/// <summary>
/// The default implementation of a judgement if the current readout unit is better than for now the best readout unit
/// </summary>
/// <param name="taskType">Type of the task</param>
/// <param name="current">Current readout unit</param>
/// <param name="best">For now the best readout unit</param>
public static bool IsBetter(CommonEnums.TaskType taskType, ReadoutUnit current, ReadoutUnit best)
{
switch (taskType)
{
case CommonEnums.TaskType.Classification:
if (current.CombinedBinaryError < best.CombinedBinaryError)
{
return(true);
}
else if (current.CombinedBinaryError == best.CombinedBinaryError)
{
if (current.TestingBinErrorStat.TotalErrStat.Sum < best.TestingBinErrorStat.TotalErrStat.Sum)
{
return(true);
}
else if (current.TrainingBinErrorStat.TotalErrStat.Sum < best.TrainingBinErrorStat.TotalErrStat.Sum)
{
return(true);
}
else if (current.CombinedPrecisionError < best.CombinedPrecisionError)
{
return(true);
}
}
return(false);
default:
//Forecast task type
return(current.CombinedPrecisionError < best.CombinedPrecisionError);
}
}
/// <summary>
/// Resets the readout layer to its initial untrained state.
/// </summary>
public void Reset()
{
_predictorFeatureFilterCollection = null;
_outputFeatureFilterCollection = null;
_predictorsMapper = null;
_readoutUnitCollection = new ReadoutUnit[ReadoutLayerCfg.ReadoutUnitsCfg.ReadoutUnitCfgCollection.Count];
for (int i = 0; i < ReadoutLayerCfg.ReadoutUnitsCfg.ReadoutUnitCfgCollection.Count; i++)
{
ReadoutUnitSettings cfg = ReadoutLayerCfg.ReadoutUnitsCfg.ReadoutUnitCfgCollection[i];
_readoutUnitCollection[i] = new ReadoutUnit(i, cfg, ReadoutLayerCfg.TaskDefaultsCfg);
}
_oneTakesAllGroupCollection = null;
if (ReadoutLayerCfg.OneTakesAllGroupsCfg != null)
{
_oneTakesAllGroupCollection = new OneTakesAllGroup[ReadoutLayerCfg.OneTakesAllGroupsCfg.OneTakesAllGroupCfgCollection.Count];
for (int i = 0; i < ReadoutLayerCfg.OneTakesAllGroupsCfg.OneTakesAllGroupCfgCollection.Count; i++)
{
OneTakesAllGroupSettings cfg = ReadoutLayerCfg.OneTakesAllGroupsCfg.OneTakesAllGroupCfgCollection[i];
_oneTakesAllGroupCollection[i] = new OneTakesAllGroup(i, cfg, ReadoutLayerCfg.GetOneTakesAllGroupMemberRUnitIndexes(cfg.Name));
}
}
Trained = false;
ResetProgressTracking();
return;
}
//Static methods
/// <summary>
/// Builds report string containing information about the regression progress.
/// It is usually called from the RegressionControl user implementation.
/// </summary>
/// <param name="inArgs">>Contains all the necessary information to control the regression.</param>
/// <param name="bestReadoutUnit">Currently the best readout unit.</param>
/// <param name="margin">Specifies how many spaces to be at the begining of the row.</param>
/// <returns>Built text report</returns>
public static string GetProgressReport(ReadoutUnit.RegressionControlInArgs inArgs,
ReadoutUnit bestReadoutUnit,
int margin = 0
)
{
//Build progress text message
StringBuilder progressText = new StringBuilder();
progressText.Append(new string(' ', margin));
progressText.Append("OutputField: ");
progressText.Append(inArgs.OutputFieldName);
progressText.Append(", Fold/Attempt/Epoch: ");
progressText.Append(inArgs.FoldNum.ToString().PadLeft(inArgs.NumOfFolds.ToString().Length, '0') + "/");
progressText.Append(inArgs.RegrAttemptNumber.ToString().PadLeft(inArgs.RegrMaxAttempts.ToString().Length, '0') + "/");
progressText.Append(inArgs.Epoch.ToString().PadLeft(inArgs.MaxEpochs.ToString().Length, '0'));
progressText.Append(", DSet-Sizes: (");
progressText.Append(inArgs.CurrReadoutUnit.TrainingErrorStat.NumOfSamples.ToString() + ", ");
progressText.Append(inArgs.CurrReadoutUnit.TestingErrorStat.NumOfSamples.ToString() + ")");
progressText.Append(", Best-Train: ");
progressText.Append(bestReadoutUnit.TrainingErrorStat.ArithAvg.ToString("E3", CultureInfo.InvariantCulture));
if (inArgs.TaskType == CommonEnums.TaskType.Classification)
{
//Append binary errors
progressText.Append("/" + bestReadoutUnit.TrainingBinErrorStat.TotalErrStat.Sum.ToString(CultureInfo.InvariantCulture));
progressText.Append("/" + bestReadoutUnit.TrainingBinErrorStat.BinValErrStat[1].Sum.ToString(CultureInfo.InvariantCulture));
}
progressText.Append(", Best-Test: ");
progressText.Append(bestReadoutUnit.TestingErrorStat.ArithAvg.ToString("E3", CultureInfo.InvariantCulture));
if (inArgs.TaskType == CommonEnums.TaskType.Classification)
{
//Append binary errors
progressText.Append("/" + bestReadoutUnit.TestingBinErrorStat.TotalErrStat.Sum.ToString(CultureInfo.InvariantCulture));
progressText.Append("/" + bestReadoutUnit.TestingBinErrorStat.BinValErrStat[1].Sum.ToString(CultureInfo.InvariantCulture));
}
progressText.Append(", Curr-Train: ");
progressText.Append(inArgs.CurrReadoutUnit.TrainingErrorStat.ArithAvg.ToString("E3", CultureInfo.InvariantCulture));
if (inArgs.TaskType == CommonEnums.TaskType.Classification)
{
//Append binary errors
progressText.Append("/" + inArgs.CurrReadoutUnit.TrainingBinErrorStat.TotalErrStat.Sum.ToString(CultureInfo.InvariantCulture));
progressText.Append("/" + inArgs.CurrReadoutUnit.TrainingBinErrorStat.BinValErrStat[1].Sum.ToString(CultureInfo.InvariantCulture));
}
progressText.Append(", Curr-Test: ");
progressText.Append(inArgs.CurrReadoutUnit.TestingErrorStat.ArithAvg.ToString("E3", CultureInfo.InvariantCulture));
if (inArgs.TaskType == CommonEnums.TaskType.Classification)
{
//Append binary errors
progressText.Append("/" + inArgs.CurrReadoutUnit.TestingBinErrorStat.TotalErrStat.Sum.ToString(CultureInfo.InvariantCulture));
progressText.Append("/" + inArgs.CurrReadoutUnit.TestingBinErrorStat.BinValErrStat[1].Sum.ToString(CultureInfo.InvariantCulture));
}
progressText.Append($" [{bestReadoutUnit.TrainerInfoMessage}]");
return(progressText.ToString());
}
/// <summary>
/// The deep copy constructor.
/// </summary>
/// <param name="source">Source instance</param>
public ReadoutUnit(ReadoutUnit source)
{
Network = null;
if (source.Network != null)
{
Network = source.Network.DeepClone();
}
TrainerInfoMessage = source.TrainerInfoMessage;
TrainingErrorStat = null;
if (source.TrainingErrorStat != null)
{
TrainingErrorStat = new BasicStat(source.TrainingErrorStat);
}
TrainingBinErrorStat = null;
if (source.TrainingBinErrorStat != null)
{
TrainingBinErrorStat = new BinErrStat(source.TrainingBinErrorStat);
}
TestingErrorStat = null;
if (source.TestingErrorStat != null)
{
TestingErrorStat = new BasicStat(source.TestingErrorStat);
}
TestingBinErrorStat = null;
if (source.TestingBinErrorStat != null)
{
TestingBinErrorStat = new BinErrStat(source.TestingBinErrorStat);
}
OutputWeightsStat = null;
if (source.OutputWeightsStat != null)
{
OutputWeightsStat = new BasicStat(source.OutputWeightsStat);
}
CombinedPrecisionError = source.CombinedPrecisionError;
CombinedBinaryError = source.CombinedBinaryError;
return;
}
/// <summary>
/// Prepares trained readout unit for specified output field and task.
/// </summary>
/// <param name="taskType">Type of the task</param>
/// <param name="readoutUnitIdx">Index of the readout unit (informative only)</param>
/// <param name="foldNum">Current fold number</param>
/// <param name="numOfFolds">Total number of the folds</param>
/// <param name="refBinDistr">Reference bin distribution (if task type is Classification)</param>
/// <param name="trainingPredictorsCollection">Collection of the predictors for training</param>
/// <param name="trainingIdealOutputsCollection">Collection of ideal outputs for training. Note that the double array always has only one member.</param>
/// <param name="testingPredictorsCollection">Collection of the predictors for testing</param>
/// <param name="testingIdealOutputsCollection">Collection of ideal outputs for testing. Note that the double array always has only one member.</param>
/// <param name="rand">Random object to be used</param>
/// <param name="readoutUnitSettings">Readout unit configuration parameters</param>
/// <param name="controller">Regression controller</param>
/// <param name="controllerUserObject">An user object to be passed to controller</param>
/// <returns>Prepared readout unit</returns>
public static ReadoutUnit CreateTrained(CommonEnums.TaskType taskType,
int readoutUnitIdx,
int foldNum,
int numOfFolds,
BinDistribution refBinDistr,
List <double[]> trainingPredictorsCollection,
List <double[]> trainingIdealOutputsCollection,
List <double[]> testingPredictorsCollection,
List <double[]> testingIdealOutputsCollection,
Random rand,
ReadoutLayerSettings.ReadoutUnitSettings readoutUnitSettings,
RegressionCallbackDelegate controller = null,
Object controllerUserObject = null
)
{
ReadoutUnit bestReadoutUnit = null;
//Regression attempts
bool stopRegression = false;
for (int regrAttemptNumber = 1; regrAttemptNumber <= readoutUnitSettings.RegressionAttempts; regrAttemptNumber++)
{
//Create network and trainer
CreateNetAndTreainer(readoutUnitSettings,
trainingPredictorsCollection,
trainingIdealOutputsCollection,
rand,
out INonRecurrentNetwork net,
out INonRecurrentNetworkTrainer trainer
);
//Reference binary distribution
//Iterate training cycles
for (int epoch = 1; epoch <= readoutUnitSettings.RegressionAttemptEpochs; epoch++)
{
trainer.Iteration();
List <double[]> testingComputedOutputsCollection = null;
//Compute current error statistics after training iteration
ReadoutUnit currReadoutUnit = new ReadoutUnit();
currReadoutUnit.Network = net;
currReadoutUnit.TrainingErrorStat = net.ComputeBatchErrorStat(trainingPredictorsCollection, trainingIdealOutputsCollection, out List <double[]> trainingComputedOutputsCollection);
if (taskType == CommonEnums.TaskType.Classification)
{
currReadoutUnit.TrainingBinErrorStat = new BinErrStat(refBinDistr, trainingComputedOutputsCollection, trainingIdealOutputsCollection);
currReadoutUnit.CombinedBinaryError = currReadoutUnit.TrainingBinErrorStat.TotalErrStat.Sum;
//currReadoutUnit.CombinedBinaryError = currReadoutUnit.TrainingBinErrorStat.ProportionalErr;
}
currReadoutUnit.CombinedPrecisionError = currReadoutUnit.TrainingErrorStat.ArithAvg;
if (testingPredictorsCollection != null && testingPredictorsCollection.Count > 0)
{
currReadoutUnit.TestingErrorStat = net.ComputeBatchErrorStat(testingPredictorsCollection, testingIdealOutputsCollection, out testingComputedOutputsCollection);
currReadoutUnit.CombinedPrecisionError = Math.Max(currReadoutUnit.CombinedPrecisionError, currReadoutUnit.TestingErrorStat.ArithAvg);
if (taskType == CommonEnums.TaskType.Classification)
{
currReadoutUnit.TestingBinErrorStat = new BinErrStat(refBinDistr, testingComputedOutputsCollection, testingIdealOutputsCollection);
currReadoutUnit.CombinedBinaryError = Math.Max(currReadoutUnit.CombinedBinaryError, currReadoutUnit.TestingBinErrorStat.TotalErrStat.Sum);
//currReadoutUnit.CombinedBinaryError = Math.Max(currReadoutUnit.CombinedBinaryError, currReadoutUnit.TestingBinErrorStat.ProportionalErr);
}
}
//Current results processing
bool better = false, stopTrainingCycle = false;
//Result first initialization
if (bestReadoutUnit == null)
{
//Adopt current regression results
bestReadoutUnit = currReadoutUnit.DeepClone();
}
//Perform call back if it is defined
if (controller != null)
{
//Evaluation of the improvement is driven externally
RegressionControlInArgs cbIn = new RegressionControlInArgs
{
TaskType = taskType,
ReadoutUnitIdx = readoutUnitIdx,
OutputFieldName = readoutUnitSettings.Name,
FoldNum = foldNum,
NumOfFolds = numOfFolds,
RegrAttemptNumber = regrAttemptNumber,
RegrMaxAttempts = readoutUnitSettings.RegressionAttempts,
Epoch = epoch,
MaxEpochs = readoutUnitSettings.RegressionAttemptEpochs,
TrainingPredictorsCollection = trainingPredictorsCollection,
TrainingIdealOutputsCollection = trainingIdealOutputsCollection,
TrainingComputedOutputsCollection = trainingComputedOutputsCollection,
TestingPredictorsCollection = testingPredictorsCollection,
TestingIdealOutputsCollection = testingIdealOutputsCollection,
TestingComputedOutputsCollection = testingComputedOutputsCollection,
CurrReadoutUnit = currReadoutUnit,
BestReadoutUnit = bestReadoutUnit,
UserObject = controllerUserObject
};
//Call external controller
RegressionControlOutArgs cbOut = controller(cbIn);
//Pick up results
better = cbOut.CurrentIsBetter;
stopTrainingCycle = cbOut.StopCurrentAttempt;
stopRegression = cbOut.StopRegression;
}
else
{
//Default implementation
better = IsBetter(taskType, currReadoutUnit, bestReadoutUnit);
}
//Best?
if (better)
{
//Adopt current regression results
bestReadoutUnit = currReadoutUnit.DeepClone();
}
//Training stop conditions
if (stopTrainingCycle || stopRegression)
{
break;
}
}//epoch
//Regression stop conditions
if (stopRegression)
{
break;
}
}//regrAttemptNumber
//Create statistics of the best network weights
bestReadoutUnit.OutputWeightsStat = bestReadoutUnit.Network.ComputeWeightsStat();
return(bestReadoutUnit);
}
/// <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 trained readout layer.
/// </summary>
/// <param name="dataBundle">Collection of input predictors and associated desired output values</param>
/// <param name="predictorsMapper">Optional specific mapping of predictors to readout units</param>
/// <param name="controller">Optional external regression controller</param>
/// <returns>Results of the regression</returns>
public RegressionOverview Build(VectorBundle dataBundle,
PredictorsMapper predictorsMapper = null,
TrainedNetworkBuilder.RegressionControllerDelegate controller = null
)
{
//Basic checks
int numOfPredictors = dataBundle.InputVectorCollection[0].Length;
int numOfOutputs = dataBundle.OutputVectorCollection[0].Length;
if (numOfPredictors == 0)
{
throw new InvalidOperationException($"Number of predictors must be greater tham 0.");
}
if (numOfOutputs != Settings.ReadoutUnitsCfg.ReadoutUnitCfgCollection.Count)
{
throw new InvalidOperationException($"Incorrect length of output vectors.");
}
//Predictors mapper (specified or default)
_predictorsMapper = predictorsMapper ?? new PredictorsMapper(numOfPredictors);
//Allocation and preparation of feature filters
//Predictors
_predictorFeatureFilterCollection = new FeatureFilterBase[numOfPredictors];
Parallel.For(0, _predictorFeatureFilterCollection.Length, nrmIdx =>
{
_predictorFeatureFilterCollection[nrmIdx] = new RealFeatureFilter(DataRange, true, true);
for (int pairIdx = 0; pairIdx < dataBundle.InputVectorCollection.Count; pairIdx++)
{
//Adjust filter
_predictorFeatureFilterCollection[nrmIdx].Update(dataBundle.InputVectorCollection[pairIdx][nrmIdx]);
}
});
//Output values
_outputFeatureFilterCollection = new FeatureFilterBase[numOfOutputs];
Parallel.For(0, _outputFeatureFilterCollection.Length, nrmIdx =>
{
_outputFeatureFilterCollection[nrmIdx] = FeatureFilterFactory.Create(DataRange, Settings.ReadoutUnitsCfg.ReadoutUnitCfgCollection[nrmIdx].TaskCfg.FeatureFilterCfg);
for (int pairIdx = 0; pairIdx < dataBundle.OutputVectorCollection.Count; pairIdx++)
{
//Adjust output normalizer
_outputFeatureFilterCollection[nrmIdx].Update(dataBundle.OutputVectorCollection[pairIdx][nrmIdx]);
}
});
//Data normalization
//Allocation
double[][] normalizedPredictorsCollection = new double[dataBundle.InputVectorCollection.Count][];
double[][] normalizedIdealOutputsCollection = new double[dataBundle.OutputVectorCollection.Count][];
//Normalization
Parallel.For(0, dataBundle.InputVectorCollection.Count, pairIdx =>
{
//Predictors
double[] predictors = new double[numOfPredictors];
for (int i = 0; i < numOfPredictors; i++)
{
if (_predictorsMapper.PredictorGeneralSwitchCollection[i])
{
predictors[i] = _predictorFeatureFilterCollection[i].ApplyFilter(dataBundle.InputVectorCollection[pairIdx][i]);
}
else
{
predictors[i] = double.NaN;
}
}
normalizedPredictorsCollection[pairIdx] = predictors;
//Outputs
double[] outputs = new double[numOfOutputs];
for (int i = 0; i < numOfOutputs; i++)
{
outputs[i] = _outputFeatureFilterCollection[i].ApplyFilter(dataBundle.OutputVectorCollection[pairIdx][i]);
}
normalizedIdealOutputsCollection[pairIdx] = outputs;
});
//Random object initialization
Random rand = new Random(0);
//Create shuffled copy of the data
VectorBundle shuffledData = new VectorBundle(normalizedPredictorsCollection, normalizedIdealOutputsCollection);
shuffledData.Shuffle(rand);
//Building of readout units
for (int unitIdx = 0; unitIdx < Settings.ReadoutUnitsCfg.ReadoutUnitCfgCollection.Count; unitIdx++)
{
List <double[]> idealValueCollection = new List <double[]>(shuffledData.OutputVectorCollection.Count);
//Transformation of ideal vectors to a single value vectors
foreach (double[] idealVector in shuffledData.OutputVectorCollection)
{
double[] value = new double[1];
value[0] = idealVector[unitIdx];
idealValueCollection.Add(value);
}
List <double[]> readoutUnitInputVectorCollection = _predictorsMapper.CreateVectorCollection(Settings.ReadoutUnitsCfg.ReadoutUnitCfgCollection[unitIdx].Name, shuffledData.InputVectorCollection);
VectorBundle readoutUnitDataBundle = new VectorBundle(readoutUnitInputVectorCollection, idealValueCollection);
TrainedNetworkClusterBuilder readoutUnitBuilder = new TrainedNetworkClusterBuilder(Settings.ReadoutUnitsCfg.ReadoutUnitCfgCollection[unitIdx].Name,
Settings.GetReadoutUnitNetworksCollection(unitIdx),
DataRange,
Settings.ReadoutUnitsCfg.ReadoutUnitCfgCollection[unitIdx].TaskCfg.Type == ReadoutUnit.TaskType.Classification ? BinBorder : double.NaN,
rand,
controller
);
//Register notification
readoutUnitBuilder.RegressionEpochDone += OnRegressionEpochDone;
//Build trained readout unit. Trained unit becomes to be the predicting cluster member
_readoutUnitCollection[unitIdx] = new ReadoutUnit(unitIdx,
readoutUnitBuilder.Build(readoutUnitDataBundle,
Settings.TestDataRatio,
Settings.Folds,
Settings.Repetitions,
new FeatureFilterBase[] { _outputFeatureFilterCollection[unitIdx] }
)
);
}//unitIdx
//Readout layer is trained and ready
Trained = true;
return(new RegressionOverview(ReadoutUnitErrStatCollection));
}
/// <summary>
/// The deep copy constructor.
/// </summary>
/// <param name="source">Source instance</param>
public ReadoutUnit(ReadoutUnit source)
{
Index = source.Index;
NetworkCluster = source.NetworkCluster.DeepClone();
return;
}
/// <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));
}
