4 instantiations of Dataset
Microsoft.ML.FastTree (4)
Dataset\Dataset.cs (2)
274null : new Dataset(datasetSkeletonPart[p], featureParts[p])).ToArray(numParts); 346Dataset dataset = new Dataset(datasetSkeleton, features);
FastTree.cs (2)
1635result = new Dataset(skeleton, features); 1940return new Dataset(CreateDatasetSkeleton(), flocks);
118 references to Dataset
Microsoft.ML.FastTree (118)
Dataset\Dataset.cs (7)
40/// Initializes a new instance of the <see cref="Dataset"/> class. 261public Dataset[] Split(double[] fraction, int randomSeed, bool destroyThisDataset) 273Dataset[] datasets = Enumerable.Range(0, numParts).Select(p => datasetSkeletonPart[p] == null ? 285public Dataset GetSubDataset(int[] docIndices, bool destroyThisDataset) 346Dataset dataset = new Dataset(datasetSkeleton, features); 916private readonly Dataset _dataset; 956public RowForwardIndexer(Dataset dataset, bool[] active = null)
Dataset\DatasetUtils.cs (1)
46public static TsvFeature CreateFeatureFromQueryId(Dataset.DatasetSkeleton skel)
Dataset\FeatureFlock.cs (2)
965/// in the larger context of a <see cref="Dataset"/> holding many flocks, the 968/// <see cref="Dataset.MapFeatureToFlockAndSubFeature"/> to see some details of this
FastTree.cs (21)
64private protected Dataset TrainSet; 65private protected Dataset ValidSet; 69private protected Dataset[] TestSets; 428private string GetDatasetStatistics(Dataset set) 823private protected ScoreTracker ConstructScoreTracker(Dataset set) 846private double[] ComputeScoresSmart(IChannel ch, Dataset set) 860private double[] ComputeScoresSlow(IChannel ch, Dataset set) 875private double[] GetInitScores(Dataset set) 990public abstract Dataset GetDataset(); 1262private readonly Dataset _dataset; 1282public override Dataset GetDataset() 1325private Dataset Construct(RoleMappedData examples, ref int numExamples, int maxBins, IParallelTraining parallelTraining) 1334Dataset result; 1632var skeleton = new Dataset.DatasetSkeleton(ratings, boundaries, qids, dids, new double[0][], actualLabels); 1933public override Dataset GetDataset() 2354private Dataset.DatasetSkeleton CreateDatasetSkeleton() 2359? new Dataset.DatasetSkeleton(_targetsList.ToArray(), _boundaries.ToArray(), queryIds, docIds, new double[0][]) 2360: new Dataset.DatasetSkeleton(_targetsList.ToArray(), _boundaries.ToArray(), queryIds, docIds, new double[0][], _actualTargets.ToArray()); 2744public Dataset FindBinsAndReturnDataset(RoleMappedData data, PredictionKind kind, IParallelTraining parallelTraining, 2755Dataset d = convData.GetDataset(); 2762public Dataset GetCompatibleDataset(RoleMappedData data, PredictionKind kind, int[] categoricalFeatures, bool categoricalSplit)
FastTreeClassification.cs (2)
244private IEnumerable<bool> GetClassificationLabelsFromRatings(Dataset set) 332Dataset trainSet,
FastTreeRanking.cs (5)
182Dataset.DatasetSkeleton.LabelGainMap = gains; 409private Test CreateStandardTest(Dataset dataset) 567public LambdaRankObjectiveFunction(Dataset trainset, short[] labels, Options options, IParallelTraining parallelTraining) 620_gain = Dataset.DatasetSkeleton.LabelGainMap; 824pScores[i] = pScores[i] * (1.0 - pLabels[i] * 1.0 / (20.0 * Dataset.DatasetSkeleton.LabelGainMap.Length));
FastTreeRegression.cs (3)
171internal static float[] GetDatasetRegressionLabels(Dataset set) 418public ObjectiveImpl(Dataset trainData, GamRegressionTrainer.Options options) : 431public ObjectiveImpl(Dataset trainData, Options options)
FastTreeTweedie.cs (2)
184internal static float[] GetDatasetRegressionLabels(Dataset set) 375public ObjectiveImpl(Dataset trainData, Options options)
GamTrainer.cs (3)
137private protected Dataset TrainSet; 138private protected Dataset ValidSet; 396private void UpdateScoresForSet(Dataset dataset, double[] scores, int iteration)
RandomForest.cs (1)
77protected RandomForestObjectiveFunction(Dataset trainData, TOptions options, double maxStepSize)
RandomForestClassification.cs (1)
388public ObjectiveFunctionImpl(Dataset trainSet, bool[] trainSetLabels, Options options)
RandomForestRegression.cs (4)
516public static ObjectiveFunctionImplBase Create(Dataset trainData, Options options) 523private ObjectiveFunctionImplBase(Dataset trainData, Options options) 543public ShuffleImpl(Dataset trainData, Options options) 581public BasicImpl(Dataset trainData, Options options)
Training\Applications\ObjectiveFunction.cs (2)
31internal readonly Dataset Dataset; 36Dataset dataset,
Training\BaggingProvider.cs (3)
11protected Dataset CompleteTrainingSet; 19public BaggingProvider(Dataset completeTrainingSet, int maxLeaves, int randomSeed, double trainFraction) 92public RankingBaggingProvider(Dataset completeTrainingSet, int maxLeaves, int randomSeed, double trainFraction) :
Training\DcgCalculator.cs (11)
159public double Ndcg3(Dataset dataset, short[] labels, double[] scores) 261public double Ndcg1(Dataset dataset, short[] labels, double[] scores) 279public double Ndcg3(Dataset dataset, short[][] labelsSorted) 300public double Ndcg1(Dataset dataset, short[][] labelsSorted) 362public double[] NdcgRangeFromScores(Dataset dataset, short[] labels, double[] scores) 394private void NdcgRangeWorkerChunkFromScores(Dataset dataset, short[] labels, double[] scores, double[] result, int startQuery, int numQueries, int threadIndex) 403private void NdcgRangeWorkerFromScores(Dataset dataset, short[] labels, double[] scores, double[] result, int query, int threadIndex) 471public double[] DcgFromScores(Dataset dataset, double[] scores, double[] discount) 503public int[] OrderingFromScores(Dataset dataset, double[] scores) 526private void OrderingRangeWorkerFromScores(Dataset dataset, double[] scores, int[] result, int startQuery, int numQueries, int threadIndex) 535private void OrderingRangeWorkerPerQueryFromScores(Dataset dataset, double[] scores, int[] result, int query, int threadIndex)
Training\DocumentPartitioning.cs (1)
54internal DocumentPartitioning(InternalRegressionTree tree, Dataset dataset)
Training\EnsembleCompression\IEnsembleCompressor.cs (1)
10void Initialize(int numTrees, Dataset trainSet, TLabel[] labels, int randomSeed);
Training\EnsembleCompression\LassoBasedEnsembleCompressor.cs (2)
52private Dataset _trainSet; 58public void Initialize(int numTrees, Dataset trainSet, short[] labels, int randomSeed)
Training\OptimizationAlgorithms\AcceleratedGradientDescent.cs (2)
11internal AcceleratedGradientDescent(InternalTreeEnsemble ensemble, Dataset trainData, double[] initTrainScores, IGradientAdjuster gradientWrapper) 16protected override ScoreTracker ConstructScoreTracker(string name, Dataset set, double[] initScores)
Training\OptimizationAlgorithms\ConjugateGradientDescent.cs (1)
15public ConjugateGradientDescent(InternalTreeEnsemble ensemble, Dataset trainData, double[] initTrainScores, IGradientAdjuster gradientWrapper)
Training\OptimizationAlgorithms\GradientDescent.cs (3)
25internal GradientDescent(InternalTreeEnsemble ensemble, Dataset trainData, double[] initTrainScores, IGradientAdjuster gradientWrapper) 32protected override ScoreTracker ConstructScoreTracker(string name, Dataset set, double[] initScores) 89Dataset.DatasetSkeleton dsSkeleton = TrainingScores.Dataset.Skeleton;
Training\OptimizationAlgorithms\NoOptimizationAlgorithm.cs (2)
16internal RandomForestOptimizer(InternalTreeEnsemble ensemble, Dataset trainData, double[] initTrainScores, IGradientAdjuster gradientWrapper) 22protected override ScoreTracker ConstructScoreTracker(string name, Dataset set, double[] initScores)
Training\OptimizationAlgorithms\OptimizationAlgorithm.cs (4)
40public OptimizationAlgorithm(InternalTreeEnsemble ensemble, Dataset trainData, double[] initTrainScores) 50public void SetTrainingData(Dataset trainData, double[] initTrainScores) 84public ScoreTracker GetScoreTracker(string name, Dataset set, double[] initScores) 99protected abstract ScoreTracker ConstructScoreTracker(string name, Dataset set, double[] initScores);
Training\Parallel\IParallelTraining.cs (2)
69void InitTreeLearner(Dataset trainData, int maxNumLeaves, int maxCatSplitPoints, ref int minDocInLeaf); 132double[] GlobalMean(Dataset dataset, InternalRegressionTree tree, DocumentPartitioning partitioning, double[] weights, bool filterZeroLambdas);
Training\Parallel\SingleTrainer.cs (2)
49double[] IParallelTraining.GlobalMean(Dataset dataset, InternalRegressionTree tree, DocumentPartitioning partitioning, double[] weights, bool filterZeroLambdas) 71void IParallelTraining.InitTreeLearner(Dataset trainData, int maxNumLeaves, int maxCatSplitPoints, ref int minDocInLeaf)
Training\ScoreTracker.cs (4)
15public Dataset Dataset; 28public ScoreTracker(string datasetName, Dataset set, double[] initScores) 32public void Initialize(string datasetName, Dataset set, double[] initScores) 126public AgdScoreTracker(string datsetName, Dataset set, double[] initScores)
Training\Test.cs (2)
147public Dataset Dataset => ScoreTracker.Dataset; 161public Test(string datasetName, Dataset set, double[] initScores)
Training\TreeLearners\FastForestLeastSquaresTreeLearner.cs (1)
15public RandomForestLeastSquaresTreeLearner(Dataset trainData, int numLeaves, int minDocsInLeaf, Double entropyCoefficient, Double featureFirstUsePenalty,
Training\TreeLearners\LeastSquaresRegressionTreeLearner.cs (3)
120public LeastSquaresRegressionTreeLearner(Dataset trainData, int numLeaves, int minDocsInLeaf, double entropyCoefficient, 190protected virtual void MakeSplitCandidateArrays(Dataset data, out LeafSplitCandidates smallerCandidates, out LeafSplitCandidates largerCandidates) 840public LeafSplitCandidates(Dataset data)
Training\TreeLearners\TreeLearner.cs (2)
12public readonly Dataset TrainData; 17protected TreeLearner(Dataset trainData, int numLeaves)
Training\WinLossCalculator.cs (3)
46public double[] WinLossRangeFromScores(Dataset dataset, short[] labels, double[] scores) 72private void WinLossRangeWorkerChunkFromScores(Dataset dataset, short[] labels, double[] scores, double[] result, int startQuery, int numQueries, int threadIndex) 79private void WinLossRangeWorkerFromScores(Dataset dataset, short[] labels, double[] scores, double[] result, int query, int threadIndex)
TreeEnsemble\InternalRegressionTree.cs (8)
700public virtual double GetOutput(Dataset.RowForwardIndexer.Row featureBins) 741public int GetLeaf(Dataset.RowForwardIndexer.Row featureBins) 993public double[] GetOutputs(Dataset dataset) 1082public void PopulateRawThresholds(Dataset dataset) 1103public void PopulateThresholds(Dataset dataset) 1369public void AddOutputsToScores(Dataset dataset, double[] scores, double multiplier) 1400public void AddOutputsToScores(Dataset dataset, double[] scores) 1423internal void AddOutputsToScores(Dataset dataset, double[] scores, int[] docIndices)
TreeEnsemble\InternalTreeEnsemble.cs (7)
87public void PopulateRawThresholds(Dataset dataset) 95/// in the training <see cref="Dataset"/> structure are different from the ones in the 98/// will no longer have features pointing to the original training <see cref="Dataset"/>, 242public double GetOutput(Dataset.RowForwardIndexer.Row featureBins, int prefix) 283public double GetOutput(Dataset.RowForwardIndexer.Row featureBins) 287public void GetOutputs(Dataset dataset, double[] outputs) { GetOutputs(dataset, outputs, -1); } 288public void GetOutputs(Dataset dataset, double[] outputs, int prefix)