C# Instances.classIndex方法代码示例

    // 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");
    }

    /* 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> Method for testing this class.
		/// 
		/// </summary>
		/// <param name="argv">should contain one element: the name of an ARFF file
		/// </param>
		//@ requires argv != null;
		//@ requires argv.length == 1;
		//@ requires argv[0] != null;
		public static void  test(System.String[] argv)
		{
			
			Instances instances, secondInstances, train, test, empty;
			//Instance instance;
			//UPGRADE_TODO: The differences in the expected value  of parameters for constructor 'java.util.Random.Random'  may cause compilation errors.  "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
			System.Random random = new System.Random((System.Int32) 2);
			//UPGRADE_ISSUE: Class hierarchy differences between 'java.io.Reader' and 'System.IO.StreamReader' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1186'"
			System.IO.StreamReader reader;
			int start, num;
			//double newWeight;
			FastVector testAtts, testVals;
			int i, j;
			
			try
			{
				if (argv.Length > 1)
				{
					throw (new System.Exception("Usage: Instances [<filename>]"));
				}
				
				// Creating set of instances from scratch
				testVals = new FastVector(2);
				testVals.addElement("first_value");
				testVals.addElement("second_value");
				testAtts = new FastVector(2);
				testAtts.addElement(new Attribute("nominal_attribute", testVals));
				testAtts.addElement(new Attribute("numeric_attribute"));
				instances = new Instances("test_set", testAtts, 10);
				instances.add(new Instance(instances.numAttributes()));
				instances.add(new Instance(instances.numAttributes()));
				instances.add(new Instance(instances.numAttributes()));
				instances.ClassIndex = 0;
				System.Console.Out.WriteLine("\nSet of instances created from scratch:\n");
				//UPGRADE_TODO: Method 'java.io.PrintStream.println' was converted to 'System.Console.Out.WriteLine' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javaioPrintStreamprintln_javalangObject'"
				System.Console.Out.WriteLine(instances);
				
				if (argv.Length == 1)
				{
					System.String filename = argv[0];
					//UPGRADE_TODO: Constructor 'java.io.FileReader.FileReader' was converted to 'System.IO.StreamReader' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073'"
					reader = new System.IO.StreamReader(filename, System.Text.Encoding.Default);
					
					// Read first five instances and print them
					System.Console.Out.WriteLine("\nFirst five instances from file:\n");
					instances = new Instances(reader, 1);
					instances.ClassIndex = instances.numAttributes() - 1;
					i = 0;
					while ((i < 5) && (instances.readInstance(reader)))
					{
						i++;
					}
					//UPGRADE_TODO: Method 'java.io.PrintStream.println' was converted to 'System.Console.Out.WriteLine' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javaioPrintStreamprintln_javalangObject'"
					System.Console.Out.WriteLine(instances);
					
					// Read all the instances in the file
					//UPGRADE_TODO: Constructor 'java.io.FileReader.FileReader' was converted to 'System.IO.StreamReader' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073'"
					reader = new System.IO.StreamReader(filename, System.Text.Encoding.Default);
					instances = new Instances(reader);
					
					// Make the last attribute be the class 
					instances.ClassIndex = instances.numAttributes() - 1;
					
					// Print header and instances.
					System.Console.Out.WriteLine("\nDataset:\n");
					//UPGRADE_TODO: Method 'java.io.PrintStream.println' was converted to 'System.Console.Out.WriteLine' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javaioPrintStreamprintln_javalangObject'"
					System.Console.Out.WriteLine(instances);
					System.Console.Out.WriteLine("\nClass index: " + instances.classIndex());
				}
				
				// Test basic methods based on class index.
				System.Console.Out.WriteLine("\nClass name: " + instances.classAttribute().name());
				System.Console.Out.WriteLine("\nClass index: " + instances.classIndex());
				System.Console.Out.WriteLine("\nClass is nominal: " + instances.classAttribute().Nominal);
				System.Console.Out.WriteLine("\nClass is numeric: " + instances.classAttribute().Numeric);
				System.Console.Out.WriteLine("\nClasses:\n");
				for (i = 0; i < instances.numClasses(); i++)
				{
					System.Console.Out.WriteLine(instances.classAttribute().value_Renamed(i));
				}
				System.Console.Out.WriteLine("\nClass values and labels of instances:\n");
				for (i = 0; i < instances.numInstances(); i++)
				{
					Instance inst = instances.instance(i);
					System.Console.Out.Write(inst.classValue() + "\t");
					System.Console.Out.Write(inst.toString(inst.classIndex()));
					if (instances.instance(i).classIsMissing())
					{
						System.Console.Out.WriteLine("\tis missing");
					}
					else
					{
//.........这里部分代码省略.........

    // 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());
        }
    }

		/// <summary> Performs one boosting iteration.</summary>
		private void  performIteration(double[][] trainYs, double[][] trainFs, double[][] probs, Instances data, double origSumOfWeights)
		{
			
			if (m_Debug)
			{
				System.Console.Error.WriteLine("Training classifier " + (m_NumGenerated + 1));
			}
			
			// Build the new models
			for (int j = 0; j < m_NumClasses; j++)
			{
				if (m_Debug)
				{
					System.Console.Error.WriteLine("\t...for class " + (j + 1) + " (" + m_ClassAttribute.name() + "=" + m_ClassAttribute.value_Renamed(j) + ")");
				}
				
				// Make copy because we want to save the weights
				Instances boostData = new Instances(data);
				
				// Set instance pseudoclass and weights
				for (int i = 0; i < probs.Length; i++)
				{
					
					// Compute response and weight
					double p = probs[i][j];
					double z, actual = trainYs[i][j];
					if (actual == 1 - m_Offset)
					{
						z = 1.0 / p;
						if (z > Z_MAX)
						{
							// threshold
							z = Z_MAX;
						}
					}
					else
					{
						z = (- 1.0) / (1.0 - p);
						if (z < - Z_MAX)
						{
							// threshold
							z = - Z_MAX;
						}
					}
					double w = (actual - p) / z;
					
					// Set values for instance
					Instance current = boostData.instance(i);
					current.setValue(boostData.classIndex(), z);
					current.Weight = current.weight() * w;
				}
				
				// Scale the weights (helps with some base learners)
				double sumOfWeights = boostData.sumOfWeights();
				double scalingFactor = (double) origSumOfWeights / sumOfWeights;
				for (int i = 0; i < probs.Length; i++)
				{
					Instance current = boostData.instance(i);
					current.Weight = current.weight() * scalingFactor;
				}
				
				// Select instances to train the classifier on
				Instances trainData = boostData;
				if (m_WeightThreshold < 100)
				{
					trainData = selectWeightQuantile(boostData, (double) m_WeightThreshold / 100);
				}
				else
				{
					if (m_UseResampling)
					{
						double[] weights = new double[boostData.numInstances()];
						for (int kk = 0; kk < weights.Length; kk++)
						{
							weights[kk] = boostData.instance(kk).weight();
						}
						trainData = boostData.resampleWithWeights(m_RandomInstance, weights);
					}
				}
				
				// Build the classifier
				m_Classifiers[j][m_NumGenerated].buildClassifier(trainData);
			}
			
			// Evaluate / increment trainFs from the classifier
			for (int i = 0; i < trainFs.Length; i++)
			{
				double[] pred = new double[m_NumClasses];
				double predSum = 0;
				for (int j = 0; j < m_NumClasses; j++)
				{
					pred[j] = m_Shrinkage * m_Classifiers[j][m_NumGenerated].classifyInstance(data.instance(i));
					predSum += pred[j];
				}
				predSum /= m_NumClasses;
				for (int j = 0; j < m_NumClasses; j++)
				{
					trainFs[i][j] += (pred[j] - predSum) * (m_NumClasses - 1) / m_NumClasses;
				}
//.........这里部分代码省略.........

		/// <summary> Builds the boosted classifier</summary>
		public virtual void  buildClassifier(Instances data)
		{
			m_RandomInstance = new Random(m_Seed);
			Instances boostData;
			int classIndex = data.classIndex();
			
			if (data.classAttribute().Numeric)
			{
				throw new Exception("LogitBoost can't handle a numeric class!");
			}
			if (m_Classifier == null)
			{
				throw new System.Exception("A base classifier has not been specified!");
			}
			
			if (!(m_Classifier is WeightedInstancesHandler) && !m_UseResampling)
			{
				m_UseResampling = true;
			}
			if (data.checkForStringAttributes())
			{
				throw new Exception("Cannot handle string attributes!");
			}
			if (m_Debug)
			{
				System.Console.Error.WriteLine("Creating copy of the training data");
			}
			
			m_NumClasses = data.numClasses();
			m_ClassAttribute = data.classAttribute();
			
			// Create a copy of the data 
			data = new Instances(data);
			data.deleteWithMissingClass();
			
			// Create the base classifiers
			if (m_Debug)
			{
				System.Console.Error.WriteLine("Creating base classifiers");
			}
			m_Classifiers = new Classifier[m_NumClasses][];
			for (int j = 0; j < m_NumClasses; j++)
			{
				m_Classifiers[j] = Classifier.makeCopies(m_Classifier, this.NumIterations);
			}
			
			// Do we want to select the appropriate number of iterations
			// using cross-validation?
			int bestNumIterations = this.NumIterations;
			if (m_NumFolds > 1)
			{
				if (m_Debug)
				{
					System.Console.Error.WriteLine("Processing first fold.");
				}
				
				// Array for storing the results
				double[] results = new double[this.NumIterations];
				
				// Iterate throught the cv-runs
				for (int r = 0; r < m_NumRuns; r++)
				{
					
					// Stratify the data
					data.randomize(m_RandomInstance);
					data.stratify(m_NumFolds);
					
					// Perform the cross-validation
					for (int i = 0; i < m_NumFolds; i++)
					{
						
						// Get train and test folds
						Instances train = data.trainCV(m_NumFolds, i, m_RandomInstance);
						Instances test = data.testCV(m_NumFolds, i);
						
						// Make class numeric
						Instances trainN = new Instances(train);
						trainN.ClassIndex = - 1;
						trainN.deleteAttributeAt(classIndex);
						trainN.insertAttributeAt(new weka.core.Attribute("'pseudo class'"), classIndex);
						trainN.ClassIndex = classIndex;
						m_NumericClassData = new Instances(trainN, 0);
						
						// Get class values
						int numInstances = train.numInstances();
						double[][] tmpArray = new double[numInstances][];
						for (int i2 = 0; i2 < numInstances; i2++)
						{
							tmpArray[i2] = new double[m_NumClasses];
						}
						double[][] trainFs = tmpArray;
						double[][] tmpArray2 = new double[numInstances][];
						for (int i3 = 0; i3 < numInstances; i3++)
						{
							tmpArray2[i3] = new double[m_NumClasses];
						}
						double[][] trainYs = tmpArray2;
						for (int j = 0; j < m_NumClasses; j++)
						{
//.........这里部分代码省略.........

		/// <summary> Generates the classifier.
		/// 
		/// </summary>
		/// <param name="instances">set of instances serving as training data 
		/// </param>
		/// <exception cref="Exception">if the classifier has not been generated successfully
		/// </exception>
		public override void  buildClassifier(Instances instances)
		{
			//UPGRADE_TODO: The equivalent in .NET for field 'java.lang.Double.MAX_VALUE' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
			double bestVal = System.Double.MaxValue, currVal;
			//UPGRADE_TODO: The equivalent in .NET for field 'java.lang.Double.MAX_VALUE' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
			double bestPoint = - System.Double.MaxValue, sum;
			int bestAtt = - 1, numClasses;
			
			if (instances.checkForStringAttributes())
			{
				throw new Exception("Can't handle string attributes!");
			}
			
			double[][] bestDist = new double[3][];
			for (int i = 0; i < 3; i++)
			{
				bestDist[i] = new double[instances.numClasses()];
			}
			
			m_Instances = new Instances(instances);
			m_Instances.deleteWithMissingClass();
			
			if (m_Instances.numInstances() == 0)
			{
				throw new System.ArgumentException("No instances without missing " + "class values in training file!");
			}
			
			if (instances.numAttributes() == 1)
			{
				throw new System.ArgumentException("Attribute missing. Need at least one " + "attribute other than class attribute!");
			}
			
			if (m_Instances.classAttribute().Nominal)
			{
				numClasses = m_Instances.numClasses();
			}
			else
			{
				numClasses = 1;
			}
			
			// For each attribute
			bool first = true;
			for (int i = 0; i < m_Instances.numAttributes(); i++)
			{
				if (i != m_Instances.classIndex())
				{
					
					// Reserve space for distribution.
					double[][] tmpArray = new double[3][];
					for (int i2 = 0; i2 < 3; i2++)
					{
						tmpArray[i2] = new double[numClasses];
					}
					m_Distribution = tmpArray;
					
					// Compute value of criterion for best split on attribute
					if (m_Instances.attribute(i).Nominal)
					{
						currVal = findSplitNominal(i);
					}
					else
					{
						currVal = findSplitNumeric(i);
					}
					if ((first) || (currVal < bestVal))
					{
						bestVal = currVal;
						bestAtt = i;
						bestPoint = m_SplitPoint;
						for (int j = 0; j < 3; j++)
						{
							Array.Copy(m_Distribution[j], 0, bestDist[j], 0, numClasses);
						}
					}
					
					// First attribute has been investigated
					first = false;
				}
			}
			
			// Set attribute, split point and distribution.
			m_AttIndex = bestAtt;
			m_SplitPoint = bestPoint;
			m_Distribution = bestDist;
			if (m_Instances.classAttribute().Nominal)
			{
				for (int i = 0; i < m_Distribution.Length; i++)
				{
					double sumCounts = Utils.sum(m_Distribution[i]);
					if (sumCounts == 0)
					{
						// This means there were only missing attribute values
//.........这里部分代码省略.........