public void GenerateTest4()
{
// Create a Wishart distribution with the parameters:
WishartDistribution wishart = new WishartDistribution(
// Degrees of freedom
degreesOfFreedom: 7,
// Scale parameter
scale: new double[, ]
{
{ 4, 1, 1 },
{ 1, 2, 2 }, // (must be symmetric and positive definite)
{ 1, 2, 6 },
}
);
double[,] one = wishart.Generate();
Assert.AreEqual(3, one.Rows());
Assert.AreEqual(3, one.Columns());
Assert.IsTrue(one.IsPositiveDefinite());
double[][,] many = wishart.Generate(100);
for (int i = 0; i < many.Length; i++)
{
Assert.AreEqual(3, many[i].Rows());
Assert.AreEqual(3, many[i].Columns());
Assert.IsTrue(many[i].IsPositiveDefinite());
}
}
public void sequence_parsing_test()
{
#region doc_learn_fraud_analysis
// Ensure results are reproducible
Accord.Math.Random.Generator.Seed = 0;
// Let's say we have the following data about credit card transactions,
// where the data is organized in order of transaction, per credit card
// holder. Everytime the "Time" column starts at zero, denotes that the
// sequence of observations follow will correspond to transactions of the
// same person:
double[,] data =
{
// "Time", "V1", "V2", "V3", "V4", "V5", "Amount", "Fraud"
{ 0, 0.521, 0.124, 0.622, 15.2, 25.6, 2.70, 0 }, // first person, ok
{ 1, 0.121, 0.124, 0.822, 12.2, 25.6, 42.0, 0 }, // first person, ok
{ 0, 0.551, 0.124, 0.422, 17.5, 25.6, 20.0, 0 }, // second person, ok
{ 1, 0.136, 0.154, 0.322, 15.3, 25.6, 50.0, 0 }, // second person, ok
{ 2, 0.721, 0.240, 0.422, 12.2, 25.6, 100.0, 1 }, // second person, fraud!
{ 3, 0.222, 0.126, 0.722, 18.1, 25.8, 10.0, 0 }, // second person, ok
};
// Transform the above data into a jagged matrix
double[][][] input;
int[][] states;
transform(data, out input, out states);
// Determine here the number of dimensions in the observations (in this case, 6)
int observationDimensions = 6; // 6 columns: "V1", "V2", "V3", "V4", "V5", "Amount"
// Create some prior distributions to help initialize our parameters
var priorC = new WishartDistribution(dimension: observationDimensions, degreesOfFreedom: 10); // this 10 is just some random number, you might have to tune as if it was a hyperparameter
var priorM = new MultivariateNormalDistribution(dimension: observationDimensions);
// Configure the learning algorithms to train the sequence classifier
var teacher = new MaximumLikelihoodLearning <MultivariateNormalDistribution, double[]>()
{
// Their emissions will be multivariate Normal distributions initialized using the prior distributions
Emissions = (j) => new MultivariateNormalDistribution(mean: priorM.Generate(), covariance: priorC.Generate()),
// We will prevent our covariance matrices from becoming degenerate by adding a small
// regularization value to their diagonal until they become positive-definite again:
FittingOptions = new NormalOptions()
{
Regularization = 1e-6
},
};
// Use the teacher to learn a new HMM
var hmm = teacher.Learn(input, states);
// Use the HMM to predict whether the transations were fradulent or not:
int[] firstPerson = hmm.Decide(input[0]); // predict the first person, output should be: 0, 0
int[] secondPerson = hmm.Decide(input[1]); // predict the second person, output should be: 0, 0, 1, 0
#endregion
Assert.AreEqual(new[] { 0, 0 }, firstPerson);
Assert.AreEqual(new[] { 0, 0, 1, 0 }, secondPerson);
}
public void learn_pendigits_normalization()
{
Console.WriteLine("Starting NormalQuasiNewtonHiddenLearningTest.learn_pendigits_normalization");
using (var travis = new KeepTravisAlive())
{
#region doc_learn_pendigits
// Ensure we get reproducible results
Accord.Math.Random.Generator.Seed = 0;
// Download the PENDIGITS dataset from UCI ML repository
var pendigits = new Pendigits(path: Path.GetTempPath());
// Get and pre-process the training set
double[][][] trainInputs = pendigits.Training.Item1;
int[] trainOutputs = pendigits.Training.Item2;
// Pre-process the digits so each of them is centered and scaled
trainInputs = trainInputs.Apply(Accord.Statistics.Tools.ZScores);
trainInputs = trainInputs.Apply((x) => x.Subtract(x.Min())); // make them positive
// Create some prior distributions to help initialize our parameters
var priorC = new WishartDistribution(dimension: 2, degreesOfFreedom: 5);
var priorM = new MultivariateNormalDistribution(dimension: 2);
// Create a new learning algorithm for creating continuous hidden Markov model classifiers
var teacher1 = new HiddenMarkovClassifierLearning <MultivariateNormalDistribution, double[]>()
{
// This tells the generative algorithm how to train each of the component models. Note: The learning
// algorithm is more efficient if all generic parameters are specified, including the fitting options
Learner = (i) => new BaumWelchLearning <MultivariateNormalDistribution, double[], NormalOptions>()
{
Topology = new Forward(5), // Each model will have a forward topology with 5 states
// Their emissions will be multivariate Normal distributions initialized using the prior distributions
Emissions = (j) => new MultivariateNormalDistribution(mean: priorM.Generate(), covariance: priorC.Generate()),
// We will train until the relative change in the average log-likelihood is less than 1e-6 between iterations
Tolerance = 1e-6,
MaxIterations = 1000, // or until we perform 1000 iterations (which is unlikely for this dataset)
// We will prevent our covariance matrices from becoming degenerate by adding a small
// regularization value to their diagonal until they become positive-definite again:
FittingOptions = new NormalOptions()
{
Regularization = 1e-6
}
}
};
// The following line is only needed to ensure reproducible results. Please remove it to enable full parallelization
teacher1.ParallelOptions.MaxDegreeOfParallelism = 1; // (Remove, comment, or change this line to enable full parallelism)
// Use the learning algorithm to create a classifier
var hmmc = teacher1.Learn(trainInputs, trainOutputs);
// Create a new learning algorithm for creating HCRFs
var teacher2 = new HiddenQuasiNewtonLearning <double[]>()
{
Function = new MarkovMultivariateFunction(hmmc),
MaxIterations = 10
};
// The following line is only needed to ensure reproducible results. Please remove it to enable full parallelization
teacher2.ParallelOptions.MaxDegreeOfParallelism = 1; // (Remove, comment, or change this line to enable full parallelism)
// Use the learning algorithm to create a classifier
var hcrf = teacher2.Learn(trainInputs, trainOutputs);
// Compute predictions for the training set
int[] trainPredicted = hcrf.Decide(trainInputs);
// Check the performance of the classifier by comparing with the ground-truth:
var m1 = new GeneralConfusionMatrix(predicted: trainPredicted, expected: trainOutputs);
double trainAcc = m1.Accuracy; // should be 0.66523727844482561
// Prepare the testing set
double[][][] testInputs = pendigits.Testing.Item1;
int[] testOutputs = pendigits.Testing.Item2;
// Apply the same normalizations
testInputs = testInputs.Apply(Accord.Statistics.Tools.ZScores);
testInputs = testInputs.Apply((x) => x.Subtract(x.Min())); // make them positive
// Compute predictions for the test set
int[] testPredicted = hcrf.Decide(testInputs);
// Check the performance of the classifier by comparing with the ground-truth:
var m2 = new GeneralConfusionMatrix(predicted: testPredicted, expected: testOutputs);
double testAcc = m2.Accuracy; // should be 0.66506538564184681
#endregion
Assert.AreEqual(0.66523727844482561, trainAcc, 1e-10);
Assert.AreEqual(0.66506538564184681, testAcc, 1e-10);
}
}
public void learn_pendigits_normalization()
{
#region doc_learn_pendigits
// Ensure we get reproducible results
Accord.Math.Random.Generator.Seed = 0;
// Download the PENDIGITS dataset from UCI ML repository
var pendigits = new Pendigits(path: Path.GetTempPath());
// Get and pre-process the training set
double[][][] trainInputs = pendigits.Training.Item1;
int[] trainOutputs = pendigits.Training.Item2;
// Pre-process the digits so each of them is centered and scaled
trainInputs = trainInputs.Apply(Accord.Statistics.Tools.ZScores);
trainInputs = trainInputs.Apply((x) => x.Subtract(x.Min())); // make them positive
// Create some prior distributions to help initialize our parameters
var priorC = new WishartDistribution(dimension: 2, degreesOfFreedom: 5);
var priorM = new MultivariateNormalDistribution(dimension: 2);
// Create a template Markov classifier that we can use as a base for the HCRF
var hmmc = new HiddenMarkovClassifier <MultivariateNormalDistribution, double[]>(
classes: pendigits.NumberOfClasses, topology: new Forward(5),
initial: (i, j) => new MultivariateNormalDistribution(mean: priorM.Generate(), covariance: priorC.Generate()));
// Create a new learning algorithm for creating HCRFs
var teacher = new HiddenQuasiNewtonLearning <double[]>()
{
Function = new MarkovMultivariateFunction(hmmc),
MaxIterations = 10
};
// 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)
// Use the learning algorithm to create a classifier
var hcrf = teacher.Learn(trainInputs, trainOutputs);
// Compute predictions for the training set
int[] trainPredicted = hcrf.Decide(trainInputs);
// Check the performance of the classifier by comparing with the ground-truth:
var m1 = new ConfusionMatrix(predicted: trainPredicted, expected: trainOutputs);
double trainAcc = m1.Accuracy; // should be 0.89594053744997137
// Prepare the testing set
double[][][] testInputs = pendigits.Testing.Item1;
int[] testOutputs = pendigits.Testing.Item2;
// Apply the same normalizations
testInputs = testInputs.Apply(Accord.Statistics.Tools.ZScores);
testInputs = testInputs.Apply((x) => x.Subtract(x.Min())); // make them positive
// Compute predictions for the test set
int[] testPredicted = hcrf.Decide(testInputs);
// Check the performance of the classifier by comparing with the ground-truth:
var m2 = new ConfusionMatrix(predicted: testPredicted, expected: testOutputs);
double testAcc = m2.Accuracy; // should be 0.89594053744997137
#endregion
Assert.AreEqual(0.89594053744997137, trainAcc, 1e-10);
Assert.AreEqual(0.896050173472111, testAcc, 1e-10);
}