// Transforms the tree into a set of decision rules</see>.
public DecisionRuleSet ToRules(Dictionary <string, AttributeListInfo> attributes, AttributeType dvt)
{
return(DecisionRuleSet.FromDecisionTree(this, attributes, dvt));
}
private void Learn()
{
using (ArffReader arffReader = new ArffReader(filePath))
{
header = arffReader.ReadHeader();
attributes = new Dictionary <string, AttributeListInfo>(); //attribute name, attribute info
attributeList = header.Attributes.ToList();
foreach (var attr in attributeList)
{
string[] array = attr.Type.ToString().Split(',');
if (decisionVariableType == AttributeType.Discrete && (array[0].ToString() == "numeric" || array[0].ToString() == "real" || array.Length == 1))
{
throw new InvalidOperationException("Variable Type Should be Continous, not Discrete");
}
List <string> myList = new List <string>();
foreach (string s in array)
{
//if s contains real, do decision tree learning for real values
myList.Add(s.Replace("{", "").Replace("}", "").Trim());
}
AttributeListInfo myAttributeInfo = new AttributeListInfo(); //define information for each attribute, then add to dictionary
myAttributeInfo.NumberOfInputs = myList.Count; //array.Length
myAttributeInfo.Inputs = myList;
attributes.Add(attr.Name, myAttributeInfo);
if (_attributes.Count < attributeList.Count - 1)
{
_attributes.Add(new Attribute(attr.Name, myAttributeInfo.NumberOfInputs));
queryList.Add(new Query(attr.Name, myList));
}
else
{
lastAttrName = attr.Name;
}
}
List <double[]> inputs2 = new List <double[]>();
List <double[]> inputsAll = new List <double[]>();
List <int> outputs2 = new List <int>();
object[] instance;
while ((instance = arffReader.ReadInstance()) != null)
{
int Length = instance.Length;
double[] newRow = new double[Length - 1];
double[] row = new double[Length];
for (int i = 0; i < Length - 1; i++)
{
Double.TryParse(instance[i] + "", out newRow[i]);
}
for (int i = 0; i < Length; i++)
{
Double.TryParse(instance[i] + "", out row[i]);
}
inputs2.Add(newRow);
inputsAll.Add(row);
outputs2.Add(Int32.Parse(instance[Length - 1] + ""));
}
dInputs = inputs2.ToArray(); //inputs (expect the last index)
allDInputs = inputsAll.ToArray(); //all double inputs
outputs = outputs2.ToArray();
//decide what algorithm to use based on options.
if (learningAlgorithm == LearningAlgorithm.C45Learning && decisionVariableType == AttributeType.Continuous)
{
c45 = new C45Algorithm();
var stopwatch = new Stopwatch();
stopwatch.Start();
tree = c45.Learn(dInputs, outputs); //induce tree from data
stopwatch.Stop();
elapsedTime = stopwatch.ElapsedMilliseconds;
}
else if (learningAlgorithm == LearningAlgorithm.C45Learning && decisionVariableType == AttributeType.Both)
{
c45 = new C45Algorithm();
var stopwatch = new Stopwatch();
stopwatch.Start();
tree = c45.Learn(dInputs, outputs); //induce tree from data
stopwatch.Stop();
elapsedTime = stopwatch.ElapsedMilliseconds;
}
else if (learningAlgorithm == LearningAlgorithm.C45Learning && decisionVariableType == AttributeType.Discrete)
{
c45 = new C45Algorithm(_attributes.ToArray());
var stopwatch = new Stopwatch();
stopwatch.Start();
tree = c45.Learn(dInputs, outputs); //induce tree from data
stopwatch.Stop();
elapsedTime = stopwatch.ElapsedMilliseconds;
}
rules = tree.ToRules(attributes, decisionVariableType);
predicted = tree.ComputeDecision(dInputs);
}
}