/// <summary>
/// Reads an arff file and gets all the headers (<see cref="ArffHeader"/>) and instances (<see cref="object[][]"/>).
/// </summary>
/// <param name="arff">Arff file name</param>
private void ReadArff(string arff)
{
Header = null;
Instances = null;
try
{
if (File.Exists(arff))
{
using (ArffReader arffReader = new ArffReader(arff))
{
Header = arffReader.ReadHeader();
Instances = arffReader.ReadAllInstances();
}
}
else
{
throw new FileNotFoundException(string.Format("File \"{0}\" does not exist.", arff), arff);
}
}
catch (Exception e)
{
if (Verbose)
{
throw new Exception(string.Format("Arff file could not be read: {0}\n{1}", e.Message, e.StackTrace), e);
}
else
{
throw new Exception(string.Format("Arff file could not be read: {0}", e.Message), e);
}
}
}
public void CRLineEndings()
{
string arff = "@relation relationName\r@attribute a1 numeric\r@data";
ArffReader arffReader = CreateArffReader(arff);
ArffHeader arffHeader = arffReader.ReadHeader();
}
public void MissingAttributes()
{
string arff = @"@relation relationName
@data";
ArffReader arffReader = CreateArffReader(arff);
ArffHeader arffHeader = arffReader.ReadHeader();
}
public void MissingRelationName()
{
string arff = @"@attribute a1 numeric
@data";
ArffReader arffReader = CreateArffReader(arff);
ArffHeader arffHeader = arffReader.ReadHeader();
}
public void ReadInstanceBeforeHeader()
{
string arff = @"@relation relationName
@attribute a1 numeric
@data";
ArffReader arffReader = CreateArffReader(arff);
arffReader.ReadInstance();
}
public void KeywordCaseInsensitivity()
{
string arff = @"@RElatION relationName
@ATTRiBUTE a1 nuMERic
@DaTa";
ArffReader arffReader = CreateArffReader(arff);
ArffHeader arffHeader = arffReader.ReadHeader();
}
public void MissingData()
{
string arff = @"@relation relationName
@attribute a1 numeric
";
ArffReader arffReader = CreateArffReader(arff);
ArffHeader arffHeader = arffReader.ReadHeader();
}
public void NoInstances()
{
string arff = @"@relation relationName
@attribute a1 numeric
@data";
ArffReader arffReader = CreateArffReader(arff);
arffReader.ReadHeader();
Assert.IsNull(arffReader.ReadInstance());
Assert.IsNull(arffReader.ReadInstance());
}
public void InstanceWeightsReadCorrectly()
{
string arff = @"@relation relationName
@attribute a1 numeric
@attribute a2 integer
@attribute a3 real
@data
-6.54,42,0.0
-6.54,42,0.0,{5}
-6.54,42,0.0,{0.476}
{0 -6.54,1 42}
{0 -6.54,1 42},{0.476}";
ArffReader arffReader = CreateArffReader(arff);
arffReader.ReadHeader();
arffReader.ReadInstance(out double?instanceWeight);
Assert.IsNull(instanceWeight);
arffReader.ReadInstance(out instanceWeight);
Assert.AreEqual(5.0, instanceWeight);
arffReader.ReadInstance(out instanceWeight);
Assert.AreEqual(0.476, instanceWeight);
arffReader.ReadInstance(out instanceWeight);
Assert.IsNull(instanceWeight);
arffReader.ReadInstance(out instanceWeight);
Assert.AreEqual(0.476, instanceWeight);
}
private void AssertReader(string arff, string expectedRelationName = null, ICollection expectedAttributes = null, object[][] expectedInstances = null)
{
ArffReader arffReader = CreateArffReader(arff);
ArffHeader arffHeader = arffReader.ReadHeader();
if (expectedRelationName != null)
{
Assert.AreEqual(expectedRelationName, arffHeader.RelationName, "Unexpected relation name.");
}
if (expectedAttributes != null)
{
CollectionAssert.AreEqual(expectedAttributes, arffHeader.Attributes, "Unexpected attributes.");
}
object[][] instances = arffReader.ReadAllInstances();
if (expectedInstances != null)
{
CollectionAssert.AreEqual(expectedInstances, instances, new InstanceComparer(), "Unexpected instances.");
}
}
static void Main(string[] args)
{
// Training
ArffHeader header = null;
List <object[]> instances = new List <object[]>();
using (ArffReader arffReader = new ArffReader(_trainingArffFile))
{
header = arffReader.ReadHeader();
object[] instance;
while ((instance = arffReader.ReadInstance()) != null)
{
instances.Add(instance);
}
}
List <int[]> trainingData = new List <int[]>(instances.Select(objectArray => objectArray.Select(o => o == null ? -1 : (int)o).ToArray()));
// Test
instances = new List <object[]>();
using (ArffReader arffReader = new ArffReader(_testArffFile))
{
header = arffReader.ReadHeader();
object[] instance;
while ((instance = arffReader.ReadInstance()) != null)
{
instances.Add(instance);
}
}
List <int[]> testData = new List <int[]>(instances.Select(objectArray => objectArray.Select(o => o == null ? -1 : (int)o).ToArray()));
double[] confidences = new double[]
{
0.0,
0.1,
0.2,
0.4,
0.6,
0.8,
0.9,
0.95,
0.99,
0.9999
};
PrintAsCsv(header, trainingData, _pathToOutputCsv);
Parallel.ForEach(confidences, confidence =>
{
Id3Classifier classifier = new Id3Classifier(trainingData, _classIndex, confidence);
Console.WriteLine($"Confidence {confidence}: Num of nodes {classifier.Tree.Count}");
// Test accuracy on training
Console.WriteLine($"Confidence {confidence}: Accuracy on train = { trainingData.Where(instance => classifier.GetClass(instance) == instance[_classIndex]).Count() / (double)trainingData.Count}");
// Test accuracy on test
Console.WriteLine($"Confidence {confidence}: Accuracy on test = { testData.Where(instance => classifier.GetClass(instance) == instance[_classIndex]).Count() / (double)testData.Count}");
StringBuilder sb = new StringBuilder();
StringBuilder sbMaxPositive = new StringBuilder();
StringBuilder sbMaxNegative = new StringBuilder();
int maxPositive = int.MinValue;
int maxNegative = int.MinValue;
// Only print small trees.
if (confidence > 0.5)
{
PrintTreeAsRules(sb, ref sbMaxPositive, ref sbMaxNegative, ref maxPositive, ref maxNegative, classifier.Tree, header);
sb.AppendLine("The most max positive rule is:");
sb.AppendLine(sbMaxPositive.ToString());
sb.AppendLine();
sb.AppendLine("The most max negative rule is:");
sb.AppendLine(sbMaxNegative.ToString());
Directory.CreateDirectory(_outputFolder);
File.WriteAllText(Path.Combine(_outputFolder, $"Tree{confidence}.txt"), sb.ToString());
}
});
Console.WriteLine("Press ENTER to exit...");
Console.ReadLine();
}
private void WriteArffFile(string[] allfiles)
{
using (ArffWriter arffWriter = new ArffWriter(textBox3.Text + ".arff"))
{
bool relation = true;
object[] inst = null;
object[][] insts = new object[allfiles.Length][];
int n = 0;
foreach (string file in allfiles)
{
FileInfo fi = new FileInfo(file);
ArffReader datafile = new ArffReader(file);
ArffHeader header = datafile.ReadHeader();
var instances = datafile.ReadAllInstances();
//var instance = datafile.ReadInstance();
object[] instance = null;
foreach (var ins in instances)
{
instance = ins;
}
if (header != null)
{
var attributes = header.Attributes;
string line;
StreamReader attrfile = new StreamReader("attributes.txt");
int i = 0;
int j = 0;
while ((line = attrfile.ReadLine()) != null)
{
foreach (var attribute in attributes)
{
if (attribute.Name == line)
{
if (relation == true)
{
arffWriter.WriteRelationName(header.RelationName);
relation = false;
}
arffWriter.WriteAttribute(new ArffAttribute(attribute.Name, attribute.Type));
j++;
}
i++;
}
}
inst = new object[j];
j = 0;
i = 0;
while ((line = attrfile.ReadLine()) != null)
{
foreach (var attribute in attributes)
{
if (attribute.Name == line)
{
inst.SetValue(instance.GetValue(i), j);
j++;
}
i++;
}
}
insts.SetValue(inst, n);
attrfile.Close();
}
datafile.Dispose();
n++;
progress++;
}
foreach (var ins in insts)
{
arffWriter.WriteInstance(new object[] { ins });
}
}
}
static void Main(string[] args)
{
// Training
ArffHeader header = null;
List <object[]> instances = new List <object[]>();
using (ArffReader arffReader = new ArffReader(TrainingArffFile))
{
header = arffReader.ReadHeader();
object[] instance;
while ((instance = arffReader.ReadInstance()) != null)
{
instances.Add(instance);
}
}
List <int[]> trainingData = new List <int[]>(instances.Select(objectArray => objectArray.Select(o => o == null ? -1 : (int)o).ToArray()));
// Test
instances = new List <object[]>();
using (ArffReader arffReader = new ArffReader(TestArffFile))
{
header = arffReader.ReadHeader();
object[] instance;
while ((instance = arffReader.ReadInstance()) != null)
{
instances.Add(instance);
}
}
List <int[]> testData = new List <int[]>(instances.Select(objectArray => objectArray.Select(o => o == null ? -1 : (int)o).ToArray()));
Console.WriteLine("Number of Samples, training accuracy, test accuracy");
// Do this excercise multiple times as sampling is random.
Parallel.For(0, 100, (k) =>
{
// Dictionaries to store results for different accuracies. KEEP IN SYNC :)
ConcurrentDictionary <int, double> sampleTrainingAccuraciesMap = new ConcurrentDictionary <int, double>(new Dictionary <int, double>
{
{ 1, 0 },
{ 3, 0 },
{ 5, 0 },
{ 10, 0 },
{ 20, 0 },
{ 25, 0 },
{ 50, 0 },
{ 75, 0 },
{ 100, 0 }
});
ConcurrentDictionary <int, double> sampleTestAccuraciesMap = new ConcurrentDictionary <int, double>(new Dictionary <int, double>
{
{ 1, 0 },
{ 3, 0 },
{ 5, 0 },
{ 10, 0 },
{ 20, 0 },
{ 25, 0 },
{ 50, 0 },
{ 75, 0 },
{ 100, 0 }
});
// Calculate different sample accuracies in parallel.
Parallel.ForEach(sampleTrainingAccuraciesMap.Keys, numOfSamples =>
{
List <Id3Classifier> classifiers = new List <Id3Classifier>();
Sampler sampler = new Sampler(trainingData, numOfSamples);
for (int i = 0; i < numOfSamples; i++)
{
Id3Classifier classifier = new Id3Classifier(sampler.Samples[i], ClassIndex, Confidence);
classifiers.Add(classifier);
}
// Evaluate training and test to look out for overfitting.
sampleTrainingAccuraciesMap[numOfSamples] = Evaluate(trainingData, classifiers);
sampleTestAccuraciesMap[numOfSamples] = Evaluate(testData, classifiers);
});
lock (_lockConsole)
{
foreach (int numOfSamples in sampleTestAccuraciesMap.Keys.OrderBy(n => n))
{
Console.WriteLine($"{numOfSamples},{sampleTrainingAccuraciesMap[numOfSamples]},{sampleTestAccuraciesMap[numOfSamples]}");
}
}
});
Console.WriteLine("Press ENTER to exit...");
Console.ReadLine();
}
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);
}
}
