C# Instances.numClasses方法代码示例

		/// <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)
		{
			
			double sumOfWeights = 0;
			
			m_Class = instances.classAttribute();
			m_ClassValue = 0;
			switch (instances.classAttribute().type())
			{
				
				case weka.core.Attribute.NUMERIC: 
					m_Counts = null;
					break;

                case weka.core.Attribute.NOMINAL: 
					m_Counts = new double[instances.numClasses()];
					for (int i = 0; i < m_Counts.Length; i++)
					{
						m_Counts[i] = 1;
					}
					sumOfWeights = instances.numClasses();
					break;
				
				default: 
					throw new System.Exception("ZeroR can only handle nominal and numeric class" + " attributes.");
				
			}
			System.Collections.IEnumerator enu = instances.enumerateInstances();
			//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
			while (enu.MoveNext())
			{
				//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
				Instance instance = (Instance) enu.Current;
				if (!instance.classIsMissing())
				{
					if (instances.classAttribute().Nominal)
					{
						//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'"
						m_Counts[(int) instance.classValue()] += instance.weight();
					}
					else
					{
						m_ClassValue += instance.weight() * instance.classValue();
					}
					sumOfWeights += instance.weight();
				}
			}
			if (instances.classAttribute().Numeric)
			{
				if (Utils.gr(sumOfWeights, 0))
				{
					m_ClassValue /= sumOfWeights;
				}
			}
			else
			{
				m_ClassValue = Utils.maxIndex(m_Counts);
				Utils.normalize(m_Counts, sumOfWeights);
			}
		}

		/// <summary> Creates split on numeric attribute.
		/// 
		/// </summary>
		/// <exception cref="Exception">if something goes wrong
		/// </exception>
		private void  handleNumericAttribute(Instances trainInstances)
		{
			
			int firstMiss;
			int next = 1;
			int last = 0;
			int splitIndex = - 1;
			double currentInfoGain;
			double defaultEnt;
			double minSplit;
			Instance instance;
			int i;
			
			// Current attribute is a numeric attribute.
			m_distribution = new Distribution(2, trainInstances.numClasses());
			
			// Only Instances with known values are relevant.
			System.Collections.IEnumerator enu = trainInstances.enumerateInstances();
			i = 0;
			//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
			while (enu.MoveNext())
			{
				//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
				instance = (Instance) enu.Current;
				if (instance.isMissing(m_attIndex))
					break;
				m_distribution.add(1, instance);
				i++;
			}
			firstMiss = i;
			
			// Compute minimum number of Instances required in each
			// subset.
			minSplit = 0.1 * (m_distribution.total()) / ((double) trainInstances.numClasses());
			if (Utils.smOrEq(minSplit, m_minNoObj))
				minSplit = m_minNoObj;
			else if (Utils.gr(minSplit, 25))
				minSplit = 25;
			
			// Enough Instances with known values?
			if (Utils.sm((double) firstMiss, 2 * minSplit))
				return ;
			
			// Compute values of criteria for all possible split
			// indices.
			defaultEnt = infoGainCrit.oldEnt(m_distribution);
			while (next < firstMiss)
			{
				
				if (trainInstances.instance(next - 1).value_Renamed(m_attIndex) + 1e-5 < trainInstances.instance(next).value_Renamed(m_attIndex))
				{
					
					// Move class values for all Instances up to next 
					// possible split point.
					m_distribution.shiftRange(1, 0, trainInstances, last, next);
					
					// Check if enough Instances in each subset and compute
					// values for criteria.
					if (Utils.grOrEq(m_distribution.perBag(0), minSplit) && Utils.grOrEq(m_distribution.perBag(1), minSplit))
					{
						currentInfoGain = infoGainCrit.splitCritValue(m_distribution, m_sumOfWeights, defaultEnt);
						if (Utils.gr(currentInfoGain, m_infoGain))
						{
							m_infoGain = currentInfoGain;
							splitIndex = next - 1;
						}
						m_index++;
					}
					last = next;
				}
				next++;
			}
			
			// Was there any useful split?
			if (m_index == 0)
				return ;
			
			// Compute modified information gain for best split.
			m_infoGain = m_infoGain - (Utils.log2(m_index) / m_sumOfWeights);
			if (Utils.smOrEq(m_infoGain, 0))
				return ;
			
			// Set instance variables' values to values for
			// best split.
			m_numSubsets = 2;
			m_splitPoint = (trainInstances.instance(splitIndex + 1).value_Renamed(m_attIndex) + trainInstances.instance(splitIndex).value_Renamed(m_attIndex)) / 2;
			
			// In case we have a numerical precision problem we need to choose the
			// smaller value
			if (m_splitPoint == trainInstances.instance(splitIndex + 1).value_Renamed(m_attIndex))
			{
				m_splitPoint = trainInstances.instance(splitIndex).value_Renamed(m_attIndex);
			}
			
			// Restore distributioN for best split.
//.........这里部分代码省略.........

		/// <summary> Initializes all the counters for the evaluation and also takes a
		/// cost matrix as parameter.
		/// Use <code>useNoPriors()</code> if the dataset is the test set and you
		/// can't initialize with the priors from the training set via 
		/// <code>setPriors(Instances)</code>.
		/// 
		/// </summary>
		/// <param name="data">	set of training instances, to get some header 
		/// information and prior class distribution information
		/// </param>
		/// <param name="costMatrix">	the cost matrix---if null, default costs will be used
		/// </param>
		/// <throws>  Exception 	if cost matrix is not compatible with  </throws>
		/// <summary> 			data, the class is not defined or the class is numeric
		/// </summary>
		/// <seealso cref="useNoPriors()">
		/// </seealso>
		/// <seealso cref="setPriors(Instances)">
		/// </seealso>
		public Evaluation(Instances data, CostMatrix costMatrix)
		{
			
			m_NumClasses = data.numClasses();
			m_NumFolds = 1;
			m_ClassIsNominal = data.classAttribute().Nominal;
			
			if (m_ClassIsNominal)
			{
				double[][] tmpArray = new double[m_NumClasses][];
				for (int i = 0; i < m_NumClasses; i++)
				{
					tmpArray[i] = new double[m_NumClasses];
				}
				m_ConfusionMatrix = tmpArray;
				m_ClassNames = new System.String[m_NumClasses];
				for (int i = 0; i < m_NumClasses; i++)
				{
					m_ClassNames[i] = data.classAttribute().value_Renamed(i);
				}
			}
			m_CostMatrix = costMatrix;
			if (m_CostMatrix != null)
			{
				if (!m_ClassIsNominal)
				{
					throw new System.Exception("Class has to be nominal if cost matrix " + "given!");
				}
				if (m_CostMatrix.size() != m_NumClasses)
				{
					throw new System.Exception("Cost matrix not compatible with data!");
				}
			}
			m_ClassPriors = new double[m_NumClasses];
			Priors = data;
			m_MarginCounts = new double[k_MarginResolution + 1];
		}

		/// <summary> Creates split on enumerated attribute.
		/// 
		/// </summary>
		/// <exception cref="Exception">if something goes wrong
		/// </exception>
		private void  handleEnumeratedAttribute(Instances trainInstances)
		{
			
			Distribution newDistribution, secondDistribution;
			int numAttValues;
			double currIG, currGR;
			Instance instance;
			int i;
			
			numAttValues = trainInstances.attribute(m_attIndex).numValues();
			newDistribution = new Distribution(numAttValues, trainInstances.numClasses());
			
			// Only Instances with known values are relevant.
			System.Collections.IEnumerator enu = trainInstances.enumerateInstances();
			//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
			while (enu.MoveNext())
			{
				//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
				instance = (Instance) enu.Current;
				if (!instance.isMissing(m_attIndex))
				{
					//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'"
					newDistribution.add((int) instance.value_Renamed(m_attIndex), instance);
				}
			}
			m_distribution = newDistribution;
			
			// For all values
			for (i = 0; i < numAttValues; i++)
			{
				
				if (Utils.grOrEq(newDistribution.perBag(i), m_minNoObj))
				{
					secondDistribution = new Distribution(newDistribution, i);
					
					// Check if minimum number of Instances in the two
					// subsets.
					if (secondDistribution.check(m_minNoObj))
					{
						m_numSubsets = 2;
						currIG = m_infoGainCrit.splitCritValue(secondDistribution, m_sumOfWeights);
						currGR = m_gainRatioCrit.splitCritValue(secondDistribution, m_sumOfWeights, currIG);
						if ((i == 0) || Utils.gr(currGR, m_gainRatio))
						{
							m_gainRatio = currGR;
							m_infoGain = currIG;
							m_splitPoint = (double) i;
							m_distribution = secondDistribution;
						}
					}
				}
			}
		}

		/// <summary> Creates split on enumerated attribute.
		/// 
		/// </summary>
		/// <exception cref="Exception">if something goes wrong
		/// </exception>
		private void  handleEnumeratedAttribute(Instances trainInstances)
		{
			
			Instance instance;
			
			m_distribution = new Distribution(m_complexityIndex, trainInstances.numClasses());
			
			// Only Instances with known values are relevant.
			System.Collections.IEnumerator enu = trainInstances.enumerateInstances();
			//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
			while (enu.MoveNext())
			{
				//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
				instance = (Instance) enu.Current;
				if (!instance.isMissing(m_attIndex))
				{
					//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'"
					m_distribution.add((int) instance.value_Renamed(m_attIndex), instance);
				}
			}
			
			// Check if minimum number of Instances in at least two
			// subsets.
			if (m_distribution.check(m_minNoObj))
			{
				m_numSubsets = m_complexityIndex;
				m_infoGain = infoGainCrit.splitCritValue(m_distribution, m_sumOfWeights);
				m_gainRatio = gainRatioCrit.splitCritValue(m_distribution, m_sumOfWeights, m_infoGain);
			}
		}

		public override void  buildClassifier(Instances insts)
		{
			
			if (insts.checkForStringAttributes())
			{
				throw new Exception("Cannot handle string attributes!");
			}
			if (insts.numClasses() > 2)
			{
				throw new System.Exception("Can only handle two-class datasets!");
			}
			if (insts.classAttribute().Numeric)
			{
				throw new Exception("Can't handle a numeric class!");
			}
			
			// Filter data
			m_Train = new Instances(insts);
			m_Train.deleteWithMissingClass();
			m_ReplaceMissingValues = new ReplaceMissingValues();
			m_ReplaceMissingValues.setInputFormat(m_Train);
			m_Train = Filter.useFilter(m_Train, m_ReplaceMissingValues);
			
			m_NominalToBinary = new NominalToBinary();
			m_NominalToBinary.setInputFormat(m_Train);
			m_Train = Filter.useFilter(m_Train, m_NominalToBinary);
			
			/** Randomize training data */
			//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'"
			m_Train.randomize(new System.Random((System.Int32) m_Seed));
			
			/** Make space to store perceptrons */
			m_Additions = new int[m_MaxK + 1];
			m_IsAddition = new bool[m_MaxK + 1];
			m_Weights = new int[m_MaxK + 1];
			
			/** Compute perceptrons */
			m_K = 0;
			for (int it = 0; it < m_NumIterations; it++)
			{
				for (int i = 0; i < m_Train.numInstances(); i++)
				{
					Instance inst = m_Train.instance(i);
					if (!inst.classIsMissing())
					{
						int prediction = makePrediction(m_K, inst);
						//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'"
						int classValue = (int) inst.classValue();
						if (prediction == classValue)
						{
							m_Weights[m_K]++;
						}
						else
						{
							m_IsAddition[m_K] = (classValue == 1);
							m_Additions[m_K] = i;
							m_K++;
							m_Weights[m_K]++;
						}
						if (m_K == m_MaxK)
						{
							//UPGRADE_NOTE: Labeled break statement was changed to a goto statement. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1012'"
							goto out_brk;
						}
					}
				}
			}
			//UPGRADE_NOTE: Label 'out_brk' was added. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1011'"

out_brk: ;
			
		}

		/// <summary> Creates a distribution according to given instances and
		/// split model.
		/// 
		/// </summary>
		/// <exception cref="Exception">if something goes wrong
		/// </exception>
		
		public Distribution(Instances source, ClassifierSplitModel modelToUse)
		{
			
			int index;
			Instance instance;
			double[] weights;
			
			m_perClassPerBag = new double[modelToUse.numSubsets()][];
			for (int i = 0; i < modelToUse.numSubsets(); i++)
			{
				m_perClassPerBag[i] = new double[0];
			}
			m_perBag = new double[modelToUse.numSubsets()];
			totaL = 0;
			m_perClass = new double[source.numClasses()];
			for (int i = 0; i < modelToUse.numSubsets(); i++)
				m_perClassPerBag[i] = new double[source.numClasses()];
			System.Collections.IEnumerator enu = source.enumerateInstances();
			//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
			while (enu.MoveNext())
			{
				//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
				instance = (Instance) enu.Current;
				index = modelToUse.whichSubset(instance);
				if (index != - 1)
					add(index, instance);
				else
				{
					weights = modelToUse.GetWeights(instance);
					addWeights(instance, weights);
				}
			}
		}

		/// <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.........