public string GetTree(string sourceFile)
{
_sourceFile = sourceFile;
RawDataSource samples = new RawDataSource(_sourceFile);
TreeAttributeCollection attributes = samples.GetValidAttributeCollection();
DecisionTree id3 = new DecisionTree();
TreeNode root = id3.mountTree(samples, "result", attributes);
return(PrintNode(root, "") + Environment.NewLine + PrologPrintNode(root, "", "result"));
}
public void GenRulesFromMt(SIProlog pEngine, string sourceMt, string destMt, string targetAttribute)
{
MtDataSource samples = new MtDataSource(pEngine, sourceMt);
TreeAttributeCollection attributes = samples.GetValidAttributeCollection(targetAttribute);
DecisionTree id3 = new DecisionTree();
TreeNode root = id3.mountTree(samples, targetAttribute, attributes);
string prologCode = PrologPrintNode(root, "", targetAttribute);
pEngine.insertKB(prologCode, destMt);
string codeSummary = PrintNode(root, "") + Environment.NewLine + PrologPrintNode(root, "", "result");
Console.WriteLine(codeSummary);
}
/// <summary>
///Returns the best attribute.
/// </summary>
/// <param name="attributes"> A vector with attributes </param>
/// <returns>Returns which has higher gain </returns>
private TreeAttribute getBestAttribute(DataTable samples, TreeAttributeCollection attributes)
{
double maxGain = -9999999.0;
TreeAttribute result = null;
foreach (TreeAttribute attribute in attributes)
{
double aux = gain(samples, attribute);
if (aux > maxGain)
{
maxGain = aux;
result = attribute;
}
}
return(result);
}
public TreeAttributeCollection GetValidAttributeCollection()
{
TreeAttributeCollection returnCollection = new TreeAttributeCollection();
foreach (DataColumn column in this.Columns)
{
TreeAttribute currentAttribute = new TreeAttribute(column.ColumnName, GetValuesFromColumn(column.ColumnName));
if (returnCollection.ContainsAttribute(currentAttribute) || currentAttribute.AttributeName.ToUpper().Trim() == "RESULT")
{
continue;
}
returnCollection.Add(currentAttribute);
}
return(returnCollection);
}
/// <summary>
/// Sets up a decision tree based on samples submitted
/// </summary>
/// <param name="samples">Table with samples that will be provided for mounting the tree </param>
/// <param name="targetAttribute">Name column of the table that otherwise has the value true or false to
/// Validate or not a sample </param>
/// <returns>The root of the decision tree mounted</returns></returns?>
public TreeNode mountTree(DataTable samples, string targetAttribute, TreeAttributeCollection attributes)
{
_sampleData = samples;
return(internalMountTree(_sampleData, targetAttribute, attributes));
}
/// <summary>
/// Sets up a decision tree based on samples submitted
/// </summary>
/// <param name="samples">Table with samples that will be provided for mounting the tree </param>
/// <param name="targetAttribute"> Name column of the table that otherwise has the value true or false to
/// Validate or not a sample</param>
/// <returns>The root of the decision tree mounted </returns></returns?>
private TreeNode internalMountTree(DataTable samples, string targetAttribute, TreeAttributeCollection attributes)
{
if (allSamplesAreUniform(samples, targetAttribute) == true)
{
return(new TreeNode(new OutcomeTreeAttribute(getUniformRefValue(samples, targetAttribute))));
}
//if (allSamplesArePositive(samples, targetAttribute) == true)
// return new TreeNode(new OutcomeTreeAttribute(true));
//if (allSamplesAreNegative(samples, targetAttribute) == true)
// return new TreeNode(new OutcomeTreeAttribute(false));
if (attributes.Count == 0)
{
return(new TreeNode(new OutcomeTreeAttribute(getMostCommonValue(samples, targetAttribute))));
}
mTotal = samples.Rows.Count;
mTargetAttribute = targetAttribute;
mTotalPositives = countTotalPositives(samples);
mEntropySet = getCalculatedEntropy(mTotalPositives, mTotal - mTotalPositives);
TreeAttribute bestAttribute = getBestAttribute(samples, attributes);
TreeNode root = new TreeNode(bestAttribute);
if (bestAttribute == null)
{
return(root);
}
PossibleValueCollection bestAttrValues = bestAttribute.PossibleValues;
bool continousSet = isContinousSet(bestAttrValues);
//DataTable aSample = samples.Clone();
if (continousSet)
{
string value = bestSplitValue(samples, bestAttribute);
{
DataTable aSample = samples.Clone();
//First Below then Above
DataRow[] rows;
string cond = bestAttribute.AttributeName + " <= " + "" + value + "";
rows = samples.Select(cond);
aSample.Rows.Clear();
foreach (DataRow row in rows)
{
aSample.Rows.Add(row.ItemArray);
Console.WriteLine(" SPLIT {0} ROW:", cond);
foreach (DataColumn myCol in samples.Columns)
{
Console.WriteLine(" " + row[myCol]);
}
}
// Create a new attribute list unless the attribute which is the current best attribute
TreeAttributeCollection aAttributes = new TreeAttributeCollection();
//ArrayList aAttributes = new ArrayList(attributes.Count - 1);
for (int i = 0; i < attributes.Count; i++)
{
if (attributes[i].AttributeName != bestAttribute.AttributeName)
{
aAttributes.Add(attributes[i]);
}
}
//Recycle the best continous attribute if there are others
if (aAttributes.Count > 0)
{
aAttributes.Add(bestAttribute);
}
// Create a new attribute list unless the attribute which is the current best attribute
if (rows.Length == 0)
{
//return new TreeNode(new OutcomeTreeAttribute(getMostCommonValue(aSample, targetAttribute)));
return(new TreeNode(new OutcomeTreeAttribute(getMostCommonValue(samples, targetAttribute))));
}
else
{
DecisionTree dc3 = new DecisionTree();
TreeNode ChildNode = dc3.mountTree(aSample, targetAttribute, aAttributes);
root.AddTreeNode(ChildNode, value, "leq");
}
}
{
DataTable aSample = samples.Clone();
DataRow[] rows2;
string cond = bestAttribute.AttributeName + " > " + "" + value + "";
rows2 = samples.Select(cond);
aSample.Rows.Clear();
foreach (DataRow row in rows2)
{
aSample.Rows.Add(row.ItemArray);
Console.WriteLine(" SPLIT {0} ROW:", cond);
foreach (DataColumn myCol in samples.Columns)
{
Console.WriteLine(" " + row[myCol]);
}
}
// Create a new attribute list unless the attribute which is the current best attribute
TreeAttributeCollection aAttributes2 = new TreeAttributeCollection();
//ArrayList aAttributes = new ArrayList(attributes.Count - 1);
for (int i = 0; i < attributes.Count; i++)
{
if (attributes[i].AttributeName != bestAttribute.AttributeName)
{
aAttributes2.Add(attributes[i]);
}
}
//Recycle the best continous attribute if there are others
if (aAttributes2.Count > 0)
{
aAttributes2.Add(bestAttribute);
}
// Create a new attribute list unless the attribute which is the current best attribute
if (rows2.Length == 0)
{
//return new TreeNode(new OutcomeTreeAttribute(getMostCommonValue(aSample, targetAttribute)));
return(new TreeNode(new OutcomeTreeAttribute(getMostCommonValue(samples, targetAttribute))));
}
else
{
DecisionTree dc3 = new DecisionTree();
TreeNode ChildNode = dc3.mountTree(aSample, targetAttribute, aAttributes2);
root.AddTreeNode(ChildNode, value, "gt");
}
}
}
else
{
DataTable aSample = samples.Clone();
foreach (string value in bestAttribute.PossibleValues)
{
// Select all elements with the value of this attribute
aSample.Rows.Clear();
DataRow[] rows;
rows = samples.Select(bestAttribute.AttributeName + " = " + "'" + value + "'");
foreach (DataRow row in rows)
{
aSample.Rows.Add(row.ItemArray);
}
// Select all elements with the value of this attribute
// Create a new attribute list unless the attribute which is the current best attribute
TreeAttributeCollection aAttributes = new TreeAttributeCollection();
//ArrayList aAttributes = new ArrayList(attributes.Count - 1);
for (int i = 0; i < attributes.Count; i++)
{
if (attributes[i].AttributeName != bestAttribute.AttributeName)
{
aAttributes.Add(attributes[i]);
}
}
// Create a new attribute list unless the attribute which is the current best attribute
if (aSample.Rows.Count == 0)
{
//return new TreeNode(new OutcomeTreeAttribute(getMostCommonValue(aSample, targetAttribute)));
return(new TreeNode(new OutcomeTreeAttribute(getMostCommonValue(samples, targetAttribute))));
}
else
{
DecisionTree dc3 = new DecisionTree();
TreeNode ChildNode = dc3.mountTree(aSample, targetAttribute, aAttributes);
root.AddTreeNode(ChildNode, value, "eq");
}
}
}
return(root);
}