NMath Reference Guide
CenterSpace.NMath.Core
NMathFunctions Class
NMathFunctions Methods
Abs Method
AbsSum Method
Acos Method
And Method
Arg Method
ArrayOfRandomNumbers Method
Asin Method
Atan Method
Atan2 Method
Beta Method
Binomial Method
BinomialLn Method
Ceil Method
CentralMoment Method
ConditionNumber Method
Conj Method
ConjDot Method
ConjTranspose Method
ConjTransposeProduct Method
CopyOnlyReal Method
CorrelatedRandomInputs Method
Correlation Method
CorrelationMatrix Method
Cos Method
Cosh Method
Count Method
CountIf Method
Counts Method
Covariance Method
CovarianceMatrix Method
CovarianceMatrixMemoized Method
Cronbach Method
Cross Method
CumulativeProduct Method
CumulativeSum Method
Decile Method
Delta Method
DenseProduct Method
DenseTransposeProduct Method
Determinant Method
Dot Method
DoubleNormalRandomMatrix Method
DoubleNormalRandomVector Method
DoubleRandomMatrix Method
DoubleRandomVector Method
DurbinWatson Method
EstimateConditionNumber Method
Exp Method
Expm Method
Factorial Method
FactorialLn Method
FillArrayWithNormalRandomNumbers Method
FillArrayWithRandomNumbers Method
Fisher Method
FisherInv Method
FishersExactTest Method
FiveParameterLogistic Method
Floor Method
FourParameterLogistic Method
FrobeniusNorm Method
FrobNormDiffSqr Method
GammaLn Method
Gather Method
GeometricMean Method
GetProjectionMatrix Method
HarmonicMean Method
If Method
Imag Method
IncompleteBeta Method
IncompleteGamma Method
IncompleteGammaComplement Method
InfinityNorm Method
InitialCenters Method
InterquartileRange Method
Inverse Method
KthSmallestValue<T> Method
Kurtosis Method
Log Method
Log10 Method
MaxAbs1Index Method
MaxAbs1Value Method
MaxAbsIndex Method
MaxAbsValue Method
MaxIndex Method
MaxValue Method
Mean Method
MeanDeviation Method
Median Method
MedianDeviationFromMean Method
MedianDeviationFromMedian Method
MinAbs1Index Method
MinAbs1Value Method
MinAbsIndex Method
MinAbsValue Method
MinIndex Method
MinValue Method
Mode Method
NaNCentralMoment Method
NaNCheck Method
NaNCorrelation Method
NaNCount Method
NaNCountIf Method
NaNCovariance Method
NaNDurbinWatson Method
NaNGeometricMean Method
NaNHarmonicMean Method
NaNIf Method
NaNKurtosis Method
NaNMaxAbsIndex Method
NaNMaxAbsValue Method
NaNMaxIndex Method
NaNMaxValue Method
NaNMean Method
NaNMeanDeviation Method
NaNMedian Method
NaNMinAbsIndex Method
NaNMinAbsValue Method
NaNMinIndex Method
NaNMinValue Method
NaNMode Method
NaNRemove Method
NaNRemoveCols Method
NaNRemoveRows Method
NaNSkewness Method
NaNSort Method
NaNStandardDeviation Method
NaNSum Method
NaNSumIf Method
NaNSumOfSquaredErrors Method
NaNSumOfSquares Method
NaNVariance Method
NaNVonNeumannRatio Method
Not Method
OneNorm Method
Or Method
OuterProduct Method
Percentile Method
PercentileRank Method
Pow Method
Product Method
ProductPlusConst Method
PseudoInverse Method
Quartile Method
Rank Method
Ranks Method
Real Method
RepMat Method
RMS Method
Round Method
Scatter Method
Sign Method
Sin Method
Sinh Method
Skewness Method
Solve Method
SolvePD Method
Sort Method
SortByColumn Method
Spearmans Method
Sqrt Method
StandardDeviation Method
Sum Method
SumIf Method
SumOfSquaredErrors Method
SumOfSquares Method
Tan Method
Tanh Method
ThreeParameterExponential Method
ThreeParameterSine Method
ToDenseMatrix Method
ToDenseSymmetricMatrix Method
ToGeneralMatrix Method
ToSparseMatrix Method
Trace Method
Transpose Method
TransposeProduct Method
TrimmedMean Method
TwoParameterAsymptotic Method
VanDerWaerdenScores Method
Variance Method
VonNeumannRatio Method
WeightedMean Method
WeightedMedian Method
WeightedStandardDeviation Method
WeightedVariance Method
Xor Method
Click or drag to resize

NMathFunctionsInitialCenters Method

Chooses the specified number of initial centers from the given data matrix, for clustering algorithms such as k-means.

Namespace: CenterSpace.NMath.Core
Assembly: NMath (in NMath.dll) Version: 7.4
Syntax
Copy
public static int[] InitialCenters(
	DoubleMatrix data,
	int k
)

Parameters

data  DoubleMatrix
A matrix of data. Each row in the matrix represents an object to be clustered.
k  Int32
The number of initial cluster centers.

Return Value

Int32
An array of row indices.
Exceptions
ExceptionCondition
InvalidArgumentException Thrown if the number of cluster centers is less than one or greater than the number of data points (data.Rows).
Remarks
Uses the following algorithm: If the distance between row r and its closest center is greater than the distance between the two closest centers (m, n), then r replaces m or n, whichever is closest to r. Otherwise, if the distance between row r and its closest center (q) is greater than the distance between q and its closest center, then row r replaces q. (Similar to SPSS QuickCluster function.)
See Also