public FeatureRegistry Add(IFeatureFactory featureFactory)
{
if (featureFactory == null)
{
throw new ArgumentNullException(nameof(featureFactory));
}
if (_featureFactoriesById.ContainsKey(featureFactory.FeatureId))
{
throw new InvalidOperationException("A factory for the given " + nameof(featureFactory.FeatureId) + " already exists.");
}
var featureFactoryType = featureFactory.GetType();
if (_featureFactoriesByType.ContainsKey(featureFactoryType))
{
throw new InvalidOperationException("A factory for the given type " + featureFactoryType.FullName + " already exists.");
}
var featureFactories = new Dictionary <Guid, IFeatureFactory>(_featureFactoriesById)
{
{ featureFactory.FeatureId, featureFactory }
};
var featureFactoriesByType = new Dictionary <Type, IFeatureFactory>(_featureFactoriesByType)
{
{ featureFactoryType, featureFactory }
};
return(new FeatureRegistry(featureFactories, featureFactoriesByType, Default));
}
public FileBrowserViewModel(IServiceProvider serviceProvider, ILog log, IMessageService messageService,
IOptionsService optionsService, ISolutionProcessor solutionProcessor, IFileTypeResolver fileTypeResolver,
ISearchMatchService searchMatchService, IShellHelperService shellHelperService,
IShellImageService shellImageService, IUtilsService utilsService, IFeatureFactory featureFactory)
: base(KnownFeature.FileBrowser, serviceProvider)
{
_log = log;
_messageService = messageService;
_optionsService = optionsService;
_solutionProcessor = solutionProcessor;
_fileTypeResolver = fileTypeResolver;
_searchMatchService = searchMatchService;
_shellHelperService = shellHelperService;
_shellImageService = shellImageService;
_utilsService = utilsService;
_featureFactory = featureFactory;
// Source files must be setup in constructor or view won't show any binding data
_sourceFiles = new ObservableCollection <FileModel>();
_files = new CollectionViewSource {
Source = _sourceFiles
}; // must be ObservableCollection
this.ShowFilesCommand = new RelayCommand(_messageService, OnShowAllFiles);
this.OpenCodeBrowserAllCommand = new RelayCommand(_messageService, OnOpenCodeBrowserAll, OnCanOpenCodeBrowser);
this.OpenCodeBrowserClassesCommand = new RelayCommand(_messageService, OnOpenCodeBrowserClasses, OnCanOpenCodeBrowser);
this.OpenCodeBrowserMethodsCommand = new RelayCommand(_messageService, OnOpenCodeBrowserMethods, OnCanOpenCodeBrowser);
this.OpenCodeBrowserPropertiesCommand = new RelayCommand(_messageService, OnOpenCodeBrowserProperties, OnCanOpenCodeBrowser);
this.OpenFilesCommand = new RelayCommand(_messageService, OnOpenFiles, OnCanOpenFiles);
}
private FeatureRegistry(IDictionary <Guid, IFeatureFactory> featureFactoriesById, IDictionary <Type, IFeatureFactory> featureFactoriesByType, IFeatureFactory defaultFeatureFactory)
{
_featureFactoriesById = featureFactoriesById;
_featureFactoriesByType = featureFactoriesByType;
Default = defaultFeatureFactory;
}
/// <summary>
/// Construct a Decision Vine using the LSearch methodology.
/// </summary>
/// <param name="data">The data to use in training the vine</param>
/// <param name="factory">The feature factory to use when creating decision stumps</param>
/// <param name="numFeatures">The number of potential features to try</param>
/// <param name="numThresholds">The number of thresholds to try per feature</param>
/// <param name="maxChildren">The maximum allowed number of children</param>
/// <param name="maximumDepth">The maximum depth of the tree</param>
/// <param name="maxIterations">The number of optimization iterations to perform per level</param>
/// <param name="numLabels">The number of labels found in the data</param>
/// <returns>The Decision Vine</returns>
public static DecisionVine <T, D> ConstructUsingLSearch(List <T> data, IFeatureFactory <T, D> factory, int numFeatures, int numThresholds, int maxChildren, int maximumDepth, int maxIterations, int numLabels)
{
UpdateManager.WriteLine("Training Decision Vine with {0} data points...", data.Count);
DecisionVineNode <T, D> root = new DecisionVineNode <T, D>();
root.Data = data;
root.NodeType = NodeType.Branch;
root.Distribution = data.ComputeDistribution <T, D>(numLabels);
DecisionVineNode <T, D>[][] levels = new DecisionVineNode <T, D> [maximumDepth][];
levels[0] = new DecisionVineNode <T, D>[] { root };
for (int i = 1; i < maximumDepth; i++)
{
int numChildren = Math.Min(1 << i, maxChildren);
int numIterations = numChildren < maxChildren ? 0 : maxIterations;
UpdateManager.WriteLine("Training level {0} with {1} children and {2} optimization iterations...", i, numChildren, numIterations);
levels[i] = computeLSearchLevel(levels[i - 1], factory, numChildren, numFeatures, numLabels, numThresholds, numIterations);
UpdateManager.WriteLine("Level {0} complete with entropy {1}", i, computeEntropy(levels[i]));
UpdateManager.WriteLine("Data distribution: [{0}]", string.Join(",", levels[i].Select(o => o.Data.Count)));
}
foreach (var level in levels[maximumDepth - 1])
{
level.Distribution = level.Distribution.Normalize();
}
UpdateManager.WriteLine("Complete.");
return(new DecisionVine <T, D>(levels));
}
static public Forest <F, HistogramAggregator> Train <F>(
DataPointCollection trainingData,
IFeatureFactory <F> featureFactory,
TrainingParameters TrainingParameters) where F : IFeatureResponse
{
if (trainingData.Dimensions != 2)
{
throw new Exception("Training data points must be 2D.");
}
if (trainingData.HasLabels == false)
{
throw new Exception("Training data points must be labelled.");
}
if (trainingData.HasTargetValues == true)
{
throw new Exception("Training data points should not have target values.");
}
Console.WriteLine("Running training...");
Random random = new Random();
ITrainingContext <F, HistogramAggregator> classificationContext =
new ClassificationTrainingContext <F>(trainingData.CountClasses(), featureFactory, random);
var forest = ForestTrainer <F, HistogramAggregator> .TrainForest(
random,
TrainingParameters,
classificationContext,
trainingData);
return(forest);
}
/// <summary>
/// Trains a decision forest from <paramref name="splits"/> based on the provided parameters using the breadth first algorithm.
/// </summary>
/// <param name="numTrees">Number of trees in the forest</param>
/// <param name="splits">Data splits to use when training the tree.</param>
/// <param name="factory">The feature factory</param>
/// <param name="numFeatures">The number of features to try for each node</param>
/// <param name="numThresholds">The number of thresholds to try for each node</param>
/// <param name="labelNames">The names for the labels</param>
/// <param name="labelWeights">An array of weights for each label</param>
/// <param name="threshold">The threshold to use to determine a "good" feature test</param>
/// <returns>The trained forest</returns>
public static DecisionForest <T, D> ComputeBreadthFirst(
int numTrees,
List <T>[] splits,
IFeatureFactory <T, D> factory,
int numFeatures,
int numThresholds,
string[] labelNames,
float[] labelWeights,
float threshold
)
{
int numLabels = labelNames.Length;
DecisionTree <T, D>[] trees = new DecisionTree <T, D> [numTrees];
int count = 0;
for (byte i = 0; i < numTrees; i++)
{
UpdateManager.WriteLine(string.Format("Training tree {0} of {1}...", i + 1, numTrees));
int split = i % splits.Length;
trees[i] = DecisionTree <T, D> .ComputeBreadthFirst(splits[split], factory, numFeatures, numThresholds, numLabels, labelWeights, threshold);
count = trees[i].SetTreeLabel(i, count);
UpdateManager.WriteLine("\ndone");
}
UpdateManager.WriteLine("Training complete");
return(new DecisionForest <T, D>(trees, labelNames));
}
/// <summary>
/// Creates an instance of this class, filled with the given <paramref name="features"/>.
/// </summary>
/// <param name="features">The features to add to the collection</param>
public FeatureCollection(IEnumerable <IFeature <T> > features)
{
Name = "FC" + Guid.NewGuid();
_factory = (IFeatureFactory <T>)features.First().Factory;
foreach (var feature in features)
{
Add(feature);
}
}
/// <summary>
/// Computes the tree from the provided data.
/// </summary>
/// <param name="data">The data to use when computing the tree</param>
/// <param name="factory">The factory which generates the random features</param>
/// <param name="numFeatures">The number of features to try at each level</param>
/// <param name="numThresholds">Number of test thresholds to try</param>
/// <param name="min_rd">The minimum relative density of a node (as a stopping condition)</param>
/// <param name="min_y">The minimum number of points in a node as a percentage of total data points (used as a stopping condition)</param>
/// <param name="maxDepth">The maximum depth of the tree</param>
/// <returns></returns>
public static RandomClusterTree <T> Compute(
List <T> data,
IFeatureFactory <T, float[]> factory,
int numFeatures,
int numThresholds,
float min_rd,
float min_y,
byte maxDepth)
{
return(new RandomClusterTree <T>(compute(data, data.Count, factory, numFeatures, numThresholds, min_rd, (int)(min_y * data.Count), 0, maxDepth)));
}
/// <summary>
/// Constructs a CLTree from the provided data.
/// </summary>
/// <param name="data">The data to use in constructing the tree</param>
/// <param name="factory">The factory used to create features</param>
/// <param name="numFeatures">The number of features to use</param>
/// <returns>A CLTree</returns>
public static CLTree <T> Compute(List <T> data, IFeatureFactory <T, float[]> factory, int numFeatures)
{
Hyperrectangle <float> bounds = new Hyperrectangle <float>(numFeatures, float.MaxValue, float.MinValue);
fillFeatureValues(factory, numFeatures, data);
for (int i = 0; i < numFeatures; i++)
{
bounds.MinimumBound[i] = _featureValues[i].Min();
bounds.MaximumBound[i] = _featureValues[i].Max();
}
return(new CLTree <T>(split(Enumerable.Range(0, data.Count).ToList(), data.Count, bounds), _buildFeatures));
}
private static void fillFeatureValues(IFeatureFactory <T, float[]> factory, int numFeatures, List <T> data)
{
_numFeatures = numFeatures;
_buildFeatures = new IFeature <T, float[]> [numFeatures];
_featureValues = new float[numFeatures][];
for (int i = 0; i < numFeatures; i++)
{
IFeature <T, float[]> feature = factory.Create();
_featureValues[i] = data.Select(o => feature.Compute(o)).ToArray();
_buildFeatures[i] = feature;
}
}
/// <summary>
/// Constructs a new decision tree using the breadth-first method. This method will attempt to split each leaf node in the tree with each step, and will stop when
/// <see cref="F:MaximumDepth" /> is reached or it is unable to split any leaf nodes. If no nodes split in a step, it will try again <see cref="F:NumberOfTries" /> times, and then
/// stop. A node will only be split if the resulting entropy increase is above <paramref name="threshold"/>.
/// </summary>
/// <param name="data">The data to use when constructing the tree</param>
/// <param name="factory">The feature factory to use for producing sample feature test for each node</param>
/// <param name="numFeatures">The number of sample feature tests to try</param>
/// <param name="numThresholds">The number of test thresholds to try with each test</param>
/// <param name="numLabels">The number of possible labels for a point</param>
/// <param name="labelWeights">The weights for each label</param>
/// <param name="threshold">Threshold used to determine a good feature test</param>
/// <returns>A new decision tree</returns>
public static DecisionTree <T, D> ComputeBreadthFirst
(
List <T> data,
IFeatureFactory <T, D> factory,
int numFeatures,
int numThresholds,
int numLabels,
float[] labelWeights,
float threshold
)
{
_isBuilding = true;
DecisionTreeNode <T, D> root = computeBreadthFirst(threshold, data, factory, numFeatures, numThresholds, numLabels, labelWeights);
_isBuilding = false;
return(new DecisionTree <T, D>(root, labelWeights, numLabels));
}
public static FeatureRegistry WithDefault(IFeatureFactory featureFactory)
{
if (featureFactory == null)
{
throw new ArgumentNullException(nameof(featureFactory));
}
var featureFactoriesById = new Dictionary <Guid, IFeatureFactory>
{
{ featureFactory.FeatureId, featureFactory }
};
var featureFactoriesByType = new Dictionary <Type, IFeatureFactory>
{
{ featureFactory.GetType(), featureFactory }
};
return(new FeatureRegistry(featureFactoriesById, featureFactoriesByType, featureFactory));
}
private void GenerateFeatures()
{
AllFeatures = new List <IFeature>();
_currFeatureCount = 0;
// start top left
FeaturePosition position = new FeaturePosition(1, 1, Direction.None);
Vector3Int size = RoomSize.GetRandomValue();
IFeature tempFeature = null;
StartPos = position + new Vector3Int(size.x / 2, size.y / 2, 0);
_factories[0].TryCreateFeature(position, size.ToVector2Int(), Tilemap, ref tempFeature);
_featureQueue.Enqueue(tempFeature);
AllFeatures.Add(tempFeature);
_currFeatureCount++;
while (_featureQueue.Count > 0 && _currFeatureCount < FeatureCount)
{
var lastFeature = _featureQueue.Dequeue();
position = lastFeature.GetNewFeaturePosition();
size = RoomSize.GetRandomValue();
Debug.Log($"feature at {position.ToString()} of size {size}");
IFeatureFactory factory = _factories[Random.Range(0, _factories.Count)];
IFeature newFeature = null;
if (factory.TryCreateFeature(position, size.ToVector2Int(), Tilemap, ref newFeature))
{
lastFeature.AddExit(position);
AllFeatures.Add(newFeature);
_featureQueue.Enqueue(newFeature);
_currFeatureCount++;
}
if (lastFeature.CanMakeNewFeature())
{
_featureQueue.Enqueue(lastFeature);
}
}
}
/// <summary>
/// Trains a decision forest from <paramref name="splits"/> based on the provided parameters using the depth first algorithm.
/// </summary>
/// <param name="numTrees">Number of trees in the forest</param>
/// <param name="splits">Data splits to use when training the tree.</param>
/// <param name="factory">The feature factory</param>
/// <param name="numFeatures">The number of features to try for each node</param>
/// <param name="numThresholds">The number of thresholds to try for each node</param>
/// <param name="labelNames">The names for the labels</param>
/// <param name="labelWeights">An array of weights for each label</param>
/// <returns>The trained forest</returns>
public static DecisionForest <T, D> ComputeDepthFirst(
int numTrees,
List <T>[] splits,
IFeatureFactory <T, D> factory,
int numFeatures,
int numThresholds,
string[] labelNames,
float[] labelWeights
)
{
int numLabels = labelNames.Length;
DecisionTree <T, D>[] trees = new DecisionTree <T, D> [numTrees];
int count = 0;
var indices = Enumerable.Range(0, numTrees).Select(o => (byte)o);
if (splits[0][0] is IComparable <T> )
{
foreach (var split in splits)
{
split.Sort();
}
}
foreach (var i in indices)
{
int split = i % splits.Length;
UpdateManager.WriteLine(string.Format("Training tree {0} of {1}...", i + 1, numTrees));
trees[i] = DecisionTree <T, D> .ComputeDepthFirst(splits[split], factory, numFeatures, numThresholds, numLabels, labelWeights);
trees[i].LabelCount = labelNames.Length;
count = trees[i].SetTreeLabel(i, count);
UpdateManager.WriteLine("\ndone");
}
;
UpdateManager.WriteLine("Training complete");
return(new DecisionForest <T, D>(trees, labelNames));
}
private static void findSplit(DecisionVineNode <T, D> node, IFeatureFactory <T, D> factory, float[] leftDistribution, float[] rightDistribution, int numFeatures, int numLabels, int numThresholds)
{
int dataCount = node.Data.Count;
using (ThreadLocal <DeciderState> results = new ThreadLocal <DeciderState>(() => new DeciderState(factory), true))
{
Parallel.For(0, numFeatures, i =>
{
results.Value.Current.LoadData(node.Data);
float energy = results.Value.Current.ChooseThreshold(numThresholds, numLabels, leftDistribution, rightDistribution);
if (energy < results.Value.BestEnergy)
{
results.Value.Best = results.Value.Current;
results.Value.BestEnergy = energy;
results.Value.Current = new Decider <T, D>(factory);
}
});
node.Decider = results.Values.OrderBy(o => o.BestEnergy).First().Best;
Decision[] decisions = node.Decider.Decide(node.Data);
float[] leftCounts = new float[numLabels];
float[] rightCounts = new float[numLabels];
for (int i = 0; i < decisions.Length; i++)
{
if (decisions[i] == Decision.Left)
{
leftCounts[node.Data[i].Label] += 1;
}
else
{
rightCounts[node.Data[i].Label] += 1;
}
}
node.LeftCounts = leftCounts;
node.RightCounts = rightCounts;
}
}
private static DecisionTreeNode <T, D> computeBreadthFirst(float threshold, List <T> data, IFeatureFactory <T, D> factory, int numFeatures, int numThresholds, int numLabels, float[] labelWeights)
{
string id = "DecisionTree.ComputeBreadthFirst";
Queue <SplitCandidate> candidates = new Queue <SplitCandidate>();
SplitCandidate start = new SplitCandidate(new List <int>(), 1, 0);
for (int i = 0; i < data.Count; i++)
{
start.Indices.Add(i);
}
start.Entropy = calculateEntropy(data, start.Indices, labelWeights, numLabels);
start.Support = calculateSupport(data, start.Indices, labelWeights);
candidates.Enqueue(start);
bool changed = true;
float[] leftDistribution, rightDistribution;
int tries = (int)_numberOfTries;
float increment = threshold / tries;
Dictionary <int, Decider <T, D> > deciders = new Dictionary <int, Decider <T, D> >();
while (tries > 0)
{
if (!changed)
{
threshold -= increment;
UpdateManager.WriteLine("Decreasing threshold to {0}", threshold);
}
GC.Collect();
int count = candidates.Count;
for (int i = 0; i < count; i++)
{
SplitCandidate candidate = candidates.Dequeue();
if (candidate.Delta)
{
candidates.Enqueue(candidate);
continue;
}
if (MaximumDepth > 0 && candidate.Level >= MaximumDepth - 1)
{
candidates.Enqueue(candidate);
continue;
}
if (candidate.Support < MinimumSupport)
{
candidates.Enqueue(candidate);
continue;
}
int dataCount = candidate.Indices.Count;
if (candidate.Values == null)
{
candidate.Values = new float[dataCount];
}
if (candidate.Labels == null)
{
candidate.Labels = new int[dataCount];
}
if (candidate.Weights == null)
{
candidate.Weights = new float[dataCount];
}
candidates.Enqueue(candidate);
}
float bestGain = float.MinValue;
for (int k = 0; k < numFeatures; k++)
{
UpdateManager.RaiseProgress(k, numFeatures);
Decider <T, D> decider = new Decider <T, D>(factory);
decider.ApplyFeature(data);
for (int i = 0; i < count; i++)
{
SplitCandidate candidate = candidates.Dequeue();
if (MaximumDepth > 0 && candidate.Level >= MaximumDepth - 1)
{
candidates.Enqueue(candidate);
continue;
}
if (candidate.Delta)
{
candidates.Enqueue(candidate);
continue;
}
if (candidate.Support < MinimumSupport)
{
candidates.Enqueue(candidate);
continue;
}
List <int> indices = candidate.Indices;
int dataCount = indices.Count;
for (int j = 0; j < dataCount; j++)
{
T point = data[indices[j]];
candidate.Values[j] = point.FeatureValue;
candidate.Labels[j] = point.Label;
candidate.Weights[j] = point.Weight;
}
decider.SetData(candidate.Values, candidate.Weights, candidate.Labels);
float gain = candidate.Entropy + decider.ChooseThreshold(numThresholds, numLabels, labelWeights, out leftDistribution, out rightDistribution);
bestGain = Math.Max(gain, bestGain);
if ((gain > threshold || candidate.Level < MinimumDepth) && gain > candidate.EntropyGain)
{
candidate.EntropyGain = gain;
candidate.Decider = new Decider <T, D>(decider.Feature, decider.Threshold);
}
candidates.Enqueue(candidate);
}
}
UpdateManager.WriteLine(id, "\rNodes Added:");
changed = false;
for (int i = 0; i < count; i++)
{
SplitCandidate candidate = candidates.Dequeue();
if (candidate.Decider == null)
{
candidates.Enqueue(candidate);
continue;
}
changed = true;
List <int> indices = candidate.Indices;
int dataCount = candidate.Indices.Count;
List <T> points = new List <T>();
for (int j = 0; j < dataCount; j++)
{
points.Add(data[indices[j]]);
}
Decision[] decisions = candidate.Decider.Decide(points);
List <int> left = new List <int>();
List <int> right = new List <int>();
for (int j = 0; j < dataCount; j++)
{
if (decisions[j] == Decision.Left)
{
left.Add(indices[j]);
}
else
{
right.Add(indices[j]);
}
}
SplitCandidate leftCandidate = new SplitCandidate(left, 2 * candidate.Index, candidate.Level + 1);
SplitCandidate rightCandidate = new SplitCandidate(right, 2 * candidate.Index + 1, candidate.Level + 1);
leftCandidate.Entropy = calculateEntropy(data, left, labelWeights, numLabels);
leftCandidate.Support = calculateSupport(data, left, labelWeights);
leftCandidate.Delta = calculateDelta(data, left);
rightCandidate.Entropy = calculateEntropy(data, right, labelWeights, numLabels);
rightCandidate.Support = calculateSupport(data, right, labelWeights);
rightCandidate.Delta = calculateDelta(data, right);
UpdateManager.WriteLine(id, "{3:00000}:{0:0.000}|{1:0.000} {2:0.000} {4}", leftCandidate.Support / candidate.Support, rightCandidate.Support / candidate.Support, candidate.EntropyGain, candidate.Index, candidate.Decider);
deciders[candidate.Index] = candidate.Decider;
candidates.Enqueue(leftCandidate);
candidates.Enqueue(rightCandidate);
}
if (!changed)
{
UpdateManager.WriteLine("No new nodes added, best entropy gain was {0}", bestGain);
tries--;
}
if (bestGain == float.MinValue)
{
break;
}
}
Dictionary <int, List <int> > leafIndices = new Dictionary <int, List <int> >();
while (candidates.Count > 0)
{
SplitCandidate candidate = candidates.Dequeue();
leafIndices[candidate.Index] = candidate.Indices;
}
return(buildTree(new DecisionTreeNode <T, D>(), 1, deciders, leafIndices, data, numLabels, labelWeights));
}
public DeciderState(IFeatureFactory <T, D> factory)
{
Current = new Decider <T, D>(factory);
BestEnergy = float.MaxValue;
}
private static DecisionVineNode <T, D>[] computeLSearchLevel(DecisionVineNode <T, D>[] parents, IFeatureFactory <T, D> factory, int numChildren, int numFeatures, int numLabels, int numThresholds, int numIterations)
{
DecisionVineNode <T, D>[] children = new DecisionVineNode <T, D> [numChildren];
// assign children in a greedy manner first
int index = 0;
Queue <DecisionVineNode <T, D> > parentQueue = new Queue <DecisionVineNode <T, D> >(parents.OrderByDescending(o => o.Data.Count * o.Distribution.CalculateEntropy()));
UpdateManager.WriteLine("Initializing children using highest-energy parents...");
while (index < numChildren)
{
var parent = parentQueue.Dequeue();
findSplit(parent, factory, new float[numLabels], new float[numLabels], numFeatures, numLabels, numThresholds);
children[index] = parent.Left = new DecisionVineNode <T, D>();
children[index].Index = index++;
if (index < numChildren)
{
children[index] = parent.Right = new DecisionVineNode <T, D>();
children[index].Index = index++;
}
else
{
parent.Right = findBestChild(parents, children, parent.RightCounts);
}
}
if (parentQueue.Any())
{
UpdateManager.WriteLine("Adding in parents without children...");
// we need to start adding nodes in without increasing the number of children
while (parentQueue.Any())
{
var parent = parentQueue.Dequeue();
if (parent.NodeType == NodeType.Leaf)
{
continue;
}
findSplit(parent, factory, new float[numLabels], new float[numLabels], numFeatures, numLabels, numThresholds);
parent.Left = findBestChild(parents, children, parent.LeftCounts);
parent.Right = findBestChild(parents, children, parent.RightCounts);
parent.Left.RemoveDistribution(parent.LeftCounts);
parent.Right.RemoveDistribution(parent.RightCounts);
findSplit(parent, factory, parent.Left.Distribution, parent.Right.Distribution, numFeatures, numLabels, numThresholds);
parent.Left.AddDistribution(parent.LeftCounts);
parent.Right.AddDistribution(parent.RightCounts);
}
}
UpdateManager.WriteLine("Optimizing...");
// optimize the nodes on this level
foreach (int i in UpdateManager.ProgressEnum(Enumerable.Range(0, numIterations)))
{
var parent = parents.SelectRandom();
if (parent.NodeType == NodeType.Leaf)
{
continue;
}
parent.Left = null;
parent.Left = findBestChild(parents, children, parent.LeftCounts);
parent.Right = null;
parent.Right = findBestChild(parents, children, parent.RightCounts);
parent.Left.RemoveDistribution(parent.LeftCounts);
parent.Right.RemoveDistribution(parent.RightCounts);
findSplit(parent, factory, parent.Left.Distribution, parent.Right.Distribution, numFeatures, numLabels, numThresholds);
parent.Left.AddDistribution(parent.LeftCounts);
parent.Right.AddDistribution(parent.RightCounts);
}
UpdateManager.WriteLine(" Done");
UpdateManager.WriteLine("Portioning out data to children...");
// fill the data
for (int i = 0; i < children.Length; i++)
{
children[i].Data = new List <T>();
}
for (int i = 0; i < parents.Length; i++)
{
var parent = parents[i];
if (parent.NodeType == NodeType.Leaf)
{
continue;
}
Decision[] decisions = parent.Decider.Decide(parent.Data);
for (int j = 0; j < decisions.Length; j++)
{
if (decisions[j] == Decision.Left)
{
parent.Left.Data.Add(parent.Data[j]);
}
else
{
parent.Right.Data.Add(parent.Data[j]);
}
}
parent.Data.Clear();
parent.Data = null;
}
for (int i = 0; i < children.Length; i++)
{
if (checkDelta(children[i].Data) || children[i].Data.Count < MinimumSupport)
{
children[i].NodeType = NodeType.Leaf;
}
else
{
children[i].NodeType = NodeType.Branch;
}
}
return(children);
}
/// <summary>
/// Creates an instance of this class just initialized with the <paramref name="factory"/>
/// </summary>
/// <param name="factory">The feature factory</param>
public FeatureCollection(IFeatureFactory <T> factory)
{
_factory = factory;
}
private static DecisionTreeNode <T, D> computeDepthFirst(DecisionTreeNode <T, D> node, List <T> data, IFeatureFactory <T, D> factory, int numFeatures, int numThresholds, int numLabels, float[] labelWeights, int depth)
{
GC.Collect();
if (data.Count == 0)
{
UpdateManager.WriteLine("No data at depth {0}", depth);
return(null);
}
if (data[0] is IComparable <T> )
{
data.Sort();
}
if (checkDelta(data))
{
UpdateManager.WriteLine("Delta function at depth {0}", depth);
int label = data[0].Label;
float[] dist = new float[numLabels];
dist[label] = 1;
return(new DecisionTreeNode <T, D>(dist));
}
int dataCount = data.Count;
Decider <T, D> bestDecider = null;
float bestScore = float.MinValue;
float[] bestLeftDistribution = null;
float[] bestRightDistribution = null;
using (ThreadLocal <DecisionResult> results = new ThreadLocal <DecisionResult>(() => new DecisionResult {
Score = bestScore
}, true))
{
Parallel.For(0, numFeatures, i =>
{
float[] leftDistribution;
float[] rightDistribution;
Decider <T, D> decider = new Decider <T, D>(factory);
decider.LoadData(data);
float score = decider.ChooseThreshold(numThresholds, numLabels, labelWeights, out leftDistribution, out rightDistribution);
if (score > results.Value.Score)
{
results.Value = new DecisionResult {
LeftDistribution = leftDistribution, RightDistribution = rightDistribution, Decider = decider, Score = score
};
}
});
foreach (var result in results.Values)
{
if (result.Score > bestScore)
{
bestLeftDistribution = result.LeftDistribution;
bestRightDistribution = result.RightDistribution;
bestDecider = result.Decider;
bestScore = result.Score;
}
}
}
float support = 0;
if (labelWeights != null)
{
foreach (T point in data)
{
support += labelWeights[point.Label];
}
}
else
{
support = dataCount;
}
if (bestScore == float.MinValue || dataCount < MinimumSupport)
{
UpdateManager.WriteLine("Stopping due to lack of data at depth {0}, {1} < {2}", depth, dataCount, MinimumSupport);
float[] distribution = new float[numLabels];
for (int i = 0; i < dataCount; i++)
{
distribution[data[i].Label]++;
}
if (labelWeights != null)
{
for (int i = 0; i < distribution.Length; i++)
{
distribution[i] *= labelWeights[i];
}
}
return(new DecisionTreeNode <T, D>(distribution));
}
if (depth == MaximumDepth - 2)
{
UpdateManager.WriteLine("Last branch node trained at depth {0}", depth);
node.Left = new DecisionTreeNode <T, D>(bestLeftDistribution);
node.Right = new DecisionTreeNode <T, D>(bestRightDistribution);
node.NodeType = NodeType.Branch;
node.Decider = bestDecider;
return(node);
}
Decision[] decisions = bestDecider.Decide(data);
List <T> leftData = new List <T>();
List <T> rightData = new List <T>();
for (int i = 0; i < decisions.Length; i++)
{
if (decisions[i] == Decision.Left)
{
leftData.Add(data[i]);
}
else
{
rightData.Add(data[i]);
}
}
if (leftData.Count == 0 || rightData.Count == 0)
{
throw new Exception("Error");
}
UpdateManager.WriteLine("Branch node at depth {0} trained.", depth);
node.Left = computeDepthFirst(new DecisionTreeNode <T, D>(), leftData, factory, numFeatures, numThresholds, numLabels, labelWeights, depth + 1);
node.Right = computeDepthFirst(new DecisionTreeNode <T, D>(), rightData, factory, numFeatures, numThresholds, numLabels, labelWeights, depth + 1);
node.Decider = bestDecider;
node.NodeType = NodeType.Branch;
return(node);
}
/// <summary>
/// Creates a new feature collection based on the provided <paramref name="collection"/>.
/// </summary>
/// <param name="collection"></param>
protected FeatureCollection(FeatureCollection <T> collection)
: base(collection)
{
Name = collection.Name;
_factory = (IFeatureFactory <T>)collection.Factory;
}
public ClassificationTrainingContext(int nClasses, IFeatureFactory <F> featureFactory, Random random)
{
nClasses_ = nClasses;
featureFactory_ = featureFactory;
random_ = random;
}
/// <summary>
/// Adds <paramref name="factory"/> to the list of factories this combination factory will choose from.
/// </summary>
/// <param name="factory">Factory to add</param>
public void AddFactory(IFeatureFactory <T, D> factory)
{
_factories.Add(factory);
}
/// <summary>
/// For autofac initialization
/// </summary>
public S122DataParser(IGeometryBuilderFactory geometryBuilderFactory, IFeatureFactory featureFactory)
{
_geometryBuilderFactory = geometryBuilderFactory;
_featureFactory = featureFactory;
}
/// <summary>
/// Constructor.
/// </summary>
/// <param name="factory">The factory to use to create the feature for this Decider</param>
public Decider(IFeatureFactory <T, D> factory) : this(factory.Create(), 0)
{
}
private static Node compute(List <T> data, int NCount, IFeatureFactory <T, float[]> factory, int numFeatures, int numThresholds, float min_rd, int min_y, int currentDepth, int maxDepth)
{
if (currentDepth == maxDepth - 1)
{
return new Node {
NodeType = NodeType.Leaf
}
}
;
int YCount = data.Count;
if (NCount < YCount)
{
NCount = YCount;
}
Split best = new Split {
Score = float.MinValue
};
for (int i = 0; i < numFeatures; i++)
{
IFeature <T, float[]> feature = factory.Create();
var featureValues = from point in data
select feature.Compute(point);
Split split = findBestSplit(featureValues.OrderBy(o => o).ToArray(), min_rd, min_y, NCount, numThresholds);
if (split.Score > best.Score)
{
best = split;
best.Feature = feature;
}
}
if (best.Feature == null)
{
return new Node {
NodeType = NodeType.Leaf
}
}
;
Node node = new Node {
NodeType = NodeType.Branch, Feature = best.Feature, Threshold = best.Threshold
};
List <T> left = new List <T>();
List <T> right = new List <T>();
foreach (T point in data)
{
if (best.Feature.Compute(point) < best.Threshold)
{
left.Add(point);
}
else
{
right.Add(point);
}
}
if (left.Count == 0 || right.Count == 0)
{
return new Node {
NodeType = NodeType.Leaf
}
}
;
UpdateManager.WriteLine("{0}:{1} {2}|{3} {4}", currentDepth, best.Score, left.Count, right.Count, best.Feature);
node.Left = compute(left, best.NLeft, factory, numFeatures, numThresholds, min_rd, min_y, currentDepth + 1, maxDepth);
node.Right = compute(right, NCount - best.NLeft, factory, numFeatures, numThresholds, min_rd, min_y, currentDepth + 1, maxDepth);
return(node);
}
}
}
/// <summary>
/// Constructs a CLTree from the provided data.
/// </summary>
/// <param name="data">The data to use in construction</param>
/// <param name="factory">A factory to create feature dimensions</param>
/// <param name="numFeatures">The number of features to use</param>
/// <param name="bounds">The bounds of the data</param>
/// <returns>A CLTree</returns>
public static CLTree <T> Compute(List <T> data, IFeatureFactory <T, float[]> factory, int numFeatures, Hyperrectangle <float> bounds)
{
fillFeatureValues(factory, numFeatures, data);
return(new CLTree <T>(split(Enumerable.Range(0, data.Count).ToList(), data.Count, bounds), _buildFeatures));
}
/// <summary>
/// Removes <paramref name="factory"/> from the list of factories this combination factory chooses from.
/// </summary>
/// <param name="factory">Factory to remove</param>
public void RemoveFactory(IFeatureFactory <T, D> factory)
{
_factories.Remove(factory);
}
