public void SelectBestNumericSplitPoint_CategoricalVariable()
{
//Given
var weatherDataNumeric = TestDataBuilder.ReadWeatherDataWithMixedAttributes();
var initialEntropy = categoricalBinarySplitQualityChecker.GetInitialEntropy(weatherDataNumeric, "Play");
// When
var bruteForceBestSplit = binaryNumericBestSplitPointSelector.FindBestSplitPoint(
weatherDataNumeric,
"Play",
"Temperature",
categoricalBinarySplitQualityChecker,
binaryNumericDataSplitter,
initialEntropy);
var dynamicProgrammingBestSplit = dynamicProgrammingBestNumericSplitFinder.FindBestSplitPoint(
weatherDataNumeric,
"Play",
"Temperature",
categoricalBinarySplitQualityChecker,
binaryNumericDataSplitter,
initialEntropy);
// Then
Assert.AreEqual(bruteForceBestSplit.Item1.SplittingFeatureName, dynamicProgrammingBestSplit.Item1.SplittingFeatureName);
Assert.AreEqual((bruteForceBestSplit.Item1 as IBinarySplittingResult).SplittingValue, (dynamicProgrammingBestSplit.Item1 as IBinarySplittingResult).SplittingValue);
Assert.AreEqual(bruteForceBestSplit.Item2, dynamicProgrammingBestSplit.Item2);
}
public ISplittingResult SelectBestSplit(
IDataFrame baseData,
string dependentFeatureName,
ISplitQualityChecker splitQualityChecker,
IAlredyUsedAttributesInfo alreadyUsedAttributesInfo)
{
ISplittingResult bestSplit = null;
double bestSplitQuality = float.NegativeInfinity;
double initialEntropy = splitQualityChecker.GetInitialEntropy(baseData, dependentFeatureName);
foreach (var attributeToSplit in baseData.ColumnNames.Except(new[] { dependentFeatureName }))
{
if (baseData.GetColumnType(attributeToSplit).TypeIsNumeric())
{
// TODO: add checking for the already used attribtues
var bestNumericSplitPointAndQuality =
BinaryNumericBestSplitingPointSelector.FindBestSplitPoint(
baseData,
dependentFeatureName,
attributeToSplit,
splitQualityChecker,
BinaryNumericDataSplitter,
initialEntropy);
if (bestNumericSplitPointAndQuality.Item2 > bestSplitQuality)
{
bestSplitQuality = bestNumericSplitPointAndQuality.Item2;
bestSplit = bestNumericSplitPointAndQuality.Item1;
}
}
else
{
var bestSplitForAttribute = EvaluateCategoricalSplit(
baseData,
dependentFeatureName,
attributeToSplit,
bestSplitQuality,
initialEntropy,
splitQualityChecker,
alreadyUsedAttributesInfo);
if (bestSplitForAttribute.Item3 > bestSplitQuality)
{
bestSplit = BuildBestSplitObject(bestSplitForAttribute.Item2, bestSplitForAttribute.Item1);
bestSplitQuality = bestSplitForAttribute.Item3;
}
}
}
return(bestSplit);
}
public ISplittingResult SelectBestSplit(
IDataFrame baseData,
string dependentFeatureName,
ISplitQualityChecker splitQualityChecker,
IAlredyUsedAttributesInfo alreadyUsedAttributesInfo)
{
ISplittingResult bestSplit = null;
double bestSplitQuality = float.NegativeInfinity;
double initialEntropy = splitQualityChecker.GetInitialEntropy(baseData, dependentFeatureName);
foreach (var attributeToSplit in baseData.ColumnNames.Except(new[] { dependentFeatureName }))
{
if (baseData.GetColumnType(attributeToSplit).TypeIsNumeric())
{
// TODO: add checking for the already used attribtues
var bestNumericSplitPointAndQuality =
BinaryNumericBestSplitingPointSelector.FindBestSplitPoint(
baseData,
dependentFeatureName,
attributeToSplit,
splitQualityChecker,
BinaryNumericDataSplitter,
initialEntropy);
if (bestNumericSplitPointAndQuality.Item2 > bestSplitQuality)
{
bestSplitQuality = bestNumericSplitPointAndQuality.Item2;
bestSplit = bestNumericSplitPointAndQuality.Item1;
}
}
else
{
var bestSplitForAttribute = EvaluateCategoricalSplit(
baseData,
dependentFeatureName,
attributeToSplit,
bestSplitQuality,
initialEntropy,
splitQualityChecker,
alreadyUsedAttributesInfo);
if (bestSplitForAttribute.Item3 > bestSplitQuality)
{
bestSplit = BuildBestSplitObject(bestSplitForAttribute.Item2, bestSplitForAttribute.Item1);
bestSplitQuality = bestSplitForAttribute.Item3;
}
}
}
return bestSplit;
}
