private NearestNeighbourModel(NearestNeighbourModel original, Cloner cloner)
: base(original, cloner) {
kdTree = new alglib.nearestneighbor.kdtree();
kdTree.approxf = original.kdTree.approxf;
kdTree.boxmax = (double[])original.kdTree.boxmax.Clone();
kdTree.boxmin = (double[])original.kdTree.boxmin.Clone();
kdTree.buf = (double[])original.kdTree.buf.Clone();
kdTree.curboxmax = (double[])original.kdTree.curboxmax.Clone();
kdTree.curboxmin = (double[])original.kdTree.curboxmin.Clone();
kdTree.curdist = original.kdTree.curdist;
kdTree.debugcounter = original.kdTree.debugcounter;
kdTree.idx = (int[])original.kdTree.idx.Clone();
kdTree.kcur = original.kdTree.kcur;
kdTree.kneeded = original.kdTree.kneeded;
kdTree.n = original.kdTree.n;
kdTree.nodes = (int[])original.kdTree.nodes.Clone();
kdTree.normtype = original.kdTree.normtype;
kdTree.nx = original.kdTree.nx;
kdTree.ny = original.kdTree.ny;
kdTree.r = (double[])original.kdTree.r.Clone();
kdTree.rneeded = original.kdTree.rneeded;
kdTree.selfmatch = original.kdTree.selfmatch;
kdTree.splits = (double[])original.kdTree.splits.Clone();
kdTree.tags = (int[])original.kdTree.tags.Clone();
kdTree.x = (double[])original.kdTree.x.Clone();
kdTree.xy = (double[,])original.kdTree.xy.Clone();
k = original.k;
targetVariable = original.targetVariable;
allowedInputVariables = (string[])original.allowedInputVariables.Clone();
if (original.classValues != null)
this.classValues = (double[])original.classValues.Clone();
}
private NearestNeighbourModel(NearestNeighbourModel original, Cloner cloner)
: base(original, cloner)
{
kdTree = new alglib.nearestneighbor.kdtree();
kdTree.approxf = original.kdTree.approxf;
kdTree.boxmax = (double[])original.kdTree.boxmax.Clone();
kdTree.boxmin = (double[])original.kdTree.boxmin.Clone();
kdTree.buf = (double[])original.kdTree.buf.Clone();
kdTree.curboxmax = (double[])original.kdTree.curboxmax.Clone();
kdTree.curboxmin = (double[])original.kdTree.curboxmin.Clone();
kdTree.curdist = original.kdTree.curdist;
kdTree.debugcounter = original.kdTree.debugcounter;
kdTree.idx = (int[])original.kdTree.idx.Clone();
kdTree.kcur = original.kdTree.kcur;
kdTree.kneeded = original.kdTree.kneeded;
kdTree.n = original.kdTree.n;
kdTree.nodes = (int[])original.kdTree.nodes.Clone();
kdTree.normtype = original.kdTree.normtype;
kdTree.nx = original.kdTree.nx;
kdTree.ny = original.kdTree.ny;
kdTree.r = (double[])original.kdTree.r.Clone();
kdTree.rneeded = original.kdTree.rneeded;
kdTree.selfmatch = original.kdTree.selfmatch;
kdTree.splits = (double[])original.kdTree.splits.Clone();
kdTree.tags = (int[])original.kdTree.tags.Clone();
kdTree.x = (double[])original.kdTree.x.Clone();
kdTree.xy = (double[, ])original.kdTree.xy.Clone();
k = original.k;
allowedInputVariables = (string[])original.allowedInputVariables.Clone();
if (original.classValues != null)
{
this.classValues = (double[])original.classValues.Clone();
}
}
private NearestNeighbourModel(bool deserializing)
: base(deserializing)
{
if (deserializing)
{
kdTree = new alglib.nearestneighbor.kdtree();
}
}
private NearestNeighbourModel(NearestNeighbourModel original, Cloner cloner)
: base(original, cloner)
{
kdTree = new alglib.nearestneighbor.kdtree();
kdTree.approxf = original.kdTree.approxf;
kdTree.boxmax = (double[])original.kdTree.boxmax.Clone();
kdTree.boxmin = (double[])original.kdTree.boxmin.Clone();
kdTree.buf = (double[])original.kdTree.buf.Clone();
kdTree.curboxmax = (double[])original.kdTree.curboxmax.Clone();
kdTree.curboxmin = (double[])original.kdTree.curboxmin.Clone();
kdTree.curdist = original.kdTree.curdist;
kdTree.debugcounter = original.kdTree.debugcounter;
kdTree.idx = (int[])original.kdTree.idx.Clone();
kdTree.kcur = original.kdTree.kcur;
kdTree.kneeded = original.kdTree.kneeded;
kdTree.n = original.kdTree.n;
kdTree.nodes = (int[])original.kdTree.nodes.Clone();
kdTree.normtype = original.kdTree.normtype;
kdTree.nx = original.kdTree.nx;
kdTree.ny = original.kdTree.ny;
kdTree.r = (double[])original.kdTree.r.Clone();
kdTree.rneeded = original.kdTree.rneeded;
kdTree.selfmatch = original.kdTree.selfmatch;
kdTree.splits = (double[])original.kdTree.splits.Clone();
kdTree.tags = (int[])original.kdTree.tags.Clone();
kdTree.x = (double[])original.kdTree.x.Clone();
kdTree.xy = (double[, ])original.kdTree.xy.Clone();
selfMatch = original.selfMatch;
k = original.k;
isCompatibilityLoaded = original.IsCompatibilityLoaded;
if (!IsCompatibilityLoaded)
{
weights = new double[original.weights.Length];
Array.Copy(original.weights, weights, weights.Length);
offsets = new double[original.offsets.Length];
Array.Copy(original.offsets, this.offsets, this.offsets.Length);
}
allowedInputVariables = (string[])original.allowedInputVariables.Clone();
if (original.classValues != null)
{
this.classValues = (double[])original.classValues.Clone();
}
}
public NearestNeighbourModel(IDataset dataset, IEnumerable <int> rows, int k, string targetVariable, IEnumerable <string> allowedInputVariables, double[] classValues = null)
{
Name = ItemName;
Description = ItemDescription;
this.k = k;
this.targetVariable = targetVariable;
this.allowedInputVariables = allowedInputVariables.ToArray();
var inputMatrix = AlglibUtil.PrepareInputMatrix(dataset,
allowedInputVariables.Concat(new string[] { targetVariable }),
rows);
if (inputMatrix.Cast <double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
{
throw new NotSupportedException(
"Nearest neighbour classification does not support NaN or infinity values in the input dataset.");
}
this.kdTree = new alglib.nearestneighbor.kdtree();
var nRows = inputMatrix.GetLength(0);
var nFeatures = inputMatrix.GetLength(1) - 1;
if (classValues != null)
{
this.classValues = (double[])classValues.Clone();
int nClasses = classValues.Length;
// map original class values to values [0..nClasses-1]
var classIndices = new Dictionary <double, double>();
for (int i = 0; i < nClasses; i++)
{
classIndices[classValues[i]] = i;
}
for (int row = 0; row < nRows; row++)
{
inputMatrix[row, nFeatures] = classIndices[inputMatrix[row, nFeatures]];
}
}
alglib.nearestneighbor.kdtreebuild(inputMatrix, nRows, inputMatrix.GetLength(1) - 1, 1, 2, kdTree);
}
public NearestNeighbourModel(IDataset dataset, IEnumerable<int> rows, int k, string targetVariable, IEnumerable<string> allowedInputVariables, double[] classValues = null) {
Name = ItemName;
Description = ItemDescription;
this.k = k;
this.targetVariable = targetVariable;
this.allowedInputVariables = allowedInputVariables.ToArray();
var inputMatrix = AlglibUtil.PrepareInputMatrix(dataset,
allowedInputVariables.Concat(new string[] { targetVariable }),
rows);
if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
throw new NotSupportedException(
"Nearest neighbour classification does not support NaN or infinity values in the input dataset.");
this.kdTree = new alglib.nearestneighbor.kdtree();
var nRows = inputMatrix.GetLength(0);
var nFeatures = inputMatrix.GetLength(1) - 1;
if (classValues != null) {
this.classValues = (double[])classValues.Clone();
int nClasses = classValues.Length;
// map original class values to values [0..nClasses-1]
var classIndices = new Dictionary<double, double>();
for (int i = 0; i < nClasses; i++)
classIndices[classValues[i]] = i;
for (int row = 0; row < nRows; row++) {
inputMatrix[row, nFeatures] = classIndices[inputMatrix[row, nFeatures]];
}
}
alglib.nearestneighbor.kdtreebuild(inputMatrix, nRows, inputMatrix.GetLength(1) - 1, 1, 2, kdTree);
}
private NearestNeighbourModel(bool deserializing)
: base(deserializing) {
if (deserializing)
kdTree = new alglib.nearestneighbor.kdtree();
}
public NearestNeighbourModel(IDataset dataset, IEnumerable <int> rows, int k, string targetVariable, IEnumerable <string> allowedInputVariables, IEnumerable <double> weights = null, double[] classValues = null)
: base(targetVariable)
{
Name = ItemName;
Description = ItemDescription;
this.k = k;
this.allowedInputVariables = allowedInputVariables.ToArray();
double[,] inputMatrix;
if (IsCompatibilityLoaded)
{
// no scaling
inputMatrix = dataset.ToArray(
this.allowedInputVariables.Concat(new string[] { targetVariable }),
rows);
}
else
{
this.offsets = this.allowedInputVariables
.Select(name => dataset.GetDoubleValues(name, rows).Average() * -1)
.Concat(new double[] { 0 }) // no offset for target variable
.ToArray();
if (weights == null)
{
// automatic determination of weights (all features should have variance = 1)
this.weights = this.allowedInputVariables
.Select(name => 1.0 / dataset.GetDoubleValues(name, rows).StandardDeviationPop())
.Concat(new double[] { 1.0 }) // no scaling for target variable
.ToArray();
}
else
{
// user specified weights (+ 1 for target)
this.weights = weights.Concat(new double[] { 1.0 }).ToArray();
if (this.weights.Length - 1 != this.allowedInputVariables.Length)
{
throw new ArgumentException("The number of elements in the weight vector must match the number of input variables");
}
}
inputMatrix = CreateScaledData(dataset, this.allowedInputVariables.Concat(new string[] { targetVariable }), rows, this.offsets, this.weights);
}
if (inputMatrix.Cast <double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
{
throw new NotSupportedException(
"Nearest neighbour model does not support NaN or infinity values in the input dataset.");
}
this.kdTree = new alglib.nearestneighbor.kdtree();
var nRows = inputMatrix.GetLength(0);
var nFeatures = inputMatrix.GetLength(1) - 1;
if (classValues != null)
{
this.classValues = (double[])classValues.Clone();
int nClasses = classValues.Length;
// map original class values to values [0..nClasses-1]
var classIndices = new Dictionary <double, double>();
for (int i = 0; i < nClasses; i++)
{
classIndices[classValues[i]] = i;
}
for (int row = 0; row < nRows; row++)
{
inputMatrix[row, nFeatures] = classIndices[inputMatrix[row, nFeatures]];
}
}
alglib.nearestneighbor.kdtreebuild(inputMatrix, nRows, inputMatrix.GetLength(1) - 1, 1, 2, kdTree);
}
private NearestNeighbourModel(StorableConstructorFlag _) : base(_)
{
kdTree = new alglib.nearestneighbor.kdtree();
}