public void TestNNMF()
{
var stringTableBuilder = new StringTableBuilder();
var data = NaiveBayesTests.GetSimpleChineseSet(stringTableBuilder).ConvertToSparseVectors(false).Vectorise(true).ToDictionary(d => _lap.Create(d.Data), d => d.Classification);
var clusters = data.Select(d => d.Key).ToList().NNMF(_lap, 2);
var clusterLabels = clusters.Select(d => d.Select(d2 => data[d2]).ToArray()).ToList();
}
public void TestRandomForest()
{
var stringTableBuilder = new StringTableBuilder();
var data = NaiveBayesTests.GetSimpleChineseSet(stringTableBuilder).ConvertToWeightedIndexList(false).ConvertToTable();
var model = data.TrainRandomForest();
var classifier = model.CreateClassifier();
var testRows = data.GetRows(new[] { 0, data.RowCount - 1 });
Assert.IsTrue(classifier.Classify(testRows[0]).GetBestClassification() == "china");
//Assert.IsTrue(classifier.Classify(testRows[1]).First() == "japan");
}
public void TestDecisionTree()
{
var stringTableBuilder = new StringTableBuilder();
var data = NaiveBayesTests.GetSimpleChineseSet(stringTableBuilder).ConvertToSparseVectors(false).ConvertToTable();
var model = data.TrainDecisionTree();
var classifier = model.CreateClassifier();
var testRows = data.GetRows(new[] { 0, data.RowCount - 1 });
Assert.IsTrue(classifier.Classify(testRows[0]).First() == "china");
Assert.IsTrue(classifier.Classify(testRows[1]).First() == "japan");
}
public void TestTFIDF()
{
var stringTableBuilder = new StringTableBuilder();
var data = NaiveBayesTests.GetSimpleChineseSet(stringTableBuilder);
Assert.AreEqual(data.Count, 4);
Assert.AreEqual(data.First().Data.Count, 3);
var set = data.ConvertToWeightedIndexList(true);
Assert.AreEqual(set.Count, 2);
Assert.AreEqual(set.First().Data.Count, 4);
var tfidf = set.TFIDF();
Assert.AreEqual(tfidf.Count, 2);
Assert.AreEqual(tfidf.First().Data.Count, 4);
}
public void TestKMeans()
{
var stringTableBuilder = new StringTableBuilder();
var data = NaiveBayesTests.GetSimpleChineseSet(stringTableBuilder)
.ConvertToWeightedIndexList(false)
.Vectorise()
.ToDictionary(d => _lap.CreateVector(d.Data), d => d.Classification)
;
var clusters = data
.Select(d => d.Key)
.ToList()
.KMeans(2)
;
var clusterLabels = clusters
.Select(d => d.Select(d2 => data[d2]).ToArray())
.ToList()
;
}
