public void TrainModelAndTestModelTest(string trainFile, string testFile, int chunkSize, int numOfChunk)
{
var trainModel = new TrainModel(numOfChunk, 2, 64, 0.1);
var trainDataset = new ClassifiedDataset(trainFile, 64, 2);
var testModel = new TestModel(numOfChunk, 2, 0.1, trainModel.GetWeights());
var testDataset = new UnclassifiedDataset(testFile, 64);
int count = 0;
foreach (var chunk in trainDataset.GetClassifiedVectorsInChunks(chunkSize))
{
trainModel.Train(chunk, count);
if (++count == numOfChunk)
{
break;
}
}
var results = testModel.Test(testDataset.GetDataVectors().Select(v => v.FeatureVector).ToArray(), 0);
}
public void GetDataVectorsTest(string testFile, bool skipParseError, int expectedNumOfVectors, int expectedNumOfClasses)
{
var dataset = new UnclassifiedDataset(testFile, 64);
if (dataset.SkipParsingErrors != skipParseError)
{
dataset.SkipParsingErrors = skipParseError;
}
IList<DataVector> vectors = dataset.GetDataVectors();
Assert.That(vectors.Count, Is.EqualTo(expectedNumOfVectors));
Assert.That(vectors.All(v => v.ClassId >= 0 && v.ClassId < expectedNumOfClasses && v.QueryId != string.Empty && v.FeatureVector.Count == 64 && v.DocumentId != string.Empty));
}
public void TrainModelAndTestModelTest(string trainFile, string testFile)
{
var trainModel = new TrainModel(2, 0.1);
var trainDataset = new ClassifiedDataset(trainFile, 64, 2);
trainModel.Train(trainDataset.GetClassifiedVectors());
var testModel = new TestModel(2, 0.1);
var testDataset = new UnclassifiedDataset(testFile, 64);
var testData = testDataset.GetDataVectors().Select(v => v.FeatureVector).ToArray();
var results = testModel.Test(trainModel.GetInferredPosterier(), testData);
Assert.That(results.Length, Is.EqualTo(testData.Length));
}
