private static void TestPredictSparseSVM()
{
Console.WriteLine("Downloading dataset");
var news20 = new Accord.DataSets.News20(@"C:\Temp\");
Sparse <double>[] inputs = news20.Training.Item1;
int[] outputs = news20.Training.Item2.ToMulticlass();
var learn = new MultilabelSupportVectorLearning <Linear, Sparse <double> >()
{
// using LIBLINEAR's L2-loss SVC dual for each SVM
Learner = (p) => new LinearDualCoordinateDescent <Linear, Sparse <double> >()
{
Loss = Loss.L2,
Complexity = 1.0,
Tolerance = 1e-4
}
};
Console.WriteLine("Learning");
Stopwatch sw = Stopwatch.StartNew();
var svm = learn.Learn(inputs.Get(0, 100), outputs.Get(0, 100));
Console.WriteLine(sw.Elapsed);
Console.WriteLine("Predicting");
sw = Stopwatch.StartNew();
int[] predicted = svm.ToMulticlass().Decide(inputs);
Console.WriteLine(sw.Elapsed);
}
public void no_samples_for_class()
{
double[][] inputs =
{
new double[] { 1, 1 }, // 0
new double[] { 1, 1 }, // 0
new double[] { 1, 1 }, // 2
};
int[] outputs =
{
0, 0, 2
};
var teacher = new MultilabelSupportVectorLearning <Gaussian>()
{
Learner = (param) => new SequentialMinimalOptimization <Gaussian>()
{
UseKernelEstimation = true
}
};
Assert.Throws <ArgumentException>(() => teacher.Learn(inputs, outputs),
"There are no samples for class label {0}. Please make sure that class " +
"labels are contiguous and there is at least one training sample for each label.", 1);
}
private static void TestSMO()
{
Console.WriteLine("Downloading dataset");
var news20 = new Accord.DataSets.News20(@"C:\Temp\");
Sparse <double>[] inputs = news20.Training.Item1.Get(0, 2000);
int[] outputs = news20.Training.Item2.ToMulticlass().Get(0, 2000);
var learn = new MultilabelSupportVectorLearning <Linear, Sparse <double> >()
{
// using LIBLINEAR's SVC dual for each SVM
Learner = (p) => new SequentialMinimalOptimization <Linear, Sparse <double> >()
{
Strategy = SelectionStrategy.SecondOrder,
Complexity = 1.0,
Tolerance = 1e-4,
CacheSize = 1000
},
};
Console.WriteLine("Learning");
Stopwatch sw = Stopwatch.StartNew();
var svm = learn.Learn(inputs, outputs);
Console.WriteLine(sw.Elapsed);
Console.WriteLine("Predicting");
sw = Stopwatch.StartNew();
int[] predicted = svm.ToMulticlass().Decide(inputs);
Console.WriteLine(sw.Elapsed);
var test = new ConfusionMatrix(predicted, outputs);
Console.WriteLine("Test acc: " + test.Accuracy);
}
public void multilabel_linear_new_usage()
{
#region doc_learn_ldcd
// Let's say we have the following data to be classified
// into three possible classes. Those are the samples:
//
double[][] inputs =
{
// input output
new double[] { 0, 1, 1, 0 }, // 0
new double[] { 0, 1, 0, 0 }, // 0
new double[] { 0, 0, 1, 0 }, // 0
new double[] { 0, 1, 1, 0 }, // 0
new double[] { 0, 1, 0, 0 }, // 0
new double[] { 1, 0, 0, 0 }, // 1
new double[] { 1, 0, 0, 0 }, // 1
new double[] { 1, 0, 0, 1 }, // 1
new double[] { 0, 0, 0, 1 }, // 1
new double[] { 0, 0, 0, 1 }, // 1
new double[] { 1, 1, 1, 1 }, // 2
new double[] { 1, 0, 1, 1 }, // 2
new double[] { 1, 1, 0, 1 }, // 2
new double[] { 0, 1, 1, 1 }, // 2
new double[] { 1, 1, 1, 1 }, // 2
};
int[] outputs = // those are the class labels
{
0, 0, 0, 0, 0,
1, 1, 1, 1, 1,
2, 2, 2, 2, 2,
};
// Create a one-vs-one multi-class SVM learning algorithm
var teacher = new MultilabelSupportVectorLearning <Linear>()
{
// using LIBLINEAR's L2-loss SVC dual for each SVM
Learner = (p) => new LinearDualCoordinateDescent()
{
Loss = Loss.L2
}
};
// The following line is only needed to ensure reproducible results. Please remove it to enable full parallelization
teacher.ParallelOptions.MaxDegreeOfParallelism = 1; // (Remove, comment, or change this line to enable full parallelism)
// Learn a machine
var machine = teacher.Learn(inputs, outputs);
// Obtain class predictions for each sample
bool[][] predicted = machine.Decide(inputs);
// Compute classification error using mean accuracy (mAcc)
double error = new HammingLoss(outputs).Loss(predicted);
#endregion
Assert.AreEqual(0, error);
Assert.IsTrue(predicted.ArgMax(dimension: 1).IsEqual(outputs));
}
public void learn_linear_multilabel()
{
#region doc_learn_multilabel
// In this example, we will learn a multi-class SVM using the one-vs-rest (OvR)
// approach. The OvR approacbh can decompose decision problems involving multiple
// classes into a series of binary ones, which can then be solved using SVMs.
// Ensure we have reproducible results
Accord.Math.Random.Generator.Seed = 0;
// We will try to learn a classifier
// for the Fisher Iris Flower dataset
var iris = new Iris();
double[][] inputs = iris.Instances; // get the flower characteristics
int[] outputs = iris.ClassLabels; // get the expected flower classes
// We will use mini-batches of size 32 to learn a SVM using SGD
var batches = MiniBatches.Create(batchSize: 32, maxIterations: 1000,
shuffle: ShuffleMethod.EveryEpoch, input: inputs, output: outputs);
// Now, we can create a multi-label teaching algorithm for the SVMs
var teacher = new MultilabelSupportVectorLearning <Linear, double[]>
{
// We will use SGD to learn each of the binary problems in the multi-class problem
Learner = (p) => new StochasticGradientDescent <Linear, double[], LogisticLoss>()
{
LearningRate = 1e-3,
MaxIterations = 1 // so the gradient is only updated once after each mini-batch
}
};
// The following line is only needed to ensure reproducible results. Please remove it to enable full parallelization
teacher.ParallelOptions.MaxDegreeOfParallelism = 1; // (Remove, comment, or change this line to enable full parallelism)
// Now, we can start training the model on mini-batches:
foreach (var batch in batches)
{
teacher.Learn(batch.Inputs, batch.Outputs);
}
// Get the final model:
var svm = teacher.Model;
// Now, we should be able to use the model to predict
// the classes of all flowers in Fisher's Iris dataset:
int[] prediction = svm.ToMulticlass().Decide(inputs);
// And from those predictions, we can compute the model accuracy:
var cm = new GeneralConfusionMatrix(expected: outputs, predicted: prediction);
double accuracy = cm.Accuracy; // should be approximately 0.913
#endregion
Assert.AreEqual(0.91333333333333333, cm.Accuracy);
Assert.AreEqual(150, batches.NumberOfSamples);
Assert.AreEqual(32, batches.MiniBatchSize);
Assert.AreEqual(213, batches.CurrentEpoch);
Assert.AreEqual(1001, batches.CurrentIteration);
Assert.AreEqual(82, batches.CurrentSample);
}
public MultilabelSupportVectorMachine <Linear> Teach(double[][] inputs, int[] outputs)
{
var teacher = new MultilabelSupportVectorLearning <Linear>()
{
Learner = (p) => new LinearDualCoordinateDescent()
{
Loss = Loss.L2
}
};
return(teacher.Learn(inputs, outputs));
}
public void multilabel_linear_smo_new_usage()
{
// Let's say we have the following data to be classified
// into three possible classes. Those are the samples:
//
double[][] inputs =
{
// input output
new double[] { 0, 1, 1, 0 }, // 0
new double[] { 0, 1, 0, 0 }, // 0
new double[] { 0, 0, 1, 0 }, // 0
new double[] { 0, 1, 1, 0 }, // 0
new double[] { 0, 1, 0, 0 }, // 0
new double[] { 1, 0, 0, 0 }, // 1
new double[] { 1, 0, 0, 0 }, // 1
new double[] { 1, 0, 0, 1 }, // 1
new double[] { 0, 0, 0, 1 }, // 1
new double[] { 0, 0, 0, 1 }, // 1
new double[] { 1, 1, 1, 1 }, // 2
new double[] { 1, 0, 1, 1 }, // 2
new double[] { 1, 1, 0, 1 }, // 2
new double[] { 0, 1, 1, 1 }, // 2
new double[] { 1, 1, 1, 1 }, // 2
};
int[] outputs = // those are the class labels
{
0, 0, 0, 0, 0,
1, 1, 1, 1, 1,
2, 2, 2, 2, 2,
};
// Create a one-vs-one learning algorithm using LIBLINEAR's L2-loss SVC dual
var teacher = new MultilabelSupportVectorLearning <Linear>();
teacher.Learner = (p) => new SequentialMinimalOptimization <Linear>()
{
UseComplexityHeuristic = true
};
#if DEBUG
teacher.ParallelOptions.MaxDegreeOfParallelism = 1;
#endif
// Learn a machine
var machine = teacher.Learn(inputs, outputs);
int[] actual = machine.Decide(inputs).ArgMax(dimension: 1);
outputs[13] = 0;
Assert.IsTrue(actual.IsEqual(outputs));
}
static void Main(string[] args)
{
double[][] inputs =
{
new double[] { 0 },
new double[] { 3 },
new double[] { 1 },
new double[] { 2 },
};
int[][] outputs =
{
new[] { -1, 1, -1 },
new[] { -1, -1, 1 },
new[] { 1, 1, -1 },
new[] { -1, -1, -1 }
};
var teacher = new MultilabelSupportVectorLearning <Linear>()
{
Learner = (p) => new SequentialMinimalOptimization <Linear>()
{
Complexity = 10000.0
}
};
var svm = teacher.Learn(inputs, outputs);
double[][] results = svm.Probabilities(inputs);
//double[][] results = new double[4][];
//for (int i = 0; i < results.Length; i++)
// results[i] = new double[4];
//double[][] results2 = svm.Decide(inputs, results);
int[] maxAnswers = svm.ToMulticlass().Decide(inputs);
Console.ReadKey();
}
private static void multilabelSvm(double[][] inputs, int[] outputs)
{
// Create the multi-label learning algorithm as one-vs-rest
var teacher = new MultilabelSupportVectorLearning <Linear>()
{
Learner = (p) => new SequentialMinimalOptimization <Linear>()
{
Complexity = 10000.0 // Create a hard SVM
}
};
// Learn a multi-label SVM using the teacher
var svm = teacher.Learn(inputs, outputs);
// Get the predictions for the inputs
bool[][] predicted = svm.Decide(inputs);
// Use the machine as if it were a multi-class machine
// instead of a multi-label, identifying the strongest
// class among the multi-label predictions:
int[] classLabels = svm.ToMulticlass().Decide(inputs);
}
private static void TestSparseSVMComplete()
{
#region doc_learn_news20
Console.WriteLine("Downloading dataset:");
var news20 = new Accord.DataSets.News20(@"C:\Temp\");
var trainInputs = news20.Training.Item1;
var trainOutputs = news20.Training.Item2.ToMulticlass();
var testInputs = news20.Testing.Item1;
var testOutputs = news20.Testing.Item2.ToMulticlass();
Console.WriteLine(" - Training samples: {0}", trainInputs.Rows());
Console.WriteLine(" - Testing samples: {0}", testInputs.Rows());
Console.WriteLine(" - Dimensions: {0}", trainInputs.Columns());
Console.WriteLine(" - Classes: {0}", trainOutputs.DistinctCount());
Console.WriteLine();
// Create and use the learning algorithm to train a sparse linear SVM
var learn = new MultilabelSupportVectorLearning <Linear, Sparse <double> >()
{
// using LIBLINEAR's L2-loss SVC dual for each SVM
Learner = (p) => new LinearDualCoordinateDescent <Linear, Sparse <double> >()
{
Loss = Loss.L2,
Tolerance = 1e-4
},
};
// Display progress in the console
learn.SubproblemFinished += (sender, e) =>
{
Console.WriteLine(" - {0} / {1} ({2:00.0%})", e.Progress, e.Maximum, e.Progress / (double)e.Maximum);
};
// Start the learning algorithm
Console.WriteLine("Learning");
Stopwatch sw = Stopwatch.StartNew();
var svm = learn.Learn(trainInputs, trainOutputs);
Console.WriteLine("Done in {0}", sw.Elapsed);
Console.WriteLine();
// Compute accuracy in the training set
Console.WriteLine("Predicting training set");
sw = Stopwatch.StartNew();
int[] trainPredicted = svm.ToMulticlass().Decide(trainInputs);
Console.WriteLine("Done in {0}", sw.Elapsed);
double trainError = new ZeroOneLoss(trainOutputs).Loss(trainPredicted);
Console.WriteLine("Training error: {0}", trainError);
Console.WriteLine();
// Compute accuracy in the testing set
Console.WriteLine("Predicting testing set");
sw = Stopwatch.StartNew();
int[] testPredicted = svm.ToMulticlass().Decide(testInputs);
Console.WriteLine("Done in {0}", sw.Elapsed);
double testError = new ZeroOneLoss(testOutputs).Loss(testPredicted);
Console.WriteLine("Testing error: {0}", testError);
#endregion
}
public void multilabel_calibration_generic_kernel()
{
// Let's say we have the following data to be classified
// into three possible classes. Those are the samples:
//
double[][] inputs =
{
// input output
new double[] { 0, 1, 1, 0 }, // 0
new double[] { 0, 1, 0, 0 }, // 0
new double[] { 0, 0, 1, 0 }, // 0
new double[] { 0, 1, 1, 0 }, // 0
new double[] { 0, 1, 0, 0 }, // 0
new double[] { 1, 0, 0, 1 }, // 1
new double[] { 0, 0, 0, 1 }, // 1
new double[] { 0, 0, 0, 1 }, // 1
new double[] { 1, 0, 1, 1 }, // 2
new double[] { 1, 1, 0, 1 }, // 2
new double[] { 0, 1, 1, 1 }, // 2
new double[] { 1, 1, 1, 1 }, // 2
};
int[] outputs = // those are the class labels
{
0, 0, 0, 0, 0,
1, 1, 1,
2, 2, 2, 2,
};
// Create the multi-class learning algorithm for the machine
var teacher = new MultilabelSupportVectorLearning <IKernel>()
{
// Configure the learning algorithm to use SMO to train the
// underlying SVMs in each of the binary class subproblems.
Learner = (param) => new SequentialMinimalOptimization <IKernel>()
{
UseKernelEstimation = false,
Kernel = Gaussian.FromGamma(0.5)
}
};
// Learn a machine
var machine = teacher.Learn(inputs, outputs);
// Create the multi-class learning algorithm for the machine
var calibration = new MultilabelSupportVectorLearning <IKernel>(machine)
{
// Configure the learning algorithm to use SMO to train the
// underlying SVMs in each of the binary class subproblems.
Learner = (p) => new ProbabilisticOutputCalibration <IKernel>(p.Model)
};
// Configure parallel execution options
calibration.ParallelOptions.MaxDegreeOfParallelism = 1;
// Learn a machine
calibration.Learn(inputs, outputs);
// Obtain class predictions for each sample
bool[][] predicted = machine.Decide(inputs);
// Get class scores for each sample
double[][] scores = machine.Scores(inputs);
// Get log-likelihoods (should be same as scores)
double[][] logl = machine.LogLikelihoods(inputs);
// Get probability for each sample
double[][] prob = machine.Probabilities(inputs);
// Compute classification error using mean accuracy (mAcc)
double error = new HammingLoss(outputs).Loss(predicted);
double loss = new CategoryCrossEntropyLoss(outputs).Loss(prob);
string a = scores.ToCSharp();
string b = logl.ToCSharp();
string c = prob.ToCSharp();
double[][] expectedScores =
{
new double[] { 1.85316017783605, -2.59688389729331, -2.32170102153988 },
new double[] { 1.84933597524124, -1.99399145231446, -2.2920299547693 },
new double[] { 1.44477953581274, -1.98592298465108, -2.27356092239125 },
new double[] { 1.85316017783605, -2.59688389729331, -2.32170102153988 },
new double[] { 1.84933597524124, -1.99399145231446, -2.2920299547693 },
new double[] { -2.40815576360914, 0.328362962196791, -0.932721757919691 },
new double[] { -2.13111157264226, 1.809192096031, -2.2920299547693 },
new double[] { -2.13111157264226, 1.809192096031, -2.2920299547693 },
new double[] { -2.14888646926108, -1.99399145231447, 1.33101148524982 },
new double[] { -2.12915064678299, -1.98592298465108, 1.3242171079396 },
new double[] { -1.47197826667149, -1.96368715704762, 0.843414180834243 },
new double[] { -2.14221021749314, -2.83117892529093, 2.61354519154994 }
};
double[][] expectedLogL =
{
new double[] { -0.145606614365135, -2.66874434442222, -2.41528841111469 },
new double[] { -0.146125659911391, -2.12163759796483, -2.3883043096263 },
new double[] { -0.211716960454159, -2.11453945718522, -2.37154474995633 },
new double[] { -0.145606614365135, -2.66874434442222, -2.41528841111469 },
new double[] { -0.146125659911391, -2.12163759796483, -2.3883043096263 },
new double[] { -2.4943161092787, -0.542383360363463, -1.26452689970624 },
new double[] { -2.24328358118314, -0.151678833375872, -2.3883043096263 },
new double[] { -2.24328358118314, -0.151678833375872, -2.3883043096263 },
new double[] { -2.25918730624753, -2.12163759796483, -0.234447327588685 },
new double[] { -2.24153091066541, -2.11453945718522, -0.2358711195715 },
new double[] { -1.67856232802554, -2.0950136294762, -0.357841632335707 },
new double[] { -2.25321037906455, -2.88845047104229, -0.0707140798850236 }
};
double[][] expectedProbs =
{
new double[] { 0.844913862516144, 0.0677684640174953, 0.0873176734663607 },
new double[] { 0.803266328757473, 0.111405242674824, 0.0853284285677024 },
new double[] { 0.790831391595502, 0.117950175028754, 0.0912184333757438 },
new double[] { 0.844913862516144, 0.0677684640174953, 0.0873176734663607 },
new double[] { 0.803266328757473, 0.111405242674824, 0.0853284285677024 },
new double[] { 0.0872387667998771, 0.614360294206236, 0.298400938993887 },
new double[] { 0.100372339295793, 0.812805149315815, 0.0868225113883914 },
new double[] { 0.100372339295793, 0.812805149315815, 0.0868225113883914 },
new double[] { 0.102863726210119, 0.11803188195247, 0.779104391837411 },
new double[] { 0.104532503226998, 0.118686968710368, 0.776780528062634 },
new double[] { 0.184996665350572, 0.121983586443407, 0.693019748206021 },
new double[] { 0.0961702585148881, 0.0509517983210315, 0.85287794316408 }
};
int[] actual = predicted.ArgMax(dimension: 1);
Assert.IsTrue(actual.IsEqual(outputs));
// Must be exactly the same as test above
Assert.AreEqual(0, error);
Assert.AreEqual(0.5, ((Gaussian)machine[0].Kernel).Gamma);
Assert.AreEqual(0.5, ((Gaussian)machine[1].Kernel).Gamma);
Assert.AreEqual(0.5, ((Gaussian)machine[2].Kernel).Gamma);
Assert.AreEqual(2.9395943260892361, loss);
Assert.IsTrue(expectedScores.IsEqual(scores, 1e-10));
Assert.IsTrue(expectedLogL.IsEqual(logl, 1e-10));
Assert.IsTrue(expectedProbs.IsEqual(prob, 1e-10));
double[] probabilities = CorrectProbabilities(machine, inputs[0]);
double[] actualProb = machine.Probabilities(inputs[0]);
Assert.IsTrue(probabilities.IsEqual(actualProb, 1e-8));
}
public void multilabel_calibration()
{
#region doc_learn_calibration
// Let's say we have the following data to be classified
// into three possible classes. Those are the samples:
//
double[][] inputs =
{
// input output
new double[] { 0, 1, 1, 0 }, // 0
new double[] { 0, 1, 0, 0 }, // 0
new double[] { 0, 0, 1, 0 }, // 0
new double[] { 0, 1, 1, 0 }, // 0
new double[] { 0, 1, 0, 0 }, // 0
new double[] { 1, 0, 0, 1 }, // 1
new double[] { 0, 0, 0, 1 }, // 1
new double[] { 0, 0, 0, 1 }, // 1
new double[] { 1, 0, 1, 1 }, // 2
new double[] { 1, 1, 0, 1 }, // 2
new double[] { 0, 1, 1, 1 }, // 2
new double[] { 1, 1, 1, 1 }, // 2
};
int[] outputs = // those are the class labels
{
0, 0, 0, 0, 0,
1, 1, 1,
2, 2, 2, 2,
};
// Create the multi-class learning algorithm for the machine
var teacher = new MultilabelSupportVectorLearning <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.
UseKernelEstimation = true
}
};
// Learn a machine
var machine = teacher.Learn(inputs, outputs);
// Create the multi-class learning algorithm for the machine
var calibration = new MultilabelSupportVectorLearning <Gaussian>()
{
Model = machine, // We will start with an existing machine
// Configure the learning algorithm to use SMO to train the
// underlying SVMs in each of the binary class subproblems.
Learner = (param) => new ProbabilisticOutputCalibration <Gaussian>()
{
Model = param.Model // Start with an existing machine
}
};
// Configure parallel execution options
calibration.ParallelOptions.MaxDegreeOfParallelism = 1;
// Learn a machine
calibration.Learn(inputs, outputs);
// Obtain class predictions for each sample
bool[][] predicted = machine.Decide(inputs);
// Get class scores for each sample
double[][] scores = machine.Scores(inputs);
// Get log-likelihoods (should be same as scores)
double[][] logl = machine.LogLikelihoods(inputs);
// Get probability for each sample
double[][] prob = machine.Probabilities(inputs);
// Compute classification error using mean accuracy (mAcc)
double error = new HammingLoss(outputs).Loss(predicted);
double loss = new CategoryCrossEntropyLoss(outputs).Loss(prob);
#endregion
string a = scores.ToCSharp();
string b = logl.ToCSharp();
string c = prob.ToCSharp();
double[][] expectedScores =
{
new double[] { 1.85316017783605, -2.59688389729331, -2.32170102153988 },
new double[] { 1.84933597524124, -1.99399145231446, -2.2920299547693 },
new double[] { 1.44477953581274, -1.98592298465108, -2.27356092239125 },
new double[] { 1.85316017783605, -2.59688389729331, -2.32170102153988 },
new double[] { 1.84933597524124, -1.99399145231446, -2.2920299547693 },
new double[] { -2.40815576360914, 0.328362962196791, -0.932721757919691 },
new double[] { -2.13111157264226, 1.809192096031, -2.2920299547693 },
new double[] { -2.13111157264226, 1.809192096031, -2.2920299547693 },
new double[] { -2.14888646926108, -1.99399145231447, 1.33101148524982 },
new double[] { -2.12915064678299, -1.98592298465108, 1.3242171079396 },
new double[] { -1.47197826667149, -1.96368715704762, 0.843414180834243 },
new double[] { -2.14221021749314, -2.83117892529093, 2.61354519154994 }
};
double[][] expectedLogL =
{
new double[] { -0.145606614365135, -2.66874434442222, -2.41528841111469 },
new double[] { -0.146125659911391, -2.12163759796483, -2.3883043096263 },
new double[] { -0.211716960454159, -2.11453945718522, -2.37154474995633 },
new double[] { -0.145606614365135, -2.66874434442222, -2.41528841111469 },
new double[] { -0.146125659911391, -2.12163759796483, -2.3883043096263 },
new double[] { -2.4943161092787, -0.542383360363463, -1.26452689970624 },
new double[] { -2.24328358118314, -0.151678833375872, -2.3883043096263 },
new double[] { -2.24328358118314, -0.151678833375872, -2.3883043096263 },
new double[] { -2.25918730624753, -2.12163759796483, -0.234447327588685 },
new double[] { -2.24153091066541, -2.11453945718522, -0.2358711195715 },
new double[] { -1.67856232802554, -2.0950136294762, -0.357841632335707 },
new double[] { -2.25321037906455, -2.88845047104229, -0.0707140798850236 }
};
double[][] expectedProbs =
{
new double[] { 0.844913862516144, 0.0677684640174953, 0.0873176734663607 },
new double[] { 0.803266328757473, 0.111405242674824, 0.0853284285677024 },
new double[] { 0.790831391595502, 0.117950175028754, 0.0912184333757438 },
new double[] { 0.844913862516144, 0.0677684640174953, 0.0873176734663607 },
new double[] { 0.803266328757473, 0.111405242674824, 0.0853284285677024 },
new double[] { 0.0872387667998771, 0.614360294206236, 0.298400938993887 },
new double[] { 0.100372339295793, 0.812805149315815, 0.0868225113883914 },
new double[] { 0.100372339295793, 0.812805149315815, 0.0868225113883914 },
new double[] { 0.102863726210119, 0.11803188195247, 0.779104391837411 },
new double[] { 0.104532503226998, 0.118686968710368, 0.776780528062634 },
new double[] { 0.184996665350572, 0.121983586443407, 0.693019748206021 },
new double[] { 0.0961702585148881, 0.0509517983210315, 0.85287794316408 }
};
int[] actual = predicted.ArgMax(dimension: 1);
Assert.IsTrue(actual.IsEqual(outputs));
Assert.AreEqual(0, error);
Assert.AreEqual(3, machine.Count);
Assert.AreEqual(0.5, machine[0].Kernel.Gamma);
Assert.AreEqual(0.5, machine[1].Kernel.Gamma);
Assert.AreEqual(0.5, machine[2].Kernel.Gamma);
Assert.AreEqual(2.9395943260892361, loss);
Assert.IsTrue(expectedScores.IsEqual(scores, 1e-10));
Assert.IsTrue(expectedLogL.IsEqual(logl, 1e-10));
Assert.IsTrue(expectedProbs.IsEqual(prob, 1e-10));
double[] rowSums = expectedProbs.Sum(1);
Assert.IsTrue(rowSums.IsEqual(Vector.Ones(expectedProbs.Length), 1e-10));
{
bool[][] predicted2 = null;
double[][] scores2 = machine.Scores(inputs, ref predicted2);
Assert.IsTrue(scores2.IsEqual(scores));
Assert.IsTrue(predicted2.IsEqual(predicted));
double[][] logl2 = machine.LogLikelihoods(inputs, ref predicted2);
Assert.IsTrue(logl2.IsEqual(logl));
Assert.IsTrue(predicted2.IsEqual(predicted));
double[][] prob2 = machine.Probabilities(inputs, ref predicted2);
Assert.IsTrue(prob2.IsEqual(prob));
Assert.IsTrue(predicted2.IsEqual(predicted));
bool[][] predicted3 = new bool[predicted2.Length][];
double[][] scores3 = inputs.ApplyWithIndex((x, i) => machine.Scores(x, ref predicted3[i]));
Assert.IsTrue(scores3.IsEqual(scores));
Assert.IsTrue(predicted3.IsEqual(predicted));
double[][] logl3 = inputs.ApplyWithIndex((x, i) => machine.LogLikelihoods(x, ref predicted3[i]));
Assert.IsTrue(logl3.IsEqual(logl));
Assert.IsTrue(predicted3.IsEqual(predicted));
double[][] prob3 = inputs.ApplyWithIndex((x, i) => machine.Probabilities(x, ref predicted3[i]));
Assert.IsTrue(prob3.IsEqual(prob));
Assert.IsTrue(predicted3.IsEqual(predicted));
}
{
double[] ed = new double[scores.Length];
double[] es = new double[scores.Length];
double[] el = new double[scores.Length];
double[] ep = new double[scores.Length];
for (int i = 0; i < expectedScores.Length; i++)
{
int j = scores[i].ArgMax();
ed[i] = j;
es[i] = scores[i][j];
el[i] = logl[i][j];
ep[i] = prob[i][j];
}
int[] predicted2 = null;
double[] scores2 = machine.ToMulticlass().Score(inputs, ref predicted2);
Assert.IsTrue(scores2.IsEqual(es));
Assert.IsTrue(predicted2.IsEqual(ed));
double[] logl2 = machine.ToMulticlass().LogLikelihood(inputs, ref predicted2);
Assert.IsTrue(logl2.IsEqual(el));
Assert.IsTrue(predicted2.IsEqual(ed));
double[] prob2 = machine.ToMulticlass().Probability(inputs, ref predicted2);
Assert.IsTrue(prob2.IsEqual(ep));
Assert.IsTrue(predicted2.IsEqual(ed));
int[] predicted3 = new int[predicted2.Length];
double[] scores3 = inputs.ApplyWithIndex((x, i) => machine.ToMulticlass().Score(x, out predicted3[i]));
Assert.IsTrue(scores3.IsEqual(es));
Assert.IsTrue(predicted3.IsEqual(ed));
double[] logl3 = inputs.ApplyWithIndex((x, i) => machine.ToMulticlass().LogLikelihood(x, out predicted3[i]));
Assert.IsTrue(logl3.IsEqual(el));
Assert.IsTrue(predicted3.IsEqual(ed));
double[] prob3 = inputs.ApplyWithIndex((x, i) => machine.ToMulticlass().Probability(x, out predicted3[i]));
Assert.IsTrue(prob3.IsEqual(ep));
Assert.IsTrue(predicted3.IsEqual(ed));
}
}
public void multilabel_calibration_generic_kernel()
{
// Let's say we have the following data to be classified
// into three possible classes. Those are the samples:
//
double[][] inputs =
{
// input output
new double[] { 0, 1, 1, 0 }, // 0
new double[] { 0, 1, 0, 0 }, // 0
new double[] { 0, 0, 1, 0 }, // 0
new double[] { 0, 1, 1, 0 }, // 0
new double[] { 0, 1, 0, 0 }, // 0
new double[] { 1, 0, 0, 1 }, // 1
new double[] { 0, 0, 0, 1 }, // 1
new double[] { 0, 0, 0, 1 }, // 1
new double[] { 1, 0, 1, 1 }, // 2
new double[] { 1, 1, 0, 1 }, // 2
new double[] { 0, 1, 1, 1 }, // 2
new double[] { 1, 1, 1, 1 }, // 2
};
int[] outputs = // those are the class labels
{
0, 0, 0, 0, 0,
1, 1, 1,
2, 2, 2, 2,
};
// Create the multi-class learning algorithm for the machine
var teacher = new MultilabelSupportVectorLearning <IKernel>()
{
// Configure the learning algorithm to use SMO to train the
// underlying SVMs in each of the binary class subproblems.
Learner = (param) => new SequentialMinimalOptimization <IKernel>()
{
UseKernelEstimation = false,
Kernel = Gaussian.FromGamma(0.5)
}
};
// Learn a machine
var machine = teacher.Learn(inputs, outputs);
// Create the multi-class learning algorithm for the machine
var calibration = new MultilabelSupportVectorLearning <IKernel>(machine)
{
// Configure the learning algorithm to use SMO to train the
// underlying SVMs in each of the binary class subproblems.
Learner = (p) => new ProbabilisticOutputCalibration <IKernel>(p.Model)
};
// Configure parallel execution options
calibration.ParallelOptions.MaxDegreeOfParallelism = 1;
// Learn a machine
calibration.Learn(inputs, outputs);
// Obtain class predictions for each sample
bool[][] predicted = machine.Decide(inputs);
// Get class scores for each sample
double[][] scores = machine.Scores(inputs);
// Get log-likelihoods (should be same as scores)
double[][] logl = machine.LogLikelihoods(inputs);
// Get probability for each sample
double[][] prob = machine.Probabilities(inputs);
// Compute classification error using mean accuracy (mAcc)
double error = new HammingLoss(outputs).Loss(predicted);
double loss = new CategoryCrossEntropyLoss(outputs).Loss(prob);
string a = scores.ToCSharp();
string b = logl.ToCSharp();
string c = prob.ToCSharp();
double[][] expectedScores =
{
new double[] { 1.85316017783605, -2.59688389729331, -2.32170102153988 },
new double[] { 1.84933597524124, -1.99399145231446, -2.2920299547693 },
new double[] { 1.44477953581274, -1.98592298465108, -2.27356092239125 },
new double[] { 1.85316017783605, -2.59688389729331, -2.32170102153988 },
new double[] { 1.84933597524124, -1.99399145231446, -2.2920299547693 },
new double[] { -2.40815576360914, 0.328362962196791, -0.932721757919691 },
new double[] { -2.13111157264226, 1.809192096031, -2.2920299547693 },
new double[] { -2.13111157264226, 1.809192096031, -2.2920299547693 },
new double[] { -2.14888646926108, -1.99399145231447, 1.33101148524982 },
new double[] { -2.12915064678299, -1.98592298465108, 1.3242171079396 },
new double[] { -1.47197826667149, -1.96368715704762, 0.843414180834243 },
new double[] { -2.14221021749314, -2.83117892529093, 2.61354519154994 }
};
double[][] expectedLogL =
{
new double[] { 1.85316017783605, -2.59688389729331, -2.32170102153988 },
new double[] { 1.84933597524124, -1.99399145231446, -2.2920299547693 },
new double[] { 1.44477953581274, -1.98592298465108, -2.27356092239125 },
new double[] { 1.85316017783605, -2.59688389729331, -2.32170102153988 },
new double[] { 1.84933597524124, -1.99399145231446, -2.2920299547693 },
new double[] { -2.40815576360914, 0.328362962196791, -0.932721757919691 },
new double[] { -2.13111157264226, 1.809192096031, -2.2920299547693 },
new double[] { -2.13111157264226, 1.809192096031, -2.2920299547693 },
new double[] { -2.14888646926108, -1.99399145231447, 1.33101148524982 },
new double[] { -2.12915064678299, -1.98592298465108, 1.3242171079396 },
new double[] { -1.47197826667149, -1.96368715704762, 0.843414180834243 },
new double[] { -2.14221021749314, -2.83117892529093, 2.61354519154994 }
};
double[][] expectedProbs =
{
new double[] { 6.37994947365835, 0.0745053832890827, 0.0981065622139132 },
new double[] { 6.35559784678136, 0.136150899620619, 0.101061104020747 },
new double[] { 4.24091706941419, 0.137253872418087, 0.102944947658882 },
new double[] { 6.37994947365835, 0.0745053832890827, 0.0981065622139132 },
new double[] { 6.35559784678136, 0.136150899620619, 0.101061104020747 },
new double[] { 0.0899810880411361, 1.38869292386051, 0.393481290780948 },
new double[] { 0.118705270957796, 6.10551277113228, 0.101061104020747 },
new double[] { 0.118705270957796, 6.10551277113228, 0.101061104020747 },
new double[] { 0.116613938707895, 0.136150899620619, 3.78486979203385 },
new double[] { 0.118938271567046, 0.137253872418087, 3.75924112261421 },
new double[] { 0.229471080877097, 0.140340010119971, 2.3242889884131 },
new double[] { 0.11739508739354, 0.0589433229176013, 13.6473476521179 }
};
int[] actual = predicted.ArgMax(dimension: 1);
Assert.IsTrue(actual.IsEqual(outputs));
// Must be exactly the same as test above
Assert.AreEqual(0, error);
Assert.AreEqual(0.5, ((Gaussian)machine[0].Kernel).Gamma);
Assert.AreEqual(0.5, ((Gaussian)machine[1].Kernel).Gamma);
Assert.AreEqual(0.5, ((Gaussian)machine[2].Kernel).Gamma);
Assert.AreEqual(-18.908706961799737, loss);
Assert.IsTrue(expectedScores.IsEqual(scores, 1e-10));
Assert.IsTrue(expectedLogL.IsEqual(logl, 1e-10));
Assert.IsTrue(expectedProbs.IsEqual(prob, 1e-10));
}