public override void SolveTransforamtion()
{
//https://numerics.mathdotnet.com/Regression.html#Regularization
/// <summary>
/// Least-Squares fitting the points (X,y) = ((x0,x1,..,xk),y) to a linear surface y : X -> p0*x0 + p1*x1 + ... + pk*xk,
/// returning a function y' for the best fitting combination.
/// If an intercept is added, its coefficient will be prepended to the resulting parameters.
/// </summary>
if (records.Count > minNumberOfPointToSolve)
{
if (records.Count % caclulationSteps == 0 || records.Count == minNumberOfPointToSolve)
{
//double[] out_x = new double[records.Count];
//double[] out_y = new double[records.Count];
double[][] out_xy = new double[records.Count][];
double[][] in_XY = new double[records.Count][];
int idx = 0;
foreach (TransformationRecord r in records)
{
out_xy[idx] = new double[] { r.ArPosition.x, r.ArPosition.z };
in_XY[idx] = new double[] { r.GpsPosition.Longitude, r.GpsPosition.Latitude };
idx++;
}
regression = ols.Learn(in_XY, out_xy);
//// We can obtain predictions using
//double[][] predictions = regression.Transform(in_XY);
//// The prediction error is
//double error = new SquareLoss(out_xy).Loss(predictions); // 0
//double[] r2 = regression.CoefficientOfDetermination(in_XY, out_xy);
}
}
}
private void btnRegress_Click(object sender, EventArgs e)
{
if (pls == null || dgvRegressionInput.DataSource == null)
{
MessageBox.Show("Please compute the analysis first.");
return;
}
int components = (int)numComponentsRegression.Value;
regression = pls.CreateRegression(components);
DataTable table = dgvRegressionInput.DataSource as DataTable;
DataTable inputTable = table.DefaultView.ToTable(false, inputColumnNames);
DataTable outputTable = table.DefaultView.ToTable(false, outputColumnNames);
double[][] sourceInput = Matrix.ToArray(inputTable as DataTable);
double[][] sourceOutput = Matrix.ToArray(outputTable as DataTable);
double[,] result = Matrix.ToMatrix(regression.Compute(sourceInput));
double[] rSquared = regression.CoefficientOfDetermination(sourceInput, sourceOutput, cbAdjusted.Checked);
dgvRegressionOutput.DataSource = new ArrayDataView(result, outputColumnNames);
dgvRSquared.DataSource = new ArrayDataView(rSquared, outputColumnNames);
}
/// <summary>
/// Learns a model that can map the given inputs to the desired outputs.
/// </summary>
/// <param name="x">The model inputs.</param>
/// <param name="weights">The weight of importance for each input sample.</param>
/// <returns>
/// A model that has learned how to produce suitable outputs
/// given the input data <paramref name="x" />.
/// </returns>
public MultivariateLinearRegression Learn(double[][] x, double[] weights = null)
{
if (weights != null)
{
throw new ArgumentException(Accord.Properties.Resources.NotSupportedWeights, "weights");
}
// Calculate common measures to speedup other calculations
this.columnMeans = Measures.Mean(x, dimension: 0);
this.columnStdDev = Measures.StandardDeviation(x, columnMeans);
NumberOfInputs = x.Columns();
if (NumberOfOutputs == 0)
{
NumberOfOutputs = NumberOfInputs;
}
// First, the data should be centered by subtracting
// the mean of each column in the source data matrix.
var matrix = Adjust(x, overwriteSourceMatrix);
// Pre-process the centered data matrix to have unit variance
var whiten = Statistics.Tools.Whitening(matrix, out whiteningMatrix);
// Generate a new unitary initial guess for the de-mixing matrix
var initial = Jagged.Random(NumberOfOutputs, matrix.Columns());
// Compute the demixing matrix using the selected algorithm
if (algorithm == IndependentComponentAlgorithm.Deflation)
{
revertMatrix = deflation(whiten, NumberOfOutputs, initial);
}
else // if (algorithm == IndependentComponentAlgorithm.Parallel)
{
revertMatrix = parallel(whiten, NumberOfOutputs, initial);
}
// Combine the rotation and demixing matrices
revertMatrix = whiteningMatrix.DotWithTransposed(revertMatrix);
revertMatrix.Divide(revertMatrix.Sum(), result: revertMatrix);
// Compute the original source mixing matrix
mixingMatrix = Matrix.PseudoInverse(revertMatrix);
mixingMatrix.Divide(mixingMatrix.Sum(), result: mixingMatrix);
this.demix = createRegression(revertMatrix, columnMeans, columnStdDev, analysisMethod);
this.mix = demix.Inverse();
// Creates the object-oriented structure to hold the principal components
var array = new IndependentComponent[NumberOfOutputs];
for (int i = 0; i < array.Length; i++)
{
array[i] = new IndependentComponent(this, i);
}
this.componentCollection = new IndependentComponentCollection(array);
return(demix);
}
public override void SolveTransforamtion()
{
//https://numerics.mathdotnet.com/Regression.html#Regularization
if (records.Count > minNumberOfPointToSolve)
{
if (records.Count % caclulationSteps == 0 || records.Count == minNumberOfPointToSolve)
{
double[][] out_x = new double[records.Count][];
double[][] out_z = new double[records.Count][];
double[][] out_y = new double[records.Count][];
double[][] in_XY = new double[records.Count][];
double[][] in_XYZ = new double[records.Count][];
int idx = 0;
foreach (TransformationRecord r in records)
{
out_x[idx] = new double[] { r.ArPosition.x };
out_z[idx] = new double[] { r.ArPosition.z };
out_y[idx] = new double[] { r.ArPosition.y };
in_XY[idx] = new double[] { r.GpsPosition.Longitude, r.GpsPosition.Latitude };
in_XYZ[idx] = new double[] { r.GpsPosition.Longitude, r.GpsPosition.Latitude, r.GpsPosition.Altitude };
idx++;
}
regression_x = ols_x.Learn(in_XY, out_x);
regression_z = ols_z.Learn(in_XY, out_z);
regression_y = ols_y.Learn(in_XYZ, out_y);
if (CalcualteError && testRecords.Count > 0)
{
List <Vector3> testArLocationsPredicted = TransformGpsToWorld(testRecords.GetGPSLocations());
Error_Horizontal = CalculateRMSE(testArLocationsPredicted, testRecords.GetARPositions());
}
}
}
}
public void SimplsComputeTest()
{
double[,] inputs;
double[,] outputs;
var pls = CreateWineExample(out inputs, out outputs);
MultivariateLinearRegression regression = pls.CreateRegression();
// test factor proportions
double[] expectedX = { 0.86, 0.12, 0.00, 0.86 };
double[] actualX = pls.Predictors.FactorProportions;
Assert.IsTrue(expectedX.IsEqual(actualX, 0.01));
double[] expectedY = { 0.67, 0.13, 0.17, 0.00 };
double[] actualY = pls.Dependents.FactorProportions;
Assert.IsTrue(expectedY.IsEqual(actualY, 0.01));
// Test Properties
double[,] weights = pls.Weights;
double[,] actual = pls.Predictors.Result;
double[,] X0 = (double[, ])pls.Source.Clone(); Tools.Center(X0, inPlace: true);
double[,] Y0 = (double[, ])pls.Output.Clone(); Tools.Center(Y0, inPlace: true);
// XSCORES = X0*W
double[,] expected = X0.Multiply(weights);
Assert.IsTrue(expected.IsEqual(actual, 0.01));
}
private static void multivariateLinear()
{
double[][] inputs =
{
// variables: x1 x2 x3
new double[] { 1, 1, 1 }, // input sample 1
new double[] { 2, 1, 1 }, // input sample 2
new double[] { 3, 1, 1 }, // input sample 3
};
double[][] outputs =
{
// variables: y1 y2
new double[] { 2, 3 }, // corresponding output to sample 1
new double[] { 4, 6 }, // corresponding output to sample 2
new double[] { 6, 9 }, // corresponding output to sample 3
};
// Use Ordinary Least Squares to create the regression
OrdinaryLeastSquares ols = new OrdinaryLeastSquares();
// Now, compute the multivariate linear regression:
MultivariateLinearRegression regression = ols.Learn(inputs, outputs);
// We can obtain predictions using
double[][] predictions = regression.Transform(inputs);
// The prediction error is
double error = new SquareLoss(outputs).Loss(predictions); // 0
}
//EXAMPLE: http://accord-framework.net/docs/html/T_Accord_Statistics_Models_Regression_Linear_MultivariateLinearRegression.htm
static void Main(string[] args)
{
CSV_Parser parser = new CSV_Parser();
RegressionData data = parser.ParseDataFile();
// Use Ordinary Least Squares to create the regression
OrdinaryLeastSquares ols = new OrdinaryLeastSquares();
// Now, compute the multivariate linear regression:
MultivariateLinearRegression regression = ols.Learn(data.InterestRatings, data.MajorRatings);
// We can obtain predictions using
double[][] predictions = regression.Transform(data.InterestRatings);
// The prediction error is
double error = new SquareLoss(data.MajorRatings).Loss(predictions); // 0
// We can also check the r-squared coefficients of determination:
//double[] r2 = regression.CoefficientOfDetermination(topicRatings, majorRatings);
double[][] r2 = regression.Weights;
Console.WriteLine("WEIGHTS:");
//writeCSVfile(data, r2);
GenerateCSFile(data, r2);
Console.WriteLine("Coefficient Of Determination");
double[] r3 = regression.CoefficientOfDetermination(data.InterestRatings, data.MajorRatings);
for (int i = 0; i < r3.Length; i++)
{
Console.WriteLine(r3[i]);
}
Console.Read();
}
public void SimplsRegressionTest_new_method()
{
double[][] inputs;
double[][] outputs;
var pls = CreateWineExample_new_method(out inputs, out outputs);
MultivariateLinearRegression regression = pls.CreateRegression();
// test regression intercepts
double[] intercepts = regression.Intercepts;
double[] expectedI = { 60.717, -8.509, -4.362 };
Assert.IsTrue(intercepts.IsEqual(expectedI, 0.01));
// test regression coefficients
double[,] coefficients = regression.Coefficients;
double[,] expectedC =
{
{ -1.6981, -0.0566, 0.07075 },
{ 1.2735, 0.2924, 0.57193 },
{ -4.0000, 1.0000, 0.50000 },
{ 1.1792, 0.1226, 0.15919 }
};
Assert.IsTrue(coefficients.IsEqual(expectedC, 0.01));
// Test computation
double[][] aY = regression.Transform(inputs);
for (int i = 0; i < outputs.Length; i++)
{
for (int j = 0; j < outputs[i].Length; j++)
{
double actualOutput = aY[i][j];
double expectedOutput = outputs[i][j];
double delta = System.Math.Abs(actualOutput - expectedOutput);
double tol = 0.21 * expectedOutput;
Assert.IsTrue(delta <= tol);
}
}
// Test output transform
double[][] bY = pls.TransformOutput(outputs);
//string str = bY.ToCSharp();
double[][] expected = new double[][] {
new double[] { 55.1168117173553, 19.9814652854436, 23.1058025430891, 8.50770527860088E-15 },
new double[] { 22.6848893220127, 7.39445606402423, 6.83504323067901, 3.73246403168482E-15 },
new double[] { -0.877117473967739, -2.79934089543989, 0.379941427036153, -1.88457062440663E-16 },
new double[] { -48.8124364962975, -9.63329642474673, -25.0857657504786, -7.17568385594517E-15 },
new double[] { -28.1121470691027, -14.9432840292812, -5.23502145032562, -4.87602839189987E-15 }
};
Assert.IsTrue(expected.IsEqual(bY, 1e-6));
}
public void prediction_test()
{
// Example from http://www.real-statistics.com/multiple-regression/confidence-and-prediction-intervals/
var dt = Accord.IO.CsvReader.FromText(Resources.linreg, true).ToTable();
double[][] y = dt.ToArray("Poverty");
double[][] x = dt.ToArray("Infant Mort", "White", "Crime");
// Use Ordinary Least Squares to learn the regression
OrdinaryLeastSquares ols = new OrdinaryLeastSquares();
// Use OLS to learn the multiple linear regression
MultivariateLinearRegression regression = ols.Learn(x, y);
Assert.AreEqual(3, regression.NumberOfInputs);
Assert.AreEqual(1, regression.NumberOfOutputs);
Assert.AreEqual(0.443650703716698, regression.Intercepts[0], 1e-5);
Assert.AreEqual(1.2791842411083394, regression.Weights[0][0], 1e-5);
Assert.AreEqual(0.036259242392669415, regression.Weights[1][0], 1e-5);
Assert.AreEqual(0.0014225014835705938, regression.Weights[2][0], 1e-5);
double rse = regression.GetStandardError(x, y)[0];
Assert.AreEqual(rse, 2.4703520840798507, 1e-5);
double[][] im = ols.GetInformationMatrix();
double[] mse = regression.GetStandardError(x, y);
double[][] se = regression.GetStandardErrors(mse, im);
Assert.AreEqual(0.30063086032754965, se[0][0], 1e-10);
Assert.AreEqual(0.033603448179240082, se[0][1], 1e-10);
Assert.AreEqual(0.0022414548866296342, se[0][2], 1e-10);
Assert.AreEqual(3.9879881671805824, se[0][3], 1e-10);
double[] x0 = new double[] { 7, 80, 400 };
double y0 = regression.Transform(x0)[0];
Assert.AreEqual(y0, 12.867680376316864, 1e-5);
double actual = regression.GetStandardError(x0, mse, im)[0];
Assert.AreEqual(0.35902764658470271, actual, 1e-10);
DoubleRange ci = regression.GetConfidenceInterval(x0, mse, x.Length, im)[0];
Assert.AreEqual(ci.Min, 12.144995206616116, 1e-5);
Assert.AreEqual(ci.Max, 13.590365546017612, 1e-5);
actual = regression.GetPredictionStandardError(x0, mse, im)[0];
Assert.AreEqual(2.4963053239397244, actual, 1e-10);
DoubleRange pi = regression.GetPredictionInterval(x0, mse, x.Length, im)[0];
Assert.AreEqual(pi.Min, 7.8428783761994554, 1e-5);
Assert.AreEqual(pi.Max, 17.892482376434273, 1e-5);
}
public DataObject DoThePCA(DataObject DataSet)
{
DataObject NewData = new DataObject(DataSet.ItemsFeatures.Length, DataSet.ItemsFeatures[0].Length)
{
ItemsFeatures = DataSet.ItemsFeatures
};
var pca = new PrincipalComponentAnalysis()
{
Method = PrincipalComponentMethod.Center,
Whiten = true
};
MultivariateLinearRegression transform = pca.Learn(DataSet.ItemsFeatures);
double[] MeansVector = new double[DataSet.ItemsFeatures[0].Length];
MeansVector = Measures.Mean(DataSet.ItemsFeatures, 0);
double[][] CovarianceMatrix = Measures.Covariance(DataSet.ItemsFeatures, MeansVector);
double[,] CovMat = new double[CovarianceMatrix.Length, CovarianceMatrix.Length];
for (int i = 0; i < CovarianceMatrix.Length; i++)
{
for (int j = 0; j < CovarianceMatrix[0].Length; j++)
{
CovMat[i, j] = CovarianceMatrix[i][j];
}
}
var evd = new EigenvalueDecomposition(CovMat);
double[] eigenval = evd.RealEigenvalues;
double[,] eigenvec = evd.Eigenvectors;
eigenvec = Matrix.Sort(eigenval, eigenvec, new GeneralComparer(ComparerDirection.Descending, true));
Console.WriteLine("Numero di componenti principali: ");
ScatterplotBox.Show(eigenval);
PrincipalComponentsNumber = Convert.ToInt32(Console.ReadLine());
pca.NumberOfOutputs = PrincipalComponentsNumber;
double[][] DataProjected = pca.Transform(DataSet.ItemsFeatures);
if (PrincipalComponentsNumber == 2)
{
ScatterplotBox.Show(DataProjected, DataSet.CatIDs);
}
NewData.ItemsFeatures = DataProjected;
NewData.CatIDs = DataSet.CatIDs;
return(NewData);
}
public void startPCA()
{
var pca = new PrincipalComponentAnalysis()
{
Method = PrincipalComponentMethod.CorrelationMatrix,
Means = meanVector,
StandardDeviations = standardDeviation
};
MultivariateLinearRegression transform = pca.Learn();
}
public void RegressTest()
{
double[][] X =
{
new double[] { 4.47 },
new double[] { 208.30 },
new double[] { 3400.00 },
};
double[][] Y =
{
new double[] { 0.51 },
new double[] { 105.66 },
new double[] { 1800.00 },
};
double eB = 0.5303528166;
double eA = -3.290915095;
MultivariateLinearRegression target = new MultivariateLinearRegression(1, 1, true);
target.Regress(X, Y);
Assert.AreEqual(target.Coefficients[0, 0], eB, 0.001);
Assert.AreEqual(target.Intercepts[0], eA, 0.001);
Assert.AreEqual(target.Inputs, 1);
Assert.AreEqual(target.Outputs, 1);
// Test manually including an constant term to generate an intercept
double[][] X1 =
{
new double[] { 4.47, 1 },
new double[] { 208.30, 1 },
new double[] { 3400.00, 1 },
};
MultivariateLinearRegression target2 = new MultivariateLinearRegression(2, 1, false);
target2.Regress(X1, Y);
Assert.AreEqual(target2.Coefficients[0, 0], eB, 0.001);
Assert.AreEqual(target2.Coefficients[1, 0], eA, 0.001);
Assert.AreEqual(target2.Inputs, 2);
Assert.AreEqual(target2.Outputs, 1);
}
public void covariance_new_interface()
{
double[] mean = Measures.Mean(data, dimension: 0);
double[][] cov = Measures.Covariance(data.ToJagged());
#region doc_learn_3
// Create the Principal Component Analysis
// specifying the CovarianceMatrix method:
var pca = new PrincipalComponentAnalysis()
{
Method = PrincipalComponentMethod.CovarianceMatrix,
Means = mean // pass the original data mean vectors
};
// Learn the PCA projection using passing the cov matrix
MultivariateLinearRegression transform = pca.Learn(cov);
// Now, we can transform data as usual
double[,] actual = pca.Transform(data);
#endregion
double[,] expected = new double[, ]
{
{ 0.827970186, -0.175115307 },
{ -1.77758033, 0.142857227 },
{ 0.992197494, 0.384374989 },
{ 0.274210416, 0.130417207 },
{ 1.67580142, -0.209498461 },
{ 0.912949103, 0.175282444 },
{ -0.099109437, -0.349824698 },
{ -1.14457216, 0.046417258 },
{ -0.438046137, 0.017764629 },
{ -1.22382056, -0.162675287 },
};
// Verify both are equal with 0.01 tolerance value
Assert.IsTrue(Matrix.IsEqual(actual, expected, 0.01));
// Transform
double[,] image = pca.Transform(data);
// Reverse
double[,] reverse = pca.Revert(image);
// Verify both are equal with 0.01 tolerance value
Assert.IsTrue(Matrix.IsEqual(reverse, data, 1e-5));
actual = transform.Transform(data.ToJagged()).ToMatrix();
Assert.IsTrue(Matrix.IsEqual(actual, expected, 1e-5));
}
public void Compute(int components)
{
NumberOfOutputs = components;
// First, the data should be centered by subtracting
// the mean of each column in the source data matrix.
double[][] matrix = Adjust(sourceMatrix.ToJagged(), overwriteSourceMatrix);
// Pre-process the centered data matrix to have unit variance
double[][] whiten = Statistics.Tools.Whitening(matrix, out whiteningMatrix);
// Generate a new unitary initial guess for the de-mixing matrix
double[][] initial = Jagged.Random(components, matrix.Columns());
// Compute the demixing matrix using the selected algorithm
if (algorithm == IndependentComponentAlgorithm.Deflation)
{
revertMatrix = deflation(whiten, components, initial);
}
else // if (algorithm == IndependentComponentAlgorithm.Parallel)
{
revertMatrix = parallel(whiten, components, initial);
}
// Combine the rotation and demixing matrices
revertMatrix = whiteningMatrix.DotWithTransposed(revertMatrix);
revertMatrix.Divide(revertMatrix.Sum(), result: revertMatrix);
// Compute the original source mixing matrix
mixingMatrix = Matrix.PseudoInverse(revertMatrix);
mixingMatrix.Divide(mixingMatrix.Sum(), result: mixingMatrix);
// Demix the data into independent components
resultMatrix = Matrix.Dot(matrix, revertMatrix).ToMatrix();
this.demix = createRegression(revertMatrix, columnMeans, columnStdDev, analysisMethod);
this.mix = demix.Inverse();
// Creates the object-oriented structure to hold the principal components
var array = new IndependentComponent[components];
for (int i = 0; i < array.Length; i++)
{
array[i] = new IndependentComponent(this, i);
}
this.componentCollection = new IndependentComponentCollection(array);
}
public void SimplsRegressionTest()
{
double[,] inputs;
double[,] outputs;
var pls = CreateWineExample(out inputs, out outputs);
MultivariateLinearRegression regression = pls.CreateRegression();
// test regression intercepts
double[] intercepts = regression.Intercepts;
double[] expectedI = { 60.717, -8.509, -4.362 };
Assert.IsTrue(intercepts.IsEqual(expectedI, 0.01));
// test regression coefficients
double[,] coefficients = regression.Coefficients;
double[,] expectedC =
{
{ -1.6981, -0.0566, 0.07075 },
{ 1.2735, 0.2924, 0.57193 },
{ -4.0000, 1.0000, 0.50000 },
{ 1.1792, 0.1226, 0.15919 }
};
Assert.IsTrue(coefficients.IsEqual(expectedC, 0.01));
// Test computation
double[][] aY = regression.Compute(inputs.ToArray());
for (int i = 0; i < outputs.GetLength(0); i++)
{
for (int j = 0; j < outputs.GetLength(1); j++)
{
double actualOutput = aY[i][j];
double expectedOutput = outputs[i, j];
double delta = System.Math.Abs(actualOutput - expectedOutput);
double tol = 0.21 * expectedOutput;
Assert.IsTrue(delta <= tol);
}
}
}
public MultivariateLinearRegression GetPredictionModel(string userId)
{
var dataSet = this.trainings
.All()
.Where(x => x.UserId == userId)
.OrderByDescending(x => x.CreatedOn)
.Take(1000)
.ToArray();
var inputDataSet = new double[dataSet.Length][];
var outputDataSet = new double[dataSet.Length][];
int i = 0;
foreach (var dataSetTraining in dataSet)
{
var inputDataRow = new double[]
{
dataSetTraining.Track.Length,
dataSetTraining.Track.Ascent,
dataSetTraining.Track.AscentLength,
};
inputDataSet[i] = inputDataRow;
var duration = dataSetTraining.EndDate - dataSetTraining.StartDate;
var outputDataRow = new double[]
{
dataSetTraining.Calories,
dataSetTraining.Water,
duration.TotalHours
};
outputDataSet[i] = outputDataRow;
i++;
}
var regression = new MultivariateLinearRegression(3, 3);
double error = regression.Regress(inputDataSet, outputDataSet);
return(regression);
}
public void startPCA()
{
var pca = new PrincipalComponentAnalysis()
{
Method = PrincipalComponentMethod.CorrelationMatrix,
Means = meanVector,
StandardDeviations = standardDeviation
};
MultivariateLinearRegression transform = pca.Learn(correlationMatrix);
eigenVectors = pca.ComponentVectors;
eigenValues = pca.Eigenvalues;
sumOfEigenValues = 0;
for (int i = 0; i < eigenValues.Length; i++)
{
sumOfEigenValues += eigenValues[i];
}
}
void Start()
{
points = new ParticleSystem.Particle[resolution];
var pca = new PrincipalComponentAnalysis()
{
Method = PrincipalComponentMethod.Center,
Whiten = true
};
MultivariateLinearRegression transform = pca.Learn(data);
pca.NumberOfOutputs = 3;
double[][] output2 = pca.Transform(data);
Debug.Log(output2[3][2]);
for (int i = 0; i < resolution; i++)
{
points [i].position = new Vector3((float)(output2 [i] [0]) * 6f, (float)(output2 [i] [1]) * 6f, (float)(output2 [i] [2]) * 6f);
points [i].startColor = new Color((float)(output2 [i] [0]) * 6f, (float)(output2 [i] [1]) * 6f, (float)(output2 [i] [2]) * 6f);
points [i].startSize = 0.075f;
}
}
public void runPCA() //DataTable mydt, List<string> numvars, string method, string subtitle)
{
if (_dt == null || _final_N == 0)
{
_subtitle += " *No data rows*";
_final_N = 0;
}
else
{
////from http://accord-framework.net/docs/html/T_Accord_Statistics_Analysis_PrincipalComponentAnalysis.htm
PrincipalComponentMethod mymethod = new PrincipalComponentMethod();
if (method == "Center")
{
mymethod = PrincipalComponentMethod.Center;
}
else if (method == "Standardize")
{
mymethod = PrincipalComponentMethod.Standardize;
}
var pca = new PrincipalComponentAnalysis()
{
Method = mymethod,
Whiten = true
};
// Learn the PCA projection using passing the cov matrix
MultivariateLinearRegression transform = pca.Learn(_data);
// Now, we can transform data as usual
double[][] out1 = pca.Transform(_data);
_pca = pca;
buildPCAtable();
}
}
private static Shapes.SimpleMesh AlignShape(Shapes.SimpleMesh mesh)
{
// Prepare matrix of all the vectors to present to PCA.
double[][] matrix = new double[mesh.VertexCount][];
for (uint i = 0; i < mesh.VertexCount; i++)
{
matrix[i] = mesh.GetVertex(i).AsArrayD();
}
// Call PCA using The Accord library.
PrincipalComponentAnalysis pca =
new PrincipalComponentAnalysis(PrincipalComponentMethod.Center,
false, 3);
MultivariateLinearRegression regression = pca.Learn(matrix);
double[][] transformed = regression.Transform(matrix);
Vector3[] vectors = transformed.Vectorize();
// Provide the new positions into the mesh.
Shapes.SimpleMesh simple = Shapes.SimpleMesh.CreateFrom(mesh);
simple.Vertices = vectors;
return(simple);
}
public override ConfusionMatrix Execute()
{
//The Least Squares algorithm
//It uses a PartialLeastSquaresAnalysis library object using a non-linear iterative partial least squares algorithm
//and runs on the mean-centered and standardized data
//Create an analysis
var pls = new PartialLeastSquaresAnalysis(trainingSet,
trainingOutput,
AnalysisMethod.Standardize,
PartialLeastSquaresAlgorithm.NIPALS);
pls.Compute();
//After computing the analysis
//create a linear model to predict new variables
MultivariateLinearRegression regression = pls.CreateRegression();
//This will hold the result of the classifications
var predictedLifted = new int[testSet.GetLength(0)][];
for (int i = 0; i < predictedLifted.Length; ++i)
{
predictedLifted[i] = regression
.Compute(testSet.GetRow(i)) //Retrieve the row vector of the test set
.Select(x => Convert.ToInt32(x)) // Convert the result to int
.ToArray();
}
//Unlift the prediction vector
var predicted = predictedLifted
.SelectMany(x => x)
.ToArray();
//Create a new confusion matrix with the calculated parameters
ConfusionMatrix cmatrix = new ConfusionMatrix(predicted, expected, POSITIVE, NEGATIVE);
return(cmatrix);
}
public void getPcaValues(int nrOfComponents)
{
float[][] data = currentData;
double[][] doubleData = new double[data.Length][];
for (int x = 0; x < data.Length; x++)
{
doubleData[x] = new double[data[x].Length];
for (int y = 0; y < data[x].Length; y++)
{
doubleData[x][y] = data[x][y];
}
}
PrincipalComponentAnalysis pca = new PrincipalComponentAnalysis()
{
Method = PrincipalComponentMethod.Center,
Whiten = true
};
MultivariateLinearRegression transform = pca.Learn(doubleData);
pca.NumberOfOutputs = nrOfComponents;
double[][] output1 = pca.Transform(doubleData);
float[][] outAsFloat = new float[output1.Length][];
for (int x = 0; x < output1.Length; x++)
{
outAsFloat[x] = new float[output1[x].Length];
for (int y = 0; y < output1[x].Length; y++)
{
outAsFloat[x][y] = (float)output1[x][y];
}
}
currentPCAValues = outAsFloat;
}
static public void Main()
{
MultivariateLinearRegression m = new MultivariateLinearRegression();
m.points = new double[, ] {
{ 10, 100, 25.2 },
{ 10, 100, 27.3 },
{ 10, 100, 28.7 },
{ 15, 225, 29.8 },
{ 15, 225, 31.1 },
{ 15, 225, 27.8 },
{ 20, 400, 31.2 },
{ 20, 400, 32.6 },
{ 20, 400, 29.7 },
{ 25, 625, 31.7 },
{ 25, 625, 30.1 },
{ 25, 625, 32.3 },
{ 30, 900, 29.4 },
{ 30, 900, 30.8 },
{ 30, 900, 32.8 }
};
Console.WriteLine(m.B.ToStr("\n\r"));
Console.Read();
}
public void learn_whiten_success()
{
#region doc_learn_1
// Below is the same data used on the excellent paper "Tutorial
// On Principal Component Analysis", by Lindsay Smith (2002).
double[][] data =
{
new double[] { 2.5, 2.4 },
new double[] { 0.5, 0.7 },
new double[] { 2.2, 2.9 },
new double[] { 1.9, 2.2 },
new double[] { 3.1, 3.0 },
new double[] { 2.3, 2.7 },
new double[] { 2.0, 1.6 },
new double[] { 1.0, 1.1 },
new double[] { 1.5, 1.6 },
new double[] { 1.1, 0.9 }
};
// Let's create an analysis with centering (covariance method)
// but no standardization (correlation method) and whitening:
var pca = new PrincipalComponentAnalysis()
{
Method = PrincipalComponentMethod.Center,
Whiten = true
};
// Now we can learn the linear projection from the data
MultivariateLinearRegression transform = pca.Learn(data);
// Finally, we can project all the data
double[][] output1 = pca.Transform(data);
// Or just its first components by setting
// NumberOfOutputs to the desired components:
pca.NumberOfOutputs = 1;
// And then calling transform again:
double[][] output2 = pca.Transform(data);
// We can also limit to 80% of explained variance:
pca.ExplainedVariance = 0.8;
// And then call transform again:
double[][] output3 = pca.Transform(data);
#endregion
double[] eigenvalues = { 1.28402771, 0.0490833989 };
double[] proportion = eigenvalues.Divide(eigenvalues.Sum());
double[,] eigenvectors =
{
{ 0.19940687993951403, -1.1061252858739095 },
{ 0.21626410214440508, 1.0199057073792104 }
};
// Everything is alright (up to the 9 decimal places shown in the tutorial)
Assert.IsTrue(eigenvectors.IsEqual(pca.ComponentMatrix, rtol: 1e-9));
Assert.IsTrue(proportion.IsEqual(pca.ComponentProportions, rtol: 1e-9));
Assert.IsTrue(eigenvalues.IsEqual(pca.Eigenvalues, rtol: 1e-5));
pca.ExplainedVariance = 1.0;
double[][] actual = pca.Transform(data);
double[][] expected =
{
new double[] { 0.243560157209023, -0.263472650637184 },
new double[] { -0.522902576315494, 0.214938218565977 },
new double[] { 0.291870144299372, 0.578317788814594 },
new double[] { 0.0806632088164338, 0.19622137941132 },
new double[] { 0.492962746459375, -0.315204397734004 },
new double[] { 0.268558011864442, 0.263724118751361 },
new double[] { -0.0291545644762578, -0.526334573603598 },
new double[] { -0.336693495487974, 0.0698378585807067 },
new double[] { -0.128858004446015, 0.0267280693333571 },
new double[] { -0.360005627922904, -0.244755811482527 }
};
// var str = actual.ToString(CSharpJaggedMatrixFormatProvider.InvariantCulture);
// Everything is correct (up to 8 decimal places)
Assert.IsTrue(expected.IsEqual(actual, atol: 1e-8));
Assert.IsTrue(expected.IsEqual(output1, atol: 1e-8));
Assert.IsTrue(expected.Get(null, 0, 1).IsEqual(output2, atol: 1e-8));
Assert.IsTrue(expected.Get(null, 0, 1).IsEqual(output3, atol: 1e-8));
actual = transform.Transform(data);
Assert.IsTrue(expected.IsEqual(actual, atol: 1e-8));
}
private static PartialLeastSquaresAnalysis CreateWineExample(out double[,] inputs, out double[,] outputs)
{
// References: http://www.utdallas.edu/~herve/Abdi-PLSR2007-pretty.pdf
// Following the small example by Hervé Abdi (Hervé Abdi, Partial Least Square Regression),
// we will create a simple example where the goal is to predict the subjective evaluation of
// a set of 5 wines. The dependent variables that we want to predict for each wine are its
// likeability, and how well it goes with meat, or dessert (as rated by a panel of experts).
// The predictors are the price, the sugar, alcohol, and acidity content of each wine.
// Here we will list the inputs, or characteristics we would like to use in order to infer
// information from our wines. Each row denotes a different wine and lists its corresponding
// observable characteristics. The inputs are usually denoted by X in the literature.
inputs = new double[, ]
{
// Wine | Price | Sugar | Alcohol | Acidity
{ 7, 7, 13, 7 },
{ 4, 3, 14, 7 },
{ 10, 5, 12, 5 },
{ 16, 7, 11, 3 },
{ 13, 3, 10, 3 },
};
// Here we will list our dependent variables. Dependent variables are the outputs, or what we
// would like to infer or predict from our available data, given a new observation. The outputs
// are usually denotes as Y in the literature.
outputs = new double[, ]
{
// Wine | Hedonic | Goes with meat | Goes with dessert
{ 14, 7, 8 },
{ 10, 7, 6 },
{ 8, 5, 5 },
{ 2, 4, 7 },
{ 6, 2, 4 },
};
// Next, we will create our Partial Least Squares Analysis passing the inputs (values for
// predictor variables) and the associated outputs (values for dependent variables).
// We will also be using the using the Covariance Matrix/Center method (data will only
// be mean centered but not normalized) and the NIPALS algorithm.
PartialLeastSquaresAnalysis pls = new PartialLeastSquaresAnalysis(inputs, outputs,
AnalysisMethod.Center, PartialLeastSquaresAlgorithm.SIMPLS);
// Compute the analysis with all factors. The number of factors
// could also have been specified in a overload of this method.
pls.Compute();
// After computing the analysis, we can create a linear regression model in order
// to predict new variables. To do that, we may call the CreateRegression() method.
MultivariateLinearRegression regression = pls.CreateRegression();
// After the regression has been created, we will be able to classify new instances.
// For example, we will compute the outputs for the first input sample:
double[] y = regression.Compute(new double[] { 7, 7, 13, 7 });
// The y output will be very close to the corresponding output used as reference.
// In this case, y is a vector of length 3 with values { 14.00, 7.00, 7.75 }.
Assert.AreEqual(14.00, y[0], 1e-2);
Assert.AreEqual(+7.00, y[1], 1e-2);
Assert.AreEqual(+7.75, y[2], 1e-2);
return(pls);
}
public void learn_test()
{
Accord.Math.Random.Generator.Seed = 0;
#region doc_learn
// Let's create a random dataset containing
// 5000 samples of two dimensional samples.
//
double[][] source = Jagged.Random(5000, 2);
// Now, we will mix the samples the dimensions of the samples.
// A small amount of the second column will be applied to the
// first, and vice-versa.
//
double[][] mix =
{
new double[] { 0.25, 0.25 },
new double[] { -0.25, 0.75 },
};
// mix the source data
double[][] input = source.Dot(mix);
// Now, we can use ICA to identify any linear mixing between the variables, such
// as the matrix multiplication we did above. After it has identified it, we will
// be able to revert the process, retrieving our original samples again
// Create a new Independent Component Analysis
var ica = new IndependentComponentAnalysis()
{
Algorithm = IndependentComponentAlgorithm.Parallel,
Contrast = new Logcosh()
};
// Learn the demixing transformation from the data
MultivariateLinearRegression demix = ica.Learn(input);
// Now, we can retrieve the mixing and demixing matrices that were
// used to alter the data. Note that the analysis was able to detect
// this information automatically:
double[][] mixingMatrix = ica.MixingMatrix; // same as the 'mix' matrix
double[][] revertMatrix = ica.DemixingMatrix; // inverse of the 'mix' matrix
// We can use the regression to recover the separate sources
double[][] result = demix.Transform(input);
#endregion
// Verify mixing matrix
mixingMatrix = mixingMatrix.Divide(mixingMatrix.Sum());
Assert.IsTrue(mix.IsEqual(mixingMatrix, atol: 0.008));
Assert.IsTrue(revertMatrix.IsEqual(demix.Weights, atol: 0.008));
var dm = demix.Inverse().Weights;
dm = dm.Divide(dm.Sum());
Assert.IsTrue(mixingMatrix.IsEqual(dm, atol: 0.008));
// Verify demixing matrix
double[,] expected =
{
{ 0.75, -0.25 },
{ 0.25, 0.25 },
};
Assert.AreEqual(IndependentComponentAlgorithm.Parallel, ica.Algorithm);
Assert.AreEqual(ica.Contrast.GetType(), typeof(Logcosh));
revertMatrix = revertMatrix.Divide(revertMatrix.Sum());
Assert.IsTrue(expected.IsEqual(revertMatrix, atol: 0.008));
}
private void btnCompute_Click(object sender, EventArgs e)
{
if (dgvAnalysisSource.DataSource == null)
{
MessageBox.Show("Please load some data first.");
return;
}
// Finishes and save any pending changes to the given data
dgvAnalysisSource.EndEdit();
DataTable table = dgvAnalysisSource.DataSource as DataTable;
// Creates a matrix from the source data table
double[,] sourceMatrix = table.ToMatrix(out inputColumnNames);
// Creates the Simple Descriptive Analysis of the given source
sda = new DescriptiveAnalysis(sourceMatrix, inputColumnNames);
sda.Compute();
// Populates statistics overview tab with analysis data
dgvDistributionMeasures.DataSource = sda.Measures;
// Extract variables
List <string> inputNames = new List <string>();
foreach (string name in clbInput.CheckedItems)
{
inputNames.Add(name);
}
this.inputColumnNames = inputNames.ToArray();
List <string> outputNames = new List <string>();
foreach (string name in clbOutput.CheckedItems)
{
outputNames.Add(name);
}
this.outputColumnNames = outputNames.ToArray();
DataTable inputTable = table.DefaultView.ToTable(false, inputColumnNames);
DataTable outputTable = table.DefaultView.ToTable(false, outputColumnNames);
double[,] inputs = inputTable.ToMatrix();
double[,] outputs = outputTable.ToMatrix();
// Creates the Partial Least Squares of the given source
pls = new PartialLeastSquaresAnalysis(inputs, outputs,
(AnalysisMethod)cbMethod.SelectedValue,
(PartialLeastSquaresAlgorithm)cbAlgorithm.SelectedValue);
// Computes the Partial Least Squares
pls.Compute();
// Populates components overview with analysis data
dgvWeightMatrix.DataSource = new ArrayDataView(pls.Weights);
dgvFactors.DataSource = pls.Factors;
dgvAnalysisLoadingsInput.DataSource = new ArrayDataView(pls.Predictors.FactorMatrix);
dgvAnalysisLoadingsOutput.DataSource = new ArrayDataView(pls.Dependents.FactorMatrix);
this.regression = pls.CreateRegression();
dgvRegressionCoefficients.DataSource = new ArrayDataView(regression.Coefficients, outputColumnNames);
dgvRegressionIntercept.DataSource = new ArrayDataView(regression.Intercepts, outputColumnNames);
dgvProjectionComponents.DataSource = pls.Factors;
numComponents.Maximum = pls.Factors.Count;
numComponents.Value = 1;
dgvRegressionComponents.DataSource = pls.Factors;
numComponentsRegression.Maximum = pls.Factors.Count;
numComponentsRegression.Value = 1;
distributionView.DataSource = pls.Factors;
cumulativeView.DataSource = pls.Factors;
dgvProjectionSourceX.DataSource = inputTable;
dgvProjectionSourceY.DataSource = outputTable;
dgvRegressionInput.DataSource = table.DefaultView.ToTable(false,
inputColumnNames.Concatenate(outputColumnNames));
}
public void learn_standardize()
{
double[][] data =
{
new double[] { 2.5, 2.4 },
new double[] { 0.5, 0.7 },
new double[] { 2.2, 2.9 },
new double[] { 1.9, 2.2 },
new double[] { 3.1, 3.0 },
new double[] { 2.3, 2.7 },
new double[] { 2.0, 1.6 },
new double[] { 1.0, 1.1 },
new double[] { 1.5, 1.6 },
new double[] { 1.1, 0.9 }
};
var pca = new PrincipalComponentAnalysis()
{
Method = PrincipalComponentMethod.Standardize,
Whiten = false
};
MultivariateLinearRegression transform = pca.Learn(data);
double[][] output1 = pca.Transform(data);
double[] eigenvalues = { 1.925929272692245, 0.074070727307754519 };
double[] proportion = eigenvalues.Divide(eigenvalues.Sum());
double[,] eigenvectors =
{
{ 0.70710678118654791, -0.70710678118654791 },
{ 0.70710678118654791, 0.70710678118654791 }
};
Assert.IsTrue(eigenvectors.IsEqual(pca.ComponentMatrix, rtol: 1e-9));
Assert.IsTrue(proportion.IsEqual(pca.ComponentProportions, rtol: 1e-9));
Assert.IsTrue(eigenvalues.IsEqual(pca.Eigenvalues, rtol: 1e-5));
pca.ExplainedVariance = 1.0;
double[][] actual = pca.Transform(data);
// var str = actual.ToCSharp();
double[][] expected =
{
new double[] { 1.03068028963519, -0.212053139513466 },
new double[] { -2.19045015647317, 0.168942295968493 },
new double[] { 1.17818776184333, 0.47577321493322 },
new double[] { 0.323294642065681, 0.161198977394117 },
new double[] { 2.07219946786664, -0.251171725759119 },
new double[] { 1.10117414355213, 0.218653302562498 },
new double[] { -0.0878525068874546, -0.430054465638535 },
new double[] { -1.40605089061245, 0.0528100914316325 },
new double[] { -0.538118242086245, 0.0202112695602547 },
new double[] { -1.48306450890365, -0.204309820939091 }
};
Assert.IsTrue(expected.IsEqual(actual, atol: 1e-8));
Assert.IsTrue(expected.IsEqual(output1, atol: 1e-8));
actual = transform.Transform(data);
Assert.IsTrue(expected.IsEqual(actual, atol: 1e-8));
}
private double[][] CreateWeights(List <Stock> listOfStocks)
{
// The multivariate linear regression is a generalization of
// the multiple linear regression. In the multivariate linear
// regression, not only the input variables are multivariate,
// but also are the output dependent variables.
// In the following example, we will perform a regression of
// a 2-dimensional output variable over a 3-dimensional input
// variable.
var inputs = new double[listOfStocks.Count][];
var outputs = new double[listOfStocks.Count][];
for (int i = 0; i < listOfStocks.Count; i++)
{
inputs[i] = new[]
{
listOfStocks[i].AdjClose,
listOfStocks[i].Close,
listOfStocks[i].High,
listOfStocks[i].Low,
listOfStocks[i].Open,
};
outputs[i] = new[] { listOfStocks[i].Volume };
}
// With a quick eye inspection, it is possible to see that
// the first output variable y1 is always the double of the
// first input variable. The second output variable y2 is
// always the triple of the first input variable. The other
// input variables are unused. Nevertheless, we will fit a
// multivariate regression model and confirm the validity
// of our impressions:
// Use Ordinary Least Squares to create the regression
OrdinaryLeastSquares ols = new OrdinaryLeastSquares();
// Now, compute the multivariate linear regression:
MultivariateLinearRegression regression = ols.Learn(inputs, outputs);
// We can obtain predictions using
double[][] predictions = regression.Transform(inputs);
// The prediction error is
double error = new SquareLoss(outputs).Loss(predictions); // 0
// At this point, the regression error will be 0 (the fit was
// perfect). The regression coefficients for the first input
// and first output variables will be 2. The coefficient for
// the first input and second output variables will be 3. All
// others will be 0.
//
// regression.Coefficients should be the matrix given by
//
// double[,] coefficients = {
// { 2, 3 },
// { 0, 0 },
// { 0, 0 },
// };
//
// We can also check the r-squared coefficients of determination:
double[] r2 = regression.CoefficientOfDetermination(inputs, outputs);
return(regression.Weights);
}
public void RegressTest2()
{
// The multivariate linear regression is a generalization of
// the multiple linear regression. In the multivariate linear
// regression, not only the input variables are multivariate,
// but also are the output dependent variables.
// In the following example, we will perform a regression of
// a 2-dimensional output variable over a 3-dimensional input
// variable.
double[][] inputs =
{
// variables: x1 x2 x3
new double[] { 1, 1, 1 }, // input sample 1
new double[] { 2, 1, 1 }, // input sample 2
new double[] { 3, 1, 1 }, // input sample 3
};
double[][] outputs =
{
// variables: y1 y2
new double[] { 2, 3 }, // corresponding output to sample 1
new double[] { 4, 6 }, // corresponding output to sample 2
new double[] { 6, 9 }, // corresponding output to sample 3
};
// With a quick eye inspection, it is possible to see that
// the first output variable y1 is always the double of the
// first input variable. The second output variable y2 is
// always the triple of the first input variable. The other
// input variables are unused. Nevertheless, we will fit a
// multivariate regression model and confirm the validity
// of our impressions:
// Create a new multivariate linear regression with 3 inputs and 2 outputs
var regression = new MultivariateLinearRegression(3, 2);
// Now, compute the multivariate linear regression:
double error = regression.Regress(inputs, outputs);
// At this point, the regression error will be 0 (the fit was
// perfect). The regression coefficients for the first input
// and first output variables will be 2. The coefficient for
// the first input and second output variables will be 3. All
// others will be 0.
//
// regression.Coefficients should be the matrix given by
//
// double[,] coefficients = {
// { 2, 3 },
// { 0, 0 },
// { 0, 0 },
// };
//
// The first input variable coefficients will be 2 and 3:
Assert.AreEqual(2, regression.Coefficients[0, 0], 1e-10);
Assert.AreEqual(3, regression.Coefficients[0, 1], 1e-10);
// And all other coefficients will be 0:
Assert.AreEqual(0, regression.Coefficients[1, 0], 1e-10);
Assert.AreEqual(0, regression.Coefficients[1, 1], 1e-10);
Assert.AreEqual(0, regression.Coefficients[2, 0], 1e-10);
Assert.AreEqual(0, regression.Coefficients[2, 1], 1e-10);
// We can also check the r-squared coefficients of determination:
double[] r2 = regression.CoefficientOfDetermination(inputs, outputs);
// Which should be one for both output variables:
Assert.AreEqual(1, r2[0]);
Assert.AreEqual(1, r2[1]);
foreach (var e in regression.Coefficients)
{
Assert.IsFalse(double.IsNaN(e));
}
Assert.AreEqual(0, error, 1e-10);
Assert.IsFalse(double.IsNaN(error));
}