public static void Train(string trainingFolder)
{
Console.WriteLine("Training SVM model with Cross-Validation...");
(double[][] inputs, int[] output) = ReadData(trainingFolder);
int crossValidateCount = Math.Min(maxCrossValidateCount, inputs.Count());
Accord.Math.Random.Generator.Seed = 0;
Console.WriteLine("Grid-Search...");
var gscv = GridSearch <double[], int> .CrossValidate(
ranges : new
{
Sigma = GridSearch.Range(fromInclusive: 0.00000001, toExclusive: 3),
},
learner : (p, ss) => new MulticlassSupportVectorLearning <Gaussian>
{
Kernel = new Gaussian(p.Sigma)
},
fit : (teacher, x, y, w) => teacher.Learn(x, y, w),
loss : (actual, expected, r) => new ZeroOneLoss(expected).Loss(actual),
folds : 10);
//gscv.ParallelOptions.MaxDegreeOfParallelism = 1;
var result = gscv.Learn(inputs.Take(crossValidateCount).ToArray(), output.Take(crossValidateCount).ToArray());
var crossValidation = result.BestModel;
double bestError = result.BestModelError;
double trainError = result.BestModel.Training.Mean;
double trainErrorVar = result.BestModel.Training.Variance;
double valError = result.BestModel.Validation.Mean;
double valErrorVar = result.BestModel.Validation.Variance;
double bestSigma = result.BestParameters.Sigma;
Console.WriteLine("Grid-Search Done.");
Console.WriteLine("Using Sigma=" + bestSigma);
// train model with best parameter
var bestTeacher = new MulticlassSupportVectorLearning <Gaussian>
{
Kernel = new Gaussian(bestSigma)
};
MulticlassSupportVectorMachine <Gaussian> svm = bestTeacher.Learn(
inputs.Take(traingRowsCount).ToArray(),
output.Take(traingRowsCount).ToArray());
// save model
svm.Save(Path.Combine(trainingFolder, "model"), SerializerCompression.GZip);
}
private static Tuple <MulticlassSupportVectorMachine <Gaussian>, double, double, double> Training(List <double[]> inputsList, List <int> outputsList)
{
var gridsearch = GridSearch <double[], int> .CrossValidate(
// Here we can specify the range of the parameters to be included in the search
ranges : new
{
Complexity = GridSearch.Values(Math.Pow(2, -10), Math.Pow(2, -8),
Math.Pow(2, -6), Math.Pow(2, -4), Math.Pow(2, -2), Math.Pow(2, 0), Math.Pow(2, 2),
Math.Pow(2, 4), Math.Pow(2, 6), Math.Pow(2, 8), Math.Pow(2, 10)),
Gamma = GridSearch.Values(Math.Pow(2, -10), Math.Pow(2, -8),
Math.Pow(2, -6), Math.Pow(2, -4), Math.Pow(2, -2), Math.Pow(2, 0), Math.Pow(2, 2),
Math.Pow(2, 4), Math.Pow(2, 6), Math.Pow(2, 8), Math.Pow(2, 10))
},
// Indicate how learning algorithms for the models should be created
learner : (p, ss) => new MulticlassSupportVectorLearning <Gaussian>()
{
// Configure the learning algorithm to use SMO to train the
// underlying SVMs in each of the binary class subproblems.
Learner = (param) => new SequentialMinimalOptimization <Gaussian>()
{
// Estimate a suitable guess for the Gaussian kernel's parameters.
// This estimate can serve as a starting point for a grid search.
//UseComplexityHeuristic = true,
//UseKernelEstimation = true
Complexity = p.Complexity,
Kernel = new Gaussian(p.Gamma)
}
},
// Define how the model should be learned, if needed
fit : (teacher, x, y, w) => teacher.Learn(x, y, w),
// Define how the performance of the models should be measured
loss : (actual, expected, m) => new HammingLoss(expected).Loss(actual),
folds : 10
);
gridsearch.ParallelOptions.MaxDegreeOfParallelism = 1;
Console.WriteLine("y nos ponemos a aprender");
// Search for the best model parameters
var result = gridsearch.Learn(inputsList.ToArray(), outputsList.ToArray());
return(new Tuple <MulticlassSupportVectorMachine <Gaussian>, double, double, double>(CreateModel(inputsList, outputsList, result.BestParameters.Complexity, result.BestParameters.Gamma), result.BestModelError, result.BestParameters.Gamma, result.BestParameters.Complexity));
}
public void cross_validation_decision_tree()
{
#region doc_learn_tree_cv
// Ensure results are reproducible
Accord.Math.Random.Generator.Seed = 0;
// This is a sample code showing how to use Grid-Search in combination with
// Cross-Validation to assess the performance of Decision Trees with C4.5.
var parkinsons = new Parkinsons();
double[][] input = parkinsons.Features;
int[] output = parkinsons.ClassLabels;
// Create a new Grid-Search with Cross-Validation algorithm. Even though the
// generic, strongly-typed approach used accross the framework is most of the
// time easier to handle, combining those both methods in a single call can be
// difficult. For this reason. the framework offers a specialized method for
// combining those two algorirthms:
var gscv = GridSearch.CrossValidate(
// Here we can specify the range of the parameters to be included in the search
ranges: new
{
Join = GridSearch.Range(fromInclusive: 1, toExclusive: 20),
MaxHeight = GridSearch.Range(fromInclusive: 1, toExclusive: 20),
},
// Indicate how learning algorithms for the models should be created
learner: (p, ss) => new C45Learning
{
// Here, we can use the parameters we have specified above:
Join = p.Join,
MaxHeight = p.MaxHeight,
},
// Define how the model should be learned, if needed
fit: (teacher, x, y, w) => teacher.Learn(x, y, w),
// Define how the performance of the models should be measured
loss: (actual, expected, r) => new ZeroOneLoss(expected).Loss(actual),
folds: 3, // use k = 3 in k-fold cross validation
x: input, y: output // so the compiler can infer generic types
);
// If needed, control the parallelization degree
gscv.ParallelOptions.MaxDegreeOfParallelism = 1;
// Search for the best decision tree
var result = gscv.Learn(input, output);
// Get the best cross-validation result:
var crossValidation = result.BestModel;
// Get an estimate of its error:
double bestAverageError = result.BestModelError;
double trainError = result.BestModel.Training.Mean;
double trainErrorVar = result.BestModel.Training.Variance;
double valError = result.BestModel.Validation.Mean;
double valErrorVar = result.BestModel.Validation.Variance;
// Get the best values for the parameters:
int bestJoin = result.BestParameters.Join;
int bestHeight = result.BestParameters.MaxHeight;
// Use the best parameter values to create the final
// model using all the training and validation data:
var bestTeacher = new C45Learning
{
Join = bestJoin,
MaxHeight = bestHeight,
};
// Use the best parameters to create the final tree model:
DecisionTree finalTree = bestTeacher.Learn(input, output);
#endregion
int height = finalTree.GetHeight();
Assert.AreEqual(5, height);
Assert.AreEqual(22, result.BestModel.NumberOfInputs);
Assert.AreEqual(2, result.BestModel.NumberOfOutputs);
Assert.AreEqual(195, result.BestModel.NumberOfSamples);
Assert.AreEqual(65, result.BestModel.AverageNumberOfSamples);
Assert.AreEqual(bestAverageError, valError);
Assert.AreEqual(5, bestJoin, 1e-10);
Assert.AreEqual(0.1076923076923077, bestAverageError, 1e-8);
Assert.AreEqual(5, bestHeight, 1e-8);
}
public void cross_validation_test()
{
#region doc_learn_cv
// Ensure results are reproducible
Accord.Math.Random.Generator.Seed = 0;
// This is a sample code showing how to use Grid-Search in combination with
// Cross-Validation to assess the performance of Support Vector Machines.
// Consider the example binary data. We will be trying to learn a XOR
// problem and see how well does SVMs perform on this data.
double[][] inputs =
{
new double[] { -1, -1 }, new double[] { 1, -1 },
new double[] { -1, 1 }, new double[] { 1, 1 },
new double[] { -1, -1 }, new double[] { 1, -1 },
new double[] { -1, 1 }, new double[] { 1, 1 },
new double[] { -1, -1 }, new double[] { 1, -1 },
new double[] { -1, 1 }, new double[] { 1, 1 },
new double[] { -1, -1 }, new double[] { 1, -1 },
new double[] { -1, 1 }, new double[] { 1, 1 },
};
int[] xor = // result of xor for the sample input data
{
-1, 1,
1, -1,
-1, 1,
1, -1,
-1, 1,
1, -1,
-1, 1,
1, -1,
};
// Create a new Grid-Search with Cross-Validation algorithm. Even though the
// generic, strongly-typed approach used accross the framework is most of the
// time easier to handle, combining those both methods in a single call can be
// difficult. For this reason. the framework offers a specialized method for
// combining those two algorirthms:
var gscv = GridSearch <double[], int> .CrossValidate(
// Here we can specify the range of the parameters to be included in the search
ranges : new
{
Complexity = GridSearch.Values(0.00000001, 5.20, 0.30, 0.50),
Degree = GridSearch.Values(1, 10, 2, 3, 4, 5),
Constant = GridSearch.Values(0, 1, 2),
},
// Indicate how learning algorithms for the models should be created
learner : (p, ss) => new SequentialMinimalOptimization <Polynomial>
{
// Here, we can use the parameters we have specified above:
Complexity = p.Complexity,
Kernel = new Polynomial(p.Degree, p.Constant)
},
// Define how the model should be learned, if needed
fit : (teacher, x, y, w) => teacher.Learn(x, y, w),
// Define how the performance of the models should be measured
loss : (actual, expected, r) => new ZeroOneLoss(expected).Loss(actual),
folds : 3 // use k = 3 in k-fold cross validation
);
// If needed, control the parallelization degree
gscv.ParallelOptions.MaxDegreeOfParallelism = 1;
// Search for the best vector machine
var result = gscv.Learn(inputs, xor);
// Get the best cross-validation result:
var crossValidation = result.BestModel;
// Estimate its error:
double bestError = result.BestModelError;
double trainError = result.BestModel.Training.Mean;
double trainErrorVar = result.BestModel.Training.Variance;
double valError = result.BestModel.Validation.Mean;
double valErrorVar = result.BestModel.Validation.Variance;
// Get the best values for the parameters:
double bestC = result.BestParameters.Complexity;
double bestDegree = result.BestParameters.Degree;
double bestConstant = result.BestParameters.Constant;
#endregion
Assert.AreEqual(2, result.BestModel.NumberOfInputs);
Assert.AreEqual(1, result.BestModel.NumberOfOutputs);
Assert.AreEqual(16, result.BestModel.NumberOfSamples);
Assert.AreEqual(5.333333333333333, result.BestModel.AverageNumberOfSamples);
Assert.AreEqual(1e-8, bestC, 1e-10);
Assert.AreEqual(0, bestError, 1e-8);
Assert.AreEqual(10, bestDegree, 1e-8);
Assert.AreEqual(0, bestConstant, 1e-8);
}
private Tuple <MulticlassSupportVectorMachine <Gaussian>, double, double, double> TrainingPaper(List <double[]> inputsList, List <int> outputsList)
{
var gridsearch = GridSearch <double[], int> .CrossValidate(
// Here we can specify the range of the parameters to be included in the search
ranges : new
{
Complexity = GridSearch.Values(Math.Pow(2, -12), Math.Pow(2, -11), Math.Pow(2, -10), Math.Pow(2, -8),
Math.Pow(2, -6), Math.Pow(2, -4), Math.Pow(2, -2), Math.Pow(2, 0), Math.Pow(2, 2),
Math.Pow(2, 4), Math.Pow(2, 6), Math.Pow(2, 8), Math.Pow(2, 10), Math.Pow(2, 11), Math.Pow(2, 12)),
Gamma = GridSearch.Values(Math.Pow(2, -12), Math.Pow(2, -11), Math.Pow(2, -10), Math.Pow(2, -8),
Math.Pow(2, -6), Math.Pow(2, -4), Math.Pow(2, -2), Math.Pow(2, 0), Math.Pow(2, 2),
Math.Pow(2, 4), Math.Pow(2, 6), Math.Pow(2, 8), Math.Pow(2, 10), Math.Pow(2, 11), Math.Pow(2, 12))
},
// Indicate how learning algorithms for the models should be created
learner : (p, ss) => new MulticlassSupportVectorLearning <Gaussian>()
{
// Configure the learning algorithm to use SMO to train the
// underlying SVMs in each of the binary class subproblems.
Learner = (param) => new SequentialMinimalOptimization <Gaussian>()
{
// Estimate a suitable guess for the Gaussian kernel's parameters.
// This estimate can serve as a starting point for a grid search.
//UseComplexityHeuristic = true,
//UseKernelEstimation = true
Complexity = p.Complexity,
Kernel = Gaussian.FromGamma(p.Gamma)
}
},
// Define how the model should be learned, if needed
fit : (teacher, x, y, w) => teacher.Learn(x, y, w),
// Define how the performance of the models should be measured
/*loss: (actual, expected, m) =>
* {
* double totalError = 0;
* foreach (var input in _originalInputsList)
* {
* if (!m.Decide(input.Item1).Equals(input.Item2))
* {
* totalError++;
* }
* }
* return totalError / _originalInputsList.Count;
* },*/
loss : (actual, expected, m) => new HammingLoss(expected).Loss(actual),
folds : 10
);
gridsearch.ParallelOptions.MaxDegreeOfParallelism = _paralelism;
Console.WriteLine("y nos ponemos a aprender");
// Search for the best model parameters
var result = gridsearch.Learn(inputsList.ToArray(), outputsList.ToArray());
Console.WriteLine("Error modelo: " + result.BestModelError);
var model = CreateModel(inputsList, outputsList, result.BestParameters.Complexity, result.BestParameters.Gamma);
double error = 0;
Console.WriteLine("Largo: " + _originalInputsList.Count);
foreach (var input in _originalInputsList)
{
if (!model.Decide(input.Item1).Equals(input.Item2))
{
error++;
}
}
error = error / (_originalInputsList.Count);
Console.WriteLine("Error real: " + error);
return(new Tuple <MulticlassSupportVectorMachine <Gaussian>, double, double, double>(model, error, result.BestParameters.Gamma.Value, result.BestParameters.Complexity.Value));
}