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 MultiSplitDecisionTreeModelBuilder(
ISplitQualityChecker splitQualityChecker,
IBestSplitSelector bestSplitSelector,
ILeafBuilder leafBuilder,
IStatisticalSignificanceChecker statisticalSignificanceChecker = null)
: base(splitQualityChecker, bestSplitSelector, leafBuilder, statisticalSignificanceChecker)
{
}
public MultiSplitDecisionTreeModelBuilder(
ISplitQualityChecker splitQualityChecker,
IBestSplitSelector bestSplitSelector,
ILeafBuilder leafBuilder,
IStatisticalSignificanceChecker statisticalSignificanceChecker = null)
: base(splitQualityChecker, bestSplitSelector, leafBuilder, statisticalSignificanceChecker)
{
}
//TODO: AAA make it nicer - maybe encapsulate Tuple in some dto
protected abstract Tuple <IList <ISplittedData>, ISplittingParams, double> EvaluateCategoricalSplit(
IDataFrame dataToSplit,
string dependentFeatureName,
string splittingFeatureName,
double bestSplitQualitySoFar,
double initialEntropy,
ISplitQualityChecker splitQualityChecker,
IAlredyUsedAttributesInfo alredyUsedAttributesInfo);
protected BaseDecisionTreeModelBuilder(
ISplitQualityChecker splitQualityChecker,
IBestSplitSelector bestSplitSelector,
ILeafBuilder leafBuilder,
IStatisticalSignificanceChecker statisticalSignificanceChecker = null)
{
SplitQualityChecker = splitQualityChecker;
BestSplitSelector = bestSplitSelector;
LeafBuilder = leafBuilder;
this.StatisticalSignificanceChecker = statisticalSignificanceChecker;
}
protected BaseDecisionTreeModelBuilder(
ISplitQualityChecker splitQualityChecker,
IBestSplitSelector bestSplitSelector,
ILeafBuilder leafBuilder,
IStatisticalSignificanceChecker statisticalSignificanceChecker = null)
{
SplitQualityChecker = splitQualityChecker;
BestSplitSelector = bestSplitSelector;
LeafBuilder = leafBuilder;
this.StatisticalSignificanceChecker = statisticalSignificanceChecker;
}
public ISplittingResult SelectBestSplit(
IDataFrame baseData,
string dependentFeatureName,
ISplitQualityChecker splitQualityChecker,
IAlredyUsedAttributesInfo alreadyUsedAttributesInfo)
{
if (!(splitQualityChecker is INumericalSplitQualityChecker))
{
throw new ArgumentException("Invalid split quality checker for numerical outcome");
}
return(SelectBestSplit(baseData, dependentFeatureName, (INumericalSplitQualityChecker)splitQualityChecker, alreadyUsedAttributesInfo));
}
public BestSplitSelectorsTests()
{
ICategoricalImpurityMeasure<string> shannonEntropy = new ShannonEntropy<string>();
IBinaryDataSplitter binaryDataSplitter = new BinaryDiscreteDataSplitter();
binaryNumericBestSplitPointSelector = new ClassBreakpointsNumericSplitFinder();
binaryBestSplitSelector = new BinarySplitSelectorForCategoricalOutcome(binaryDataSplitter, binaryNumericDataSplitter, binaryNumericBestSplitPointSelector);
categoricalBinarySplitQualityChecker = new InformationGainCalculator<string>(shannonEntropy, shannonEntropy);
categoricalMultiValueSplitQualityChecker = new InformationGainCalculator<string>(shannonEntropy, shannonEntropy);
multiValueCategoricalDataSplitter = new MultiValueDiscreteDataSplitter();
multiValueBestSplitSelector = new MultiValueSplitSelectorForCategoricalOutcome(multiValueCategoricalDataSplitter, binaryNumericDataSplitter, binaryNumericBestSplitPointSelector);
dynamicProgrammingBestNumericSplitFinder = new DynamicProgrammingNumericSplitFinder();
}
public ISplittingResult SelectBestSplit(
IDataFrame baseData,
string dependentFeatureName,
ISplitQualityChecker splitQualityChecker,
IAlredyUsedAttributesInfo alreadyUsedAttributesInfo)
{
if (!(splitQualityChecker is INumericalSplitQualityChecker))
{
throw new ArgumentException("Invalid split quality checker for numerical outcome");
}
return SelectBestSplit(baseData, dependentFeatureName, (INumericalSplitQualityChecker)splitQualityChecker, alreadyUsedAttributesInfo);
}
public BestSplitSelectorsTests()
{
ICategoricalImpurityMeasure <string> shannonEntropy = new ShannonEntropy <string>();
IBinaryDataSplitter binaryDataSplitter = new BinaryDiscreteDataSplitter();
binaryNumericBestSplitPointSelector = new ClassBreakpointsNumericSplitFinder();
binaryBestSplitSelector = new BinarySplitSelectorForCategoricalOutcome(binaryDataSplitter, binaryNumericDataSplitter, binaryNumericBestSplitPointSelector);
categoricalBinarySplitQualityChecker = new InformationGainCalculator <string>(shannonEntropy, shannonEntropy);
categoricalMultiValueSplitQualityChecker = new InformationGainCalculator <string>(shannonEntropy, shannonEntropy);
multiValueCategoricalDataSplitter = new MultiValueDiscreteDataSplitter();
multiValueBestSplitSelector = new MultiValueSplitSelectorForCategoricalOutcome(multiValueCategoricalDataSplitter, binaryNumericDataSplitter, binaryNumericBestSplitPointSelector);
dynamicProgrammingBestNumericSplitFinder = new DynamicProgrammingNumericSplitFinder();
}
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);
}
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));
}
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 Tuple <ISplittingResult, double> FindBestSplitPoint(
IDataFrame baseData,
string dependentFeatureName,
string numericFeatureToProcess,
ISplitQualityChecker splitQualityChecker,
IBinaryNumericDataSplitter binaryNumericDataSplitter,
double initialEntropy)
{
return(FindBestSplitPoint(
baseData,
dependentFeatureName,
numericFeatureToProcess,
splitQualityChecker as ICategoricalSplitQualityChecker,
binaryNumericDataSplitter,
initialEntropy));
}
public Tuple<ISplittingResult, double> FindBestSplitPoint(
IDataFrame baseData,
string dependentFeatureName,
string numericFeatureToProcess,
ISplitQualityChecker splitQualityChecker,
IBinaryNumericDataSplitter binaryNumericDataSplitter,
double initialEntropy)
{
return FindBestSplitPoint(
baseData,
dependentFeatureName,
numericFeatureToProcess,
splitQualityChecker as ICategoricalSplitQualityChecker,
binaryNumericDataSplitter,
initialEntropy);
}
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);
}
private IDecisionTreeModelBuilder BuildCustomModelBuilder(
bool binary = false,
ISplitQualityChecker splitQualityChecker = null,
IBestSplitSelector bestSplitSelector = null,
ILeafBuilder leafBuilder = null,
IStatisticalSignificanceChecker statisticalSignificanceChecker = null)
{
if (binary)
{
return(new BinaryDecisionTreeModelBuilder(
splitQualityChecker ?? new InformationGainRatioCalculator <string>(shannonEntropy, shannonEntropy as ICategoricalImpurityMeasure <string>),
bestSplitSelector as IBinaryBestSplitSelector ?? new BinarySplitSelectorForCategoricalOutcome(new BinaryDiscreteDataSplitter(), new BinaryNumericDataSplitter(), new ClassBreakpointsNumericSplitFinder()),
leafBuilder ?? new CategoricalDecisionTreeLeafBuilder(),
statisticalSignificanceChecker));
}
return(new MultiSplitDecisionTreeModelBuilder(
splitQualityChecker ?? new InformationGainRatioCalculator <string>(shannonEntropy, shannonEntropy as ICategoricalImpurityMeasure <string>),
bestSplitSelector ?? new MultiValueSplitSelectorForCategoricalOutcome(new MultiValueDiscreteDataSplitter(), new BinaryNumericDataSplitter(), new DynamicProgrammingNumericSplitFinder()),
leafBuilder ?? new CategoricalDecisionTreeLeafBuilder(),
statisticalSignificanceChecker));
}
private IDecisionTreeModelBuilder BuildCustomModelBuilder(
bool binary = false,
ISplitQualityChecker splitQualityChecker = null,
IBestSplitSelector bestSplitSelector = null,
ILeafBuilder leafBuilder = null,
IStatisticalSignificanceChecker statisticalSignificanceChecker = null)
{
if (binary)
{
return new BinaryDecisionTreeModelBuilder(
splitQualityChecker ?? new InformationGainRatioCalculator<string>(shannonEntropy, shannonEntropy as ICategoricalImpurityMeasure<string>),
bestSplitSelector as IBinaryBestSplitSelector ?? new BinarySplitSelectorForCategoricalOutcome(new BinaryDiscreteDataSplitter(), new BinaryNumericDataSplitter(), new ClassBreakpointsNumericSplitFinder()),
leafBuilder ?? new CategoricalDecisionTreeLeafBuilder(),
statisticalSignificanceChecker);
}
return new MultiSplitDecisionTreeModelBuilder(
splitQualityChecker ?? new InformationGainRatioCalculator<string>(shannonEntropy, shannonEntropy as ICategoricalImpurityMeasure<string>),
bestSplitSelector ?? new MultiValueSplitSelectorForCategoricalOutcome(new MultiValueDiscreteDataSplitter(), new BinaryNumericDataSplitter(), new DynamicProgrammingNumericSplitFinder()),
leafBuilder ?? new CategoricalDecisionTreeLeafBuilder(),
statisticalSignificanceChecker);
}
//TODO: AAA make it nicer - maybe encapsulate Tuple in some dto
protected abstract Tuple<IList<ISplittedData>, ISplittingParams, double> EvaluateCategoricalSplit(
IDataFrame dataToSplit,
string dependentFeatureName,
string splittingFeatureName,
double bestSplitQualitySoFar,
double initialEntropy,
ISplitQualityChecker splitQualityChecker,
IAlredyUsedAttributesInfo alredyUsedAttributesInfo);
