnums.TaskType.Classification)
{
//Classification task
subBundleCollection = DivideSamplesForClassificationTask(shuffledData.InputVectorCollection,
idealValueCollection,
refBinDistr,
testDataSetLength
);
}
else
{
//Forecast task
subBundleCollection = DivideSamplesForForecastTask(shuffledData.InputVectorCollection,
idealValueCollection,
testDataSetLength
);
}
//Best predicting unit per each fold in the cluster.
ClusterErrStatistics ces = new ClusterErrStatistics(_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType, numOfFolds, refBinDistr);
int arrayPos = 0;
for (int foldIdx = 0; foldIdx < numOfFolds; foldIdx++)
{
//Build training samples
List <double[]> trainingPredictorsCollection = new List <double[]>();
List <double[]> trainingIdealValueCollection = new List <double[]>();
for (int bundleIdx = 0; bundleIdx < subBundleCollection.Count; bundleIdx++)
{
if (bundleIdx != foldIdx)
{
trainingPredictorsCollection.AddRange(subBundleCollection[bundleIdx].InputVectorCollection);
trainingIdealValueCollection.AddRange(subBundleCollection[bundleIdx].OutputVectorCollection);
}
}
//Call training regression to get the best fold's readout unit.
//The best unit becomes to be the predicting cluster member.
_clusterCollection[clusterIdx][foldIdx] = ReadoutUnit.CreateTrained(_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType,
clusterIdx,
foldIdx + 1,
numOfFolds,
refBinDistr,
trainingPredictorsCollection,
trainingIdealValueCollection,
subBundleCollection[foldIdx].InputVectorCollection,
subBundleCollection[foldIdx].OutputVectorCollection,
rand,
_settings.ReadoutUnitCfgCollection[clusterIdx],
regressionController,
regressionControllerData
);
//Cluster error statistics & data for validation bundle (pesimistic approach)
for (int sampleIdx = 0; sampleIdx < subBundleCollection[foldIdx].OutputVectorCollection.Count; sampleIdx++)
{
double value = _clusterCollection[clusterIdx][foldIdx].Network.Compute(subBundleCollection[foldIdx].InputVectorCollection[sampleIdx])[0];
ces.Update(value, subBundleCollection[foldIdx].OutputVectorCollection[sampleIdx][0]);
validationIdealVectorCollection[arrayPos][clusterIdx] = subBundleCollection[foldIdx].OutputVectorCollection[sampleIdx][0];
validationComputedVectorCollection[arrayPos][clusterIdx] = value;
++arrayPos;
}
} //foldIdx
_clusterErrStatisticsCollection.Add(ces);
} //clusterIdx
//Validation bundle is returned.
return(new ValidationBundle(validationComputedVectorCollection, validationIdealVectorCollection));
}
/// <summary>
/// Builds readout layer.
/// Prepares prediction clusters containing trained readout units.
/// </summary>
/// <param name="dataBundle">Collection of input predictors and associated desired output values</param>
/// <param name="regressionController">Regression controller delegate</param>
/// <param name="regressionControllerData">An user object</param>
/// <param name="predictorsMapper">Optional specific mapping of predictors to readout units</param>
/// <returns>Returned ResultComparativeBundle is something like a protocol.
/// There is recorded fold by fold (unit by unit) predicted and corresponding ideal values.
/// This is the pesimistic approach. Real results on unseen data could be better due to the clustering synergy.
/// </returns>
public ResultComparativeBundle Build(VectorBundle dataBundle,
ReadoutUnit.RegressionCallbackDelegate regressionController,
Object regressionControllerData,
PredictorsMapper predictorsMapper = null
)
{
//Basic checks
int numOfPredictors = dataBundle.InputVectorCollection[0].Length;
int numOfOutputs = dataBundle.OutputVectorCollection[0].Length;
if (numOfPredictors == 0)
{
throw new Exception("Number of predictors must be greater tham 0.");
}
if (numOfOutputs != _settings.ReadoutUnitCfgCollection.Count)
{
throw new Exception("Incorrect number of ideal output values in the vector.");
}
//Normalization of predictors and output data collections
//Allocation of normalizers
_predictorNormalizerCollection = new Normalizer[numOfPredictors];
for (int i = 0; i < numOfPredictors; i++)
{
_predictorNormalizerCollection[i] = new Normalizer(DataRange, NormalizerDefaultReserve, true, false);
}
_outputNormalizerCollection = new Normalizer[numOfOutputs];
for (int i = 0; i < numOfOutputs; i++)
{
bool classificationTask = (_settings.ReadoutUnitCfgCollection[i].TaskType == CommonEnums.TaskType.Classification);
_outputNormalizerCollection[i] = new Normalizer(DataRange,
classificationTask ? 0 : NormalizerDefaultReserve,
classificationTask ? false : true,
false
);
}
//Normalizers adjustment
for (int pairIdx = 0; pairIdx < dataBundle.InputVectorCollection.Count; pairIdx++)
{
//Checks
if (dataBundle.InputVectorCollection[pairIdx].Length != numOfPredictors)
{
throw new Exception("Inconsistent number of predictors in the predictors collection.");
}
if (dataBundle.OutputVectorCollection[pairIdx].Length != numOfOutputs)
{
throw new Exception("Inconsistent number of values in the ideal values collection.");
}
//Adjust predictors normalizers
for (int i = 0; i < numOfPredictors; i++)
{
_predictorNormalizerCollection[i].Adjust(dataBundle.InputVectorCollection[pairIdx][i]);
}
//Adjust outputs normalizers
for (int i = 0; i < numOfOutputs; i++)
{
_outputNormalizerCollection[i].Adjust(dataBundle.OutputVectorCollection[pairIdx][i]);
}
}
//Data normalization
//Allocation
List <double[]> predictorsCollection = new List <double[]>(dataBundle.InputVectorCollection.Count);
List <double[]> idealOutputsCollection = new List <double[]>(dataBundle.OutputVectorCollection.Count);
//Normalization
for (int pairIdx = 0; pairIdx < dataBundle.InputVectorCollection.Count; pairIdx++)
{
//Predictors
double[] predictors = new double[numOfPredictors];
for (int i = 0; i < numOfPredictors; i++)
{
predictors[i] = _predictorNormalizerCollection[i].Normalize(dataBundle.InputVectorCollection[pairIdx][i]);
}
predictorsCollection.Add(predictors);
//Outputs
double[] outputs = new double[numOfOutputs];
for (int i = 0; i < numOfOutputs; i++)
{
outputs[i] = _outputNormalizerCollection[i].Normalize(dataBundle.OutputVectorCollection[pairIdx][i]);
}
idealOutputsCollection.Add(outputs);
}
//Data processing
//Random object initialization
Random rand = new Random(0);
//Predictors mapper (specified or default)
_predictorsMapper = predictorsMapper ?? new PredictorsMapper(numOfPredictors);
//Allocation of computed and ideal vectors for result comparative bundle
List <double[]> validationComputedVectorCollection = new List <double[]>(idealOutputsCollection.Count);
List <double[]> validationIdealVectorCollection = new List <double[]>(idealOutputsCollection.Count);
for (int i = 0; i < idealOutputsCollection.Count; i++)
{
validationComputedVectorCollection.Add(new double[numOfOutputs]);
validationIdealVectorCollection.Add(new double[numOfOutputs]);
}
//Test dataset size
if (_settings.TestDataRatio > MaxRatioOfTestData)
{
throw new ArgumentException($"Test dataset size is greater than {MaxRatioOfTestData.ToString(CultureInfo.InvariantCulture)}", "TestDataSetSize");
}
int testDataSetLength = (int)Math.Round(idealOutputsCollection.Count * _settings.TestDataRatio, 0);
if (testDataSetLength < MinLengthOfTestDataset)
{
throw new ArgumentException($"Num of test samples is less than {MinLengthOfTestDataset.ToString(CultureInfo.InvariantCulture)}", "TestDataSetSize");
}
//Number of folds
int numOfFolds = _settings.NumOfFolds;
if (numOfFolds <= 0)
{
//Auto setup
numOfFolds = idealOutputsCollection.Count / testDataSetLength;
if (numOfFolds > MaxNumOfFolds)
{
numOfFolds = MaxNumOfFolds;
}
}
//Create shuffled copy of the data
VectorBundle shuffledData = new VectorBundle(predictorsCollection, idealOutputsCollection);
shuffledData.Shuffle(rand);
//Data inspection, preparation of datasets and training of ReadoutUnits
//Clusters of readout units (one cluster for each output field)
for (int clusterIdx = 0; clusterIdx < _settings.ReadoutUnitCfgCollection.Count; clusterIdx++)
{
_clusterCollection[clusterIdx] = new ReadoutUnit[numOfFolds];
List <double[]> idealValueCollection = new List <double[]>(idealOutputsCollection.Count);
BinDistribution refBinDistr = null;
if (_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType == CommonEnums.TaskType.Classification)
{
//Reference binary distribution is relevant only for classification task
refBinDistr = new BinDistribution(DataRange.Mid);
}
//Transformation to a single value vectors and data analysis
foreach (double[] idealVector in shuffledData.OutputVectorCollection)
{
double[] value = new double[1];
value[0] = idealVector[clusterIdx];
idealValueCollection.Add(value);
if (_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType == CommonEnums.TaskType.Classification)
{
//Reference binary distribution is relevant only for classification task
refBinDistr.Update(value);
}
}
List <VectorBundle> subBundleCollection = null;
List <double[]> readoutUnitInputVectorCollection = _predictorsMapper.CreateVectorCollection(_settings.ReadoutUnitCfgCollection[clusterIdx].Name, shuffledData.InputVectorCollection);
//Datasets preparation is depending on the task type
if (_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType == CommonEnums.TaskType.Classification)
{
//Classification task
subBundleCollection = DivideSamplesForClassificationTask(readoutUnitInputVectorCollection,
idealValueCollection,
refBinDistr,
testDataSetLength
);
}
else
{
//Forecast task
subBundleCollection = DivideSamplesForForecastTask(readoutUnitInputVectorCollection,
idealValueCollection,
testDataSetLength
);
}
//Find best unit per each fold in the cluster.
ClusterErrStatistics ces = new ClusterErrStatistics(_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType, numOfFolds, refBinDistr);
int arrayPos = 0;
for (int foldIdx = 0; foldIdx < numOfFolds; foldIdx++)
{
//Build training samples
List <double[]> trainingPredictorsCollection = new List <double[]>();
List <double[]> trainingIdealValueCollection = new List <double[]>();
for (int bundleIdx = 0; bundleIdx < subBundleCollection.Count; bundleIdx++)
{
if (bundleIdx != foldIdx)
{
trainingPredictorsCollection.AddRange(subBundleCollection[bundleIdx].InputVectorCollection);
trainingIdealValueCollection.AddRange(subBundleCollection[bundleIdx].OutputVectorCollection);
}
}
//Call training regression to get the best fold's readout unit.
//The best unit becomes to be the predicting cluster member.
_clusterCollection[clusterIdx][foldIdx] = ReadoutUnit.CreateTrained(_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType,
clusterIdx,
foldIdx + 1,
numOfFolds,
refBinDistr,
trainingPredictorsCollection,
trainingIdealValueCollection,
subBundleCollection[foldIdx].InputVectorCollection,
subBundleCollection[foldIdx].OutputVectorCollection,
rand,
_settings.ReadoutUnitCfgCollection[clusterIdx],
regressionController,
regressionControllerData
);
//Cluster error statistics & data for validation bundle (pesimistic approach)
for (int sampleIdx = 0; sampleIdx < subBundleCollection[foldIdx].OutputVectorCollection.Count; sampleIdx++)
{
double nrmComputedValue = _clusterCollection[clusterIdx][foldIdx].Network.Compute(subBundleCollection[foldIdx].InputVectorCollection[sampleIdx])[0];
double natComputedValue = _outputNormalizerCollection[clusterIdx].Naturalize(nrmComputedValue);
double natIdealValue = _outputNormalizerCollection[clusterIdx].Naturalize(subBundleCollection[foldIdx].OutputVectorCollection[sampleIdx][0]);
ces.Update(nrmComputedValue,
subBundleCollection[foldIdx].OutputVectorCollection[sampleIdx][0],
natComputedValue,
natIdealValue);
validationIdealVectorCollection[arrayPos][clusterIdx] = natIdealValue;
validationComputedVectorCollection[arrayPos][clusterIdx] = natComputedValue;
++arrayPos;
}
} //foldIdx
_clusterErrStatisticsCollection.Add(ces);
} //clusterIdx
//Validation bundle is returned.
return(new ResultComparativeBundle(validationComputedVectorCollection, validationIdealVectorCollection));
}