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 alredyUsedAttributesInfo)
{
var totalRowsCount = dataToSplit.RowCount;
var uniqueFeatureValues = dataToSplit.GetColumnVector(splittingFeatureName).Distinct();
double locallyBestSplitQuality = double.NegativeInfinity;
IBinarySplittingParams localBestSplitParams = null;
IList <ISplittedData> locallyBestSplitData = null;
foreach (var featureValue in uniqueFeatureValues)
{
if (!alredyUsedAttributesInfo.WasAttributeAlreadyUsedWithValue(splittingFeatureName, featureValue))
{
var binarySplitParams = new BinarySplittingParams(splittingFeatureName, featureValue, dependentFeatureName);
var splittedData = CategoricalDataSplitter.SplitData(dataToSplit, binarySplitParams);
if (splittedData.Count == 1)
{
return(new Tuple <IList <ISplittedData>, ISplittingParams, double>(
new List <ISplittedData>(),
binarySplitParams,
double.NegativeInfinity));
}
var splitQuality = splitQualityChecker.CalculateSplitQuality(
initialEntropy,
totalRowsCount,
splittedData,
dependentFeatureName);
if (splitQuality > locallyBestSplitQuality)
{
locallyBestSplitQuality = splitQuality;
locallyBestSplitData = splittedData;
localBestSplitParams = binarySplitParams;
}
}
}
return(new Tuple <IList <ISplittedData>, ISplittingParams, double>(
locallyBestSplitData,
localBestSplitParams,
locallyBestSplitQuality));
}