protected override Tuple<IList<ISplittedData>, ISplittingParams, double> EvaluateCategoricalSplit(
IDataFrame dataToSplit,
string dependentFeatureName,
string splittingFeatureName,
double bestSplitQualitySoFar,
double initialEntropy,
ISplitQualityChecker splitQualityChecker,
IAlredyUsedAttributesInfo alreadyUsedAttributesInfo)
{
if (alreadyUsedAttributesInfo.WasAttributeAlreadyUsed(splittingFeatureName))
{
return new Tuple<IList<ISplittedData>, ISplittingParams, double>(
new List<ISplittedData>(),
new SplittingParams(splittingFeatureName, dependentFeatureName),
double.NegativeInfinity);
}
var totalRowsCount = dataToSplit.RowCount;
var splitParams = new SplittingParams(splittingFeatureName, dependentFeatureName);
var splitData = CategoricalDataSplitter.SplitData(dataToSplit, splitParams);
if (splitData.Count == 1)
{
return new Tuple<IList<ISplittedData>, ISplittingParams, double>(
new List<ISplittedData>(),
splitParams,
double.NegativeInfinity);
}
var splitQuality = splitQualityChecker.CalculateSplitQuality(initialEntropy, totalRowsCount, splitData, dependentFeatureName);
return new Tuple<IList<ISplittedData>, ISplittingParams, double>(splitData, splitParams, splitQuality);
}
protected override Tuple <IList <ISplittedData>, ISplittingParams, double> EvaluateCategoricalSplit(
IDataFrame dataToSplit,
string dependentFeatureName,
string splittingFeatureName,
double bestSplitQualitySoFar,
double initialEntropy,
ISplitQualityChecker splitQualityChecker,
IAlredyUsedAttributesInfo alreadyUsedAttributesInfo)
{
if (alreadyUsedAttributesInfo.WasAttributeAlreadyUsed(splittingFeatureName))
{
return(new Tuple <IList <ISplittedData>, ISplittingParams, double>(
new List <ISplittedData>(),
new SplittingParams(splittingFeatureName, dependentFeatureName),
double.NegativeInfinity));
}
var totalRowsCount = dataToSplit.RowCount;
var splitParams = new SplittingParams(splittingFeatureName, dependentFeatureName);
var splitData = CategoricalDataSplitter.SplitData(dataToSplit, splitParams);
if (splitData.Count == 1)
{
return(new Tuple <IList <ISplittedData>, ISplittingParams, double>(
new List <ISplittedData>(),
splitParams,
double.NegativeInfinity));
}
var splitQuality = splitQualityChecker.CalculateSplitQuality(initialEntropy, totalRowsCount, splitData, dependentFeatureName);
return(new Tuple <IList <ISplittedData>, ISplittingParams, double>(splitData, splitParams, splitQuality));
}
public void PerformMultiValueDiscreteDataSplit()
{
// Given
var testData = TestDataBuilder.ReadWeatherDataWithCategoricalAttributes();
var splitParams = new SplittingParams("Outlook", "Play");
var expectedRowCounts = new Dictionary <object, int>
{
["Sunny"] = 5,
["Overcast"] = 4,
["Rainy"] = 5
};
// When
var splittedData = MultiValueDiscreteDataSplitter.SplitData(testData, splitParams);
// Then
Assert.AreEqual(expectedRowCounts.Count, splittedData.Count);
foreach (var splittedResult in splittedData)
{
var expectedCount = expectedRowCounts[splittedResult.SplitLink.TestResult];
Assert.AreEqual(expectedCount, splittedResult.SplittedDataFrame.RowCount);
Assert.AreEqual(expectedCount, splittedResult.SplitLink.InstancesCount);
}
}