public Tuple <ISplittingResult, double> FindBestSplitPoint(
IDataFrame baseData,
string dependentFeatureName,
string numericFeatureToProcess,
ICategoricalSplitQualityChecker splitQualityChecker,
IBinaryNumericDataSplitter binaryNumericDataSplitter,
double initialEntropy)
{
ISplittingResult bestSplit = null;
double bestSplitQuality = double.NegativeInfinity;
var totalRowsCount = baseData.RowCount;
var sortedRowData =
baseData.GetNumericColumnVector(numericFeatureToProcess)
.AsParallel()
.Select((val, rowIdx) =>
new
{
RowIdx = rowIdx,
FeatureValue = val,
DependentFeatureValue = baseData[rowIdx, dependentFeatureName].FeatureValue
})
.OrderBy(elem => elem.FeatureValue).ThenBy(elem => elem.RowIdx)
.ToList();
var previousClass = sortedRowData[0].DependentFeatureValue;
var previousFeatureVal = sortedRowData[0].FeatureValue;
foreach (var rowData in sortedRowData)
{
var currentClass = rowData.DependentFeatureValue;
var currentFeatureVal = rowData.FeatureValue;
if (!currentClass.Equals(previousClass) && !currentFeatureVal.Equals(previousFeatureVal))
{
var halfWay = (previousFeatureVal + currentFeatureVal) / 2.0;
var splitParams = new BinarySplittingParams(numericFeatureToProcess, halfWay, dependentFeatureName);
var splitResult = binaryNumericDataSplitter.SplitData(baseData, splitParams);
var quality = splitQualityChecker.CalculateSplitQuality(
initialEntropy,
totalRowsCount,
splitResult,
dependentFeatureName);
if (quality >= bestSplitQuality)
{
bestSplitQuality = quality;
bestSplit = new BinarySplittingResult(true, numericFeatureToProcess, splitResult, halfWay);
}
previousClass = currentClass;
}
previousFeatureVal = currentFeatureVal;
}
return(new Tuple <ISplittingResult, double>(bestSplit, bestSplitQuality));
}
public Tuple<ISplittingResult, double> FindBestSplitPoint(
IDataFrame baseData,
string dependentFeatureName,
string numericFeatureToProcess,
ICategoricalSplitQualityChecker splitQualityChecker,
IBinaryNumericDataSplitter binaryNumericDataSplitter,
double initialEntropy)
{
ISplittingResult bestSplit = null;
double bestSplitQuality = double.NegativeInfinity;
var totalRowsCount = baseData.RowCount;
var sortedRowData =
baseData.GetNumericColumnVector(numericFeatureToProcess)
.AsParallel()
.Select((val, rowIdx) =>
new
{
RowIdx = rowIdx,
FeatureValue = val,
DependentFeatureValue = baseData[rowIdx, dependentFeatureName].FeatureValue
})
.OrderBy(elem => elem.FeatureValue).ThenBy(elem => elem.RowIdx)
.ToList();
var previousClass = sortedRowData[0].DependentFeatureValue;
var previousFeatureVal = sortedRowData[0].FeatureValue;
foreach (var rowData in sortedRowData)
{
var currentClass = rowData.DependentFeatureValue;
var currentFeatureVal = rowData.FeatureValue;
if (!currentClass.Equals(previousClass) && !currentFeatureVal.Equals(previousFeatureVal))
{
var halfWay = (previousFeatureVal + currentFeatureVal) / 2.0;
var splitParams = new BinarySplittingParams(numericFeatureToProcess, halfWay, dependentFeatureName);
var splitResult = binaryNumericDataSplitter.SplitData(baseData, splitParams);
var quality = splitQualityChecker.CalculateSplitQuality(
initialEntropy,
totalRowsCount,
splitResult,
dependentFeatureName);
if (quality >= bestSplitQuality)
{
bestSplitQuality = quality;
bestSplit = new BinarySplittingResult(true, numericFeatureToProcess, splitResult, halfWay);
}
previousClass = currentClass;
}
previousFeatureVal = currentFeatureVal;
}
return new Tuple<ISplittingResult, double>(bestSplit, bestSplitQuality);
}
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 Tuple<ISplittingResult, double> FindBestSplitPoint(
IDataFrame baseData,
string dependentFeatureName,
string numericFeatureToProcess,
ICategoricalSplitQualityChecker splitQualityChecker,
IBinaryNumericDataSplitter binaryNumericDataSplitter,
double initialEntropy)
{
var uniqueDependentValues = baseData.GetColumnVector(dependentFeatureName).Values.Distinct().ToList();
var dependentValuesSortedByNumericFeature = OrderColumn(baseData, dependentFeatureName, numericFeatureToProcess);
var dependentValsCounts = new List<Vector<double>>();
var breakPoints = new List<int>();
var lastKnowDependentValue = dependentValuesSortedByNumericFeature.First().DependentVal;
for (int elemIdx = 0; elemIdx < dependentValuesSortedByNumericFeature.Count; elemIdx++)
{
var currentElem = dependentValuesSortedByNumericFeature[elemIdx];
var currentDependentValue = currentElem.DependentVal;
var indexOfCurrentDependentValue = uniqueDependentValues.IndexOf(currentDependentValue);
var dependentValsCountAllocation = DenseVector.OfArray(Enumerable.Repeat(0.0, uniqueDependentValues.Count).ToArray());
if (elemIdx != 0)
{
dependentValsCounts[elemIdx - 1].CopyTo(dependentValsCountAllocation);
}
dependentValsCountAllocation[indexOfCurrentDependentValue]++;
if (!currentDependentValue.Equals(lastKnowDependentValue))
{
lastKnowDependentValue = currentDependentValue;
breakPoints.Add(elemIdx - 1);
}
dependentValsCounts.Add(dependentValsCountAllocation);
}
var bestSplitQualitySoFar = double.NegativeInfinity;
int bestBreakpointSoFar = -1;
foreach (var breakpointIdx in breakPoints)
{
var dependentValsCountUpToBreakpoint = dependentValsCounts[breakpointIdx];
var dependentValsCountAboveBreakpoint =
dependentValsCounts.Last().Subtract(dependentValsCountUpToBreakpoint);
var splitEntropy = splitQualityChecker.CalculateSplitQuality(
initialEntropy,
baseData.RowCount,
new List<IList<int>>
{
VectorToIntArray(dependentValsCountUpToBreakpoint), VectorToIntArray(dependentValsCountAboveBreakpoint)
});
if (splitEntropy > bestSplitQualitySoFar)
{
bestSplitQualitySoFar = splitEntropy;
bestBreakpointSoFar = breakpointIdx;
}
}
var splitVal = CalculateSplitPoint(
dependentValuesSortedByNumericFeature[bestBreakpointSoFar + 1].FeatureVal,
dependentValuesSortedByNumericFeature[bestBreakpointSoFar].FeatureVal);
var split = binaryNumericDataSplitter.SplitData(
baseData,
new BinarySplittingParams(numericFeatureToProcess, splitVal, dependentFeatureName));
var splitResult = new BinarySplittingResult(true, numericFeatureToProcess, split, splitVal);
return new Tuple<ISplittingResult, double>(splitResult, bestSplitQualitySoFar);
}
public Tuple <ISplittingResult, double> FindBestSplitPoint(
IDataFrame baseData,
string dependentFeatureName,
string numericFeatureToProcess,
ICategoricalSplitQualityChecker splitQualityChecker,
IBinaryNumericDataSplitter binaryNumericDataSplitter,
double initialEntropy)
{
var uniqueDependentValues = baseData.GetColumnVector(dependentFeatureName).Values.Distinct().ToList();
var dependentValuesSortedByNumericFeature = OrderColumn(baseData, dependentFeatureName, numericFeatureToProcess);
var dependentValsCounts = new List <Vector <double> >();
var breakPoints = new List <int>();
var lastKnowDependentValue = dependentValuesSortedByNumericFeature.First().DependentVal;
for (int elemIdx = 0; elemIdx < dependentValuesSortedByNumericFeature.Count; elemIdx++)
{
var currentElem = dependentValuesSortedByNumericFeature[elemIdx];
var currentDependentValue = currentElem.DependentVal;
var indexOfCurrentDependentValue = uniqueDependentValues.IndexOf(currentDependentValue);
var dependentValsCountAllocation = DenseVector.OfArray(Enumerable.Repeat(0.0, uniqueDependentValues.Count).ToArray());
if (elemIdx != 0)
{
dependentValsCounts[elemIdx - 1].CopyTo(dependentValsCountAllocation);
}
dependentValsCountAllocation[indexOfCurrentDependentValue]++;
if (!currentDependentValue.Equals(lastKnowDependentValue))
{
lastKnowDependentValue = currentDependentValue;
breakPoints.Add(elemIdx - 1);
}
dependentValsCounts.Add(dependentValsCountAllocation);
}
var bestSplitQualitySoFar = double.NegativeInfinity;
int bestBreakpointSoFar = -1;
foreach (var breakpointIdx in breakPoints)
{
var dependentValsCountUpToBreakpoint = dependentValsCounts[breakpointIdx];
var dependentValsCountAboveBreakpoint =
dependentValsCounts.Last().Subtract(dependentValsCountUpToBreakpoint);
var splitEntropy = splitQualityChecker.CalculateSplitQuality(
initialEntropy,
baseData.RowCount,
new List <IList <int> >
{
VectorToIntArray(dependentValsCountUpToBreakpoint), VectorToIntArray(dependentValsCountAboveBreakpoint)
});
if (splitEntropy > bestSplitQualitySoFar)
{
bestSplitQualitySoFar = splitEntropy;
bestBreakpointSoFar = breakpointIdx;
}
}
var splitVal = CalculateSplitPoint(
dependentValuesSortedByNumericFeature[bestBreakpointSoFar + 1].FeatureVal,
dependentValuesSortedByNumericFeature[bestBreakpointSoFar].FeatureVal);
var split = binaryNumericDataSplitter.SplitData(
baseData,
new BinarySplittingParams(numericFeatureToProcess, splitVal, dependentFeatureName));
var splitResult = new BinarySplittingResult(true, numericFeatureToProcess, split, splitVal);
return(new Tuple <ISplittingResult, double>(splitResult, bestSplitQualitySoFar));
}
