/// <summary>
/// Normalizes all values in the sample data bundle
/// </summary>
/// <param name="bundle">Sample data bundle</param>
public void Normalize(VectorBundle bundle)
{
AdjustNormalizers(bundle);
NormalizeInputVectorCollection(bundle.InputVectorCollection);
NormalizeOutputVectorCollection(bundle.OutputVectorCollection);
return;
}
/// <summary>
/// Loads the vector bundle from the csv data (patterned input feeding).
/// </summary>
/// <param name="csvData">The csv data.</param>
/// <param name="numOfOutputFields">The number of output fields.</param>
public static VectorBundle Load(CsvDataHolder csvData, int numOfOutputFields)
{
VectorBundle bundle = new VectorBundle();
foreach (DelimitedStringValues dataRow in csvData.DataRowCollection)
{
int numOfInputValues = dataRow.NumOfStringValues - numOfOutputFields;
//Check data length
if (numOfInputValues <= 0)
{
throw new ArgumentException("Incorrect length of data row.", "csvData");
}
//Input data
double[] inputData = new double[numOfInputValues];
for (int i = 0; i < numOfInputValues; i++)
{
inputData[i] = dataRow.GetValueAt(i).ParseDouble(true, $"Can't parse double data value {dataRow.GetValueAt(i)}.");
}
//Output data
double[] outputData = new double[numOfOutputFields];
for (int i = 0; i < numOfOutputFields; i++)
{
outputData[i] = dataRow.GetValueAt(numOfInputValues + i).ParseDouble(true, $"Can't parse double data value {dataRow.GetValueAt(numOfInputValues + i)}.");
}
bundle.AddPair(inputData, outputData);
}
return(bundle);
}
/// <summary>
/// Adjusts internal normalizers
/// </summary>
/// <param name="bundle">Sample data bundle</param>
public void AdjustNormalizers(VectorBundle bundle)
{
ResetNormalizers();
foreach (double[] inputVector in bundle.InputVectorCollection)
{
AdjustInputNormalizers(inputVector);
}
foreach (double[] outputVector in bundle.OutputVectorCollection)
{
AdjustOutputNormalizers(outputVector);
}
return;
}
//Static methods
/// <summary>
/// Loads the data and prepares TimeSeriesBundle.
/// The first line of the csv file must contain field names. These field names must
/// match the names of the input and output fields.
/// </summary>
/// <param name="fileName"> Data file name </param>
/// <param name="inputFieldNameCollection"> Input fields to be extracted from a file</param>
/// <param name="outputFieldNameCollection"> Output fields to be extracted from a file</param>
/// <param name="remainingInputVector"> Returned the last input vector unused in the bundle </param>
public static VectorBundle LoadFromCsv(string fileName,
List <string> inputFieldNameCollection,
List <string> outputFieldNameCollection,
out double[] remainingInputVector
)
{
VectorBundle bundle = null;
remainingInputVector = null;
using (StreamReader streamReader = new StreamReader(new FileStream(fileName, FileMode.Open)))
{
List <int> inputFieldIndexes = new List <int>();
List <int> outputFieldIndexes = new List <int>();
//First row contains column names (data fields)
string delimitedColumnNames = streamReader.ReadLine();
//What data delimiter is used?
char csvDelimiter = DelimitedStringValues.RecognizeDelimiter(delimitedColumnNames);
//Split column names
DelimitedStringValues columnNames = new DelimitedStringValues(csvDelimiter);
columnNames.LoadFromString(delimitedColumnNames);
//Check if the recognized data delimiter works properly
if (columnNames.NumOfStringValues < inputFieldNameCollection.Count)
{
throw new FormatException("1st row of the file doesn't contain delimited column names or the value delimiter was not properly recognized.");
}
//Collect indexes of allowed fields
foreach (string name in inputFieldNameCollection)
{
inputFieldIndexes.Add(columnNames.IndexOf(name));
}
for (int i = 0; i < outputFieldNameCollection.Count; i++)
{
outputFieldIndexes.Add(columnNames.IndexOf(outputFieldNameCollection[i]));
}
//Load full data in string form
List <DelimitedStringValues> fullData = new List <DelimitedStringValues>();
while (!streamReader.EndOfStream)
{
DelimitedStringValues row = new DelimitedStringValues(csvDelimiter);
row.LoadFromString(streamReader.ReadLine());
fullData.Add(row);
}
//Prepare input and output vectors
List <double[]> inputVectorCollection = new List <double[]>(fullData.Count);
List <double[]> outputVectorCollection = new List <double[]>(fullData.Count);
for (int i = 0; i < fullData.Count; i++)
{
//Input vector
double[] inputVector = new double[inputFieldIndexes.Count];
for (int j = 0; j < inputFieldIndexes.Count; j++)
{
inputVector[j] = fullData[i].GetValue(inputFieldIndexes[j]).ParseDouble(true, $"Can't parse double value {fullData[i].GetValue(inputFieldIndexes[j])}.");
}
if (i < fullData.Count - 1)
{
//Within the bundle
inputVectorCollection.Add(inputVector);
}
else
{
//remaining input vector out of the bundle
remainingInputVector = inputVector;
}
if (i > 0)
{
//Output vector
double[] outputVector = new double[outputFieldIndexes.Count];
for (int j = 0; j < outputFieldIndexes.Count; j++)
{
outputVector[j] = fullData[i].GetValue(outputFieldIndexes[j]).ParseDouble(true, $"Can't parse double value {fullData[i].GetValue(outputFieldIndexes[j])}.");
}
outputVectorCollection.Add(outputVector);
}
}
//Create bundle
bundle = new VectorBundle(inputVectorCollection, outputVectorCollection);
}
return(bundle);
} //LoadFromCsv
/// <summary>
/// Naturalizes all values in the sample data bundle
/// </summary>
/// <param name="bundle">Sample data bundle</param>
public void Naturalize(VectorBundle bundle)
{
NaturalizeInputVectorCollection(bundle.InputVectorCollection);
NaturalizeOutputVectorCollection(bundle.OutputVectorCollection);
return;
}
/// <summary>
/// Splits this bundle to a collection of smaller folds (sub-bundles) suitable for the cross-validation.
/// </summary>
/// <param name="foldDataRatio">The requested ratio of the samples constituting the single fold (sub-bundle).</param>
/// <param name="binBorder">When the binBorder is specified then all the output features are considered as binary features within the one-takes-all group and function then keeps balanced ratios of 0 and 1 for every output feature and the fold.</param>
/// <returns>A collection of the created folds.</returns>
public List <VectorBundle> Folderize(double foldDataRatio, double binBorder = double.NaN)
{
if (OutputVectorCollection.Count < 2)
{
throw new InvalidOperationException($"Insufficient number of samples ({OutputVectorCollection.Count.ToString(CultureInfo.InvariantCulture)}).");
}
List <VectorBundle> foldCollection = new List <VectorBundle>();
//Fold data ratio basic correction
if (foldDataRatio > MaxRatioOfFoldData)
{
foldDataRatio = MaxRatioOfFoldData;
}
//Prelimitary fold size estimation
int foldSize = Math.Max(1, (int)Math.Round(OutputVectorCollection.Count * foldDataRatio, 0));
//Prelimitary number of folds
int numOfFolds = (int)Math.Round((double)OutputVectorCollection.Count / foldSize);
//Folds creation
if (double.IsNaN(binBorder))
{
//No binary output -> simple split
int samplesPos = 0;
for (int foldIdx = 0; foldIdx < numOfFolds; foldIdx++)
{
VectorBundle fold = new VectorBundle();
for (int i = 0; i < foldSize && samplesPos < OutputVectorCollection.Count; i++)
{
fold.InputVectorCollection.Add(InputVectorCollection[samplesPos]);
fold.OutputVectorCollection.Add(OutputVectorCollection[samplesPos]);
++samplesPos;
}
foldCollection.Add(fold);
}
//Remaining samples
for (int i = 0; i < OutputVectorCollection.Count - samplesPos; i++)
{
int foldIdx = i % foldCollection.Count;
foldCollection[foldIdx].InputVectorCollection.Add(InputVectorCollection[samplesPos + i]);
foldCollection[foldIdx].OutputVectorCollection.Add(OutputVectorCollection[samplesPos + i]);
}
}//Indifferent output
else
{
//Binary outputs -> keep balanced ratios of outputs
int numOfOutputs = OutputVectorCollection[0].Length;
if (numOfOutputs == 1)
{
//Special case there is only one binary output
//Investigation of the output data metrics
BinDistribution refBinDistr = new BinDistribution(binBorder);
refBinDistr.Update(OutputVectorCollection, 0);
int min01 = Math.Min(refBinDistr.NumOf[0], refBinDistr.NumOf[1]);
if (min01 < 2)
{
throw new InvalidOperationException($"Insufficient bin 0 or 1 samples (less than 2).");
}
if (numOfFolds > min01)
{
numOfFolds = min01;
}
//Scan data
int[] bin0SampleIdxs = new int[refBinDistr.NumOf[0]];
int bin0SamplesPos = 0;
int[] bin1SampleIdxs = new int[refBinDistr.NumOf[1]];
int bin1SamplesPos = 0;
for (int i = 0; i < OutputVectorCollection.Count; i++)
{
if (OutputVectorCollection[i][0] >= refBinDistr.BinBorder)
{
bin1SampleIdxs[bin1SamplesPos++] = i;
}
else
{
bin0SampleIdxs[bin0SamplesPos++] = i;
}
}
//Determine distributions of 0 and 1 for one fold
int bundleBin0Count = Math.Max(1, refBinDistr.NumOf[0] / numOfFolds);
int bundleBin1Count = Math.Max(1, refBinDistr.NumOf[1] / numOfFolds);
//Bundles creation
bin0SamplesPos = 0;
bin1SamplesPos = 0;
for (int foldIdx = 0; foldIdx < numOfFolds; foldIdx++)
{
VectorBundle fold = new VectorBundle();
//Bin 0
for (int i = 0; i < bundleBin0Count; i++)
{
fold.InputVectorCollection.Add(InputVectorCollection[bin0SampleIdxs[bin0SamplesPos]]);
fold.OutputVectorCollection.Add(OutputVectorCollection[bin0SampleIdxs[bin0SamplesPos]]);
++bin0SamplesPos;
}
//Bin 1
for (int i = 0; i < bundleBin1Count; i++)
{
fold.InputVectorCollection.Add(InputVectorCollection[bin1SampleIdxs[bin1SamplesPos]]);
fold.OutputVectorCollection.Add(OutputVectorCollection[bin1SampleIdxs[bin1SamplesPos]]);
++bin1SamplesPos;
}
foldCollection.Add(fold);
}
//Remaining samples
for (int i = 0; i < bin0SampleIdxs.Length - bin0SamplesPos; i++)
{
int foldIdx = i % foldCollection.Count;
foldCollection[foldIdx].InputVectorCollection.Add(InputVectorCollection[bin0SampleIdxs[bin0SamplesPos + i]]);
foldCollection[foldIdx].OutputVectorCollection.Add(OutputVectorCollection[bin0SampleIdxs[bin0SamplesPos + i]]);
}
for (int i = 0; i < bin1SampleIdxs.Length - bin1SamplesPos; i++)
{
int foldIdx = i % foldCollection.Count;
foldCollection[foldIdx].InputVectorCollection.Add(InputVectorCollection[bin1SampleIdxs[bin1SamplesPos + i]]);
foldCollection[foldIdx].OutputVectorCollection.Add(OutputVectorCollection[bin1SampleIdxs[bin1SamplesPos + i]]);
}
}//Only 1 binary output
else
{
//There is more than 1 binary output - "one takes all approach"
//Investigation of the output data metrics
//Collect bin 1 sample indexes and check "one takes all" consistency for every output feature
List <int>[] outBin1SampleIdxs = new List <int> [numOfOutputs];
for (int i = 0; i < numOfOutputs; i++)
{
outBin1SampleIdxs[i] = new List <int>();
}
for (int sampleIdx = 0; sampleIdx < OutputVectorCollection.Count; sampleIdx++)
{
int numOf1 = 0;
for (int outFeatureIdx = 0; outFeatureIdx < numOfOutputs; outFeatureIdx++)
{
if (OutputVectorCollection[sampleIdx][outFeatureIdx] >= binBorder)
{
outBin1SampleIdxs[outFeatureIdx].Add(sampleIdx);
++numOf1;
}
}
if (numOf1 != 1)
{
throw new ArgumentException($"Data are inconsistent on data index {sampleIdx.ToString(CultureInfo.InvariantCulture)}. Output vector has {numOf1.ToString(CultureInfo.InvariantCulture)} feature(s) having bin value 1.", "binBorder");
}
}
//Determine max possible number of folds
int maxNumOfFolds = OutputVectorCollection.Count;
for (int outFeatureIdx = 0; outFeatureIdx < numOfOutputs; outFeatureIdx++)
{
int outFeatureMaxFolds = Math.Min(outBin1SampleIdxs[outFeatureIdx].Count, OutputVectorCollection.Count - outBin1SampleIdxs[outFeatureIdx].Count);
maxNumOfFolds = Math.Min(outFeatureMaxFolds, maxNumOfFolds);
}
//Correct the number of folds to be created
if (numOfFolds > maxNumOfFolds)
{
numOfFolds = maxNumOfFolds;
}
//Create the folds
for (int foldIdx = 0; foldIdx < numOfFolds; foldIdx++)
{
foldCollection.Add(new VectorBundle());
}
//Samples distribution
for (int outFeatureIdx = 0; outFeatureIdx < numOfOutputs; outFeatureIdx++)
{
for (int bin1SampleRefIdx = 0; bin1SampleRefIdx < outBin1SampleIdxs[outFeatureIdx].Count; bin1SampleRefIdx++)
{
int foldIdx = bin1SampleRefIdx % foldCollection.Count;
int dataIdx = outBin1SampleIdxs[outFeatureIdx][bin1SampleRefIdx];
foldCollection[foldIdx].AddPair(InputVectorCollection[dataIdx], OutputVectorCollection[dataIdx]);
}
}
} //More binary outputs
} //Binary output
return(foldCollection);
}
/// <summary>
/// Adds all the vector pairs from another vector bundle.
/// </summary>
/// <param name="data">Another vector bundle.</param>
public void Add(VectorBundle data)
{
InputVectorCollection.AddRange(data.InputVectorCollection);
OutputVectorCollection.AddRange(data.OutputVectorCollection);
return;
}
//Methods
/// <summary>
/// Splits this bundle to a collection of smaller bundles.
/// Method expects length of the output vectors = 1.
/// </summary>
/// <param name="subBundleSize">Sub-bundle size</param>
/// <param name="binBorder">If specified and there is only one output value, method will keep balanced number of output values GE to binBorder in the each sub-bundle</param>
/// <returns>Collection of extracted sub-bundles</returns>
public List <VectorBundle> Split(int subBundleSize, double binBorder = double.NaN)
{
int numOfBundles = OutputVectorCollection.Count / subBundleSize;
List <VectorBundle> bundleCollection = new List <VectorBundle>(numOfBundles);
if (!double.IsNaN(binBorder) && OutputVectorCollection[0].Length == 1)
{
BinDistribution refBinDistr = new BinDistribution(binBorder);
refBinDistr.Update(OutputVectorCollection, 0);
//Scan
int[] bin0SampleIdxs = new int[refBinDistr.NumOf[0]];
int bin0SamplesPos = 0;
int[] bin1SampleIdxs = new int[refBinDistr.NumOf[1]];
int bin1SamplesPos = 0;
for (int i = 0; i < OutputVectorCollection.Count; i++)
{
if (OutputVectorCollection[i][0] >= refBinDistr.BinBorder)
{
bin1SampleIdxs[bin1SamplesPos++] = i;
}
else
{
bin0SampleIdxs[bin0SamplesPos++] = i;
}
}
//Division
int bundleBin0Count = Math.Max(1, refBinDistr.NumOf[0] / numOfBundles);
int bundleBin1Count = Math.Max(1, refBinDistr.NumOf[1] / numOfBundles);
if (bundleBin0Count * numOfBundles > bin0SampleIdxs.Length)
{
throw new InvalidOperationException($"Insufficient bin 0 samples");
}
if (bundleBin1Count * numOfBundles > bin1SampleIdxs.Length)
{
throw new InvalidOperationException($"Insufficient bin 1 samples");
}
//Bundles creation
bin0SamplesPos = 0;
bin1SamplesPos = 0;
for (int bundleNum = 0; bundleNum < numOfBundles; bundleNum++)
{
VectorBundle bundle = new VectorBundle();
//Bin 0
for (int i = 0; i < bundleBin0Count; i++)
{
bundle.InputVectorCollection.Add(InputVectorCollection[bin0SampleIdxs[bin0SamplesPos]]);
bundle.OutputVectorCollection.Add(OutputVectorCollection[bin0SampleIdxs[bin0SamplesPos]]);
++bin0SamplesPos;
}
//Bin 1
for (int i = 0; i < bundleBin1Count; i++)
{
bundle.InputVectorCollection.Add(InputVectorCollection[bin1SampleIdxs[bin1SamplesPos]]);
bundle.OutputVectorCollection.Add(OutputVectorCollection[bin1SampleIdxs[bin1SamplesPos]]);
++bin1SamplesPos;
}
bundleCollection.Add(bundle);
}
//Remaining samples
for (int i = 0; i < bin0SampleIdxs.Length - bin0SamplesPos; i++)
{
int bundleIdx = i % bundleCollection.Count;
bundleCollection[bundleIdx].InputVectorCollection.Add(InputVectorCollection[bin0SampleIdxs[bin0SamplesPos + i]]);
bundleCollection[bundleIdx].OutputVectorCollection.Add(OutputVectorCollection[bin0SampleIdxs[bin0SamplesPos + i]]);
}
for (int i = 0; i < bin1SampleIdxs.Length - bin1SamplesPos; i++)
{
int bundleIdx = i % bundleCollection.Count;
bundleCollection[bundleIdx].InputVectorCollection.Add(InputVectorCollection[bin1SampleIdxs[bin1SamplesPos + i]]);
bundleCollection[bundleIdx].OutputVectorCollection.Add(OutputVectorCollection[bin1SampleIdxs[bin1SamplesPos + i]]);
}
}
else
{
//Bundles creation
int samplesPos = 0;
for (int bundleNum = 0; bundleNum < numOfBundles; bundleNum++)
{
VectorBundle bundle = new VectorBundle();
for (int i = 0; i < subBundleSize && samplesPos < OutputVectorCollection.Count; i++)
{
bundle.InputVectorCollection.Add(InputVectorCollection[samplesPos]);
bundle.OutputVectorCollection.Add(OutputVectorCollection[samplesPos]);
++samplesPos;
}
bundleCollection.Add(bundle);
}
//Remaining samples
for (int i = 0; i < OutputVectorCollection.Count - samplesPos; i++)
{
int bundleIdx = i % bundleCollection.Count;
bundleCollection[bundleIdx].InputVectorCollection.Add(InputVectorCollection[samplesPos + i]);
bundleCollection[bundleIdx].OutputVectorCollection.Add(OutputVectorCollection[samplesPos + i]);
}
}
return(bundleCollection);
}
