public static DataSet ConstructFromCsv(string filePath, bool hasClassLabel)
{
var set = new DataSet();
var contents = File.ReadAllText(filePath);
var entries = contents.Split(new[] { '\n' }, StringSplitOptions.RemoveEmptyEntries);
var correctAttrCount = 0;
foreach (var entry in entries)
{
var example = new Example();
var fields = entry.Split(new[] { ',' }, StringSplitOptions.RemoveEmptyEntries);
// if we have a class label, the last field is not an attribute
var attrCount = hasClassLabel ? fields.Length - 1 : fields.Length;
// make sure that all entries have the same number of attributes
if (correctAttrCount == 0)
{
correctAttrCount = attrCount;
}
else if (correctAttrCount != attrCount)
{
throw new Exception("Invalid CSV entry, wrong number of attributes.");
}
// add all attributes to example
for (var i = 0; i < attrCount; i++)
{
var value = fields[i].Trim();
example.Attributes[i] = value;
if (set.Attributes.Count == i)
{
set.Attributes.Add(new DataAttribute(i));
}
set.Attributes[i].Values.Add(value);
}
// add class label if we have it
if (hasClassLabel)
{
example.ClassLabel = fields[attrCount].Trim();
}
set.Examples.Add(example);
}
return set;
}
/// <summary>
/// Recursive down the decision tree using the example's attributes
/// until we hit a leaf node, which has the class label
/// </summary>
private static string GetClassLabel(TreeNode decisionTree, Example testExample)
{
if (decisionTree.ClassLabel != null)
{
return decisionTree.ClassLabel;
}
var exampleAttrVal = testExample.Attributes[decisionTree.ColNum];
var subTree = decisionTree.Children[exampleAttrVal];
return GetClassLabel(subTree, testExample);
}
