protected virtual IDecisionTreeNode BuildDecisionNode(
IDataFrame dataFrame,
string dependentFeatureName,
IDecisionTreeModelBuilderParams additionalParams,
IAlredyUsedAttributesInfo alreadyUsedAttributesInfo,
int treeDepth,
bool isFirstSplit = false)
{
if (dataFrame.GetColumnVector <object>(dependentFeatureName).DataItems.Distinct().Count() == 1 || MaximalTreeDepthHasBeenReached(additionalParams, treeDepth))
{
return(BuildLeaf(dataFrame, dependentFeatureName));
}
// TODO: later on add additional params indicating which features were already used
ISplittingResult splitResult = BestSplitSelector.SelectBestSplit(
dataFrame,
dependentFeatureName,
SplitQualityChecker,
alreadyUsedAttributesInfo);
if (SplitIsEmpty(splitResult))
{
return(BuildLeaf(dataFrame, dependentFeatureName));
}
if (additionalParams.UsePrunningHeuristicDuringTreeBuild && this.StatisticalSignificanceChecker != null)
{
var isSplitSignificant = StatisticalSignificanceChecker.IsSplitStatisticallySignificant(
dataFrame,
splitResult,
dependentFeatureName);
if (!isSplitSignificant)
{
return(BuildLeaf(dataFrame, dependentFeatureName));
}
}
var children = new ConcurrentDictionary <IDecisionTreeLink, IDecisionTreeNode>();
if (isFirstSplit)
{
Parallel.ForEach(
splitResult.SplittedDataSets,
splitData =>
{
this.AddChildFromSplit(dependentFeatureName, additionalParams, splitData, children, alreadyUsedAttributesInfo, treeDepth + 1);
});
}
else
{
foreach (var splitData in splitResult.SplittedDataSets)
{
this.AddChildFromSplit(dependentFeatureName, additionalParams, splitData, children, alreadyUsedAttributesInfo, treeDepth + 1);
}
}
return(BuildConcreteDecisionTreeNode(splitResult, children));
}
protected virtual void AddLeafFromSplit(
string dependentFeatureName,
IDecisionTreeModelBuilderParams additionalParams,
ISplittedData splitData,
IDataFrame baseData,
ConcurrentDictionary <IDecisionTreeLink, IDecisionTreeNode> children)
{
var leafNode = BuildLeaf(baseData, dependentFeatureName);
var link = splitData.SplitLink;
children.TryAdd(link, leafNode);
}
protected virtual void AddChildFromSplit(
string dependentFeatureName,
IDecisionTreeModelBuilderParams additionalParams,
ISplittedData splitData,
ConcurrentDictionary <IDecisionTreeLink, IDecisionTreeNode> children,
IAlredyUsedAttributesInfo alreadyUsedAttributesInfo,
int treeDepth)
{
var decisionTreeNode = BuildDecisionNode(
splitData.SplittedDataFrame,
dependentFeatureName,
additionalParams,
alreadyUsedAttributesInfo,
treeDepth);
var link = splitData.SplitLink;
children.TryAdd(link, decisionTreeNode);
}
protected virtual void AddChildFromSplit(
string dependentFeatureName,
IDecisionTreeModelBuilderParams additionalParams,
ISplittedData splitData,
ConcurrentDictionary<IDecisionTreeLink, IDecisionTreeNode> children,
IAlredyUsedAttributesInfo alreadyUsedAttributesInfo,
int treeDepth)
{
var decisionTreeNode = BuildDecisionNode(
splitData.SplittedDataFrame,
dependentFeatureName,
additionalParams,
alreadyUsedAttributesInfo,
treeDepth);
var link = splitData.SplitLink;
children.TryAdd(link, decisionTreeNode);
}
private static bool MaximalTreeDepthHasBeenReached(IDecisionTreeModelBuilderParams additionalParams, int treeDepth)
{
return additionalParams.MaximalTreeDepth.HasValue && treeDepth >= additionalParams.MaximalTreeDepth;
}
protected virtual IDecisionTreeNode BuildDecisionNode(
IDataFrame dataFrame,
string dependentFeatureName,
IDecisionTreeModelBuilderParams additionalParams,
IAlredyUsedAttributesInfo alreadyUsedAttributesInfo,
int treeDepth,
bool isFirstSplit = false)
{
if (dataFrame.GetColumnVector<object>(dependentFeatureName).DataItems.Distinct().Count() == 1 || MaximalTreeDepthHasBeenReached(additionalParams, treeDepth))
{
return BuildLeaf(dataFrame, dependentFeatureName);
}
// TODO: later on add additional params indicating which features were already used
ISplittingResult splitResult = BestSplitSelector.SelectBestSplit(
dataFrame,
dependentFeatureName,
SplitQualityChecker,
alreadyUsedAttributesInfo);
if (SplitIsEmpty(splitResult))
{
return BuildLeaf(dataFrame, dependentFeatureName);
}
if (additionalParams.UsePrunningHeuristicDuringTreeBuild && this.StatisticalSignificanceChecker != null)
{
var isSplitSignificant = StatisticalSignificanceChecker.IsSplitStatisticallySignificant(
dataFrame,
splitResult,
dependentFeatureName);
if (!isSplitSignificant)
{
return BuildLeaf(dataFrame, dependentFeatureName);
}
}
var children = new ConcurrentDictionary<IDecisionTreeLink, IDecisionTreeNode>();
if (isFirstSplit)
{
Parallel.ForEach(
splitResult.SplittedDataSets,
splitData =>
{
this.AddChildFromSplit(dependentFeatureName, additionalParams, splitData, children, alreadyUsedAttributesInfo, treeDepth + 1);
});
}
else
{
foreach (var splitData in splitResult.SplittedDataSets)
{
this.AddChildFromSplit(dependentFeatureName, additionalParams, splitData, children, alreadyUsedAttributesInfo, treeDepth + 1);
}
}
return BuildConcreteDecisionTreeNode(splitResult, children);
}
protected virtual void AddLeafFromSplit(
string dependentFeatureName,
IDecisionTreeModelBuilderParams additionalParams,
ISplittedData splitData,
IDataFrame baseData,
ConcurrentDictionary<IDecisionTreeLink, IDecisionTreeNode> children)
{
var leafNode = BuildLeaf(baseData, dependentFeatureName);
var link = splitData.SplitLink;
children.TryAdd(link, leafNode);
}
private static bool MaximalTreeDepthHasBeenReached(IDecisionTreeModelBuilderParams additionalParams, int treeDepth)
{
return(additionalParams.MaximalTreeDepth.HasValue && treeDepth >= additionalParams.MaximalTreeDepth);
}
