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));
}
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,
INumericalSplitQualityChecker splitQualityChecker,
IAlredyUsedAttributesInfo alreadyUsedAttributesInfo)
{
var bestSplitQuality = double.NegativeInfinity;
var initialEntropy = splitQualityChecker.GetInitialEntropy(baseData, dependentFeatureName);
Tuple <string, double> bestSplit = null;
/*
* if (baseData.RowCount <= baseData.ColumnsCount)
* {
* return null;
* }
*/
var featureColumns = baseData.ColumnNames.Except(new[] { dependentFeatureName });
foreach (var feature in featureColumns)
{
var dataOrderedByFeature =
baseData.GetNumericColumnVector(feature)
.Select((rowVal, idx) => new Tuple <double, double, int>(rowVal, (double)baseData[idx, dependentFeatureName].FeatureValue, idx))
.OrderBy(tpl => tpl.Item1)
.ToList();
var dependentFeatureValuesOrdered = dataOrderedByFeature.Select(elem => elem.Item2).ToList();
var previousFeatureValue = dataOrderedByFeature.First().Item1;
for (int i = 0; i < (dataOrderedByFeature.Count - 1); i++)
{
var dataPoint = dataOrderedByFeature[i];
var currentFeatureValue = dataPoint.Item1;
if (currentFeatureValue != previousFeatureValue)
{
var splitPoint = (currentFeatureValue + previousFeatureValue) / 2.0;
if (!alreadyUsedAttributesInfo.WasAttributeAlreadyUsedWithValue(feature, splitPoint))
{
var dependentValsBelow = dependentFeatureValuesOrdered.Take(i).ToList();
var dependentValsAbove = dependentFeatureValuesOrdered.Skip(i).ToList();
var splitQuality = splitQualityChecker.CalculateSplitQuality(
initialEntropy,
baseData.RowCount,
new[] { dependentValsBelow, dependentValsAbove });
if (splitQuality > bestSplitQuality)
{
bestSplitQuality = splitQuality;
bestSplit = new Tuple <string, double>(feature, splitPoint);
}
}
}
previousFeatureValue = currentFeatureValue;
}
}
if (bestSplit == null)
{
return(null);
}
var splittedData = binaryNumericDataSplitter.SplitData(
baseData,
new BinarySplittingParams(bestSplit.Item1, bestSplit.Item2, dependentFeatureName));
return(new BinarySplittingResult(true, bestSplit.Item1, splittedData, bestSplit.Item2));
}
public ISplittingResult SelectBestSplit(
IDataFrame baseData,
string dependentFeatureName,
INumericalSplitQualityChecker splitQualityChecker,
IAlredyUsedAttributesInfo alreadyUsedAttributesInfo)
{
var bestSplitQuality = double.NegativeInfinity;
var initialEntropy = splitQualityChecker.GetInitialEntropy(baseData, dependentFeatureName);
Tuple<string, double> bestSplit = null;
/*
if (baseData.RowCount <= baseData.ColumnsCount)
{
return null;
}
*/
var featureColumns = baseData.ColumnNames.Except(new[] { dependentFeatureName });
foreach (var feature in featureColumns)
{
var dataOrderedByFeature =
baseData.GetNumericColumnVector(feature)
.Select((rowVal, idx) => new Tuple<double, double, int>(rowVal, (double)baseData[idx, dependentFeatureName].FeatureValue, idx))
.OrderBy(tpl => tpl.Item1)
.ToList();
var dependentFeatureValuesOrdered = dataOrderedByFeature.Select(elem => elem.Item2).ToList();
var previousFeatureValue = dataOrderedByFeature.First().Item1;
for (int i = 0; i < (dataOrderedByFeature.Count -1); i++)
{
var dataPoint = dataOrderedByFeature[i];
var currentFeatureValue = dataPoint.Item1;
if (currentFeatureValue != previousFeatureValue)
{
var splitPoint = (currentFeatureValue + previousFeatureValue) / 2.0;
if (!alreadyUsedAttributesInfo.WasAttributeAlreadyUsedWithValue(feature, splitPoint))
{
var dependentValsBelow = dependentFeatureValuesOrdered.Take(i).ToList();
var dependentValsAbove = dependentFeatureValuesOrdered.Skip(i).ToList();
var splitQuality = splitQualityChecker.CalculateSplitQuality(
initialEntropy,
baseData.RowCount,
new[] { dependentValsBelow, dependentValsAbove });
if (splitQuality > bestSplitQuality)
{
bestSplitQuality = splitQuality;
bestSplit = new Tuple<string, double>(feature, splitPoint);
}
}
}
previousFeatureValue = currentFeatureValue;
}
}
if (bestSplit == null)
{
return null;
}
var splittedData = binaryNumericDataSplitter.SplitData(
baseData,
new BinarySplittingParams(bestSplit.Item1, bestSplit.Item2, dependentFeatureName));
return new BinarySplittingResult(true, bestSplit.Item1, splittedData, bestSplit.Item2);
}
