public override IRegressionModel Build(IRegressionProblemData pd, IRandom random,
CancellationToken cancellationToken, out int numberOfParameters)
{
var pca = PrincipleComponentTransformation.CreateProjection(pd.Dataset, pd.TrainingIndices, pd.AllowedInputVariables, normalize: true);
var pcdata = pca.TransformProblemData(pd);
ComponentReducedLinearModel bestModel = null;
var bestCvrmse = double.MaxValue;
numberOfParameters = 1;
for (var i = 1; i <= Math.Min(NumberOfComponents, pd.AllowedInputVariables.Count()); i++)
{
var pd2 = (IRegressionProblemData)pcdata.Clone();
var inputs = new HashSet <string>(pca.ComponentNames.Take(i));
foreach (var v in pd2.InputVariables.CheckedItems.ToArray())
{
pd2.InputVariables.SetItemCheckedState(v.Value, inputs.Contains(v.Value.Value));
}
double rmse;
var model = PreconstructedLinearModel.CreateLinearModel(pd2, out rmse);
if (rmse > bestCvrmse)
{
continue;
}
bestModel = new ComponentReducedLinearModel(pd2.TargetVariable, model, pca);
numberOfParameters = i + 1;
bestCvrmse = rmse;
}
return(bestModel);
}
private static PreconstructedLinearModel ClassicCalculation(IRegressionProblemData pd)
{
var inputMatrix = pd.Dataset.ToArray(pd.AllowedInputVariables.Concat(new[] {
pd.TargetVariable
}), pd.AllIndices);
var nFeatures = inputMatrix.GetLength(1) - 1;
double[] coefficients;
alglib.linearmodel lm;
alglib.lrreport ar;
int retVal;
alglib.lrbuild(inputMatrix, inputMatrix.GetLength(0), nFeatures, out retVal, out lm, out ar);
if (retVal != 1)
{
throw new ArgumentException("Error in calculation of linear regression solution");
}
alglib.lrunpack(lm, out coefficients, out nFeatures);
var coeffs = pd.AllowedInputVariables.Zip(coefficients, (s, d) => new { s, d }).ToDictionary(x => x.s, x => x.d);
var res = new PreconstructedLinearModel(coeffs, coefficients[nFeatures], pd.TargetVariable);
return(res);
}
private PreconstructedLinearModel(PreconstructedLinearModel original, Cloner cloner) : base(original, cloner)
{
if (original.Coefficients != null)
{
Coefficients = original.Coefficients.ToDictionary(x => x.Key, x => x.Value);
}
Intercept = original.Intercept;
}
private static PreconstructedLinearModel AlternativeCalculation(IRegressionProblemData pd, out double rmse)
{
var variables = pd.AllowedInputVariables.ToList();
var n = variables.Count;
var m = pd.TrainingIndices.Count();
//Set up X^T
var inTr = new double[n + 1, m];
for (var i = 0; i < n; i++)
{
var vdata = pd.Dataset.GetDoubleValues(variables[i], pd.TrainingIndices).ToArray();
for (var j = 0; j < m; j++)
{
inTr[i, j] = vdata[j];
}
}
for (var i = 0; i < m; i++)
{
inTr[n, i] = 1;
}
//Set up y
var y = new double[m, 1];
var ydata = pd.TargetVariableTrainingValues.ToArray();
for (var i = 0; i < m; i++)
{
y[i, 0] = ydata[i];
}
//Perform linear regression
var aTy = new double[n + 1, 1];
var aTa = new double[n + 1, n + 1];
var aTyVector = new double[n + 1];
int info;
alglib.densesolverreport report;
double[] coefficients;
//Perform linear regression
alglib.rmatrixgemm(n + 1, 1, m, 1, inTr, 0, 0, 0, y, 0, 0, 0, 0, ref aTy, 0, 0); //aTy = inTr * y;
alglib.rmatrixgemm(n + 1, n + 1, m, 1, inTr, 0, 0, 0, inTr, 0, 0, 1, 0, ref aTa, 0, 0); //aTa = inTr * t(inTr) +aTa //
alglib.spdmatrixcholesky(ref aTa, n + 1, true);
for (var i = 0; i < n + 1; i++)
{
aTyVector[i] = aTy[i, 0];
}
alglib.spdmatrixcholeskysolve(aTa, n + 1, true, aTyVector, out info, out report, out coefficients);
//if Cholesky calculation fails fall back to classic linear regresseion
if (info != 1)
{
alglib.linearmodel lm;
alglib.lrreport ar;
int retVal;
var inputMatrix = pd.Dataset.ToArray(pd.AllowedInputVariables.Concat(new[] {
pd.TargetVariable
}), pd.AllIndices);
alglib.lrbuild(inputMatrix, inputMatrix.GetLength(0), n, out retVal, out lm, out ar);
if (retVal != 1)
{
throw new ArgumentException("Error in calculation of linear regression solution");
}
alglib.lrunpack(lm, out coefficients, out n);
}
var coeffs = Enumerable.Range(0, n).ToDictionary(i => variables[i], i => coefficients[i]);
var model = new PreconstructedLinearModel(coeffs, coefficients[n], pd.TargetVariable);
rmse = pd.TrainingIndices.Select(i => pd.Dataset.GetDoubleValue(pd.TargetVariable, i) - model.GetEstimatedValue(pd.Dataset, i)).Sum(r => r * r) / m;
rmse = Math.Sqrt(rmse);
return(model);
}
