public void Test_ClassificationWith_BackwardsEliminationKnnModel()
{
// Given
var randomizer = new Random(55);
var data = TestDataBuilder.ReadIrisData();
var trainingDataPercentage = 0.8;
int trainingDataCount = (int)(data.RowCount * trainingDataPercentage);
var shuffledIndices = data.RowIndices.Shuffle();
var trainingIndices = shuffledIndices.Take(trainingDataCount).ToList();
var testIndices =
shuffledIndices.Skip(trainingDataCount).Take(shuffledIndices.Count - trainingDataCount).ToList();
var trainingData = data.GetSubsetByRows(trainingIndices);
var testData = data.GetSubsetByRows(testIndices);
var weightingFunction = new GaussianFunction(0.07);
var predictor = new SimpleKnnClassifier<string>(
new EuclideanDistanceMeasure(),
new MinMaxNormalizer(),
weightingFunction.GetValue);
var modelBuilder = new BackwardsEliminationKnnModelBuilder<string>(
new MinMaxNormalizer(),
predictor,
new ClassificationAccuracyError<string>()
);
var modelParams = new KnnAdditionalParams(3, true);
var errorMeasure = new MeanSquareError();
var subject = new BackwardsEliminationKnnClassifier<string>(
new EuclideanDistanceMeasure(),
new MinMaxNormalizer(),
weightingFunction.GetValue);
// When
var model = modelBuilder.BuildModel(trainingData, "iris_class", modelParams);
var actualResults = subject.Predict(testData, model, "iris_class");
var confusionMatrix = new ConfusionMatrix<string>(testData.GetColumnVector<string>("iris_class"),
actualResults);
// Then
Assert.IsTrue(confusionMatrix.Accuracy >= 0.95);
}
public void Test_RegressionWith_SimpleKnnModel()
{
// Given
var randomizer = new Random(55);
var baseDataFrame = TestDataBuilder.BuildRandomAbstractNumericDataFrameWithRedundantAttrs(randomizer: randomizer);
var queryDataFrame = new DataFrame(new DataTable("some data")
{
Columns =
{
new DataColumn("F1", typeof(double)),
new DataColumn("F2", typeof(double)),
new DataColumn("F3", typeof(double)),
new DataColumn("F4", typeof(double)),
new DataColumn("F5", typeof(double))
},
Rows =
{
new object[] { 10, 1, 1, 4, 5 },
new object[] { 4, 2, 1, 9, 10},
new object[] { 2, 1, 1, 3, 7},
}
});
var expectedValues = Enumerable.Range(0, queryDataFrame.RowCount)
.Select(
rowIdx =>
TestDataBuilder.CalcualteLinearlyDependentFeatureValue(queryDataFrame.GetNumericRowVector(rowIdx))).ToList();
var modelBuilder = new SimpleKnnModelBuilder<double>();
var modelParams = new KnnAdditionalParams(4, true);
var weightingFunction = new GaussianFunction(0.3);
var predictor = new SimpleKnnRegressor(new EuclideanDistanceMeasure(), new MinMaxNormalizer(), weightingFunction.GetValue, normalizeNumericValues: true);
var errorMeasure = new MeanSquareError();
// When
var model = modelBuilder.BuildModel(baseDataFrame, "F6", modelParams);
var results = predictor.Predict(queryDataFrame, model, "F6");
// Then
var mse = errorMeasure.CalculateError(Vector<double>.Build.DenseOfEnumerable(expectedValues), Vector<double>.Build.DenseOfEnumerable(results));
Assert.IsTrue(mse < 0.55);
}
public void TestBuildKnnModel()
{
// Given
var randomizer = new Random(55);
var baseDataFrame = TestDataBuilder.BuildRandomAbstractNumericDataFrameWithRedundantAttrs(randomizer: randomizer, rowCount: 100);
var weightingFunction = new GaussianFunction(0.3);
var modelParams = new KnnAdditionalParams(4, true);
var predictor = new SimpleKnnRegressor(new EuclideanDistanceMeasure(), new MinMaxNormalizer(), weightingFunction.GetValue);
var subject = new BackwardsEliminationKnnModelBuilder<double>(
new MinMaxNormalizer(),
predictor,
new MeanSquareError());
var expectedRemovedFeaturesNames = new[] { "F4" };
// When
var model = subject.BuildModel(baseDataFrame, "F6", modelParams) as IBackwardsEliminationKnnModel<double>;
// Then
Assert.AreEqual(1, model.RemovedFeaturesData.Count);
CollectionAssert.AreEquivalent(expectedRemovedFeaturesNames, model.RemovedFeaturesData.Select(f => f.FeatureName));
}