/// <summary> /// Apply a trained forest to some test data. /// </summary> /// <typeparam name="F">Type of split function</typeparam> /// <param name="forest">Trained forest</param> /// <param name="testData">Test data</param> /// <returns>An array of class distributions, one per test data point</returns> public static HistogramAggregator[] Test <F>(Forest <F, HistogramAggregator> forest, DataPointCollection testData) where F : IFeatureResponse { int nClasses = forest.GetTree(0).GetNode(0).TrainingDataStatistics.BinCount; int[][] leafIndicesPerTree = forest.Apply(testData); HistogramAggregator[] result = new HistogramAggregator[testData.Count()]; for (int i = 0; i < testData.Count(); i++) { // Aggregate statistics for this sample over all leaf nodes reached result[i] = new HistogramAggregator(nClasses); for (int t = 0; t < forest.TreeCount; t++) { int leafIndex = leafIndicesPerTree[t][i]; result[i].Aggregate(forest.GetTree(t).GetNode(leafIndex).TrainingDataStatistics); } } return(result); }
public static Bitmap Visualize( Forest <AxisAlignedFeatureResponse, GaussianAggregator2d> forest, DataPointCollection trainingData, Size PlotSize, PointF PlotDilation) { // Generate some test samples in a grid pattern (a useful basis for creating visualization images) PlotCanvas plotCanvas = new PlotCanvas(trainingData.GetRange(0), trainingData.GetRange(1), PlotSize, PlotDilation); // Apply the trained forest to the test data Console.WriteLine("\nApplying the forest to test data..."); DataPointCollection testData = DataPointCollection.Generate2dGrid(plotCanvas.plotRangeX, PlotSize.Width, plotCanvas.plotRangeY, PlotSize.Height); int[][] leafNodeIndices = forest.Apply(testData); // Compute normalization factors per node int nTrainingPoints = (int)(trainingData.Count()); // could also count over tree nodes if training data no longer accessible double[][] normalizationFactors = new double[forest.TreeCount][]; for (int t = 0; t < forest.TreeCount; t++) { normalizationFactors[t] = new double[forest.GetTree(t).NodeCount]; ComputeNormalizationFactorsRecurse(forest.GetTree(t), 0, nTrainingPoints, new Bounds(2), normalizationFactors[t]); } Bitmap result = new Bitmap(PlotSize.Width, PlotSize.Height); // Paint the test data int index = 0; for (int j = 0; j < PlotSize.Height; j++) { for (int i = 0; i < PlotSize.Width; i++) { // Map pixel coordinate (i,j) in visualization image back to point in input space float x = plotCanvas.plotRangeX.Item1 + i * plotCanvas.stepX; float y = plotCanvas.plotRangeY.Item1 + j * plotCanvas.stepY; // Aggregate statistics for this sample over all trees double probability = 0.0; for (int t = 0; t < forest.TreeCount; t++) { int leafIndex = leafNodeIndices[t][index]; probability += normalizationFactors[t][leafIndex] * forest.GetTree(t).GetNode(leafIndex).TrainingDataStatistics.GetPdf().GetProbability(x, y); } probability /= forest.TreeCount; // 'Gamma correct' probability density for better display float l = (float)(LuminanceScaleFactor * Math.Pow(probability, Gamma)); if (l < 0) { l = 0; } else if (l > 255) { l = 255; } Color c = Color.FromArgb(255, (byte)(l), 0, 0); result.SetPixel(i, j, c); index++; } } // Also plot the original training data using (Graphics g = Graphics.FromImage(result)) { g.InterpolationMode = System.Drawing.Drawing2D.InterpolationMode.HighQualityBicubic; g.SmoothingMode = System.Drawing.Drawing2D.SmoothingMode.HighQuality; for (int s = 0; s < trainingData.Count(); s++) { PointF x = new PointF( (trainingData.GetDataPoint(s)[0] - plotCanvas.plotRangeX.Item1) / plotCanvas.stepX, (trainingData.GetDataPoint(s)[1] - plotCanvas.plotRangeY.Item1) / plotCanvas.stepY); RectangleF rectangle = new RectangleF(x.X - 2.0f, x.Y - 2.0f, 4.0f, 4.0f); g.FillRectangle(new SolidBrush(DataPointColor), rectangle); g.DrawRectangle(new Pen(Color.Black), rectangle.X, rectangle.Y, rectangle.Width, rectangle.Height); } } return(result); }
static void Main(string[] args) { if (args.Length == 0 || args[0] == "/?" || args[0].ToLower() == "help") { DisplayHelp(); return; } // These command line parameters are reused over several command line modes... StringParameter trainingDataPath = new StringParameter("path", "Path of file containing training data."); NaturalParameter T = new NaturalParameter("t", "No. of trees in the forest (default = {0}).", 10); NaturalParameter D = new NaturalParameter("d", "Maximum tree levels (default = {0}).", 10, 20); NaturalParameter F = new NaturalParameter("f", "No. of candidate feature responses per decision node (default = {0}).", 10); NaturalParameter L = new NaturalParameter("l", "No. of candidate thresholds per feature response (default = {0}).", 1); SingleParameter a = new SingleParameter("a", "The number of 'effective' prior observations (default = {0}).", true, false, 10.0f); SingleParameter b = new SingleParameter("b", "The variance of the effective observations (default = {0}).", true, true, 400.0f); SimpleSwitchParameter verboseSwitch = new SimpleSwitchParameter("Enables verbose progress indication."); SingleParameter plotPaddingX = new SingleParameter("padx", "Pad plot horizontally (default = {0}).", true, false, 0.1f); SingleParameter plotPaddingY = new SingleParameter("pady", "Pad plot vertically (default = {0}).", true, false, 0.1f); EnumParameter split = new EnumParameter( "s", "Specify what kind of split function to use (default = {0}).", new string[] { "axis", "linear" }, new string[] { "axis-aligned split", "linear split" }, "axis"); // Behaviour depends on command line mode... string mode = args[0].ToLower(); // first argument defines the command line mode if (mode == "clas" || mode == "class") { #region Supervised classification CommandLineParser parser = new CommandLineParser(); parser.Command = "SW " + mode.ToUpper(); parser.AddArgument(trainingDataPath); parser.AddSwitch("T", T); parser.AddSwitch("D", D); parser.AddSwitch("F", F); parser.AddSwitch("L", L); parser.AddSwitch("SPLIT", split); parser.AddSwitch("PADX", plotPaddingX); parser.AddSwitch("PADY", plotPaddingY); parser.AddSwitch("VERBOSE", verboseSwitch); // Default values up above should be fine here. if (args.Length == 1) { parser.PrintHelp(); DisplayTextFiles(CLAS_DATA_PATH); return; } if (parser.Parse(args, 1) == false) { return; } TrainingParameters trainingParameters = new TrainingParameters() { MaxDecisionLevels = D.Value - 1, NumberOfCandidateFeatures = F.Value, NumberOfCandidateThresholdsPerFeature = L.Value, NumberOfTrees = T.Value, Verbose = verboseSwitch.Used }; PointF plotDilation = new PointF(plotPaddingX.Value, plotPaddingY.Value); DataPointCollection trainingData = LoadTrainingData( trainingDataPath.Value, CLAS_DATA_PATH, 2, DataDescriptor.HasClassLabels); if (split.Value == "linear") { Forest <LinearFeatureResponse2d, HistogramAggregator> forest = ClassificationExample.Train( trainingData, new LinearFeatureFactory(), trainingParameters); using (Bitmap result = ClassificationExample.Visualize(forest, trainingData, new Size(300, 300), plotDilation)) { ShowVisualizationImage(result); } } else if (split.Value == "axis") { Forest <AxisAlignedFeatureResponse, HistogramAggregator> forest = ClassificationExample.Train( trainingData, new AxisAlignedFeatureFactory(), trainingParameters); using (Bitmap result = ClassificationExample.Visualize(forest, trainingData, new Size(300, 300), plotDilation)) { ShowVisualizationImage(result); } } #endregion } else if (mode == "density") { #region Density Estimation CommandLineParser parser = new CommandLineParser(); parser.Command = "SW " + mode.ToUpper(); parser.AddArgument(trainingDataPath); parser.AddSwitch("T", T); parser.AddSwitch("D", D); parser.AddSwitch("F", F); parser.AddSwitch("L", L); // For density estimation (and semi-supervised learning) we add // a command line option to set the hyperparameters of the prior. parser.AddSwitch("a", a); parser.AddSwitch("b", b); parser.AddSwitch("PADX", plotPaddingX); parser.AddSwitch("PADY", plotPaddingY); parser.AddSwitch("VERBOSE", verboseSwitch); // Override default values for command line options. T.Value = 1; D.Value = 3; F.Value = 5; L.Value = 1; a.Value = 0; b.Value = 900; if (args.Length == 1) { parser.PrintHelp(); DisplayTextFiles(DENSITY_DATA_PATH); return; } if (parser.Parse(args, 1) == false) { return; } TrainingParameters parameters = new TrainingParameters() { MaxDecisionLevels = D.Value - 1, NumberOfCandidateFeatures = F.Value, NumberOfCandidateThresholdsPerFeature = L.Value, NumberOfTrees = T.Value, Verbose = verboseSwitch.Used }; DataPointCollection trainingData = LoadTrainingData( trainingDataPath.Value, DENSITY_DATA_PATH, 2, DataDescriptor.Unadorned); Forest <AxisAlignedFeatureResponse, GaussianAggregator2d> forest = DensityEstimationExample.Train(trainingData, parameters, a.Value, b.Value); PointF plotDilation = new PointF(plotPaddingX.Value, plotPaddingY.Value); using (Bitmap result = DensityEstimationExample.Visualize(forest, trainingData, new Size(300, 300), plotDilation)) { ShowVisualizationImage(result); } #endregion } else if (mode == "ssclas" || mode == "ssclas") { #region Semi-supervised classification CommandLineParser parser = new CommandLineParser(); parser.Command = "SW " + mode.ToUpper(); parser.AddArgument(trainingDataPath); parser.AddSwitch("T", T); parser.AddSwitch("D", D); parser.AddSwitch("F", F); parser.AddSwitch("L", L); parser.AddSwitch("split", split); parser.AddSwitch("a", a); parser.AddSwitch("b", b); EnumParameter plotMode = new EnumParameter( "plot", "Determines what to plot", new string[] { "density", "labels" }, new string[] { "plot recovered density estimate", "plot class likelihood" }, "labels"); parser.AddSwitch("plot", plotMode); parser.AddSwitch("PADX", plotPaddingX); parser.AddSwitch("PADY", plotPaddingY); parser.AddSwitch("VERBOSE", verboseSwitch); // Override default values for command line options. T.Value = 10; D.Value = 12 - 1; F.Value = 30; L.Value = 1; if (args.Length == 1) { parser.PrintHelp(); DisplayTextFiles(SSCLAS_DATA_PATH); return; } if (parser.Parse(args, 1) == false) { return; } DataPointCollection trainingData = LoadTrainingData( trainingDataPath.Value, SSCLAS_DATA_PATH, 2, DataDescriptor.HasClassLabels); TrainingParameters parameters = new TrainingParameters() { MaxDecisionLevels = D.Value - 1, NumberOfCandidateFeatures = F.Value, NumberOfCandidateThresholdsPerFeature = L.Value, NumberOfTrees = T.Value, Verbose = verboseSwitch.Used }; Forest <LinearFeatureResponse2d, SemiSupervisedClassificationStatisticsAggregator> forest = SemiSupervisedClassificationExample.Train( trainingData, parameters, a.Value, b.Value); PointF plotPadding = new PointF(plotPaddingX.Value, plotPaddingY.Value); if (plotMode.Value == "labels") { using (Bitmap result = SemiSupervisedClassificationExample.VisualizeLabels(forest, trainingData, new Size(300, 300), plotPadding)) { ShowVisualizationImage(result); } } else if (plotMode.Value == "density") { using (Bitmap result = SemiSupervisedClassificationExample.VisualizeDensity(forest, trainingData, new Size(300, 300), plotPadding)) { ShowVisualizationImage(result); } } #endregion } else if (mode == "regression") { #region Regression CommandLineParser parser = new CommandLineParser(); parser.Command = "SW " + mode.ToUpper(); parser.AddArgument(trainingDataPath); parser.AddSwitch("T", T); parser.AddSwitch("D", D); parser.AddSwitch("F", F); parser.AddSwitch("L", L); parser.AddSwitch("PADX", plotPaddingX); parser.AddSwitch("PADY", plotPaddingY); parser.AddSwitch("VERBOSE", verboseSwitch); // Override default values for command line options T.Value = 10; D.Value = 2; a.Value = 0; // prior turned off by default b.Value = 900; if (args.Length == 1) { parser.PrintHelp(); DisplayTextFiles(REGRESSION_DATA_PATH); return; } if (parser.Parse(args, 1) == false) { return; } RegressionExample regressionDemo = new RegressionExample(); regressionDemo.PlotDilation.X = plotPaddingX.Value; regressionDemo.PlotDilation.Y = plotPaddingY.Value; regressionDemo.TrainingParameters = new TrainingParameters() { MaxDecisionLevels = D.Value - 1, NumberOfCandidateFeatures = F.Value, NumberOfCandidateThresholdsPerFeature = L.Value, NumberOfTrees = T.Value, Verbose = verboseSwitch.Used }; DataPointCollection trainingData = LoadTrainingData( trainingDataPath.Value, REGRESSION_DATA_PATH, 1, DataDescriptor.HasTargetValues); using (Bitmap result = regressionDemo.Run(trainingData)) { ShowVisualizationImage(result); } #endregion } else { Console.WriteLine("Unrecognized command line argument, try SW HELP."); return; } }
public static Bitmap Visualize <F>( Forest <F, HistogramAggregator> forest, DataPointCollection trainingData, Size PlotSize, PointF PlotDilation) where F : IFeatureResponse { // Size PlotSize = new Size(300, 300), PointF PlotDilation = new PointF(0.1f, 0.1f) // Generate some test samples in a grid pattern (a useful basis for creating visualization images) PlotCanvas plotCanvas = new PlotCanvas(trainingData.GetRange(0), trainingData.GetRange(1), PlotSize, PlotDilation); DataPointCollection testData = DataPointCollection.Generate2dGrid(plotCanvas.plotRangeX, PlotSize.Width, plotCanvas.plotRangeY, PlotSize.Height); Console.WriteLine("\nApplying the forest to test data..."); int[][] leafNodeIndices = forest.Apply(testData); // Form a palette of random colors, one per class Color[] colors = new Color[Math.Max(trainingData.CountClasses(), 4)]; // First few colours are same as those in the book, remainder are random. colors[0] = Color.FromArgb(183, 170, 8); colors[1] = Color.FromArgb(194, 32, 14); colors[2] = Color.FromArgb(4, 154, 10); colors[3] = Color.FromArgb(13, 26, 188); Color grey = Color.FromArgb(255, 127, 127, 127); System.Random r = new Random(0); // same seed every time so colours will be consistent for (int c = 4; c < colors.Length; c++) { colors[c] = Color.FromArgb(255, r.Next(0, 255), r.Next(0, 255), r.Next(0, 255)); } // Create a visualization image Bitmap result = new Bitmap(PlotSize.Width, PlotSize.Height); // For each pixel... int index = 0; for (int j = 0; j < PlotSize.Height; j++) { for (int i = 0; i < PlotSize.Width; i++) { // Aggregate statistics for this sample over all leaf nodes reached HistogramAggregator h = new HistogramAggregator(trainingData.CountClasses()); for (int t = 0; t < forest.TreeCount; t++) { int leafIndex = leafNodeIndices[t][index]; h.Aggregate(forest.GetTree(t).GetNode(leafIndex).TrainingDataStatistics); } // Let's muddy the colors with grey where the entropy is high. float mudiness = 0.5f * (float)(h.Entropy()); float R = 0.0f, G = 0.0f, B = 0.0f; for (int b = 0; b < trainingData.CountClasses(); b++) { float p = (1.0f - mudiness) * h.GetProbability(b); // NB probabilities sum to 1.0 over the classes R += colors[b].R * p; G += colors[b].G * p; B += colors[b].B * p; } R += grey.R * mudiness; G += grey.G * mudiness; B += grey.B * mudiness; Color c = Color.FromArgb(255, (byte)(R), (byte)(G), (byte)(B)); result.SetPixel(i, j, c); // painfully slow but safe index++; } } // Also draw the original training data using (Graphics g = Graphics.FromImage(result)) { g.InterpolationMode = System.Drawing.Drawing2D.InterpolationMode.HighQualityBicubic; g.SmoothingMode = System.Drawing.Drawing2D.SmoothingMode.HighQuality; for (int s = 0; s < trainingData.Count(); s++) { PointF x = new PointF( (trainingData.GetDataPoint(s)[0] - plotCanvas.plotRangeX.Item1) / plotCanvas.stepX, (trainingData.GetDataPoint(s)[1] - plotCanvas.plotRangeY.Item1) / plotCanvas.stepY); RectangleF rectangle = new RectangleF(x.X - 3.0f, x.Y - 3.0f, 6.0f, 6.0f); g.FillRectangle(new SolidBrush(colors[trainingData.GetIntegerLabel(s)]), rectangle); g.DrawRectangle(new Pen(Color.Black), rectangle.X, rectangle.Y, rectangle.Width, rectangle.Height); } } return(result); }
public static Bitmap VisualizeLabels(Forest <LinearFeatureResponse2d, SemiSupervisedClassificationStatisticsAggregator> forest, DataPointCollection trainingData, Size PlotSize, PointF PlotDilation) { // Generate some test samples in a grid pattern (a useful basis for creating visualization images) PlotCanvas plotCanvas = new PlotCanvas(trainingData.GetRange(0), trainingData.GetRange(1), PlotSize, PlotDilation); // Apply the trained forest to the test data Console.WriteLine("\nApplying the forest to test data..."); DataPointCollection testData = DataPointCollection.Generate2dGrid(plotCanvas.plotRangeX, PlotSize.Width, plotCanvas.plotRangeY, PlotSize.Height); int[][] leafNodeIndices = forest.Apply(testData); Bitmap result = new Bitmap(PlotSize.Width, PlotSize.Height); // Paint the test data GaussianPdf2d[][] leafDistributions = new GaussianPdf2d[forest.TreeCount][]; for (int t = 0; t < forest.TreeCount; t++) { leafDistributions[t] = new GaussianPdf2d[forest.GetTree(t).NodeCount]; for (int i = 0; i < forest.GetTree(t).NodeCount; i++) { Node <LinearFeatureResponse2d, SemiSupervisedClassificationStatisticsAggregator> nodeCopy = forest.GetTree(t).GetNode(i); if (nodeCopy.IsLeaf) { leafDistributions[t][i] = nodeCopy.TrainingDataStatistics.GaussianAggregator2d.GetPdf(); } } } // Form a palette of random colors, one per class Color[] colors = new Color[Math.Max(trainingData.CountClasses(), 4)]; // First few colours are same as those in the book, remainder are random. colors[0] = Color.FromArgb(183, 170, 8); colors[1] = Color.FromArgb(194, 32, 14); colors[2] = Color.FromArgb(4, 154, 10); colors[3] = Color.FromArgb(13, 26, 188); Color grey = Color.FromArgb(255, 127, 127, 127); System.Random r = new Random(0); // same seed every time so colours will be consistent for (int c = 4; c < colors.Length; c++) { colors[c] = Color.FromArgb(255, r.Next(0, 255), r.Next(0, 255), r.Next(0, 255)); } int index = 0; for (int j = 0; j < PlotSize.Height; j++) { for (int i = 0; i < PlotSize.Width; i++) { // Aggregate statistics for this sample over all leaf nodes reached HistogramAggregator h = new HistogramAggregator(trainingData.CountClasses()); for (int t = 0; t < forest.TreeCount; t++) { int leafIndex = leafNodeIndices[t][index]; SemiSupervisedClassificationStatisticsAggregator a = forest.GetTree(t).GetNode(leafIndex).TrainingDataStatistics; h.Aggregate(a.HistogramAggregator); } // Let's muddy the colors with a little grey where entropy is high. float mudiness = 0.5f * (float)(h.Entropy()); float R = 0.0f, G = 0.0f, B = 0.0f; for (int b = 0; b < trainingData.CountClasses(); b++) { float p = (1.0f - mudiness) * h.GetProbability(b); // NB probabilities sum to 1.0 over the classes R += colors[b].R * p; G += colors[b].G * p; B += colors[b].B * p; } R += grey.R * mudiness; G += grey.G * mudiness; B += grey.B * mudiness; Color c = Color.FromArgb(255, (byte)(R), (byte)(G), (byte)(B)); result.SetPixel(i, j, c); index++; } } PaintTrainingData(trainingData, plotCanvas, result); return(result); }