C# Instances.sumOfWeights方法代码示例

		/// <summary> Builds the tree structure with hold out set
		/// 
		/// </summary>
		/// <param name="train">the data for which the tree structure is to be
		/// generated.
		/// </param>
		/// <param name="test">the test data for potential pruning
		/// </param>
		/// <param name="keepData">is training Data to be kept?
		/// </param>
		/// <exception cref="Exception">if something goes wrong
		/// </exception>
		public virtual void  buildTree(Instances train, Instances test, bool keepData)
		{
			
			Instances[] localTrain, localTest;
			int i;
			
			if (keepData)
			{
				m_train = train;
			}
			m_isLeaf = false;
			m_isEmpty = false;
			m_sons = null;
			m_localModel = m_toSelectModel.selectModel(train, test);
			m_test = new Distribution(test, m_localModel);
			if (m_localModel.numSubsets() > 1)
			{
				localTrain = m_localModel.split(train);
				localTest = m_localModel.split(test);
				train = test = null;
				m_sons = new ClassifierTree[m_localModel.numSubsets()];
				for (i = 0; i < m_sons.Length; i++)
				{
					m_sons[i] = getNewTree(localTrain[i], localTest[i]);
					localTrain[i] = null;
					localTest[i] = null;
				}
			}
			else
			{
				m_isLeaf = true;
				if (Utils.eq(train.sumOfWeights(), 0))
					m_isEmpty = true;
				train = test = null;
			}
		}

		/// <summary> Selects C4.5-type split for the given dataset.</summary>
		public override ClassifierSplitModel selectModel(Instances data)
		{
			
			double minResult;
			//double currentResult;
			BinC45Split[] currentModel;
			BinC45Split bestModel = null;
			NoSplit noSplitModel = null;
			double averageInfoGain = 0;
			int validModels = 0;
			bool multiVal = true;
			Distribution checkDistribution;
			double sumOfWeights;
			int i;
			
			try
			{
				
				// Check if all Instances belong to one class or if not
				// enough Instances to split.
				checkDistribution = new Distribution(data);
				noSplitModel = new NoSplit(checkDistribution);
				if (Utils.sm(checkDistribution.total(), 2 * m_minNoObj) || Utils.eq(checkDistribution.total(), checkDistribution.perClass(checkDistribution.maxClass())))
					return noSplitModel;
				
				// Check if all attributes are nominal and have a 
				// lot of values.
				System.Collections.IEnumerator enu = data.enumerateAttributes();
				//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'"
                    weka.core.Attribute attribute = (weka.core.Attribute)enu.Current;
					if ((attribute.Numeric) || (Utils.sm((double) attribute.numValues(), (0.3 * (double) m_allData.numInstances()))))
					{
						multiVal = false;
						break;
					}
				}
				currentModel = new BinC45Split[data.numAttributes()];
				sumOfWeights = data.sumOfWeights();
				
				// For each attribute.
				for (i = 0; i < data.numAttributes(); i++)
				{
					
					// Apart from class attribute.
					if (i != (data).classIndex())
					{
						
						// Get models for current attribute.
						currentModel[i] = new BinC45Split(i, m_minNoObj, sumOfWeights);
						currentModel[i].buildClassifier(data);
						
						// Check if useful split for current attribute
						// exists and check for enumerated attributes with 
						// a lot of values.
						if (currentModel[i].checkModel())
							if ((data.attribute(i).Numeric) || (multiVal || Utils.sm((double) data.attribute(i).numValues(), (0.3 * (double) m_allData.numInstances()))))
							{
								averageInfoGain = averageInfoGain + currentModel[i].infoGain();
								validModels++;
							}
					}
					else
						currentModel[i] = null;
				}
				
				// Check if any useful split was found.
				if (validModels == 0)
					return noSplitModel;
				averageInfoGain = averageInfoGain / (double) validModels;
				
				// Find "best" attribute to split on.
				minResult = 0;
				for (i = 0; i < data.numAttributes(); i++)
				{
					if ((i != (data).classIndex()) && (currentModel[i].checkModel()))
					// Use 1E-3 here to get a closer approximation to the original
					// implementation.
						if ((currentModel[i].infoGain() >= (averageInfoGain - 1e-3)) && Utils.gr(currentModel[i].gainRatio(), minResult))
						{
							bestModel = currentModel[i];
							minResult = currentModel[i].gainRatio();
						}
				}
				
				// Check if useful split was found.
				if (Utils.eq(minResult, 0))
					return noSplitModel;
				
				// Add all Instances with unknown values for the corresponding
				// attribute to the distribution for the model, so that
				// the complete distribution is stored with the model. 
				bestModel.distribution().addInstWithUnknown(data, bestModel.attIndex());
				
				// Set the split point analogue to C45 if attribute numeric.
				bestModel.SplitPoint = m_allData;
				return bestModel;
//.........这里部分代码省略.........

		/// <summary> Computes new distributions of instances for nodes
		/// in tree.
		/// 
		/// </summary>
		/// <exception cref="Exception">if something goes wrong
		/// </exception>
		private void  newDistribution(Instances data)
		{
			
			Instances[] localInstances;
			
			localModel().resetDistribution(data);
			m_train = data;
			if (!m_isLeaf)
			{
				localInstances = (Instances[]) localModel().split(data);
				for (int i = 0; i < m_sons.Length; i++)
					son(i).newDistribution(localInstances[i]);
			}
			else
			{
				
				// Check whether there are some instances at the leaf now!
				if (!Utils.eq(data.sumOfWeights(), 0))
				{
					m_isEmpty = false;
				}
			}
		}

//.........这里部分代码省略.........
				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
					{
						System.Console.Out.WriteLine();
					}
				}
				
				// Create random weights.
				System.Console.Out.WriteLine("\nCreating random weights for instances.");
				for (i = 0; i < instances.numInstances(); i++)
				{
					instances.instance(i).Weight = random.NextDouble();
				}
				
				// Print all instances and their weights (and the sum of weights).
				System.Console.Out.WriteLine("\nInstances and their weights:\n");
				System.Console.Out.WriteLine(instances.instancesAndWeights());
				System.Console.Out.Write("\nSum of weights: ");
				System.Console.Out.WriteLine(instances.sumOfWeights());
				
				// Insert an attribute
				secondInstances = new Instances(instances);
				Attribute testAtt = new Attribute("Inserted");
				secondInstances.insertAttributeAt(testAtt, 0);
				System.Console.Out.WriteLine("\nSet with inserted attribute:\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(secondInstances);
				System.Console.Out.WriteLine("\nClass name: " + secondInstances.classAttribute().name());
				
				// Delete the attribute
				secondInstances.deleteAttributeAt(0);
				System.Console.Out.WriteLine("\nSet with attribute deleted:\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(secondInstances);
				System.Console.Out.WriteLine("\nClass name: " + secondInstances.classAttribute().name());
				
				// Test if headers are equal
				System.Console.Out.WriteLine("\nHeaders equal: " + instances.equalHeaders(secondInstances) + "\n");
				
				// Print data in internal format.
				System.Console.Out.WriteLine("\nData (internal values):\n");
				for (i = 0; i < instances.numInstances(); i++)
				{
					for (j = 0; j < instances.numAttributes(); j++)
					{
						if (instances.instance(i).isMissing(j))
						{
							System.Console.Out.Write("? ");
						}
						else
						{

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

//.........这里部分代码省略.........
						// 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++)
						{
							for (int k = 0; k < numInstances; k++)
							{
								trainYs[k][j] = (train.instance(k).classValue() == j)?1.0 - m_Offset:0.0 + (m_Offset / (double) m_NumClasses);
							}
						}
						
						// Perform iterations
						double[][] probs = initialProbs(numInstances);
						m_NumGenerated = 0;
						double sumOfWeights = train.sumOfWeights();
						for (int j = 0; j < this.NumIterations; j++)
						{
							performIteration(trainYs, trainFs, probs, trainN, sumOfWeights);
							Evaluation eval = new Evaluation(train);
							eval.evaluateModel(this, test);
							results[j] += eval.correct();
						}
					}
				}
				
				// Find the number of iterations with the lowest error
				//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 bestResult = - System.Double.MaxValue;
				for (int j = 0; j < this.NumIterations; j++)
				{
					if (results[j] > bestResult)
					{
						bestResult = results[j];
						bestNumIterations = j;
					}
				}
				if (m_Debug)
				{
					System.Console.Error.WriteLine("Best result for " + bestNumIterations + " iterations: " + bestResult);
				}
			}
			
			// Build classifier on all the data
			int numInstances2 = data.numInstances();
			double[][] trainFs2 = new double[numInstances2][];
			for (int i4 = 0; i4 < numInstances2; i4++)
			{