/* Use when the player logs in to initially create the classifier with data from server */
public void InitializeClassifier(String dataString)
{
try {
java.io.StringReader stringReader = new java.io.StringReader(dataString);
java.io.BufferedReader buffReader = new java.io.BufferedReader(stringReader);
playerData = new weka.core.Instances(buffReader);
/* State where in each Instance the class attribute is, if its not already specified by the file */
if (playerData.classIndex() == -1)
{
playerData.setClassIndex(playerData.numAttributes() - 1);
}
/* NAIVE BAYES */
//classifier = new weka.classifiers.bayes.NaiveBayes();
/* NEURAL NET */
//classifier = new weka.classifiers.functions.MultilayerPerceptron();
//((weka.classifiers.functions.MultilayerPerceptron)classifier).setHiddenLayers("12");
/* J48 TREE */
//classifier = new weka.classifiers.trees.J48();
/* IB1 NEAREST NEIGHBOUR */
//classifier = new weka.classifiers.lazy.IB1();
/* RANDOM FOREST */
classifier = new weka.classifiers.trees.RandomForest();
classifier.buildClassifier(playerData);
Debug.Log("Initialized Classifier");
}
catch (java.lang.Exception ex)
{
Debug.LogError(ex.getMessage());
}
}
/// <summary> Applies the cost matrix to a set of instances. If a random number generator is
/// supplied the instances will be resampled, otherwise they will be rewighted.
/// Adapted from code once sitting in Instances.java
///
/// </summary>
/// <param name="data">the instances to reweight.
/// </param>
/// <param name="random">a random number generator for resampling, if null then instances are
/// rewighted.
/// </param>
/// <returns> a new dataset reflecting the cost of misclassification.
/// </returns>
/// <exception cref="Exception">if the data has no class or the matrix in inappropriate.
/// </exception>
public virtual Instances applyCostMatrix(Instances data, System.Random random)
{
double sumOfWeightFactors = 0, sumOfMissClassWeights, sumOfWeights;
double[] weightOfInstancesInClass, weightFactor, weightOfInstances;
Instances newData;
if (data.classIndex() < 0)
{
throw new System.Exception("Class index is not set!");
}
if (size() != data.numClasses())
{
throw new System.Exception("Misclassification cost matrix has " + "wrong format!");
}
weightFactor = new double[data.numClasses()];
weightOfInstancesInClass = new double[data.numClasses()];
for (int j = 0; j < data.numInstances(); j++)
{
//UPGRADE_WARNING: Data types in Visual C# might be different. Verify the accuracy of narrowing conversions. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1042'"
weightOfInstancesInClass[(int) data.instance(j).classValue()] += data.instance(j).weight();
}
sumOfWeights = Utils.sum(weightOfInstancesInClass);
// normalize the matrix if not already
for (int i = 0; i < size(); i++)
if (!Utils.eq(getXmlElement(i, i), 0))
{
CostMatrix normMatrix = new CostMatrix(this);
normMatrix.normalize();
return normMatrix.applyCostMatrix(data, random);
}
for (int i = 0; i < data.numClasses(); i++)
{
// Using Kai Ming Ting's formula for deriving weights for
// the classes and Breiman's heuristic for multiclass
// problems.
sumOfMissClassWeights = 0;
for (int j = 0; j < data.numClasses(); j++)
{
if (Utils.sm(getXmlElement(i, j), 0))
{
throw new System.Exception("Neg. weights in misclassification " + "cost matrix!");
}
sumOfMissClassWeights += getXmlElement(i, j);
}
weightFactor[i] = sumOfMissClassWeights * sumOfWeights;
sumOfWeightFactors += sumOfMissClassWeights * weightOfInstancesInClass[i];
}
for (int i = 0; i < data.numClasses(); i++)
{
weightFactor[i] /= sumOfWeightFactors;
}
// Store new weights
weightOfInstances = new double[data.numInstances()];
for (int i = 0; i < data.numInstances(); i++)
{
//UPGRADE_WARNING: Data types in Visual C# might be different. Verify the accuracy of narrowing conversions. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1042'"
weightOfInstances[i] = data.instance(i).weight() * weightFactor[(int) data.instance(i).classValue()];
}
// Change instances weight or do resampling
if (random != null)
{
return data.resampleWithWeights(random, weightOfInstances);
}
else
{
Instances instances = new Instances(data);
for (int i = 0; i < data.numInstances(); i++)
{
instances.instance(i).Weight = weightOfInstances[i];
}
return instances;
}
}
// Test the classification result of each map that a user played,
// with the data available as if they were playing through it
public static void classifyTest(String dataString, String playerID)
{
String results = "";
try {
java.io.StringReader stringReader = new java.io.StringReader(dataString);
java.io.BufferedReader buffReader = new java.io.BufferedReader(stringReader);
/* NOTE THAT FOR NAIVE BAYES ALL WEIGHTS CAN BE = 1*/
//weka.core.converters.ConverterUtils.DataSource source = new weka.core.converters.ConverterUtils.DataSource("iris.arff");
weka.core.Instances data = new weka.core.Instances(buffReader); //source.getDataSet();
// setting class attribute if the data format does not provide this information
// For example, the XRFF format saves the class attribute information as well
if (data.classIndex() == -1)
{
data.setClassIndex(data.numAttributes() - 1);
}
weka.classifiers.Classifier cl;
for (int i = 3; i < data.numInstances(); i++)
{
cl = new weka.classifiers.bayes.NaiveBayes();
//cl = new weka.classifiers.trees.J48();
//cl = new weka.classifiers.lazy.IB1();
//cl = new weka.classifiers.functions.MultilayerPerceptron();
((weka.classifiers.functions.MultilayerPerceptron)cl).setHiddenLayers("12");
weka.core.Instances subset = new weka.core.Instances(data, 0, i);
cl.buildClassifier(subset);
weka.classifiers.Evaluation eval = new weka.classifiers.Evaluation(subset);
eval.crossValidateModel(cl, subset, 3, new java.util.Random(1));
results = results + eval.pctCorrect(); // For accuracy measurement
/* For Mathews Correlation Coefficient */
//double TP = eval.numTruePositives(1);
//double FP = eval.numFalsePositives(1);
//double TN = eval.numTrueNegatives(1);
//double FN = eval.numFalseNegatives(1);
//double correlationCoeff = ((TP*TN)-(FP*FN))/Math.Sqrt((TP+FP)*(TP+FN)*(TN+FP)*(TN+FN));
//results = results + correlationCoeff;
if (i != data.numInstances() - 1)
{
results = results + ", ";
}
if (i == data.numInstances() - 1)
{
Debug.Log("Player: " + playerID + ", Num Maps: " + data.numInstances() + ", AUC: " + eval.areaUnderROC(1));
}
}
} catch (java.lang.Exception ex)
{
Debug.LogError(ex.getMessage());
}
// Write values to file for a matlab read
// For accuracy
StreamWriter writer = new StreamWriter("DataForMatlab/" + playerID + "_CrossFoldValidations_NeuralNet.txt");
//StreamWriter writer = new StreamWriter("DataForMatlab/"+playerID+"_CrossFoldCorrCoeff.txt"); // For mathews cc
writer.WriteLine(results);
writer.Close();
Debug.Log(playerID + " has been written to file");
}
/// <summary> Sets the format of the input instances.
///
/// </summary>
/// <param name="instanceInfo">an Instances object containing the input
/// instance structure (any instances contained in the object are
/// ignored - only the structure is required).
/// </param>
/// <returns> true if the outputFormat may be collected immediately
/// </returns>
/// <exception cref="Exception">if the input format can't be set
/// successfully
/// </exception>
public override bool setInputFormat(Instances instanceInfo)
{
if (instanceInfo.classIndex() < 0 || !instanceInfo.classAttribute().Nominal)
{
throw new System.ArgumentException("Supervised resample requires nominal class");
}
base.setInputFormat(instanceInfo);
setOutputFormat(instanceInfo);
return true;
}
/// <summary> Sets the format of the input instances.
///
/// </summary>
/// <param name="instanceInfo">an Instances object containing the input instance
/// structure (any instances contained in the object are ignored - only the
/// structure is required).
/// </param>
/// <returns> true if the outputFormat may be collected immediately
/// </returns>
/// <exception cref="Exception">if the format couldn't be set successfully
/// </exception>
public override bool setInputFormat(Instances instanceInfo)
{
base.setInputFormat(instanceInfo);
m_SelectCols.Upper = instanceInfo.numAttributes() - 1;
// Create the output buffer
FastVector attributes = new FastVector();
int outputClass = - 1;
m_SelectedAttributes = m_SelectCols.Selection;
int inStrKeepLen = 0;
int[] inStrKeep = new int[m_SelectedAttributes.Length];
for (int i = 0; i < m_SelectedAttributes.Length; i++)
{
int current = m_SelectedAttributes[i];
if (instanceInfo.classIndex() == current)
{
outputClass = attributes.size();
}
Attribute keep = (Attribute) instanceInfo.attribute(current).copy();
if (keep.type() == Attribute.STRING)
{
inStrKeep[inStrKeepLen++] = current;
}
attributes.addElement(keep);
}
m_InputStringIndex = new int[inStrKeepLen];
Array.Copy(inStrKeep, 0, m_InputStringIndex, 0, inStrKeepLen);
Instances outputFormat = new Instances(instanceInfo.relationName(), attributes, 0);
outputFormat.ClassIndex = outputClass;
setOutputFormat(outputFormat);
return true;
}
// Test the classification result of each map that a user played,
// with the data available as if they were playing through it
public static void classifyTest(String dataString, String playerID)
{
try {
java.io.StringReader stringReader = new java.io.StringReader(dataString);
java.io.BufferedReader buffReader = new java.io.BufferedReader(stringReader);
/* NOTE THAT FOR NAIVE BAYES ALL WEIGHTS CAN BE = 1*/
//weka.core.converters.ConverterUtils.DataSource source = new weka.core.converters.ConverterUtils.DataSource("iris.arff");
weka.core.Instances thisData = new weka.core.Instances(buffReader); //source.getDataSet();
if (thisData.classIndex() == -1)
{
thisData.setClassIndex(thisData.numAttributes() - 1);
}
weka.core.Instances thisUniqueData = new weka.core.Instances(thisData);
if (thisUniqueData.classIndex() == -1)
{
thisUniqueData.setClassIndex(thisUniqueData.numAttributes() - 1);
}
thisUniqueData.delete();
if (allUniqueData == null)
{
allUniqueData = new weka.core.Instances(thisData);
if (allUniqueData.classIndex() == -1)
{
allUniqueData.setClassIndex(allUniqueData.numAttributes() - 1);
}
allUniqueData.delete();
}
weka.core.InstanceComparator com = new weka.core.InstanceComparator(false);
for (int i = 0; i < thisData.numInstances(); i++)
{
bool dup = false;
for (int j = 0; j < allUniqueData.numInstances(); j++)
{
if (com.compare(thisData.instance(i), allUniqueData.instance(j)) == 0)
{
Debug.Log("Duplicate found!");
dup = true;
break;
}
}
if (!dup)
{
allUniqueData.add(thisData.instance(i));
}
else
{
dupInstances++;
}
}
for (int i = 0; i < thisData.numInstances(); i++)
{
bool dup = false;
for (int j = 0; j < thisUniqueData.numInstances(); j++)
{
if (com.compare(thisData.instance(i), thisUniqueData.instance(j)) == 0)
{
Debug.Log("Duplicate found!");
dup = true;
break;
}
}
if (!dup)
{
thisUniqueData.add(thisData.instance(i));
}
else
{
dupInstancesSamePlayer++;
}
}
//Debug.Log("All Data Instance Count = " + thisData.numInstances());
//Debug.Log("Unique Data Instance Count = " + thisUniqueData.numInstances());
//Debug.Log("Done!");
} catch (java.lang.Exception ex)
{
Debug.LogError(ex.getMessage());
}
}
