public void TestKmeans()
{
FloatMatrixIndexer data = new FloatMatrixIndexer(new float[, ] {
{ 1, 2, 3, 1 }, { 2, 3, 4, 2 }
});
KmeansClustering.GenerateClusters(data.Transpose(), 2, 100, 1, i => { }, out var clusterCenters, out var clusterIndices);
Assert.AreEqual(2, clusterCenters.GetLength(0));
}
/* K MEANS CLUSTERING ALGORITHM - My implementation */
public Cluster[] computeClusters(List <Frame> framesToSearch)
{
KmeansClustering.Entity[] dataset = new KmeansClustering.Entity[framesToSearch.Count];
int i, K = this.UAVs.Length;
i = 0;
foreach (Frame f in framesToSearch)
{
dataset[i] = new KmeansClustering.Entity(2);
dataset[i].setIthFeature(0, f.center.x);
dataset[i].setIthFeature(1, f.center.z);
// Debug.Log(dataset[i]);
i++;
}
/* dataset = center of frames
* K = number of UAVS */
KmeansClustering clusterer = new KmeansClustering(dataset, this.UAVs.Length);
KmeansClustering.ClusteringSolution sol = clusterer.runKmeans(5); // 10 random starts
//final number of clusters K could be less than number of UAV if entities are less than K.
Cluster[] clustersArray = new Cluster[sol.finalK];
for (i = 0; i < sol.finalK; i++)
{
clustersArray [i] = new Cluster();
}
i = 0;
foreach (Frame f in framesToSearch)
{
//Debug.Log ("Point: "+dataset[i]+" - Cluster: " +sol.mapDataPointToCluster[i]);
clustersArray[sol.mapDataPointToCluster[i]].addFrame(f);
i++;
}
foreach (Cluster c in clustersArray)
{
c.debugCentroid();
foreach (Frame f in c.frames)
{
f.displayDebug(colorList[currentColor], f.profitDensity);
}
currentColor++; currentColor %= colorList.Length;
}
return(clustersArray);
}
/* K MEANS CLUSTERING ALGORITHM - ALGLIB */
public Cluster[] computeClustersWithAlgLib(List <Frame> framesToSearch)
{
int i, K = this.UAVs.Length;
Cluster[] clustersArray = new Cluster[K];
for (i = 0; i < K; i++)
{
clustersArray [i] = new Cluster();
}
// array of points (frames' centers used in the clustering algorithm)
double[,] dataset = new double[framesToSearch.Count, 2]; //{{1,1},{1,2},{4,1},{2,3},{4,1.5}};
i = 0;
foreach (Frame f in framesToSearch)
{
dataset[i, 0] = f.center.x;
dataset[i, 1] = f.center.z; i++;
}
alglib.kmeansreport rep = KmeansClustering.computeClusters(dataset, K);
i = 0;
foreach (Frame f in framesToSearch)
{
// Debug.Log(dataset[i,0] + "," + dataset[i,1] + " - cluster:" + rep.cidx[i]);
clustersArray[rep.cidx[i]].addFrame(f);
i++;
}
foreach (Cluster c in clustersArray)
{
c.debugCentroid();
foreach (Frame f in c.frames)
{
f.displayDebug(colorList[currentColor], f.profitDensity);
}
currentColor++; currentColor %= colorList.Length;
}
return(clustersArray);
}
public void Execute(Arguments arguments)
{
LoggedConsole.WriteLine("feature learning process...");
var inputDir = @"D:\Mahnoosh\Liz\Least_Bittern\";
var inputPath = Path.Combine(inputDir, "TrainSet\\one_min_recordings");
var trainSetPath = Path.Combine(inputDir, "TrainSet\\train_data");
// var testSetPath = Path.Combine(inputDir, "TestSet");
var configPath = @"D:\Mahnoosh\Liz\Least_Bittern\FeatureLearningConfig.yml";
var resultDir = Path.Combine(inputDir, "FeatureLearning");
Directory.CreateDirectory(resultDir);
// var outputMelImagePath = Path.Combine(resultDir, "MelScaleSpectrogram.png");
// var outputNormMelImagePath = Path.Combine(resultDir, "NormalizedMelScaleSpectrogram.png");
// var outputNoiseReducedMelImagePath = Path.Combine(resultDir, "NoiseReducedMelSpectrogram.png");
// var outputReSpecImagePath = Path.Combine(resultDir, "ReconstrcutedSpectrogram.png");
// var outputClusterImagePath = Path.Combine(resultDir, "Clusters.bmp");
// +++++++++++++++++++++++++++++++++++++++++++++++++patch sampling from 1-min recordings
var configFile = configPath.ToFileInfo();
if (configFile == null)
{
throw new FileNotFoundException("No config file argument provided");
}
else if (!configFile.Exists)
{
throw new ArgumentException($"Config file {configFile.FullName} not found");
}
var configuration = ConfigFile.Deserialize <FeatureLearningSettings>(configFile);
int patchWidth =
(configuration.MaxFreqBin - configuration.MinFreqBin + 1) / configuration.NumFreqBand;
var clusteringOutputList = FeatureLearning.UnsupervisedFeatureLearning(configuration, inputPath);
List <double[][]> allBandsCentroids = new List <double[][]>();
for (int i = 0; i < clusteringOutputList.Count; i++)
{
var clusteringOutput = clusteringOutputList[i];
// writing centroids to a csv file
// note that Csv.WriteToCsv can't write data types like dictionary<int, double[]> (problems with arrays)
// I converted the dictionary values to a matrix and used the Csv.WriteMatrixToCsv
// it might be a better way to do this
string pathToClusterCsvFile = Path.Combine(resultDir, "ClusterCentroids" + i.ToString() + ".csv");
var clusterCentroids = clusteringOutput.ClusterIdCentroid.Values.ToArray();
Csv.WriteMatrixToCsv(pathToClusterCsvFile.ToFileInfo(), clusterCentroids.ToMatrix());
// sorting clusters based on size and output it to a csv file
Dictionary <int, double> clusterIdSize = clusteringOutput.ClusterIdSize;
int[] sortOrder = KmeansClustering.SortClustersBasedOnSize(clusterIdSize);
// Write cluster ID and size to a CSV file
string pathToClusterSizeCsvFile = Path.Combine(resultDir, "ClusterSize" + i.ToString() + ".csv");
Csv.WriteToCsv(pathToClusterSizeCsvFile.ToFileInfo(), clusterIdSize);
// Draw cluster image directly from clustering output
List <KeyValuePair <int, double[]> > list = clusteringOutput.ClusterIdCentroid.ToList();
double[][] centroids = new double[list.Count][];
for (int j = 0; j < list.Count; j++)
{
centroids[j] = list[j].Value;
}
allBandsCentroids.Add(centroids);
List <double[, ]> allCentroids = new List <double[, ]>();
for (int k = 0; k < centroids.Length; k++)
{
// convert each centroid to a matrix in order of cluster ID
// double[,] cent = PatchSampling.ArrayToMatrixByColumn(centroids[i], patchWidth, patchHeight);
// OR: in order of cluster size
double[,] cent = MatrixTools.ArrayToMatrixByColumn(centroids[sortOrder[k]], patchWidth, configuration.PatchHeight);
// normalize each centroid
double[,] normCent = DataTools.normalise(cent);
// add a row of zero to each centroid
double[,] cent2 = PatchSampling.AddRow(normCent);
allCentroids.Add(cent2);
}
// concatenate all centroids
double[,] mergedCentroidMatrix = PatchSampling.ListOf2DArrayToOne2DArray(allCentroids);
// Draw clusters
var clusterImage = ImageTools.DrawMatrixWithoutNormalisation(mergedCentroidMatrix);
clusterImage.RotateFlip(RotateFlipType.Rotate270FlipNone);
var outputClusteringImage = Path.Combine(resultDir, "ClustersWithGrid" + i.ToString() + ".bmp");
clusterImage.Save(outputClusteringImage);
}
// extracting features
FeatureExtraction.UnsupervisedFeatureExtraction(configuration, allBandsCentroids, trainSetPath, resultDir);
LoggedConsole.WriteLine("Done...");
}
public void TestFeatureLearning()
{
// var outputDir = this.outputDirectory;
var resultDir = PathHelper.ResolveAssetPath("FeatureLearning");
var folderPath = Path.Combine(resultDir, "random_audio_segments"); // Liz
// PathHelper.ResolveAssetPath(@"C:\Users\kholghim\Mahnoosh\PcaWhitening\random_audio_segments\1192_1000");
// var resultDir = PathHelper.ResolveAssetPath(@"C:\Users\kholghim\Mahnoosh\PcaWhitening");
var outputMelImagePath = Path.Combine(resultDir, "MelScaleSpectrogram.png");
var outputNormMelImagePath = Path.Combine(resultDir, "NormalizedMelScaleSpectrogram.png");
var outputNoiseReducedMelImagePath = Path.Combine(resultDir, "NoiseReducedMelSpectrogram.png");
var outputReSpecImagePath = Path.Combine(resultDir, "ReconstrcutedSpectrogram.png");
// var outputClusterImagePath = Path.Combine(resultDir, "Clusters.bmp");
// +++++++++++++++++++++++++++++++++++++++++++++++++patch sampling from 1000 random 1-min recordings from Gympie
// check whether there is any file in the folder/subfolders
if (Directory.GetFiles(folderPath, "*", SearchOption.AllDirectories).Length == 0)
{
throw new ArgumentException("The folder of recordings is empty...");
}
// get the nyquist value from the first wav file in the folder of recordings
int nq = new AudioRecording(Directory.GetFiles(folderPath, "*.wav")[0]).Nyquist;
int nyquist = nq; // 11025;
int frameSize = 1024;
int finalBinCount = 128; // 256; // 100; // 40; // 200; //
int hertzInterval = 1000;
FreqScaleType scaleType = FreqScaleType.Mel;
var freqScale = new FrequencyScale(scaleType, nyquist, frameSize, finalBinCount, hertzInterval);
var fst = freqScale.ScaleType;
var sonoConfig = new SonogramConfig
{
WindowSize = frameSize,
// since each 24 frames duration is equal to 1 second
WindowOverlap = 0.1028,
DoMelScale = (scaleType == FreqScaleType.Mel) ? true : false,
MelBinCount = (scaleType == FreqScaleType.Mel) ? finalBinCount : frameSize / 2,
NoiseReductionType = NoiseReductionType.None,
};
/*
* // testing
* var recordingPath3 = PathHelper.ResolveAsset(folderPath, "SM304264_0+1_20160421_024539_46-47min.wav");
* var recording3 = new AudioRecording(recordingPath3);
* var sonogram3 = new SpectrogramStandard(sonoConfig, recording3.WavReader);
*
* // DO DRAW SPECTROGRAM
* var image4 = sonogram3.GetImageFullyAnnotated(sonogram3.GetImage(), "MELSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
* image4.Save(outputMelImagePath);
*
* // Do RMS normalization
* sonogram3.Data = SNR.RmsNormalization(sonogram3.Data);
* var image5 = sonogram3.GetImageFullyAnnotated(sonogram3.GetImage(), "NORMALISEDMELSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
* image5.Save(outputNormMelImagePath);
*
* // NOISE REDUCTION
* sonogram3.Data = PcaWhitening.NoiseReduction(sonogram3.Data);
* var image6 = sonogram3.GetImageFullyAnnotated(sonogram3.GetImage(), "NOISEREDUCEDMELSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
* image6.Save(outputNoiseReducedMelImagePath);
*
* //testing
*/
// Define the minFreBin and MaxFreqBin to be able to work at arbitrary frequency bin bounds.
// The default value is minFreqBin = 1 and maxFreqBin = finalBinCount.
// To work with arbitrary frequency bin bounds we need to manually set these two parameters.
int minFreqBin = 40; //1
int maxFreqBin = 80; //finalBinCount;
int numFreqBand = 1; //4;
int patchWidth = (maxFreqBin - minFreqBin + 1) / numFreqBand; // finalBinCount / numFreqBand;
int patchHeight = 1; // 2; // 4; // 16; // 6; // Frame size
int numRandomPatches = 20; // 40; // 80; // 30; // 100; // 500; //
// int fileCount = Directory.GetFiles(folderPath, "*.wav").Length;
// Define variable number of "randomPatch" lists based on "numFreqBand"
Dictionary <string, List <double[, ]> > randomPatchLists = new Dictionary <string, List <double[, ]> >();
for (int i = 0; i < numFreqBand; i++)
{
randomPatchLists.Add(string.Format("randomPatch{0}", i.ToString()), new List <double[, ]>());
}
List <double[, ]> randomPatches = new List <double[, ]>();
/*
* foreach (string filePath in Directory.GetFiles(folderPath, "*.wav"))
* {
* FileInfo f = filePath.ToFileInfo();
* if (f.Length == 0)
* {
* Debug.WriteLine(f.Name);
* }
* }
*/
double[,] inputMatrix;
foreach (string filePath in Directory.GetFiles(folderPath, "*.wav"))
{
FileInfo fileInfo = filePath.ToFileInfo();
// process the wav file if it is not empty
if (fileInfo.Length != 0)
{
var recording = new AudioRecording(filePath);
sonoConfig.SourceFName = recording.BaseName;
var sonogram = new SpectrogramStandard(sonoConfig, recording.WavReader);
// DO RMS NORMALIZATION
sonogram.Data = SNR.RmsNormalization(sonogram.Data);
// DO NOISE REDUCTION
// sonogram.Data = SNR.NoiseReduce_Median(sonogram.Data, nhBackgroundThreshold: 2.0);
sonogram.Data = PcaWhitening.NoiseReduction(sonogram.Data);
// check whether the full band spectrogram is needed or a matrix with arbitrary freq bins
if (minFreqBin != 1 || maxFreqBin != finalBinCount)
{
inputMatrix = PatchSampling.GetArbitraryFreqBandMatrix(sonogram.Data, minFreqBin, maxFreqBin);
}
else
{
inputMatrix = sonogram.Data;
}
// creating matrices from different freq bands of the source spectrogram
List <double[, ]> allSubmatrices = PatchSampling.GetFreqBandMatrices(inputMatrix, numFreqBand);
// Second: selecting random patches from each freq band matrix and add them to the corresponding patch list
int count = 0;
while (count < allSubmatrices.Count)
{
randomPatchLists[$"randomPatch{count.ToString()}"].Add(PatchSampling
.GetPatches(allSubmatrices.ToArray()[count], patchWidth, patchHeight, numRandomPatches,
PatchSampling.SamplingMethod.Random).ToMatrix());
count++;
}
}
}
foreach (string key in randomPatchLists.Keys)
{
randomPatches.Add(PatchSampling.ListOf2DArrayToOne2DArray(randomPatchLists[key]));
}
// convert list of random patches matrices to one matrix
int numberOfClusters = 50; //256; // 128; // 64; // 32; // 10; //
List <double[][]> allBandsCentroids = new List <double[][]>();
List <KMeansClusterCollection> allClusteringOutput = new List <KMeansClusterCollection>();
for (int i = 0; i < randomPatches.Count; i++)
{
double[,] patchMatrix = randomPatches[i];
// Apply PCA Whitening
var whitenedSpectrogram = PcaWhitening.Whitening(true, patchMatrix);
// Do k-means clustering
var clusteringOutput = KmeansClustering.Clustering(whitenedSpectrogram.Reversion, numberOfClusters);
// var clusteringOutput = KmeansClustering.Clustering(patchMatrix, noOfClusters, pathToClusterCsvFile);
// writing centroids to a csv file
// note that Csv.WriteToCsv can't write data types like dictionary<int, double[]> (problems with arrays)
// I converted the dictionary values to a matrix and used the Csv.WriteMatrixToCsv
// it might be a better way to do this
string pathToClusterCsvFile = Path.Combine(resultDir, "ClusterCentroids" + i.ToString() + ".csv");
var clusterCentroids = clusteringOutput.ClusterIdCentroid.Values.ToArray();
Csv.WriteMatrixToCsv(pathToClusterCsvFile.ToFileInfo(), clusterCentroids.ToMatrix());
//Csv.WriteToCsv(pathToClusterCsvFile.ToFileInfo(), clusterCentroids);
// sorting clusters based on size and output it to a csv file
Dictionary <int, double> clusterIdSize = clusteringOutput.ClusterIdSize;
int[] sortOrder = KmeansClustering.SortClustersBasedOnSize(clusterIdSize);
// Write cluster ID and size to a CSV file
string pathToClusterSizeCsvFile = Path.Combine(resultDir, "ClusterSize" + i.ToString() + ".csv");
Csv.WriteToCsv(pathToClusterSizeCsvFile.ToFileInfo(), clusterIdSize);
// Draw cluster image directly from clustering output
List <KeyValuePair <int, double[]> > list = clusteringOutput.ClusterIdCentroid.ToList();
double[][] centroids = new double[list.Count][];
for (int j = 0; j < list.Count; j++)
{
centroids[j] = list[j].Value;
}
allBandsCentroids.Add(centroids);
allClusteringOutput.Add(clusteringOutput.Clusters);
List <double[, ]> allCentroids = new List <double[, ]>();
for (int k = 0; k < centroids.Length; k++)
{
// convert each centroid to a matrix in order of cluster ID
// double[,] cent = PatchSampling.ArrayToMatrixByColumn(centroids[i], patchWidth, patchHeight);
// OR: in order of cluster size
double[,] cent =
MatrixTools.ArrayToMatrixByColumn(centroids[sortOrder[k]], patchWidth, patchHeight);
// normalize each centroid
double[,] normCent = DataTools.normalise(cent);
// add a row of zero to each centroid
double[,] cent2 = PatchSampling.AddRow(normCent);
allCentroids.Add(cent2);
}
// concatenate all centroids
double[,] mergedCentroidMatrix = PatchSampling.ListOf2DArrayToOne2DArray(allCentroids);
// Draw clusters
// int gridInterval = 1000;
// var freqScale = new FrequencyScale(FreqScaleType.Mel, nyquist, frameSize, finalBinCount, gridInterval);
var clusterImage = ImageTools.DrawMatrixWithoutNormalisation(mergedCentroidMatrix);
clusterImage.RotateFlip(RotateFlipType.Rotate270FlipNone);
// clusterImage.Save(outputClusterImagePath, ImageFormat.Bmp);
var outputClusteringImage = Path.Combine(resultDir, "ClustersWithGrid" + i.ToString() + ".bmp");
// Image bmp = Image.Load<Rgb24>(filename);
FrequencyScale.DrawFrequencyLinesOnImage((Image <Rgb24>)clusterImage, freqScale, includeLabels: false);
clusterImage.Save(outputClusteringImage);
}
//+++++++++++++++++++++++++++++++++++++++++++++++++++++Processing and generating features for the target recordings
var recording2Path = PathHelper.ResolveAsset("Recordings", "BAC2_20071008-085040.wav");
// var recording2Path = PathHelper.ResolveAsset(folderPath, "gympie_np_1192_353972_20160303_055854_60_0.wav"); // folder with 1000 files
// var recording2Path = PathHelper.ResolveAsset(folderPath, "gympie_np_1192_353887_20151230_042625_60_0.wav"); // folder with 1000 files
// var recording2Path = PathHelper.ResolveAsset(folderPath, "gympie_np_1192_354744_20151018_053923_60_0.wav"); // folder with 100 files
var recording2 = new AudioRecording(recording2Path);
var sonogram2 = new SpectrogramStandard(sonoConfig, recording2.WavReader);
// DO DRAW SPECTROGRAM
var image = sonogram2.GetImageFullyAnnotated(sonogram2.GetImage(), "MELSPECTROGRAM: " + fst.ToString(),
freqScale.GridLineLocations);
image.Save(outputMelImagePath);
// Do RMS normalization
sonogram2.Data = SNR.RmsNormalization(sonogram2.Data);
var image2 = sonogram2.GetImageFullyAnnotated(sonogram2.GetImage(),
"NORMALISEDMELSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
image2.Save(outputNormMelImagePath);
// NOISE REDUCTION
sonogram2.Data = PcaWhitening.NoiseReduction(sonogram2.Data);
var image3 = sonogram2.GetImageFullyAnnotated(sonogram2.GetImage(),
"NOISEREDUCEDMELSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
image3.Save(outputNoiseReducedMelImagePath);
// check whether the full band spectrogram is needed or a matrix with arbitrary freq bins
if (minFreqBin != 1 || maxFreqBin != finalBinCount)
{
inputMatrix = PatchSampling.GetArbitraryFreqBandMatrix(sonogram2.Data, minFreqBin, maxFreqBin);
}
else
{
inputMatrix = sonogram2.Data;
}
// extracting sequential patches from the target spectrogram
List <double[, ]> allSubmatrices2 = PatchSampling.GetFreqBandMatrices(inputMatrix, numFreqBand);
double[][,] matrices2 = allSubmatrices2.ToArray();
List <double[, ]> allSequentialPatchMatrix = new List <double[, ]>();
for (int i = 0; i < matrices2.GetLength(0); i++)
{
int rows = matrices2[i].GetLength(0);
int columns = matrices2[i].GetLength(1);
var sequentialPatches = PatchSampling.GetPatches(matrices2[i], patchWidth, patchHeight,
(rows / patchHeight) * (columns / patchWidth), PatchSampling.SamplingMethod.Sequential);
allSequentialPatchMatrix.Add(sequentialPatches.ToMatrix());
}
// +++++++++++++++++++++++++++++++++++Feature Transformation
// to do the feature transformation, we normalize centroids and
// sequential patches from the input spectrogram to unit length
// Then, we calculate the dot product of each patch with the centroids' matrix
List <double[][]> allNormCentroids = new List <double[][]>();
for (int i = 0; i < allBandsCentroids.Count; i++)
{
// double check the index of the list
double[][] normCentroids = new double[allBandsCentroids.ToArray()[i].GetLength(0)][];
for (int j = 0; j < allBandsCentroids.ToArray()[i].GetLength(0); j++)
{
normCentroids[j] = ART_2A.NormaliseVector(allBandsCentroids.ToArray()[i][j]);
}
allNormCentroids.Add(normCentroids);
}
List <double[][]> allFeatureTransVectors = new List <double[][]>();
for (int i = 0; i < allSequentialPatchMatrix.Count; i++)
{
double[][] featureTransVectors = new double[allSequentialPatchMatrix.ToArray()[i].GetLength(0)][];
for (int j = 0; j < allSequentialPatchMatrix.ToArray()[i].GetLength(0); j++)
{
var normVector =
ART_2A.NormaliseVector(allSequentialPatchMatrix.ToArray()[i]
.ToJagged()[j]); // normalize each patch to unit length
featureTransVectors[j] = allNormCentroids.ToArray()[i].ToMatrix().Dot(normVector);
}
allFeatureTransVectors.Add(featureTransVectors);
}
// +++++++++++++++++++++++++++++++++++Feature Transformation
// +++++++++++++++++++++++++++++++++++Temporal Summarization
// The resolution to generate features is 1 second
// Each 24 single-frame patches form 1 second
// for each 24 patch, we generate 3 vectors of mean, std, and max
// The pre-assumption is that each input spectrogram is 1 minute
List <double[, ]> allMeanFeatureVectors = new List <double[, ]>();
List <double[, ]> allMaxFeatureVectors = new List <double[, ]>();
List <double[, ]> allStdFeatureVectors = new List <double[, ]>();
// number of frames needs to be concatenated to form 1 second. Each 24 frames make 1 second.
int numFrames = (24 / patchHeight) * 60;
foreach (var freqBandFeature in allFeatureTransVectors)
{
// store features of different bands in lists
List <double[]> meanFeatureVectors = new List <double[]>();
List <double[]> maxFeatureVectors = new List <double[]>();
List <double[]> stdFeatureVectors = new List <double[]>();
int c = 0;
while (c + numFrames < freqBandFeature.GetLength(0))
{
// First, make a list of patches that would be equal to 1 second
List <double[]> sequencesOfFramesList = new List <double[]>();
for (int i = c; i < c + numFrames; i++)
{
sequencesOfFramesList.Add(freqBandFeature[i]);
}
List <double> mean = new List <double>();
List <double> std = new List <double>();
List <double> max = new List <double>();
double[,] sequencesOfFrames = sequencesOfFramesList.ToArray().ToMatrix();
// int len = sequencesOfFrames.GetLength(1);
// Second, calculate mean, max, and standard deviation of six vectors element-wise
for (int j = 0; j < sequencesOfFrames.GetLength(1); j++)
{
double[] temp = new double[sequencesOfFrames.GetLength(0)];
for (int k = 0; k < sequencesOfFrames.GetLength(0); k++)
{
temp[k] = sequencesOfFrames[k, j];
}
mean.Add(AutoAndCrossCorrelation.GetAverage(temp));
std.Add(AutoAndCrossCorrelation.GetStdev(temp));
max.Add(temp.GetMaxValue());
}
meanFeatureVectors.Add(mean.ToArray());
maxFeatureVectors.Add(max.ToArray());
stdFeatureVectors.Add(std.ToArray());
c += numFrames;
}
allMeanFeatureVectors.Add(meanFeatureVectors.ToArray().ToMatrix());
allMaxFeatureVectors.Add(maxFeatureVectors.ToArray().ToMatrix());
allStdFeatureVectors.Add(stdFeatureVectors.ToArray().ToMatrix());
}
// +++++++++++++++++++++++++++++++++++Temporal Summarization
// ++++++++++++++++++++++++++++++++++Writing features to file
// First, concatenate mean, max, std for each second.
// Then write to CSV file.
for (int j = 0; j < allMeanFeatureVectors.Count; j++)
{
// write the features of each pre-defined frequency band into a separate CSV file
var outputFeatureFile = Path.Combine(resultDir, "FeatureVectors" + j.ToString() + ".csv");
// creating the header for CSV file
List <string> header = new List <string>();
for (int i = 0; i < allMeanFeatureVectors.ToArray()[j].GetLength(1); i++)
{
header.Add("mean" + i.ToString());
}
for (int i = 0; i < allMaxFeatureVectors.ToArray()[j].GetLength(1); i++)
{
header.Add("max" + i.ToString());
}
for (int i = 0; i < allStdFeatureVectors.ToArray()[j].GetLength(1); i++)
{
header.Add("std" + i.ToString());
}
// concatenating mean, std, and max vector together for each 1 second
List <double[]> featureVectors = new List <double[]>();
for (int i = 0; i < allMeanFeatureVectors.ToArray()[j].ToJagged().GetLength(0); i++)
{
List <double[]> featureList = new List <double[]>
{
allMeanFeatureVectors.ToArray()[j].ToJagged()[i],
allMaxFeatureVectors.ToArray()[j].ToJagged()[i],
allStdFeatureVectors.ToArray()[j].ToJagged()[i],
};
double[] featureVector = DataTools.ConcatenateVectors(featureList);
featureVectors.Add(featureVector);
}
// writing feature vectors to CSV file
using (StreamWriter file = new StreamWriter(outputFeatureFile))
{
// writing the header to CSV file
foreach (var entry in header.ToArray())
{
file.Write(entry + ",");
}
file.Write(Environment.NewLine);
foreach (var entry in featureVectors.ToArray())
{
foreach (var value in entry)
{
file.Write(value + ",");
}
file.Write(Environment.NewLine);
}
}
}
/*
* // Reconstructing the target spectrogram based on clusters' centroids
* List<double[,]> convertedSpec = new List<double[,]>();
* int columnPerFreqBand = sonogram2.Data.GetLength(1) / numFreqBand;
* for (int i = 0; i < allSequentialPatchMatrix.Count; i++)
* {
* double[,] reconstructedSpec2 = KmeansClustering.ReconstructSpectrogram(allSequentialPatchMatrix.ToArray()[i], allClusteringOutput.ToArray()[i]);
* convertedSpec.Add(PatchSampling.ConvertPatches(reconstructedSpec2, patchWidth, patchHeight, columnPerFreqBand));
* }
*
* sonogram2.Data = PatchSampling.ConcatFreqBandMatrices(convertedSpec);
*
* // DO DRAW SPECTROGRAM
* var reconstructedSpecImage = sonogram2.GetImageFullyAnnotated(sonogram2.GetImage(), "RECONSTRUCTEDSPECTROGRAM: " + freqScale.ScaleType.ToString(), freqScale.GridLineLocations);
* reconstructedSpecImage.Save(outputReSpecImagePath);
*/
}
public void TestKmeansClustering()
{
var outputDir = this.outputDirectory;
var recordingsPath = PathHelper.ResolveAssetPath("FeatureLearning");
var folderPath = Path.Combine(recordingsPath, "random_audio_segments");
var outputImagePath = Path.Combine(outputDir.FullName, "ReconstrcutedSpectrogram.png");
// check whether there is any file in the folder/subfolders
if (Directory.GetFiles(folderPath, "*", SearchOption.AllDirectories).Length == 0)
{
throw new ArgumentException("The folder of recordings is empty. Test will fail!");
}
// get the nyquist value from the first wav file in the folder of recordings
int nq = new AudioRecording(Directory.GetFiles(folderPath, "*.wav")[0]).Nyquist;
int nyquist = nq;
int frameSize = 1024;
int finalBinCount = 128;
int hertzInterval = 1000;
FreqScaleType scaleType = FreqScaleType.Mel;
var freqScale = new FrequencyScale(scaleType, nyquist, frameSize, finalBinCount, hertzInterval);
var sonoConfig = new SonogramConfig
{
WindowSize = frameSize,
//WindowOverlap is set based on the fact that each 24 frames is equal to 1 second
WindowOverlap = 0.1028,
DoMelScale = (scaleType == FreqScaleType.Mel) ? true : false,
MelBinCount = (scaleType == FreqScaleType.Mel) ? finalBinCount : frameSize / 2,
NoiseReductionType = NoiseReductionType.None,
};
int numberOfFreqBand = 4;
int patchWidth = finalBinCount / numberOfFreqBand;
int patchHeight = 1;
int numberOfRandomPatches = 20;
// Define variable number of "randomPatch" lists based on "numberOfFreqBand"
Dictionary <string, List <double[, ]> > randomPatchLists = new Dictionary <string, List <double[, ]> >();
for (int i = 0; i < numberOfFreqBand; i++)
{
randomPatchLists.Add(string.Format("randomPatch{0}", i.ToString()), new List <double[, ]>());
}
List <double[, ]> randomPatches = new List <double[, ]>();
foreach (string filePath in Directory.GetFiles(folderPath, "*.wav"))
{
FileInfo fileInfo = filePath.ToFileInfo();
// process the wav file if it is not empty
if (fileInfo.Length != 0)
{
var recording = new AudioRecording(filePath);
sonoConfig.SourceFName = recording.BaseName;
var sonogram = new SpectrogramStandard(sonoConfig, recording.WavReader);
// DO RMS NORMALIZATION
sonogram.Data = SNR.RmsNormalization(sonogram.Data);
// DO NOISE REDUCTION
sonogram.Data = PcaWhitening.NoiseReduction(sonogram.Data);
// creating matrices from different freq bands of the source spectrogram
List <double[, ]> allSubmatrices = PatchSampling.GetFreqBandMatrices(sonogram.Data, numberOfFreqBand);
// Second: selecting random patches from each freq band matrix and add them to the corresponding patch list
int count = 0;
while (count < allSubmatrices.Count)
{
randomPatchLists[string.Format("randomPatch{0}", count.ToString())].Add(PatchSampling.GetPatches(allSubmatrices.ToArray()[count], patchWidth, patchHeight, numberOfRandomPatches, PatchSampling.SamplingMethod.Random).ToMatrix());
count++;
}
}
}
foreach (string key in randomPatchLists.Keys)
{
randomPatches.Add(PatchSampling.ListOf2DArrayToOne2DArray(randomPatchLists[key]));
}
// convert list of random patches matrices to one matrix
int numberOfClusters = 32;
List <KMeansClusterCollection> allClusteringOutput = new List <KMeansClusterCollection>();
for (int i = 0; i < randomPatches.Count; i++)
{
double[,] patchMatrix = randomPatches[i];
// Do k-means clustering
string pathToClusterCsvFile = Path.Combine(outputDir.FullName, "ClusterCentroids" + i.ToString() + ".csv");
var clusteringOutput = KmeansClustering.Clustering(patchMatrix, numberOfClusters);
// sorting clusters based on size and output it to a csv file
Dictionary <int, double> clusterIdSize = clusteringOutput.ClusterIdSize;
int[] sortOrder = KmeansClustering.SortClustersBasedOnSize(clusterIdSize);
// Write cluster ID and size to a CSV file
string pathToClusterSizeCsvFile = Path.Combine(outputDir.FullName, "ClusterSize" + i.ToString() + ".csv");
Csv.WriteToCsv(pathToClusterSizeCsvFile.ToFileInfo(), clusterIdSize);
// Draw cluster image directly from clustering output
List <KeyValuePair <int, double[]> > listCluster = clusteringOutput.ClusterIdCentroid.ToList();
double[][] centroids = new double[listCluster.Count][];
for (int j = 0; j < listCluster.Count; j++)
{
centroids[j] = listCluster[j].Value;
}
allClusteringOutput.Add(clusteringOutput.Clusters);
List <double[, ]> allCentroids = new List <double[, ]>();
for (int k = 0; k < centroids.Length; k++)
{
// convert each centroid to a matrix in order of cluster ID
// OR: in order of cluster size
double[,] centroid = MatrixTools.ArrayToMatrixByColumn(centroids[sortOrder[k]], patchWidth, patchHeight);
// normalize each centroid
double[,] normalizedCentroid = DataTools.normalise(centroid);
// add a row of zero to each centroid
double[,] newCentroid = PatchSampling.AddRow(normalizedCentroid);
allCentroids.Add(newCentroid);
}
// concatenate all centroids
double[,] mergedCentroidMatrix = PatchSampling.ListOf2DArrayToOne2DArray(allCentroids);
// Draw clusters
var clusterImage = ImageTools.DrawMatrixWithoutNormalisation(mergedCentroidMatrix);
clusterImage.RotateFlip(RotateFlipType.Rotate270FlipNone);
var outputClusteringImage = Path.Combine(outputDir.FullName, "ClustersWithGrid" + i.ToString() + ".bmp");
FrequencyScale.DrawFrequencyLinesOnImage((Bitmap)clusterImage, freqScale, includeLabels: false);
clusterImage.Save(outputClusteringImage);
}
//+++++++++++++++++++++++++++++++++++++++++++Reconstructing a target spectrogram from sequential patches and the cluster centroids
var recording2Path = PathHelper.ResolveAsset("Recordings", "BAC2_20071008-085040.wav");
var recording2 = new AudioRecording(recording2Path);
var sonogram2 = new SpectrogramStandard(sonoConfig, recording2.WavReader);
var targetSpec = sonogram2.Data;
// Do RMS normalization
sonogram2.Data = SNR.RmsNormalization(sonogram2.Data);
// NOISE REDUCTION
sonogram2.Data = PcaWhitening.NoiseReduction(sonogram2.Data);
// extracting sequential patches from the target spectrogram
List <double[, ]> allSubmatrices2 = PatchSampling.GetFreqBandMatrices(sonogram2.Data, numberOfFreqBand);
double[][,] matrices2 = allSubmatrices2.ToArray();
List <double[, ]> allSequentialPatchMatrix = new List <double[, ]>();
for (int i = 0; i < matrices2.GetLength(0); i++)
{
int rows = matrices2[i].GetLength(0);
int columns = matrices2[i].GetLength(1);
var sequentialPatches = PatchSampling.GetPatches(matrices2[i], patchWidth, patchHeight, (rows / patchHeight) * (columns / patchWidth), PatchSampling.SamplingMethod.Sequential);
allSequentialPatchMatrix.Add(sequentialPatches.ToMatrix());
}
List <double[, ]> convertedSpectrogram = new List <double[, ]>();
int columnPerFreqBand = sonogram2.Data.GetLength(1) / numberOfFreqBand;
for (int i = 0; i < allSequentialPatchMatrix.Count; i++)
{
double[,] reconstructedSpec2 = KmeansClustering.ReconstructSpectrogram(allSequentialPatchMatrix.ToArray()[i], allClusteringOutput.ToArray()[i]);
convertedSpectrogram.Add(PatchSampling.ConvertPatches(reconstructedSpec2, patchWidth, patchHeight, columnPerFreqBand));
}
sonogram2.Data = PatchSampling.ConcatFreqBandMatrices(convertedSpectrogram);
// DO DRAW SPECTROGRAM
var reconstructedSpecImage = sonogram2.GetImageFullyAnnotated(sonogram2.GetImage(), "RECONSTRUCTEDSPECTROGRAM: " + freqScale.ScaleType.ToString(), freqScale.GridLineLocations);
reconstructedSpecImage.Save(outputImagePath, ImageFormat.Png);
// DO UNIT TESTING
Assert.AreEqual(targetSpec.GetLength(0), sonogram2.Data.GetLength(0));
Assert.AreEqual(targetSpec.GetLength(1), sonogram2.Data.GetLength(1));
}