private void TestDataBundleFolderization(string dataFile, int numOfClasses)
{
//Load csv data
CsvDataHolder csvData = new CsvDataHolder(dataFile);
//Convert csv data to a VectorBundle
VectorBundle vectorData = VectorBundle.Load(csvData, numOfClasses);
double binBorder = 0.5d;
double[] foldDataRatios = { -1d, 0d, 0.1d, 0.5d, 0.75d, 1d, 2d };
Console.WriteLine($"Folderization test of {dataFile}. NumOfSamples={vectorData.InputVectorCollection.Count.ToString(CultureInfo.InvariantCulture)}, NumOfFoldDataRatios={foldDataRatios.Length.ToString(CultureInfo.InvariantCulture)}");
foreach (double foldDataRatio in foldDataRatios)
{
Console.WriteLine($" Testing fold data ratio = {foldDataRatio.ToString(CultureInfo.InvariantCulture)}");
List <VectorBundle> folds = vectorData.Folderize(foldDataRatio, binBorder);
Console.WriteLine($" Number of resulting folds = {folds.Count.ToString(CultureInfo.InvariantCulture)}");
for (int foldIdx = 0; foldIdx < folds.Count; foldIdx++)
{
int numOfFoldSamples = folds[foldIdx].InputVectorCollection.Count;
Console.WriteLine($" FoldIdx={foldIdx.ToString(CultureInfo.InvariantCulture),-4} FoldSize={numOfFoldSamples.ToString(CultureInfo.InvariantCulture),-4}");
int[] classesBin1Counts = new int[numOfClasses];
classesBin1Counts.Populate(0);
for (int sampleIdx = 0; sampleIdx < numOfFoldSamples; sampleIdx++)
{
for (int classIdx = 0; classIdx < numOfClasses; classIdx++)
{
if (folds[foldIdx].OutputVectorCollection[sampleIdx][classIdx] >= binBorder)
{
++classesBin1Counts[classIdx];
}
}
}
Console.WriteLine($" Number of positive samples per class");
for (int classIdx = 0; classIdx < numOfClasses; classIdx++)
{
Console.WriteLine($" ClassID={classIdx.ToString(CultureInfo.InvariantCulture),-3}, Bin1Samples={classesBin1Counts[classIdx].ToString(CultureInfo.InvariantCulture)}");
}
}
Console.ReadLine();
}
return;
}
/// <summary>
/// Builds the cluster chain.
/// </summary>
/// <param name="dataBundle">The data bundle for training.</param>
/// <param name="filters">The filters to be used to denormalize outputs.</param>
public TNRNetClusterChain Build(VectorBundle dataBundle, FeatureFilterBase[] filters)
{
//The chain to be built
TNRNetClusterChain chain = new TNRNetClusterChain(_chainName, _clusterChainCfg.Output);
//Instantiate chained clusters
List <TNRNetCluster> chainClusters = new List <TNRNetCluster>(_clusterChainCfg.ClusterCfgCollection.Count);
for (int clusterIdx = 0; clusterIdx < _clusterChainCfg.ClusterCfgCollection.Count; clusterIdx++)
{
//Cluster
chainClusters.Add(new TNRNetCluster(_chainName,
_clusterChainCfg.ClusterCfgCollection[clusterIdx].Output,
_clusterChainCfg.ClusterCfgCollection[clusterIdx].TrainingGroupWeight,
_clusterChainCfg.ClusterCfgCollection[clusterIdx].TestingGroupWeight,
_clusterChainCfg.ClusterCfgCollection[clusterIdx].SamplesWeight,
_clusterChainCfg.ClusterCfgCollection[clusterIdx].NumericalPrecisionWeight,
_clusterChainCfg.ClusterCfgCollection[clusterIdx].MisrecognizedFalseWeight,
_clusterChainCfg.ClusterCfgCollection[clusterIdx].UnrecognizedTrueWeight
)
);
}
//Common crossvalidation configuration
double boolBorder = _clusterChainCfg.Output == TNRNet.OutputType.Real ? double.NaN : chain.OutputDataRange.Mid;
VectorBundle localDataBundle = dataBundle.CreateShallowCopy();
//Member's training
ResetProgressTracking();
for (_repetitionIdx = 0; _repetitionIdx < _clusterChainCfg.CrossvalidationCfg.Repetitions; _repetitionIdx++)
{
//Split data to folds
List <VectorBundle> foldCollection = localDataBundle.Folderize(_clusterChainCfg.CrossvalidationCfg.FoldDataRatio, boolBorder);
_numOfFoldsPerRepetition = Math.Min(_clusterChainCfg.CrossvalidationCfg.Folds <= 0 ? foldCollection.Count : _clusterChainCfg.CrossvalidationCfg.Folds, foldCollection.Count);
List <VectorBundle> currentClusterFoldCollection = CopyFolds(foldCollection);
List <VectorBundle> nextClusterFoldCollection = new List <VectorBundle>(foldCollection.Count);
//For each cluster
for (_clusterIdx = 0; _clusterIdx < chainClusters.Count; _clusterIdx++)
{
//Train networks for each testing fold.
for (_testingFoldIdx = 0; _testingFoldIdx < _numOfFoldsPerRepetition; _testingFoldIdx++)
{
//Prepare training data bundle
VectorBundle trainingData = new VectorBundle();
for (int foldIdx = 0; foldIdx < currentClusterFoldCollection.Count; foldIdx++)
{
if (foldIdx != _testingFoldIdx)
{
trainingData.Add(currentClusterFoldCollection[foldIdx]);
}
}
VectorBundle nextClusterUpdatedDataFold = foldCollection[_testingFoldIdx].CreateShallowCopy();
for (_netCfgIdx = 0; _netCfgIdx < _clusterChainCfg.ClusterCfgCollection[_clusterIdx].ClusterNetConfigurations.Count; _netCfgIdx++)
{
TNRNetBuilder netBuilder = new TNRNetBuilder(_chainName,
_clusterChainCfg.ClusterCfgCollection[_clusterIdx].ClusterNetConfigurations[_netCfgIdx],
_clusterChainCfg.ClusterCfgCollection[_clusterIdx].Output,
trainingData,
currentClusterFoldCollection[_testingFoldIdx],
_rand,
_controller
);
//Register notification
netBuilder.NetworkBuildProgressChanged += OnNetworkBuildProgressChanged;
//Build trained network. Trained network becomes to be the cluster member
TNRNet tn = netBuilder.Build();
int netScopeID = _repetitionIdx * NetScopeDelimiterCoeff + _testingFoldIdx;
chainClusters[_clusterIdx].AddMember(tn, netScopeID, currentClusterFoldCollection[_testingFoldIdx], filters);
//Update input data in the data fold for the next cluster
for (int sampleIdx = 0; sampleIdx < currentClusterFoldCollection[_testingFoldIdx].InputVectorCollection.Count; sampleIdx++)
{
double[] computedNetData = tn.Network.Compute(currentClusterFoldCollection[_testingFoldIdx].InputVectorCollection[sampleIdx]);
nextClusterUpdatedDataFold.InputVectorCollection[sampleIdx] = nextClusterUpdatedDataFold.InputVectorCollection[sampleIdx].Concat(computedNetData);
}
}//netCfgIdx
//Add updated data fold for the next cluster
nextClusterFoldCollection.Add(nextClusterUpdatedDataFold);
}//testingFoldIdx
//Switch fold collection
currentClusterFoldCollection = nextClusterFoldCollection;
nextClusterFoldCollection = new List <VectorBundle>(currentClusterFoldCollection.Count);
}//clusterIdx
if (_repetitionIdx < _clusterChainCfg.CrossvalidationCfg.Repetitions - 1)
{
//Reshuffle the data
localDataBundle.Shuffle(_rand);
}
}//repetitionIdx
//Make the clusters operable and add them into the chain
for (int clusterIdx = 0; clusterIdx < chainClusters.Count; clusterIdx++)
{
chainClusters[clusterIdx].FinalizeCluster();
chain.AddCluster(chainClusters[clusterIdx]);
}
//Return the built chain
return(chain);
}
/// <summary>
/// Builds the cluster.
/// </summary>
/// <param name="dataBundle">The data bundle for training.</param>
/// <param name="filters">The filters to be used to denormalize outputs.</param>
public TNRNetCluster Build(VectorBundle dataBundle, FeatureFilterBase[] filters)
{
VectorBundle localDataBundle = dataBundle.CreateShallowCopy();
//Cluster of trained networks
TNRNetCluster cluster = new TNRNetCluster(_clusterName,
_clusterCfg.Output,
_clusterCfg.TrainingGroupWeight,
_clusterCfg.TestingGroupWeight,
_clusterCfg.SamplesWeight,
_clusterCfg.NumericalPrecisionWeight,
_clusterCfg.MisrecognizedFalseWeight,
_clusterCfg.UnrecognizedTrueWeight
);
//Member's training
ResetProgressTracking();
for (_repetitionIdx = 0; _repetitionIdx < _crossvalidationCfg.Repetitions; _repetitionIdx++)
{
//Data split to folds
List <VectorBundle> foldCollection = localDataBundle.Folderize(_crossvalidationCfg.FoldDataRatio, _clusterCfg.Output == TNRNet.OutputType.Real ? double.NaN : cluster.OutputDataRange.Mid);
_numOfFoldsPerRepetition = Math.Min(_crossvalidationCfg.Folds <= 0 ? foldCollection.Count : _crossvalidationCfg.Folds, foldCollection.Count);
//Train the collection of networks for each processing fold.
for (_testingFoldIdx = 0; _testingFoldIdx < _numOfFoldsPerRepetition; _testingFoldIdx++)
{
//Prepare training data bundle
VectorBundle trainingData = new VectorBundle();
for (int foldIdx = 0; foldIdx < foldCollection.Count; foldIdx++)
{
if (foldIdx != _testingFoldIdx)
{
trainingData.Add(foldCollection[foldIdx]);
}
}
for (_netCfgIdx = 0; _netCfgIdx < _clusterCfg.ClusterNetConfigurations.Count; _netCfgIdx++)
{
TNRNetBuilder netBuilder = new TNRNetBuilder(_clusterName,
_clusterCfg.ClusterNetConfigurations[_netCfgIdx],
_clusterCfg.Output,
trainingData,
foldCollection[_testingFoldIdx],
_rand,
_controller
);
//Register notification
netBuilder.NetworkBuildProgressChanged += OnNetworkBuildProgressChanged;
//Build trained network. Trained network becomes to be the cluster member
TNRNet tn = netBuilder.Build();
//Build an unique network scope identifier
int netScopeID = _repetitionIdx * NetScopeDelimiterCoeff + _testingFoldIdx;
//Add trained network to a cluster
cluster.AddMember(tn, netScopeID, foldCollection[_testingFoldIdx], filters);
} //netCfgIdx
} //testingFoldIdx
if (_repetitionIdx < _crossvalidationCfg.Repetitions - 1)
{
//Reshuffle the data
localDataBundle.Shuffle(_rand);
}
}//repetitionIdx
//Make the cluster operable
cluster.FinalizeCluster();
//Return the built cluster
return(cluster);
}