public void RandomForestBuild(List <train> datalist)
{
int length = datalist.Count;
int d = datalist[0].d;
forest = new List <DecisionTree>();
int n = datalist.Count;
int k = d; //(int)Math.Sqrt(d);
int m = 100;
for (int i = 0; i < m; ++i)
{
double[][] inputs;
int[] outputs;
int[] indexs;
GetData(out inputs, out outputs, datalist, n, k, out indexs);
DecisionVariable[] variables = new DecisionVariable[k];
for (int j = 0; j < k; ++j)
{
variables[j] = new DecisionVariable("attribute" + (indexs[j] + 1), DecisionVariableKind.Continuous);
}
// Create the C4.5 learning algorithm
var c45 = new C45Learning(variables);
// Learn the decision tree using C4.5
DecisionTree dtmp = c45.Learn(inputs, outputs);
forest.Add(dtmp);
}
log("The random forest model has been trained");
}
private double run(double[][] inputs, int[] output)
{
int rows = inputs.Length;
int cols = inputs[0].Length;
int colsPerTree = 0;
if (CoverageRatio == 0)
{
colsPerTree = (int)(System.Math.Sqrt(cols));
}
else
{
colsPerTree = (int)(cols * CoverageRatio);
}
var trees = forest.Trees;
Parallel.For(0, trees.Length, ParallelOptions, i =>
{
int[] idx = Vector.Sample(SampleRatio, output.Length);
var x = inputs.Get(idx);
var y = output.Get(idx);
var c45 = new C45Learning(forest.Trees[i])
{
MaxVariables = colsPerTree,
Join = 100
};
c45.Learn(x, y);
});
return(0);
}
public void Learn()
{
var stopWatch = new Stopwatch();
stopWatch.Start();
var variables = new List <DecisionVariable>();
foreach (var vector in LearningData.TrainingData.First().ToVectorArray(Metadata, PropertiesToSkip))
{
variables.Add(new DecisionVariable(variables.Count.ToString(), new DoubleRange(-1, 1)));
}
Tree = new DecisionTree(variables, 2);
var learner = new C45Learning(Tree);
learner.Learn(LearningData.TrainingData.Select(data => data.ToVectorArray(Metadata, PropertiesToSkip)).ToArray(),
LearningData.TrainingData.Select(data => data.PercentMatch > 0 ? 1 : 0).ToArray());
var matcher = new LoggingDecisionTreeMatcher(LearningData.TrainingData);
matcher.LogMatchCount($"{Name} TrainingData", Tree, Metadata, PropertiesToSkip);
matcher = new LoggingDecisionTreeMatcher(LearningData.TestData);
matcher.LogMatchCount($"{Name} TestData", Tree, Metadata, PropertiesToSkip);
stopWatch.Stop();
Logger.InfoFormat("DecisionTreeLearning took {0}", stopWatch.Elapsed);
}
static void Main(string[] args)
{
DataTable table = new Accord.IO.CsvReader("C:\\Users\\michael\\Downloads\\JulyToOct2015Test.csv", true).ToTable();
// Convert the DataTable to input and output vectors
double[][] inputs = table.ToJagged <double>("BookToPrice", "DividendYield", "DebtToEquity", "MarketBeta", "SectorID");
int[] outputs = table.Columns["MonthlyReturn"].ToArray <int>();
//SecurityID BookToPrice DividendYield EarningsYield SalesGrowth AssetsToEquity MarketCap MarketBeta DebtToEquity 1YrVol 5YrVol 3YrVol ExposureToCurrencyGain SectorID countryID
DecisionTree tree = new DecisionTree(
inputs: new List <DecisionVariable>
{
DecisionVariable.Continuous("BookToPrice"),
DecisionVariable.Continuous("DividendYield"),
DecisionVariable.Continuous("DebtToEquity"),
DecisionVariable.Continuous("MarketBeta"),
DecisionVariable.Discrete("SectorID", 11)
},
classes: 2);
C45Learning teacher = new C45Learning(tree);
teacher.Learn(inputs, outputs);
int[] answers = tree.Decide(inputs);
// Plot the results
// ScatterplotBox.Show("Expected results", inputs, outputs);
//ScatterplotBox.Show("Ans", inputs, answers)
// .Hold();
}
private static void decisionTree(double[][] inputs, int[] outputs)
{
// In our problem, we have 2 classes (samples can be either
// positive or negative), and 2 continuous-valued inputs.
DecisionTree tree = new DecisionTree(attributes: new[]
{
DecisionVariable.Continuous("X"),
DecisionVariable.Continuous("Y")
}, outputClasses: 2);
C45Learning teacher = new C45Learning(tree);
// The C4.5 algorithm expects the class labels to
// range from 0 to k, so we convert -1 to be zero:
//
outputs = outputs.Apply(x => x < 0 ? 0 : x);
double error = teacher.Run(inputs, outputs);
// Classify the samples using the model
int[] answers = inputs.Apply(tree.Compute);
// Plot the results
ScatterplotBox.Show("Expected results", inputs, outputs);
ScatterplotBox.Show("Decision Tree results", inputs, answers)
.Hold();
}
public DecisionTree GenerateDecisionTree(int inputsCount, ref double[][] inputs, ref int[] outputs,
int outputClassNum, List <string> listVariablesName, int neiWindowSize, int landuseTypesCount)
{
DecisionVariable[] variable = new DecisionVariable[inputsCount];
for (int i = 0; i < inputsCount - 2; i++)
{
DecisionVariable v = new DecisionVariable(listVariablesName[i], DecisionVariableKind.Continuous);
variable[i] = v;
}
;
DecisionVariable dv = new DecisionVariable(listVariablesName[inputsCount - 2], neiWindowSize * neiWindowSize + 1);
variable[inputsCount - 2] = dv;
DecisionVariable dv2 = new DecisionVariable(listVariablesName[inputsCount - 1], landuseTypesCount);
variable[inputsCount - 1] = dv2;
DecisionTree tree = new DecisionTree(variable, outputClassNum);
C45Learning c45 = new C45Learning(tree);
//double error = c45.Run(inputs, outputs);
tree = c45.Learn(inputs, outputs);
return(tree);
}
public void ArgumentCheck1()
{
double[][] samples =
{
new [] { 0, 2, 4.0 },
new [] { 1, 5, 2.0 },
null,
new [] { 1, 5, 6.0 },
};
int[] outputs =
{
1, 1, 0, 0
};
DecisionVariable[] vars = new DecisionVariable[3];
for (int i = 0; i < vars.Length; i++)
{
vars[i] = DecisionVariable.Continuous(i.ToString());
}
DecisionTree tree = new DecisionTree(vars, 2);
var teacher = new C45Learning(tree);
bool thrown = false;
try { double error = teacher.Run(samples, outputs); }
catch (ArgumentNullException) { thrown = true; }
Assert.IsTrue(thrown);
}
public void LargeSampleTest2()
{
Accord.Math.Tools.SetupGenerator(0);
double[][] dataSamples = Matrix.Random(500, 3, 0.0, 10.0).ToJagged();
int[] target = Matrix.Random(500, 1, 0.0, 2.0).ToInt32().GetColumn(0);
DecisionVariable[] features =
{
new DecisionVariable("Outlook", DecisionVariableKind.Continuous),
new DecisionVariable("Temperature", DecisionVariableKind.Continuous),
new DecisionVariable("Humidity", DecisionVariableKind.Continuous),
};
DecisionTree tree = new DecisionTree(features, 2);
C45Learning teacher = new C45Learning(tree);
double error = teacher.Run(dataSamples, target);
foreach (var node in tree)
{
if (node.IsLeaf)
{
Assert.IsNotNull(node.Output);
}
}
Assert.IsTrue(error < 0.50);
}
protected void btnchangepassword0_Click(object sender, EventArgs e)
{
DataTable data = new DataTable();
data = f1.getrecord1("select * from dataset");
if (data.Rows.Count > 0)
{
double[][] inputs = data.ToJagged <double>("n", "p", "k", "ph", "ec");
string[] labels = new string[data.Rows.Count];
for (int i = 0; i < data.Rows.Count; i++)
{
labels[i] = data.Rows[i]["fertility"].ToString();
}
var codebook = new Codification("fertility", labels);
// With the codebook, we can convert the labels:
int[] outputs = codebook.Translate("fertility", labels);
C45Learning teacher = new C45Learning();
var tree = teacher.Learn(inputs, outputs);
int[] predicted = tree.Decide(inputs);
DecisionSet rules = tree.ToRules();
string ruleText = rules.ToString(codebook, "fertility", System.Globalization.CultureInfo.InvariantCulture);
var cm1 = new GeneralConfusionMatrix(classes: 3, expected: outputs, predicted: predicted);
//int[,] matrix = cm.Matrix;
double cm = cm1.Accuracy;
double cm2 = cm * 100;
Label1.Text = cm2.ToString();
}
}
public void ConsistencyTest1()
{
double[,] random = Matrix.Random(1000, 10, 0.0, 1.0);
double[][] samples = random.ToJagged();
int[] outputs = new int[1000];
for (int i = 0; i < samples.Length; i++)
{
if (samples[i][0] > 0.8)
{
outputs[i] = 1;
}
}
DecisionVariable[] vars = new DecisionVariable[10];
for (int i = 0; i < vars.Length; i++)
{
vars[i] = new DecisionVariable(i.ToString(), DecisionVariableKind.Continuous);
}
DecisionTree tree = new DecisionTree(vars, 2);
C45Learning teacher = new C45Learning(tree);
double error = teacher.Run(samples, outputs);
Assert.AreEqual(0, error);
Assert.AreEqual(2, tree.Root.Branches.Count);
Assert.IsTrue(tree.Root.Branches[0].IsLeaf);
Assert.IsTrue(tree.Root.Branches[1].IsLeaf);
}
/// <summary>
/// Creates and learns a Decision Tree to recognize the
/// previously loaded dataset using the current settings.
/// </summary>
///
private void btnCreate_Click(object sender, EventArgs e)
{
if (dgvLearningSource.DataSource == null)
{
MessageBox.Show("Please load some data first.");
return;
}
// Finishes and save any pending changes to the given data
dgvLearningSource.EndEdit();
// Creates a matrix from the entire source data table
double[,] table = (dgvLearningSource.DataSource as DataTable).ToMatrix(out columnNames);
// Get only the input vector values (first two columns)
double[][] inputs = table.GetColumns(0, 1).ToArray();
// Get only the output labels (last column)
int[] outputs = table.GetColumn(2).ToInt32();
// Specify the input variables
DecisionVariable[] variables =
{
new DecisionVariable("x", DecisionVariableKind.Continuous),
new DecisionVariable("y", DecisionVariableKind.Continuous),
};
// Create the discrete Decision tree
tree = new DecisionTree(variables, 2);
// Create the C4.5 learning algorithm
C45Learning c45 = new C45Learning(tree);
// Learn the decision tree using C4.5
double error = c45.Run(inputs, outputs);
// Show the learned tree in the view
decisionTreeView1.TreeSource = tree;
// Get the ranges for each variable (X and Y)
DoubleRange[] ranges = Matrix.Range(table, 0);
// Generate a Cartesian coordinate system
double[][] map = Matrix.CartesianProduct(
Matrix.Interval(ranges[0], 0.05),
Matrix.Interval(ranges[1], 0.05));
// Classify each point in the Cartesian coordinate system
double[] result = map.Apply(tree.Compute).ToDouble();
double[,] surface = map.ToMatrix().InsertColumn(result);
CreateScatterplot(zedGraphControl2, surface);
lbStatus.Text = "Learning finished! Click the other tabs to explore results!";
}
public static TrainingSet[] GenerateTrainingSets(IEnumerable <KeyValuePair <User, double[]> > studentsAndMarks, string[] normalRecords, string[] anomalies)
{
var countOfEntries = normalRecords.Length + anomalies.Length;
var inputData = new double[countOfEntries][];
var outputData = new int[countOfEntries];
var counter = 0;
foreach (var studentAndMarks in studentsAndMarks)
{
if (normalRecords.Contains(studentAndMarks.Key.OpenId))
{
inputData[counter] = studentAndMarks.Value;
outputData[counter++] = 1;
}
if (!anomalies.Contains(studentAndMarks.Key.OpenId))
{
continue;
}
inputData[counter] = studentAndMarks.Value;
outputData[counter++] = 0;
}
var countOfFeatures = studentsAndMarks.ElementAt(0).Value.Length;
var features = new DecisionVariable[countOfFeatures];
features[0] = new DecisionVariable("0", DecisionAttributeKind.Continuous, new AForge.DoubleRange(80, 1200));
for (var i = 1; i < countOfFeatures; i++)
{
features[i] = new DecisionVariable(i.ToString(), DecisionAttributeKind.Continuous, new AForge.DoubleRange(0, 10));
}
// Create the Decision tree with only 2 result values
var tree = new DecisionTree(features, 2);
// Creates a new instance of the C4.5 learning algorithm
var c45 = new C45Learning(tree);
// Learn the decision tree
var error = c45.Run(inputData, outputData);
// Split all data into normal and anomalies
var setOfNormalRecords = studentsAndMarks.Where(x => tree.Compute(x.Value) == 1);
var setOfAnomalies = studentsAndMarks.Where(x => tree.Compute(x.Value) == 0);
// Split normal records into 2 groups (one for training set and one for anomaly detection ocurency detection)
var setOfNormalRecordsList = setOfNormalRecords.ToList();
var splitCount = setOfNormalRecordsList.Count * 2 / 3;
var setOfNormalRecordsTr1 = setOfNormalRecordsList.GetRange(0, splitCount);
var setOfNormalRecordsTr2 = setOfNormalRecordsList.GetRange(splitCount, setOfNormalRecordsList.Count - splitCount);
// Create Training Sets
var trSetNormalFirst = CreateTrainingSetFromResources(setOfNormalRecordsTr1);
var trSetNormalSecond = CreateTrainingSetFromResources(setOfNormalRecordsTr2);
var trSetAnomalies = CreateTrainingSetFromResources(setOfAnomalies);
return(new[] { trSetNormalFirst, trSetNormalSecond, trSetAnomalies });
}
private void btnCreate_Click(object sender, EventArgs e)
{
if (dgvLearningSource.DataSource == null)
{
MessageBox.Show("Please load some data first.");
return;
}
// Finishes and save any pending changes to the given data
dgvLearningSource.EndEdit();
// Creates a matrix from the source data table
double[,] sourceMatrix = (dgvLearningSource.DataSource as DataTable).ToMatrix(out sourceColumns);
// Perform classification
C45Learning c45;
// Get only the input vector values
double[][] inputs = sourceMatrix.Submatrix(null, 0, 1).ToArray();
// Get only the label outputs
int[] outputs = sourceMatrix.GetColumn(2).ToInt32();
DecisionVariable[] attributes =
{
new DecisionVariable("x", DecisionAttributeKind.Continuous),
new DecisionVariable("y", DecisionAttributeKind.Continuous),
};
// Create the Decision tree
tree = new DecisionTree(attributes, 2);
// Creates a new instance of the C4.5 learning algorithm
c45 = new C45Learning(tree);
// Learn the decision tree
double error = c45.Run(inputs, outputs);
// Show the learned tree in the view
decisionTreeView1.TreeSource = tree;
// Draw the separating surface
var ranges = Matrix.Range(sourceMatrix);
double[][] map = Matrix.CartesianProduct(
Matrix.Interval(ranges[0], 0.05),
Matrix.Interval(ranges[1], 0.05));
var result = map.Apply(tree.Compute).Apply(Math.Sign);
var graph = map.ToMatrix().InsertColumn(result.ToDouble());
CreateScatterplot(zedGraphControl2, graph);
}
private void trainingC45lib()
{
Accord.Math.Random.Generator.Seed = 0;
c45Learning = new C45Learning()
{
Join = 2,
MaxHeight = 5
};
int size = trainingSets.Count;
double[][] inputs1 = new double[size][];
int[] outputs1 = new int[size];
int i = 0;
foreach (Patient patient in trainingSets)
{
double[] aux = new double[9];
for (int j = 1; j <= 9; j++)
{
if (j == 1)
{
aux[j - 1] = patient.get(j) < 30 ? 0 : patient.get(j) < 60 ? 1 : 2;
}
else
{
aux[j - 1] = patient.get(j);
}
}
inputs1[i] = aux;
outputs1[i] = patient.get(10);
i++;
}
var crossValidation = CrossValidation.Create(
k: 5,
learner: (p) => new C45Learning()
{
Join = 2,
MaxHeight = 5
},
loss: (actual, expected, p) => new ZeroOneLoss(expected).Loss(actual),
fit: (teacher, x, y, w) => teacher.Learn(x, y, w),
x: inputs1, y: outputs1
);
decisionTreeLib = c45Learning.Learn(inputs1, outputs1);
var result = crossValidation.Learn(inputs1, outputs1);
GeneralConfusionMatrix gcm = result.ToConfusionMatrix(inputs1, outputs1);
accuracyC45lib = Math.Round(gcm.Accuracy, 3);
}
public static void Main(string[] args)
{
//getting example data
Iris iris = new Iris();
//we are creating training data arrays
double[][] input = new double[147][];
int[] output = new int[147];
//we process 'Iris' data and delete 1 from each type for later test purpose
int j = 0;
for (int i = 0; i < 147; i++)
{
if (i != 0 || i != 50 || i != 100)
{
input[j] = new double[4];
output[j] = iris.ClassLabels[i];
for (int k = 0; k < 4; k++)
{
input[j][k] = iris.Instances[i][k];
}
j++;
}
}
//learning algorithm for decision tree
C45Learning teacher = new C45Learning(new[] {
DecisionVariable.Continuous(iris.VariableNames[0]),
DecisionVariable.Continuous(iris.VariableNames[1]),
DecisionVariable.Continuous(iris.VariableNames[2]),
DecisionVariable.Continuous(iris.VariableNames[3]),
});
//model learning
DecisionTree tree = teacher.Learn(input, output);
//If we would have some other irises we could just wrote like this
//DecisionTree tree = teacher.Learn(iris.Instances, iris.ClassLabels);
//but we prefer to left some for test purpose (to check if our programm is working fine)
//testing our model
double[][] test = { iris.Instances[0], iris.Instances[50], iris.Instances[100] };
int[] answers = tree.Decide(test);
Console.WriteLine("Answer should be as follow:\n0,1,2,\nAnswer is:");
foreach (int ans in answers)
{
Console.Write(ans + ",");
}
Console.Write("\nPress any key to continue . . . ");
Console.ReadKey(true);
}
public override Task <List <GeneralConfusionMatrix> > ComputeFoldedConfusionMatrixAsync(ClassificationModel classificationModel, int folds)
{
return(Task.Factory.StartNew(() =>
{
int numFeatures = classificationModel.FeatureVectors.Count;
DecisionVariable[] decisionVariables = Enumerable.ToArray(classificationModel.Bands.Select(b => DecisionVariable.Continuous(b.ToString())));
double[][] input = new double[numFeatures][];
int[] responses = new int[numFeatures];
for (int featureIndex = 0; featureIndex < classificationModel.FeatureVectors.Count; ++featureIndex)
{
var featureVector = classificationModel.FeatureVectors[featureIndex];
input[featureIndex] = Array.ConvertAll(featureVector.FeatureVector.BandIntensities, s => (double)s / ushort.MaxValue);
responses[featureIndex] = featureVector.FeatureClass;
}
List <GeneralConfusionMatrix> confusionMatrices = new List <GeneralConfusionMatrix>();
// Create a new Cross-validation algorithm passing the data set size and the number of folds
var crossvalidation = new CrossValidation(input.Length, folds);
crossvalidation.Fitting = delegate(int k, int[] indicesTrain, int[] indicesValidation)
{
// Lets now grab the training data:
var trainingInputs = input.Get(indicesTrain);
var trainingOutputs = responses.Get(indicesTrain);
// And now the validation data:
var validationInputs = input.Get(indicesValidation);
var validationOutputs = responses.Get(indicesValidation);
var tree = new DecisionTree(decisionVariables, Enum.GetValues(typeof(LandcoverTypeViewModel)).Length);
C45Learning id3Learning = new C45Learning(tree);
id3Learning.Learn(trainingInputs, trainingOutputs);
var predictedTraining = tree.Decide(trainingInputs);
var predictedValidation = tree.Decide(validationInputs);
double trainingError = new ZeroOneLoss(trainingOutputs).Loss(predictedTraining);
double validationError = new ZeroOneLoss(validationOutputs).Loss(predictedValidation);
GeneralConfusionMatrix confusionMatrix = new GeneralConfusionMatrix(Enum.GetValues(typeof(LandcoverTypeViewModel)).Length - 1, validationOutputs, predictedValidation);
confusionMatrices.Add(confusionMatrix);
// Return a new information structure containing the model and the errors achieved.
return new CrossValidationValues(trainingError, validationError);
};
var result = crossvalidation.Compute();
return confusionMatrices;
}));
}
public void Classification_Train(double[,] train_docrule, int[] label, string algorithm)
{
string classmodelpath;
int attrSize = eclatlitems.Count;
int attrSizeTest = eclatlitems.Count;
// Specify the input variables
DecisionVariable[] variables = new DecisionVariable[attrSize];
for (int i = 0; i < attrSize; i++)
{
variables[i] = new DecisionVariable((i + 1).ToString(), DecisionVariableKind.Discrete);
}
if (algorithm == "Tree")
{
classmodelpath = algorithm + ".model";
//RandomForest tree2 = new RandomForest(2, variables);
DecisionTree tree = new DecisionTree(variables, 2);
C45Learning teacher = new C45Learning(tree);
var model = teacher.Learn(train_docrule.ToJagged(), label);
//save model
teacher.Save(Path.Combine("", classmodelpath));
}
if (algorithm == "SVM")
{
classmodelpath = algorithm + ".model";
var learn = new SequentialMinimalOptimization()
{
UseComplexityHeuristic = true,
UseKernelEstimation = false
};
SupportVectorMachine teacher = learn.Learn(train_docrule.ToJagged(), label);
//save model
teacher.Save(Path.Combine("", classmodelpath));
}
if (algorithm == "Logistic")
{
classmodelpath = algorithm + ".model";
var learner = new IterativeReweightedLeastSquares <LogisticRegression>()
{
Tolerance = 1e-4, // Let's set some convergence parameters
Iterations = 1, // maximum number of iterations to perform
Regularization = 0
};
LogisticRegression teacher = learner.Learn(train_docrule.ToJagged(), label);
teacher.Save(Path.Combine("", classmodelpath));
}
if (algorithm == "GA")
{
weights_ga_matlab();
}
}
/*************************** Primary Methods *******************************/
public double learnDecisionTreeModel(DataSet trainSet)
{
// Convert TrainSet --> TrainDataTable
this.convertToTrainIntputTable(trainSet);
// C4.5 Decision Tree Algorithm
double learningError;
C45Learning c45 = new C45Learning(this.descisionTree);
learningError = c45.Run(this.trainInputArray, this.trainOutputVector);
return(learningError);
}
public override Task TrainAsync(ClassificationModel classificationModel)
{
int numFeatures = classificationModel.FeatureVectors.Count;
DecisionVariable[] decisionVariables = Enumerable.ToArray(classificationModel.Bands.Select(b => DecisionVariable.Continuous(b.ToString())));
double[][] input = new double[numFeatures][];
int[] responses = new int[numFeatures];
for (int featureIndex = 0; featureIndex < classificationModel.FeatureVectors.Count; ++featureIndex)
{
var featureVector = classificationModel.FeatureVectors[featureIndex];
input[featureIndex] = Array.ConvertAll(featureVector.FeatureVector.BandIntensities, s => (double)s / ushort.MaxValue);
responses[featureIndex] = featureVector.FeatureClass;
}
if (Boosting)
{
return(Task.Factory.StartNew(() =>
{
var classifier = new Boost <Weak <DecisionTree> >();
var teacher = new AdaBoostM1 <Weak <DecisionTree> >(classifier)
{
Creation = (weights) =>
{
var tree = new DecisionTree(decisionVariables, Enum.GetValues(typeof(LandcoverTypeViewModel)).Length);
var c45Learning = new C45Learning(tree);
c45Learning.Learn(input, responses, weights);
return new Weak <DecisionTree>(tree, (s, x) => s.Decide(x));
},
Iterations = Iterations,
Tolerance = 1e-2
};
teacher.Run(input, responses);
_tree = Either.Right <DecisionTree, Boost <Weak <DecisionTree> > >(classifier);
}));
}
else
{
return(Task.Factory.StartNew(() =>
{
var tree = new DecisionTree(decisionVariables, Enum.GetValues(typeof(LandcoverTypeViewModel)).Length);
C45Learning id3Learning = new C45Learning(tree);
id3Learning.Learn(input, responses);
_tree = Either.Left <DecisionTree, Boost <Weak <DecisionTree> > >(tree);
}));
}
}
public static DecisionTree Learn(DataTable data, string[] inputColumns, string outputColumn)
{
var codebook = new Codification(data);
var symbols = codebook.Apply(data);
double[][] inputs = symbols.ToJagged(inputColumns);
int[] outputs = symbols.ToArray <int>(outputColumn);
var attributes = DecisionVariable.FromCodebook(codebook, inputColumns);
var c45 = new C45Learning(attributes);
return(c45.Learn(inputs, outputs));
}
private void btnSampleRunAnalysis_Click(object sender, EventArgs e)
{
if (!isTrainingDataLoaded)
{
MessageBox.Show("Please load your training data first");
return;
}
// Creates a matrix from the entire source data table
double[,] table = (dgvLearningSource.DataSource as DataTable).ToMatrix(out columnNames);
// Get only the input vector values (in the first two columns)
double[][] inputs = ConvertDataTableToMatrix(TrainingData.Tables["InterestedTrainingDataValues"]);
// Get only the output labels (last column)
int[] outputs = table.GetColumn(2).ToInt32();
// Creates a new instance of the SMO learning algorithm
DecisionVariable[] variables =
{
new DecisionVariable("x", DecisionVariableKind.Continuous),
new DecisionVariable("y", DecisionVariableKind.Continuous),
};
// Create the C4.5 learning algorithm
var c45 = new C45Learning(variables);
// Learn the decision tree using C4.5
tree = c45.Learn(inputs, outputs);
// Show the learned tree in the view
decisionTreeView1.TreeSource = tree;
// Get the ranges for each variable (X and Y)
DoubleRange[] ranges = table.GetRange(0);
// Generate a Cartesian coordinate system
double[][] map = Matrix.Cartesian(
Vector.Interval(ranges[0], 0.05),
Vector.Interval(ranges[1], 0.05));
// Classify each point in the Cartesian coordinate system
double[] result = map.Apply(tree.Compute).ToDouble();
double[,] surface = map.ToMatrix().InsertColumn(result);
MessageBox.Show("Training Complete");
}
public void AttributeReuseTest1()
{
string[][] text = Resources.iris_data.Split(
new[] { '\n' }, StringSplitOptions.RemoveEmptyEntries)
.Apply(x => x.Split(','));
double[][] inputs = new double[text.Length][];
for (int i = 0; i < inputs.Length; i++)
{
inputs[i] = text[i].First(4).Convert(s => Double.Parse(s, System.Globalization.CultureInfo.InvariantCulture));
}
string[] labels = text.GetColumn(4);
Codification codebook = new Codification("Label", labels);
int[] outputs = codebook.Translate("Label", labels);
DecisionVariable[] features =
{
new DecisionVariable("sepal length", DecisionVariableKind.Continuous),
new DecisionVariable("sepal width", DecisionVariableKind.Continuous),
new DecisionVariable("petal length", DecisionVariableKind.Continuous),
new DecisionVariable("petal width", DecisionVariableKind.Continuous),
};
DecisionTree tree = new DecisionTree(features, codebook.Columns[0].Symbols);
C45Learning teacher = new C45Learning(tree);
teacher.Join = 3;
double error = teacher.Run(inputs, outputs);
Assert.AreEqual(0.02, error, 1e-10);
DecisionSet rules = tree.ToRules();
double newError = ComputeError(rules, inputs, outputs);
Assert.AreEqual(0.02, newError, 1e-10);
string ruleText = rules.ToString(codebook,
System.Globalization.CultureInfo.InvariantCulture);
// TODO: implement this assertion properly, actually checking
// the text contents once the feature is completely finished.
Assert.AreEqual(600, ruleText.Length);
}
public void new_method_create_tree()
{
string[][] text = Resources.iris_data.Split(new[] { '\n' }, StringSplitOptions.RemoveEmptyEntries).Apply(x => x.Split(','));
double[][] inputs = text.GetColumns(0, 1, 2, 3).To <double[][]>();
string[] labels = text.GetColumn(4);
var codebook = new Codification("Output", labels);
int[] outputs = codebook.Translate("Output", labels);
// And we can use the C4.5 for learning:
var teacher = new C45Learning();
// And finally induce the tree:
var tree = teacher.Learn(inputs, outputs);
// To get the estimated class labels, we can use
int[] predicted = tree.Decide(inputs);
// And the classification error can be computed as
double error = new ZeroOneLoss(outputs) // 0.0266
{
Mean = true
}.Loss(tree.Decide(inputs));
// Moreover, we may decide to convert our tree to a set of rules:
DecisionSet rules = tree.ToRules();
// And using the codebook, we can inspect the tree reasoning:
string ruleText = rules.ToString(codebook, "Output",
System.Globalization.CultureInfo.InvariantCulture);
// The output is:
string expected = @"Iris-setosa =: (2 <= 2.45)
Iris-versicolor =: (2 > 2.45) && (3 <= 1.75) && (0 <= 7.05) && (1 <= 2.85)
Iris-versicolor =: (2 > 2.45) && (3 <= 1.75) && (0 <= 7.05) && (1 > 2.85)
Iris-versicolor =: (2 > 2.45) && (3 > 1.75) && (0 <= 5.95) && (1 > 3.05)
Iris-virginica =: (2 > 2.45) && (3 <= 1.75) && (0 > 7.05)
Iris-virginica =: (2 > 2.45) && (3 > 1.75) && (0 > 5.95)
Iris-virginica =: (2 > 2.45) && (3 > 1.75) && (0 <= 5.95) && (1 <= 3.05)
";
Assert.AreEqual(0.026666666666666668, error, 1e-10);
double newError = ComputeError(rules, inputs, outputs);
Assert.AreEqual(0.026666666666666668, newError, 1e-10);
Assert.AreEqual(expected, ruleText);
}
public static void CreateMitchellExample(out DecisionTree tree, out double[][] inputs, out int[] outputs)
{
DataTable data = new DataTable("Mitchell's Tennis Example");
data.Columns.Add("Day", typeof(string));
data.Columns.Add("Outlook", typeof(string));
data.Columns.Add("Temperature", typeof(double));
data.Columns.Add("Humidity", typeof(double));
data.Columns.Add("Wind", typeof(string));
data.Columns.Add("PlayTennis", typeof(string));
data.Rows.Add("D1", "Sunny", 85, 85, "Weak", "No");
data.Rows.Add("D2", "Sunny", 80, 90, "Strong", "No");
data.Rows.Add("D3", "Overcast", 83, 78, "Weak", "Yes");
data.Rows.Add("D4", "Rain", 70, 96, "Weak", "Yes");
data.Rows.Add("D5", "Rain", 68, 80, "Weak", "Yes");
data.Rows.Add("D6", "Rain", 65, 70, "Strong", "No");
data.Rows.Add("D7", "Overcast", 64, 65, "Strong", "Yes");
data.Rows.Add("D8", "Sunny", 72, 95, "Weak", "No");
data.Rows.Add("D9", "Sunny", 69, 70, "Weak", "Yes");
data.Rows.Add("D10", "Rain", 75, 80, "Weak", "Yes");
data.Rows.Add("D11", "Sunny", 75, 70, "Strong", "Yes");
data.Rows.Add("D12", "Overcast", 72, 90, "Strong", "Yes");
data.Rows.Add("D13", "Overcast", 81, 75, "Weak", "Yes");
data.Rows.Add("D14", "Rain", 71, 80, "Strong", "No");
// Create a new codification codebook to
// convert strings into integer symbols
Codification codebook = new Codification(data);
DecisionVariable[] attributes =
{
new DecisionVariable("Outlook", codebook["Outlook"].Symbols), // 3 possible values (Sunny, overcast, rain)
new DecisionVariable("Temperature", DecisionVariableKind.Continuous), // continuous values
new DecisionVariable("Humidity", DecisionVariableKind.Continuous), // continuous values
new DecisionVariable("Wind", codebook["Wind"].Symbols) // 2 possible values (Weak, strong)
};
int classCount = codebook["PlayTennis"].Symbols; // 2 possible values (yes, no)
tree = new DecisionTree(attributes, classCount);
C45Learning c45 = new C45Learning(tree);
// Extract symbols from data and train the classifier
DataTable symbols = codebook.Apply(data);
inputs = symbols.ToArray("Outlook", "Temperature", "Humidity", "Wind");
outputs = symbols.ToArray <int>("PlayTennis");
double error = c45.Run(inputs, outputs);
}
/// <summary>
/// Train the classifier with some data, using parameters.
/// </summary>
/// <param name="trainingData">Data used to train the classifier.</param>
/// <param name="maxJoin">How many times a variable can join
/// the decision process.</param>
/// <param name="maxHeight">Maximum height when learning the tree.</param>
/// <returns>Classifier prediction error.</returns>
public double TrainClassifierWithParameters(
ClassificationData trainingData,
int maxJoin = 0,
int maxHeight = 0)
{
double classifierError = 0;
List <DecisionVariable> decisionVariables = new List <DecisionVariable>();
if (DecisionVariableNames != null)
{
for (int n = 0; n < trainingData.InputAttributeNumber; ++n)
{
decisionVariables.Add(
new DecisionVariable(DecisionVariableNames[n], DecisionVariableKind.Continuous)
);
}
}
// Generate automatic names for the variables if no names are provided.
else
{
for (int n = 0; n < trainingData.InputAttributeNumber; ++n)
{
decisionVariables.Add(
new DecisionVariable("variable_" + (n + 1).ToString(),
DecisionVariableKind.Continuous));
}
}
// Create a new Decision Tree classifier.
ClassificationDecisionTree = new DecisionTree(decisionVariables, trainingData.OutputPossibleValues);
// Create a new instance of the C45 algorithm to be learned by the tree.
C45LearningTree = new C45Learning(ClassificationDecisionTree);
// Change some classifier's parameters if valid new
// values are provided.
if (maxJoin > 0)
{
C45LearningTree.Join = maxJoin;
}
if (maxHeight > 0)
{
C45LearningTree.MaxHeight = maxHeight;
}
// Use data to train the tree.
classifierError = C45LearningTree.Run(trainingData.InputData, trainingData.OutputData);
return(classifierError);
}
public void Learn()
{
var inputs = GetLearnInputs();
var outputs = GetOutputs();
var teacher = new C45Learning {
Join = 0
};
foreach (var controllerOutputProperty in GetControllerOutputProperties())
{
teacher.Attributes.Add(DecisionVariable.Continuous(controllerOutputProperty));
}
DecisionTree = teacher.Learn(inputs, outputs);
}
protected void btnshow_Click(object sender, EventArgs e)
{
quality.Visible = true;
DataTable _dataTable = new DataTable();
Panel1.Visible = true;
n = Convert.ToDouble(txtN.Text);
p = Convert.ToDouble(txtP.Text);
k = Convert.ToDouble(txtK.Text);
ph = Convert.ToDouble(txtPh.Text);
ec = Convert.ToDouble(txtec.Text);
_dataTable = f1.getrecord1("select * from dataset");
double[][] inputs = _dataTable.ToJagged <double>("n", "p", "k", "ph", "ec");
string[] labels = new string[_dataTable.Rows.Count];
for (int i = 0; i < _dataTable.Rows.Count; i++)
{
labels[i] = _dataTable.Rows[i]["fertility"].ToString();
}
var codebook = new Codification("fertility", labels);
// With the codebook, we can convert the labels:
int[] outputs = codebook.Translate("fertility", labels);
C45Learning teacher = new C45Learning();
var tree = teacher.Learn(inputs, outputs);
double[][] input_test =
{
new double[] { n, p, k, ph, ec },
};
int[] val = tree.Decide(input_test);
if (val[0] == 0)
{
quality.Text = "Low";
}
else if (val[0] == 1)
{
quality.Text = "Medium";
}
else
{
quality.Text = "High";
}
}
// Decision Tree
public DecisionTree DecisionThrust(double[][] inputs, int[] outputs)
{
C45Learning teacher = new C45Learning(new[] {
DecisionVariable.Continuous("X"),
DecisionVariable.Continuous("Y"),
DecisionVariable.Continuous("Z"),
DecisionVariable.Continuous("W")
});
teacher.ParallelOptions.MaxDegreeOfParallelism = 1;
// Use the learning algorithm to induce the tree
DecisionTree tree = teacher.Learn(inputs, outputs);
return(tree);
}
private static DecisionTree createTree(out double[][] inputs, out int[] outputs)
{
string nurseryData = Resources.nursery;
string[] inputColumns =
{
"parents", "has_nurs", "form", "children",
"housing", "finance", "social", "health"
};
string outputColumn = "output";
DataTable table = new DataTable("Nursery");
table.Columns.Add(inputColumns);
table.Columns.Add(outputColumn);
string[] lines = nurseryData.Split(
new[] { Environment.NewLine }, StringSplitOptions.None);
foreach (var line in lines)
{
table.Rows.Add(line.Split(','));
}
Codification codebook = new Codification(table);
DataTable symbols = codebook.Apply(table);
inputs = symbols.ToArray(inputColumns);
outputs = symbols.ToArray <int>(outputColumn);
var attributes = DecisionVariable.FromCodebook(codebook, inputColumns);
var tree = new DecisionTree(attributes, classes: 5);
C45Learning c45 = new C45Learning(tree);
c45.Run(inputs, outputs);
return(tree);
}
public void Train(List <TrainingValue> trainingData)
{
List <DecisionVariable> trainingVariables = new List <DecisionVariable>();
for (int i = 0; i < featureSize; i++)
{
trainingVariables.Add(DecisionVariable.Continuous(i.ToString()));
}
tree = new DecisionTree(inputs: trainingVariables, classes: 2);
double[][] featuresArray = new double[trainingData.Count][];
int[] labels = new int[trainingData.Count];
for (int i = 0; i < featuresArray.Length; i++)
{
featuresArray[i] = trainingData[i].Features;
labels[i] = Convert.ToInt32(trainingData[i].State);
}
switch (type)
{
case ClassifierType.DecisionTree:
C45Learning teacher = new C45Learning(tree);
teacher.Learn(featuresArray, labels);
break;
case ClassifierType.LDA:
LinearDiscriminantAnalysis lda = new LinearDiscriminantAnalysis();
pipeline = lda.Learn(featuresArray, labels);
break;
case ClassifierType.SVM:
LinearCoordinateDescent svmLearner = new LinearCoordinateDescent();
svm = svmLearner.Learn(featuresArray, labels);
break;
case ClassifierType.Bayes:
NaiveBayesLearning <NormalDistribution> learner = new NaiveBayesLearning <NormalDistribution>();
bayes = learner.Learn(featuresArray, labels);
break;
}
Trained = true;
}
