/**
* <summary> Adds a new instance to the {@link InstanceList}.</summary>
*
* <param name="current">{@link Instance} to add.</param>
*/
public void AddInstance(Instance.Instance current)
{
if (_definition == null)
{
SetDefinition(current);
_instances.Add(current);
}
else
{
if (CheckDefinition(current))
{
_instances.Add(current);
}
}
}
/**
* <summary> Training algorithm for K-Means classifier. K-Means finds the mean of each class for training.</summary>
*
* <param name="trainSet"> Training data given to the algorithm.</param>
* <param name="parameters">distanceMetric: distance metric used to calculate the distance between two instances.</param>
*/
public override void Train(InstanceList.InstanceList trainSet, Parameter.Parameter parameters)
{
var priorDistribution = trainSet.ClassDistribution();
var classMeans = new InstanceList.InstanceList();
var classLists = trainSet.DivideIntoClasses();
for (var i = 0; i < classLists.Size(); i++)
{
classMeans.Add(classLists.Get(i).Average());
}
model = new KMeansModel(priorDistribution, classMeans, ((KMeansParameter)parameters).GetDistanceMetric());
}
/**
* <summary> Constructor for generating a new {@link DataSet} from given {@link File}.</summary>
*
* <param name="file">{@link File} to generate {@link DataSet} from.</param>
*/
public DataSet(string fileName)
{
var i = 0;
_instances = new InstanceList.InstanceList();
_definition = new DataDefinition();
var input = new StreamReader(fileName);
while (!input.EndOfStream)
{
var instanceText = input.ReadLine();
var attributes = instanceText.Split(",");
if (i == 0)
{
for (var j = 0; j < attributes.Length - 1; j++)
{
try
{
double.Parse(attributes[j]);
_definition.AddAttribute(AttributeType.CONTINUOUS);
}
catch (Exception)
{
_definition.AddAttribute(AttributeType.DISCRETE);
}
}
}
else
{
if (attributes.Length != _definition.AttributeCount() + 1)
{
continue;
}
}
Instance.Instance instance;
if (!attributes[attributes.Length - 1].Contains(";"))
{
instance = new Instance.Instance(attributes[attributes.Length - 1]);
}
else
{
var labels = attributes[attributes.Length - 1].Split(";");
instance = new CompositeInstance(labels);
}
for (var j = 0; j < attributes.Length - 1; j++)
{
switch (_definition.GetAttributeType(j))
{
case AttributeType.CONTINUOUS:
instance.AddAttribute(new ContinuousAttribute(double.Parse(attributes[j])));
break;
case AttributeType.DISCRETE:
instance.AddAttribute(new DiscreteAttribute(attributes[j]));
break;
}
}
if (instance.AttributeSize() == _definition.AttributeCount())
{
_instances.Add(instance);
}
i++;
}
input.Close();
}
