/// <summary>
/// Main Program
/// </summary>
/// <param name="args">
/// There should be at least two input parameters from command line:
/// file name of the stored boost tree, and
/// file name of the source test/validation data
/// </param>
public static void Main(string[] args)
{
TestArgs cmd = new TestArgs(args);
Random r = new Random(cmd.seed);
//Load the model first
BoostTree boostTree = BoostTree.Read(cmd.binaryTreeFile);
if (boostTree == null)
{
Debug.Assert(false, "Fail to load model");
Console.WriteLine("Fail to load model " + cmd.binaryTreeFile);
return;
}
int numIter = cmd.numIter;
if (cmd.numIter == 0) // If iteration not specified, use the optimal validation iteration found during training
{
numIter = boostTree.OptIter;
}
//compute and output the feature importance for the specified number of iterations
// boostTree.SummarizeFeatureImporance(numIter, "featureImportance.txt");
string[] activeFeatureNames = null;
//read and process only a subset of activated features as specified in the activeFeatureFile
if (cmd.activeFeatureFile != null)
{
activeFeatureNames = TsvFileLoader.ReadFeatureNames(cmd.activeFeatureFile);
}
//feature parser: special module that understand MSN style value encoding
MsnFeatureParser featureParser = new MsnFeatureParser(activeFeatureNames);
//the column name for label: values to regress to
string[] labelName = { cmd.labelName };
//label/rating parser: special module that understand regression value
IParser<float> RateParser = new MsnLabelParser(labelName, cmd.labelNameValueFile);
//data boundary: every row of data is by itself / all data is in one group / no data groups
OnelineGroup noBoundary = new OnelineGroup();
//Load coded data if exist
LabelFeatureData labelFeatureData = (CLabelFeatureData)CLabelFeatureData.Load(cmd.inputFile, featureParser, RateParser, noBoundary, typeof(CLabelFeatureData), activeFeatureNames, cmd.cThreads);
if (!boostTree.SetFeatureNames(labelFeatureData.FeatureNames))
{
Debug.Assert(false, "Sub-model failed to initialize");
Console.WriteLine("Sub-model failed to initialize, program exits");
return;
}
//All data are for test
float[] percentage = DataGroups.DataSplit("0:0:10"); //"Train:Valid:Test"
labelFeatureData.DataGroups.PartitionData(percentage, r);
//Specify the data partitions to be tested
DataPartitionType[] dataTypes = DataGroups.PartitionTypes("Train:Valid:Test"); //using all data as default
LabelConverter labelConvert = new LabelConverterNull();
//set up the error metrics that we like to keep tract of during testing
//dp.LabelFeatureData is the data we are evaluating
Metrics metrics;
if (string.Compare(cmd.metric, "ErrRate", true) == 0)
{
metrics = new ClassError(labelFeatureData, labelConvert, dataTypes);
}
else if (string.Compare(cmd.metric, "PrecRecall", true) == 0)
{
metrics = new PrecRecall(labelFeatureData, labelConvert, dataTypes);
}
else
{
metrics = new ClassError(labelFeatureData, labelConvert, dataTypes);
}
boostTree.Predict(labelFeatureData, numIter, metrics, cmd.silent);
// Output the testing error history. This should at least help validate the optimal
// number of iterations, although it is probably better that we use NDCG history
// for the optimum.
metrics.SaveAllResults("testErrHistory.txt");
}
/// <summary>
/// Main Program
/// </summary>
/// <param name="args">
/// Should contain five parameters in the order of
/// file name for training source data (DataProcess class),
/// file name for saving the tree
/// tree size, i.e., maximum number of terminal nodes, usually 16 - 20
/// learning rate, usually 0.02 - 0.06
/// number of iterations, usallay >500(can be pruned later)
/// </param>
public static void Main(string[] args)
{
try
{
TrainArgs cmd = new TrainArgs(args);
Random r = null;
if (cmd.seed == -1)
{
r = new Random();
}
else
{
r = new Random(cmd.seed);
}
string[] activeFeatureNames = null;
//read and process only a subset of activated features as specified in the activeFeatureFile
if (cmd.activeFeatureFile != null)
{
activeFeatureNames = TsvFileLoader.ReadFeatureNames(cmd.activeFeatureFile);
}
//feature parser: special module that understand MSN style value encoding
MsnFeatureParser featureParser = new MsnFeatureParser(activeFeatureNames);
//the column name for label:
string[] labelName = { cmd.labelName };
//label/rating parser:
IParser<float> RateParser = new MsnLabelParser(labelName, cmd.labelNameValueFile);
//data boundary: no boundary
OnelineGroup noBounadry = new OnelineGroup();
//Load coded data if exist
LabelFeatureDataCoded trainLabelFeatureDataCoded = (CLabelFeatureDataCoded)CLabelFeatureData.Load(cmd.trainFile, featureParser, RateParser, noBounadry, typeof(CLabelFeatureDataCoded), activeFeatureNames, cmd.cThreads, cmd.SparseCoded);
LabelFeatureData validLabelFeatureData = (CLabelFeatureData)CLabelFeatureData.Load(cmd.validFile, featureParser, RateParser, noBounadry, typeof(CLabelFeatureData), activeFeatureNames, cmd.cThreads, cmd.SparseCoded);
LabelFeatureData testLabelFeatureData = (CLabelFeatureData)CLabelFeatureData.Load(cmd.testFile, featureParser, RateParser, noBounadry, typeof(CLabelFeatureData), activeFeatureNames, cmd.cThreads, cmd.SparseCoded);
//build composite data - an aggregated data object that keeps tract of train/valid/test data
CLabelFeatureDataCodedComposite labelFeatureDataCoded = CLabelFeatureDataCodedComposite.Create(trainLabelFeatureDataCoded, validLabelFeatureData, testLabelFeatureData);
//initial submodel to boost on
Model subModel = null;
if (cmd.subModel != null && cmd.subModel.Length > 0)
{
if (cmd.cLayer > 0)
{
string[] layerNames = new string[cmd.cLayer];
for (int i = 0; i < cmd.cLayer; i++)
{
string num = "";
if (cmd.cLayer > 1)
{
num = (i + 1).ToString();
}
layerNames[i] = cmd.subModel + "layer" + num + ".txt";
}
subModel = new NNModel(layerNames);
}
else
{
string iniName = cmd.subModel + ".ini";
subModel = NNModelMSN.Create(iniName);
}
}
if (subModel != null && !subModel.SetFeatureNames(labelFeatureDataCoded.FeatureNames))
{
Console.WriteLine("Fail to initialize specified submodel - training with empty submodel");
subModel = null;
}
LabelConverter labelConvert = new LabelConverterNull();
LabelFeatureData subModelScore = null;
McBoostTreeLoss boostTreeLoss = new McBoostTreeLoss(labelFeatureDataCoded, labelConvert, cmd.learnRate);
BoostTree boostTree = new BoostTree(labelFeatureDataCoded, subModelScore, subModel, boostTreeLoss,
cmd.binaryTreeFile, cmd.textTreeFile);
//set up the error metrics that we like to keep tract of during testing
DataPartitionType[] dataTypes = { DataPartitionType.Train, DataPartitionType.Validation, DataPartitionType.Test };
//dp.LabelFeatureData is the data we are evaluating
Metrics metrics = new ClassError(labelFeatureDataCoded, labelConvert, dataTypes);
DataFeatureSampleRate dataFeatureSampleRate = new DataFeatureSampleRate(cmd.sampleFeatureRate, cmd.sampleDataRate, cmd.sampleDataGroupRate);
boostTree.Build(metrics, dataFeatureSampleRate, cmd.cLeafNodes, cmd.minNumSamples, cmd.numIter, cmd.cThreads, r);
metrics.SaveAllResults("TrainingErrHistory.txt");
}
catch (Exception exc)
{
Console.WriteLine(exc.Message);
}
}