static void Main()
{
var records = LoadData();
int crossValidationSetsCount = 277 / 5;
int totalCount = records.Count();
int testingSetCount = totalCount / crossValidationSetsCount;
double totalAccuracy = 0;
for (int i = 0; i < crossValidationSetsCount; i++)
{
var testSet = records.Skip(i * testingSetCount).Take(testingSetCount);
var trainingSet = records.Take(i * testingSetCount).Concat(records.Skip((i + 1) * testingSetCount).Take((crossValidationSetsCount - i) * testingSetCount));
TreeNode root = CreateNode(trainingSet, Attributes, GetdominatingClass(trainingSet));//the dominatingOutcome should not be used in the first children
double succesfullPredictions = 0;
foreach (var testRecord in testSet)
{
OutcomeClass predictedOutcome = PredictOutcome(root, testRecord);
if (predictedOutcome == testRecord.OutcomeClass)
{
succesfullPredictions++;
}
}
Console.WriteLine($"For test set {i} success is {succesfullPredictions / testingSetCount * 100}%");
totalAccuracy += succesfullPredictions / testingSetCount;
}
Console.WriteLine($"The total accuracy is {totalAccuracy / crossValidationSetsCount * 100}%");
}
private static TreeNode CreateNode(IEnumerable <Record> records, IEnumerable <string> attributes, OutcomeClass dominatingParentOutcome)
{
var treeNode = new TreeNode();
treeNode.DominatingParrentOutcome = dominatingParentOutcome;
double minEntropy = 1000;
string chosenAttribute = "";
if (records.Count() == 0)//there are no examples in the subset, which happens when no example in the parent set was found to match a specific value of the selected attribute.Then a leaf node is created and labelled with the most common class of the examples in the parent node's set.
{
treeNode.IsLeaf = true;
treeNode.Outcome = dominatingParentOutcome;
return(treeNode);
}
if (attributes.Count() == 0)//there are no more attributes to be selected, but the examples still do not belong to the same class. In this case, the node is made a leaf node and labelled with the most common class of the examples in the subset.
{
var dominatingOutcome = GetdominatingClass(records);
treeNode.IsLeaf = true;
treeNode.Outcome = dominatingOutcome;
return(treeNode);
}
foreach (var attribute in attributes)
{
double entropy = getEntropy(records, attribute);
if (entropy < minEntropy)
{
minEntropy = entropy;
chosenAttribute = attribute;
}
}
treeNode.NextAttributeName = chosenAttribute;
var property = typeof(Record).GetProperties().First(prop => prop.Name == chosenAttribute);
var grouped = records.GroupBy(
record => property.GetValue(record)
);
foreach (var group in grouped)
{
var childNode = new TreeNode();
if (getEntropy(group, chosenAttribute) == 0)
{
childNode.IsLeaf = true;
childNode.Outcome = group.First().OutcomeClass;
childNode.AttributeValue = group.Key as string;
}
else
{
childNode = CreateNode(group, attributes.Where(attr => attr != chosenAttribute), GetdominatingClass(records));
childNode.AttributeValue = group.Key as string; //property.GetValue(group.First()) as string;
}
treeNode.Children.Add(childNode);
}
return(treeNode);
}
