public static IDictionary <int, string> GetComponentTypes()
{
MetadataRepository repository = new MetadataRepository();
OptionSetMetadata componentTypeSet = repository.GetOptionSet("componenttype") as OptionSetMetadata;
LabelConverter lc = new LabelConverter();
return(componentTypeSet.Options.ToDictionary(k => k.Value.GetValueOrDefault(), e => ((string)lc.ConvertTo(e.Label, typeof(string), null, true)).Replace(" ", "")));
}
/// <summary>
/// Constructor of McBoostTreeLoss
/// </summary>
/// <param name="dp">the input data used to train boosted regression trees</param>
/// <param name="learnRate">the input learning rate specified in training</param>
public McBoostTreeLoss(LabelFeatureDataCoded labelFeatureDataCoded, LabelConverter labelConvert,
float learnRate)
{
this.learnRate = learnRate;
this.numClass = 0;
this.numSamples = labelFeatureDataCoded.NumDataPoint;
this.classLabels = new int[labelFeatureDataCoded.NumDataPoint];
for (int i = 0; i < this.numSamples; i++)
{
this.classLabels[i] = (int)labelConvert.convert(labelFeatureDataCoded.GetLabel(i));
if (this.classLabels[i] + 1 > this.numClass)
this.numClass = this.classLabels[i] + 1;
}
//qiangwu: we probably don't need a matrix to store the label information though it is more convinent coding-wise
this.classLabelsMatrix = BulidClassLabelsMatrix(this.classLabels, this.numClass);
this.classProb = new float[this.numClass][];
this.classFunValue = new float[this.numClass][];
this.pseudoResponses = new float[this.numClass][];
this.weights = new float[this.numClass][];
for (int k = 0; k < this.numClass; k++)
{
this.classProb[k] = new float[this.numSamples];
this.classFunValue[k] = new float[this.numSamples];
this.pseudoResponses[k] = new float[this.numSamples];
this.weights[k] = new float[this.numSamples];
}
//float[] weightsByLabel = WeightsByLabel(this.classLabels);
//float[] probWeights = new float[this.numSamples];
}
/// <summary>
/// Constructor of BoostTreeRankNetLoss
/// </summary>
/// <param name="dp">the input data used to train boosted regression trees</param>
/// <param name="learnRate">the input learning rate specified in training</param>
public BoostTreeNoGainLambdaLoss(LabelFeatureDataCoded labelFeatureDataCoded, LabelConverter labelConvert,
float learnRate, float labelWeight, StepSizeType stepSizeType, FindStepLib fs,
float labelForUnlabeled, double scoreForDegenerateQuery, int truncLevel)
{
this.learnRate = learnRate;
this.labelWeight = labelWeight;
this.labelForUnlabeled = labelForUnlabeled;
this.scoreForDegenerateQuery = scoreForDegenerateQuery;
this.truncLevel = truncLevel;
this.labels = new float[labelFeatureDataCoded.NumDataPoint];
for (int i = 0; i < labelFeatureDataCoded.NumDataPoint; i++)
{
this.labels[i] = labelConvert.convert(labelFeatureDataCoded.GetLabel(i));
}
this.numSamples = labels.Length;
this.score = new float[this.numSamples];
this.funValue = new float[this.numSamples];
this.pseudoResponses = new float[this.numSamples];
this.weights = new float[this.numSamples];
this.labelFeatureDataCoded = labelFeatureDataCoded;
//data member to compute the optimal adjustment factor (step size) for leaf nodes response
this.qcAccum = this.CreateQueryCollection();
this.qcCurrent = this.CreateQueryCollection();
this.fs = fs;
this.stepSizeType = stepSizeType;
}
/// <summary>
/// Constructor of BoostTreeRankNetLoss
/// </summary>
/// <param name="dp">the input data used to train boosted regression trees</param>
/// <param name="learnRate">the input learning rate specified in training</param>
public BoostTreeRankNetLoss(LabelFeatureDataCoded labelFeatureDataCoded, LabelConverter labelConvert,
float learnRate)
{
this.learnRate = learnRate;
this.numSamples = labelFeatureDataCoded.NumDataPoint;
this.labels = new float[labelFeatureDataCoded.NumDataPoint];
for (int i = 0; i < labelFeatureDataCoded.NumDataPoint; i++)
{
this.labels[i] = labelConvert.convert(labelFeatureDataCoded.GetLabel(i));
}
this.score = new float[this.numSamples];
this.funValue = new float[this.numSamples];
this.pseudoResponses = new float[this.numSamples];
this.weights = new float[this.numSamples];
this.labelFeatureDataCoded = labelFeatureDataCoded;
}
public NDCGPairwise(LabelFeatureCore labelFeatureCore, LabelConverter labelConvert, DataPartitionType[] dataTypes,
int ndcgAt, bool dropEmptyQueries, float scoreForEmptyQuery)
: base(labelFeatureCore, labelConvert, dataTypes)
{
this.ndcg = new NDCG(dropEmptyQueries, scoreForEmptyQuery, ndcgAt);
}
public Metrics(LabelFeatureCore labelFeatureCore, LabelConverter labelConvert, DataPartitionType[] dataTypes)
{
this.labelFeatureCore = labelFeatureCore;
this.dataTypes = dataTypes;
this.optimalID = -1;
this.labels = new float[labelFeatureCore.NumDataPoint];
if (labelConvert != null)
{
for (int i = 0; i < labelFeatureCore.NumDataPoint; i++)
{
this.labels[i] = labelConvert.convert(labelFeatureCore.GetLabel(i));
}
}
else
{
for (int i = 0; i < labelFeatureCore.NumDataPoint; i++)
{
this.labels[i] = labelFeatureCore.GetLabel(i);
}
}
this.dataSegments = new int[(int)DataPartitionType.cTypes][];
this.metricsCur = new float[(int)DataPartitionType.cTypes][];
for (int i = 0; i < (int)DataPartitionType.cTypes; i++)
{
metricsCur[i] = new float[SIZE];
}
foreach (DataPartitionType dataType in dataTypes)
{
DataSet dataSet = labelFeatureCore.DataGroups.GetDataPartition(dataType);
int[] dataSegment = dataSet.DataIndex;
if (dataSegment != null)
{
dataSegments[(int)dataType] = dataSegment;
}
else
{
//we will fill in the non-existing data sections with 0
//throw new Exception("data partition does not exist");
}
}
this.results_list = new List<Result>();
}
//dataType==null <=> all the data are used in one partition
public PrecRecall(LabelFeatureData labelFeatureData, LabelConverter labelConvert, DataPartitionType[] dataTypes)
: base(labelFeatureData, labelConvert, dataTypes)
{
this.stats = new int[2, 2];
}
//dataType==null <=> all the data are used in one partition
public ClassError(LabelFeatureCore labelFeatureCore, LabelConverter labelConvert, DataPartitionType[] dataTypes)
: base(labelFeatureCore, labelConvert, dataTypes)
{
}
