umappp 0.1.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/LICENSE.txt +25 -0
- data/README.md +110 -0
- data/ext/umappp/extconf.rb +25 -0
- data/ext/umappp/numo.hpp +867 -0
- data/ext/umappp/umappp.cpp +225 -0
- data/lib/umappp/version.rb +5 -0
- data/lib/umappp.rb +41 -0
- data/vendor/Eigen/Cholesky +45 -0
- data/vendor/Eigen/CholmodSupport +48 -0
- data/vendor/Eigen/Core +384 -0
- data/vendor/Eigen/Dense +7 -0
- data/vendor/Eigen/Eigen +2 -0
- data/vendor/Eigen/Eigenvalues +60 -0
- data/vendor/Eigen/Geometry +59 -0
- data/vendor/Eigen/Householder +29 -0
- data/vendor/Eigen/IterativeLinearSolvers +48 -0
- data/vendor/Eigen/Jacobi +32 -0
- data/vendor/Eigen/KLUSupport +41 -0
- data/vendor/Eigen/LU +47 -0
- data/vendor/Eigen/MetisSupport +35 -0
- data/vendor/Eigen/OrderingMethods +70 -0
- data/vendor/Eigen/PaStiXSupport +49 -0
- data/vendor/Eigen/PardisoSupport +35 -0
- data/vendor/Eigen/QR +50 -0
- data/vendor/Eigen/QtAlignedMalloc +39 -0
- data/vendor/Eigen/SPQRSupport +34 -0
- data/vendor/Eigen/SVD +50 -0
- data/vendor/Eigen/Sparse +34 -0
- data/vendor/Eigen/SparseCholesky +37 -0
- data/vendor/Eigen/SparseCore +69 -0
- data/vendor/Eigen/SparseLU +50 -0
- data/vendor/Eigen/SparseQR +36 -0
- data/vendor/Eigen/StdDeque +27 -0
- data/vendor/Eigen/StdList +26 -0
- data/vendor/Eigen/StdVector +27 -0
- data/vendor/Eigen/SuperLUSupport +64 -0
- data/vendor/Eigen/UmfPackSupport +40 -0
- data/vendor/Eigen/src/Cholesky/LDLT.h +688 -0
- data/vendor/Eigen/src/Cholesky/LLT.h +558 -0
- data/vendor/Eigen/src/Cholesky/LLT_LAPACKE.h +99 -0
- data/vendor/Eigen/src/CholmodSupport/CholmodSupport.h +682 -0
- data/vendor/Eigen/src/Core/ArithmeticSequence.h +413 -0
- data/vendor/Eigen/src/Core/Array.h +417 -0
- data/vendor/Eigen/src/Core/ArrayBase.h +226 -0
- data/vendor/Eigen/src/Core/ArrayWrapper.h +209 -0
- data/vendor/Eigen/src/Core/Assign.h +90 -0
- data/vendor/Eigen/src/Core/AssignEvaluator.h +1010 -0
- data/vendor/Eigen/src/Core/Assign_MKL.h +178 -0
- data/vendor/Eigen/src/Core/BandMatrix.h +353 -0
- data/vendor/Eigen/src/Core/Block.h +448 -0
- data/vendor/Eigen/src/Core/BooleanRedux.h +162 -0
- data/vendor/Eigen/src/Core/CommaInitializer.h +164 -0
- data/vendor/Eigen/src/Core/ConditionEstimator.h +175 -0
- data/vendor/Eigen/src/Core/CoreEvaluators.h +1741 -0
- data/vendor/Eigen/src/Core/CoreIterators.h +132 -0
- data/vendor/Eigen/src/Core/CwiseBinaryOp.h +183 -0
- data/vendor/Eigen/src/Core/CwiseNullaryOp.h +1001 -0
- data/vendor/Eigen/src/Core/CwiseTernaryOp.h +197 -0
- data/vendor/Eigen/src/Core/CwiseUnaryOp.h +103 -0
- data/vendor/Eigen/src/Core/CwiseUnaryView.h +132 -0
- data/vendor/Eigen/src/Core/DenseBase.h +701 -0
- data/vendor/Eigen/src/Core/DenseCoeffsBase.h +685 -0
- data/vendor/Eigen/src/Core/DenseStorage.h +652 -0
- data/vendor/Eigen/src/Core/Diagonal.h +258 -0
- data/vendor/Eigen/src/Core/DiagonalMatrix.h +391 -0
- data/vendor/Eigen/src/Core/DiagonalProduct.h +28 -0
- data/vendor/Eigen/src/Core/Dot.h +318 -0
- data/vendor/Eigen/src/Core/EigenBase.h +160 -0
- data/vendor/Eigen/src/Core/ForceAlignedAccess.h +150 -0
- data/vendor/Eigen/src/Core/Fuzzy.h +155 -0
- data/vendor/Eigen/src/Core/GeneralProduct.h +465 -0
- data/vendor/Eigen/src/Core/GenericPacketMath.h +1040 -0
- data/vendor/Eigen/src/Core/GlobalFunctions.h +194 -0
- data/vendor/Eigen/src/Core/IO.h +258 -0
- data/vendor/Eigen/src/Core/IndexedView.h +237 -0
- data/vendor/Eigen/src/Core/Inverse.h +117 -0
- data/vendor/Eigen/src/Core/Map.h +171 -0
- data/vendor/Eigen/src/Core/MapBase.h +310 -0
- data/vendor/Eigen/src/Core/MathFunctions.h +2057 -0
- data/vendor/Eigen/src/Core/MathFunctionsImpl.h +200 -0
- data/vendor/Eigen/src/Core/Matrix.h +565 -0
- data/vendor/Eigen/src/Core/MatrixBase.h +547 -0
- data/vendor/Eigen/src/Core/NestByValue.h +85 -0
- data/vendor/Eigen/src/Core/NoAlias.h +109 -0
- data/vendor/Eigen/src/Core/NumTraits.h +335 -0
- data/vendor/Eigen/src/Core/PartialReduxEvaluator.h +232 -0
- data/vendor/Eigen/src/Core/PermutationMatrix.h +605 -0
- data/vendor/Eigen/src/Core/PlainObjectBase.h +1128 -0
- data/vendor/Eigen/src/Core/Product.h +191 -0
- data/vendor/Eigen/src/Core/ProductEvaluators.h +1179 -0
- data/vendor/Eigen/src/Core/Random.h +218 -0
- data/vendor/Eigen/src/Core/Redux.h +515 -0
- data/vendor/Eigen/src/Core/Ref.h +381 -0
- data/vendor/Eigen/src/Core/Replicate.h +142 -0
- data/vendor/Eigen/src/Core/Reshaped.h +454 -0
- data/vendor/Eigen/src/Core/ReturnByValue.h +119 -0
- data/vendor/Eigen/src/Core/Reverse.h +217 -0
- data/vendor/Eigen/src/Core/Select.h +164 -0
- data/vendor/Eigen/src/Core/SelfAdjointView.h +365 -0
- data/vendor/Eigen/src/Core/SelfCwiseBinaryOp.h +47 -0
- data/vendor/Eigen/src/Core/Solve.h +188 -0
- data/vendor/Eigen/src/Core/SolveTriangular.h +235 -0
- data/vendor/Eigen/src/Core/SolverBase.h +168 -0
- data/vendor/Eigen/src/Core/StableNorm.h +251 -0
- data/vendor/Eigen/src/Core/StlIterators.h +463 -0
- data/vendor/Eigen/src/Core/Stride.h +116 -0
- data/vendor/Eigen/src/Core/Swap.h +68 -0
- data/vendor/Eigen/src/Core/Transpose.h +464 -0
- data/vendor/Eigen/src/Core/Transpositions.h +386 -0
- data/vendor/Eigen/src/Core/TriangularMatrix.h +1001 -0
- data/vendor/Eigen/src/Core/VectorBlock.h +96 -0
- data/vendor/Eigen/src/Core/VectorwiseOp.h +784 -0
- data/vendor/Eigen/src/Core/Visitor.h +381 -0
- data/vendor/Eigen/src/Core/arch/AVX/Complex.h +372 -0
- data/vendor/Eigen/src/Core/arch/AVX/MathFunctions.h +228 -0
- data/vendor/Eigen/src/Core/arch/AVX/PacketMath.h +1574 -0
- data/vendor/Eigen/src/Core/arch/AVX/TypeCasting.h +115 -0
- data/vendor/Eigen/src/Core/arch/AVX512/Complex.h +422 -0
- data/vendor/Eigen/src/Core/arch/AVX512/MathFunctions.h +362 -0
- data/vendor/Eigen/src/Core/arch/AVX512/PacketMath.h +2303 -0
- data/vendor/Eigen/src/Core/arch/AVX512/TypeCasting.h +89 -0
- data/vendor/Eigen/src/Core/arch/AltiVec/Complex.h +417 -0
- data/vendor/Eigen/src/Core/arch/AltiVec/MathFunctions.h +90 -0
- data/vendor/Eigen/src/Core/arch/AltiVec/MatrixProduct.h +2937 -0
- data/vendor/Eigen/src/Core/arch/AltiVec/MatrixProductCommon.h +221 -0
- data/vendor/Eigen/src/Core/arch/AltiVec/MatrixProductMMA.h +629 -0
- data/vendor/Eigen/src/Core/arch/AltiVec/PacketMath.h +2711 -0
- data/vendor/Eigen/src/Core/arch/CUDA/Complex.h +258 -0
- data/vendor/Eigen/src/Core/arch/Default/BFloat16.h +700 -0
- data/vendor/Eigen/src/Core/arch/Default/ConjHelper.h +117 -0
- data/vendor/Eigen/src/Core/arch/Default/GenericPacketMathFunctions.h +1649 -0
- data/vendor/Eigen/src/Core/arch/Default/GenericPacketMathFunctionsFwd.h +110 -0
- data/vendor/Eigen/src/Core/arch/Default/Half.h +942 -0
- data/vendor/Eigen/src/Core/arch/Default/Settings.h +49 -0
- data/vendor/Eigen/src/Core/arch/Default/TypeCasting.h +120 -0
- data/vendor/Eigen/src/Core/arch/GPU/MathFunctions.h +103 -0
- data/vendor/Eigen/src/Core/arch/GPU/PacketMath.h +1685 -0
- data/vendor/Eigen/src/Core/arch/GPU/TypeCasting.h +80 -0
- data/vendor/Eigen/src/Core/arch/HIP/hcc/math_constants.h +23 -0
- data/vendor/Eigen/src/Core/arch/MSA/Complex.h +648 -0
- data/vendor/Eigen/src/Core/arch/MSA/MathFunctions.h +387 -0
- data/vendor/Eigen/src/Core/arch/MSA/PacketMath.h +1233 -0
- data/vendor/Eigen/src/Core/arch/NEON/Complex.h +584 -0
- data/vendor/Eigen/src/Core/arch/NEON/GeneralBlockPanelKernel.h +183 -0
- data/vendor/Eigen/src/Core/arch/NEON/MathFunctions.h +75 -0
- data/vendor/Eigen/src/Core/arch/NEON/PacketMath.h +4587 -0
- data/vendor/Eigen/src/Core/arch/NEON/TypeCasting.h +1419 -0
- data/vendor/Eigen/src/Core/arch/SSE/Complex.h +351 -0
- data/vendor/Eigen/src/Core/arch/SSE/MathFunctions.h +199 -0
- data/vendor/Eigen/src/Core/arch/SSE/PacketMath.h +1505 -0
- data/vendor/Eigen/src/Core/arch/SSE/TypeCasting.h +142 -0
- data/vendor/Eigen/src/Core/arch/SVE/MathFunctions.h +44 -0
- data/vendor/Eigen/src/Core/arch/SVE/PacketMath.h +752 -0
- data/vendor/Eigen/src/Core/arch/SVE/TypeCasting.h +49 -0
- data/vendor/Eigen/src/Core/arch/SYCL/InteropHeaders.h +232 -0
- data/vendor/Eigen/src/Core/arch/SYCL/MathFunctions.h +301 -0
- data/vendor/Eigen/src/Core/arch/SYCL/PacketMath.h +670 -0
- data/vendor/Eigen/src/Core/arch/SYCL/SyclMemoryModel.h +694 -0
- data/vendor/Eigen/src/Core/arch/SYCL/TypeCasting.h +85 -0
- data/vendor/Eigen/src/Core/arch/ZVector/Complex.h +426 -0
- data/vendor/Eigen/src/Core/arch/ZVector/MathFunctions.h +233 -0
- data/vendor/Eigen/src/Core/arch/ZVector/PacketMath.h +1060 -0
- data/vendor/Eigen/src/Core/functors/AssignmentFunctors.h +177 -0
- data/vendor/Eigen/src/Core/functors/BinaryFunctors.h +541 -0
- data/vendor/Eigen/src/Core/functors/NullaryFunctors.h +189 -0
- data/vendor/Eigen/src/Core/functors/StlFunctors.h +166 -0
- data/vendor/Eigen/src/Core/functors/TernaryFunctors.h +25 -0
- data/vendor/Eigen/src/Core/functors/UnaryFunctors.h +1131 -0
- data/vendor/Eigen/src/Core/products/GeneralBlockPanelKernel.h +2645 -0
- data/vendor/Eigen/src/Core/products/GeneralMatrixMatrix.h +517 -0
- data/vendor/Eigen/src/Core/products/GeneralMatrixMatrixTriangular.h +317 -0
- data/vendor/Eigen/src/Core/products/GeneralMatrixMatrixTriangular_BLAS.h +145 -0
- data/vendor/Eigen/src/Core/products/GeneralMatrixMatrix_BLAS.h +124 -0
- data/vendor/Eigen/src/Core/products/GeneralMatrixVector.h +518 -0
- data/vendor/Eigen/src/Core/products/GeneralMatrixVector_BLAS.h +136 -0
- data/vendor/Eigen/src/Core/products/Parallelizer.h +180 -0
- data/vendor/Eigen/src/Core/products/SelfadjointMatrixMatrix.h +544 -0
- data/vendor/Eigen/src/Core/products/SelfadjointMatrixMatrix_BLAS.h +295 -0
- data/vendor/Eigen/src/Core/products/SelfadjointMatrixVector.h +262 -0
- data/vendor/Eigen/src/Core/products/SelfadjointMatrixVector_BLAS.h +118 -0
- data/vendor/Eigen/src/Core/products/SelfadjointProduct.h +133 -0
- data/vendor/Eigen/src/Core/products/SelfadjointRank2Update.h +94 -0
- data/vendor/Eigen/src/Core/products/TriangularMatrixMatrix.h +472 -0
- data/vendor/Eigen/src/Core/products/TriangularMatrixMatrix_BLAS.h +317 -0
- data/vendor/Eigen/src/Core/products/TriangularMatrixVector.h +350 -0
- data/vendor/Eigen/src/Core/products/TriangularMatrixVector_BLAS.h +255 -0
- data/vendor/Eigen/src/Core/products/TriangularSolverMatrix.h +337 -0
- data/vendor/Eigen/src/Core/products/TriangularSolverMatrix_BLAS.h +167 -0
- data/vendor/Eigen/src/Core/products/TriangularSolverVector.h +148 -0
- data/vendor/Eigen/src/Core/util/BlasUtil.h +583 -0
- data/vendor/Eigen/src/Core/util/ConfigureVectorization.h +512 -0
- data/vendor/Eigen/src/Core/util/Constants.h +563 -0
- data/vendor/Eigen/src/Core/util/DisableStupidWarnings.h +106 -0
- data/vendor/Eigen/src/Core/util/ForwardDeclarations.h +322 -0
- data/vendor/Eigen/src/Core/util/IndexedViewHelper.h +186 -0
- data/vendor/Eigen/src/Core/util/IntegralConstant.h +272 -0
- data/vendor/Eigen/src/Core/util/MKL_support.h +137 -0
- data/vendor/Eigen/src/Core/util/Macros.h +1464 -0
- data/vendor/Eigen/src/Core/util/Memory.h +1163 -0
- data/vendor/Eigen/src/Core/util/Meta.h +812 -0
- data/vendor/Eigen/src/Core/util/NonMPL2.h +3 -0
- data/vendor/Eigen/src/Core/util/ReenableStupidWarnings.h +31 -0
- data/vendor/Eigen/src/Core/util/ReshapedHelper.h +51 -0
- data/vendor/Eigen/src/Core/util/StaticAssert.h +221 -0
- data/vendor/Eigen/src/Core/util/SymbolicIndex.h +293 -0
- data/vendor/Eigen/src/Core/util/XprHelper.h +856 -0
- data/vendor/Eigen/src/Eigenvalues/ComplexEigenSolver.h +346 -0
- data/vendor/Eigen/src/Eigenvalues/ComplexSchur.h +462 -0
- data/vendor/Eigen/src/Eigenvalues/ComplexSchur_LAPACKE.h +91 -0
- data/vendor/Eigen/src/Eigenvalues/EigenSolver.h +622 -0
- data/vendor/Eigen/src/Eigenvalues/GeneralizedEigenSolver.h +418 -0
- data/vendor/Eigen/src/Eigenvalues/GeneralizedSelfAdjointEigenSolver.h +226 -0
- data/vendor/Eigen/src/Eigenvalues/HessenbergDecomposition.h +374 -0
- data/vendor/Eigen/src/Eigenvalues/MatrixBaseEigenvalues.h +158 -0
- data/vendor/Eigen/src/Eigenvalues/RealQZ.h +657 -0
- data/vendor/Eigen/src/Eigenvalues/RealSchur.h +558 -0
- data/vendor/Eigen/src/Eigenvalues/RealSchur_LAPACKE.h +77 -0
- data/vendor/Eigen/src/Eigenvalues/SelfAdjointEigenSolver.h +904 -0
- data/vendor/Eigen/src/Eigenvalues/SelfAdjointEigenSolver_LAPACKE.h +87 -0
- data/vendor/Eigen/src/Eigenvalues/Tridiagonalization.h +561 -0
- data/vendor/Eigen/src/Geometry/AlignedBox.h +486 -0
- data/vendor/Eigen/src/Geometry/AngleAxis.h +247 -0
- data/vendor/Eigen/src/Geometry/EulerAngles.h +114 -0
- data/vendor/Eigen/src/Geometry/Homogeneous.h +501 -0
- data/vendor/Eigen/src/Geometry/Hyperplane.h +282 -0
- data/vendor/Eigen/src/Geometry/OrthoMethods.h +235 -0
- data/vendor/Eigen/src/Geometry/ParametrizedLine.h +232 -0
- data/vendor/Eigen/src/Geometry/Quaternion.h +870 -0
- data/vendor/Eigen/src/Geometry/Rotation2D.h +199 -0
- data/vendor/Eigen/src/Geometry/RotationBase.h +206 -0
- data/vendor/Eigen/src/Geometry/Scaling.h +188 -0
- data/vendor/Eigen/src/Geometry/Transform.h +1563 -0
- data/vendor/Eigen/src/Geometry/Translation.h +202 -0
- data/vendor/Eigen/src/Geometry/Umeyama.h +166 -0
- data/vendor/Eigen/src/Geometry/arch/Geometry_SIMD.h +168 -0
- data/vendor/Eigen/src/Householder/BlockHouseholder.h +110 -0
- data/vendor/Eigen/src/Householder/Householder.h +176 -0
- data/vendor/Eigen/src/Householder/HouseholderSequence.h +545 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/BasicPreconditioners.h +226 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/BiCGSTAB.h +212 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/ConjugateGradient.h +229 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/IncompleteCholesky.h +394 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/IncompleteLUT.h +453 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/IterativeSolverBase.h +444 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/LeastSquareConjugateGradient.h +198 -0
- data/vendor/Eigen/src/IterativeLinearSolvers/SolveWithGuess.h +117 -0
- data/vendor/Eigen/src/Jacobi/Jacobi.h +483 -0
- data/vendor/Eigen/src/KLUSupport/KLUSupport.h +358 -0
- data/vendor/Eigen/src/LU/Determinant.h +117 -0
- data/vendor/Eigen/src/LU/FullPivLU.h +877 -0
- data/vendor/Eigen/src/LU/InverseImpl.h +432 -0
- data/vendor/Eigen/src/LU/PartialPivLU.h +624 -0
- data/vendor/Eigen/src/LU/PartialPivLU_LAPACKE.h +83 -0
- data/vendor/Eigen/src/LU/arch/InverseSize4.h +351 -0
- data/vendor/Eigen/src/MetisSupport/MetisSupport.h +137 -0
- data/vendor/Eigen/src/OrderingMethods/Amd.h +435 -0
- data/vendor/Eigen/src/OrderingMethods/Eigen_Colamd.h +1863 -0
- data/vendor/Eigen/src/OrderingMethods/Ordering.h +153 -0
- data/vendor/Eigen/src/PaStiXSupport/PaStiXSupport.h +678 -0
- data/vendor/Eigen/src/PardisoSupport/PardisoSupport.h +545 -0
- data/vendor/Eigen/src/QR/ColPivHouseholderQR.h +674 -0
- data/vendor/Eigen/src/QR/ColPivHouseholderQR_LAPACKE.h +97 -0
- data/vendor/Eigen/src/QR/CompleteOrthogonalDecomposition.h +635 -0
- data/vendor/Eigen/src/QR/FullPivHouseholderQR.h +713 -0
- data/vendor/Eigen/src/QR/HouseholderQR.h +434 -0
- data/vendor/Eigen/src/QR/HouseholderQR_LAPACKE.h +68 -0
- data/vendor/Eigen/src/SPQRSupport/SuiteSparseQRSupport.h +335 -0
- data/vendor/Eigen/src/SVD/BDCSVD.h +1366 -0
- data/vendor/Eigen/src/SVD/JacobiSVD.h +812 -0
- data/vendor/Eigen/src/SVD/JacobiSVD_LAPACKE.h +91 -0
- data/vendor/Eigen/src/SVD/SVDBase.h +376 -0
- data/vendor/Eigen/src/SVD/UpperBidiagonalization.h +414 -0
- data/vendor/Eigen/src/SparseCholesky/SimplicialCholesky.h +697 -0
- data/vendor/Eigen/src/SparseCholesky/SimplicialCholesky_impl.h +174 -0
- data/vendor/Eigen/src/SparseCore/AmbiVector.h +378 -0
- data/vendor/Eigen/src/SparseCore/CompressedStorage.h +274 -0
- data/vendor/Eigen/src/SparseCore/ConservativeSparseSparseProduct.h +352 -0
- data/vendor/Eigen/src/SparseCore/MappedSparseMatrix.h +67 -0
- data/vendor/Eigen/src/SparseCore/SparseAssign.h +270 -0
- data/vendor/Eigen/src/SparseCore/SparseBlock.h +571 -0
- data/vendor/Eigen/src/SparseCore/SparseColEtree.h +206 -0
- data/vendor/Eigen/src/SparseCore/SparseCompressedBase.h +370 -0
- data/vendor/Eigen/src/SparseCore/SparseCwiseBinaryOp.h +722 -0
- data/vendor/Eigen/src/SparseCore/SparseCwiseUnaryOp.h +150 -0
- data/vendor/Eigen/src/SparseCore/SparseDenseProduct.h +342 -0
- data/vendor/Eigen/src/SparseCore/SparseDiagonalProduct.h +138 -0
- data/vendor/Eigen/src/SparseCore/SparseDot.h +98 -0
- data/vendor/Eigen/src/SparseCore/SparseFuzzy.h +29 -0
- data/vendor/Eigen/src/SparseCore/SparseMap.h +305 -0
- data/vendor/Eigen/src/SparseCore/SparseMatrix.h +1518 -0
- data/vendor/Eigen/src/SparseCore/SparseMatrixBase.h +398 -0
- data/vendor/Eigen/src/SparseCore/SparsePermutation.h +178 -0
- data/vendor/Eigen/src/SparseCore/SparseProduct.h +181 -0
- data/vendor/Eigen/src/SparseCore/SparseRedux.h +49 -0
- data/vendor/Eigen/src/SparseCore/SparseRef.h +397 -0
- data/vendor/Eigen/src/SparseCore/SparseSelfAdjointView.h +659 -0
- data/vendor/Eigen/src/SparseCore/SparseSolverBase.h +124 -0
- data/vendor/Eigen/src/SparseCore/SparseSparseProductWithPruning.h +198 -0
- data/vendor/Eigen/src/SparseCore/SparseTranspose.h +92 -0
- data/vendor/Eigen/src/SparseCore/SparseTriangularView.h +189 -0
- data/vendor/Eigen/src/SparseCore/SparseUtil.h +186 -0
- data/vendor/Eigen/src/SparseCore/SparseVector.h +478 -0
- data/vendor/Eigen/src/SparseCore/SparseView.h +254 -0
- data/vendor/Eigen/src/SparseCore/TriangularSolver.h +315 -0
- data/vendor/Eigen/src/SparseLU/SparseLU.h +923 -0
- data/vendor/Eigen/src/SparseLU/SparseLUImpl.h +66 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_Memory.h +226 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_Structs.h +110 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_SupernodalMatrix.h +375 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_Utils.h +80 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_column_bmod.h +181 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_column_dfs.h +179 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_copy_to_ucol.h +107 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_gemm_kernel.h +280 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_heap_relax_snode.h +126 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_kernel_bmod.h +130 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_panel_bmod.h +223 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_panel_dfs.h +258 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_pivotL.h +137 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_pruneL.h +136 -0
- data/vendor/Eigen/src/SparseLU/SparseLU_relax_snode.h +83 -0
- data/vendor/Eigen/src/SparseQR/SparseQR.h +758 -0
- data/vendor/Eigen/src/StlSupport/StdDeque.h +116 -0
- data/vendor/Eigen/src/StlSupport/StdList.h +106 -0
- data/vendor/Eigen/src/StlSupport/StdVector.h +131 -0
- data/vendor/Eigen/src/StlSupport/details.h +84 -0
- data/vendor/Eigen/src/SuperLUSupport/SuperLUSupport.h +1025 -0
- data/vendor/Eigen/src/UmfPackSupport/UmfPackSupport.h +642 -0
- data/vendor/Eigen/src/misc/Image.h +82 -0
- data/vendor/Eigen/src/misc/Kernel.h +79 -0
- data/vendor/Eigen/src/misc/RealSvd2x2.h +55 -0
- data/vendor/Eigen/src/misc/blas.h +440 -0
- data/vendor/Eigen/src/misc/lapack.h +152 -0
- data/vendor/Eigen/src/misc/lapacke.h +16292 -0
- data/vendor/Eigen/src/misc/lapacke_mangling.h +17 -0
- data/vendor/Eigen/src/plugins/ArrayCwiseBinaryOps.h +358 -0
- data/vendor/Eigen/src/plugins/ArrayCwiseUnaryOps.h +696 -0
- data/vendor/Eigen/src/plugins/BlockMethods.h +1442 -0
- data/vendor/Eigen/src/plugins/CommonCwiseBinaryOps.h +115 -0
- data/vendor/Eigen/src/plugins/CommonCwiseUnaryOps.h +177 -0
- data/vendor/Eigen/src/plugins/IndexedViewMethods.h +262 -0
- data/vendor/Eigen/src/plugins/MatrixCwiseBinaryOps.h +152 -0
- data/vendor/Eigen/src/plugins/MatrixCwiseUnaryOps.h +95 -0
- data/vendor/Eigen/src/plugins/ReshapedMethods.h +149 -0
- data/vendor/aarand/aarand.hpp +114 -0
- data/vendor/annoy/annoylib.h +1495 -0
- data/vendor/annoy/kissrandom.h +120 -0
- data/vendor/annoy/mman.h +242 -0
- data/vendor/hnswlib/bruteforce.h +152 -0
- data/vendor/hnswlib/hnswalg.h +1192 -0
- data/vendor/hnswlib/hnswlib.h +108 -0
- data/vendor/hnswlib/space_ip.h +282 -0
- data/vendor/hnswlib/space_l2.h +281 -0
- data/vendor/hnswlib/visited_list_pool.h +79 -0
- data/vendor/irlba/irlba.hpp +575 -0
- data/vendor/irlba/lanczos.hpp +212 -0
- data/vendor/irlba/parallel.hpp +474 -0
- data/vendor/irlba/utils.hpp +224 -0
- data/vendor/irlba/wrappers.hpp +228 -0
- data/vendor/kmeans/Base.hpp +75 -0
- data/vendor/kmeans/Details.hpp +79 -0
- data/vendor/kmeans/HartiganWong.hpp +492 -0
- data/vendor/kmeans/InitializeKmeansPP.hpp +144 -0
- data/vendor/kmeans/InitializeNone.hpp +44 -0
- data/vendor/kmeans/InitializePCAPartition.hpp +309 -0
- data/vendor/kmeans/InitializeRandom.hpp +91 -0
- data/vendor/kmeans/Kmeans.hpp +161 -0
- data/vendor/kmeans/Lloyd.hpp +134 -0
- data/vendor/kmeans/MiniBatch.hpp +269 -0
- data/vendor/kmeans/QuickSearch.hpp +179 -0
- data/vendor/kmeans/compute_centroids.hpp +32 -0
- data/vendor/kmeans/compute_wcss.hpp +27 -0
- data/vendor/kmeans/is_edge_case.hpp +42 -0
- data/vendor/kmeans/random.hpp +55 -0
- data/vendor/knncolle/Annoy/Annoy.hpp +193 -0
- data/vendor/knncolle/BruteForce/BruteForce.hpp +120 -0
- data/vendor/knncolle/Hnsw/Hnsw.hpp +225 -0
- data/vendor/knncolle/Kmknn/Kmknn.hpp +286 -0
- data/vendor/knncolle/VpTree/VpTree.hpp +256 -0
- data/vendor/knncolle/knncolle.hpp +34 -0
- data/vendor/knncolle/utils/Base.hpp +100 -0
- data/vendor/knncolle/utils/NeighborQueue.hpp +94 -0
- data/vendor/knncolle/utils/distances.hpp +98 -0
- data/vendor/knncolle/utils/find_nearest_neighbors.hpp +112 -0
- data/vendor/powerit/PowerIterations.hpp +157 -0
- data/vendor/umappp/NeighborList.hpp +37 -0
- data/vendor/umappp/Umap.hpp +662 -0
- data/vendor/umappp/combine_neighbor_sets.hpp +95 -0
- data/vendor/umappp/find_ab.hpp +157 -0
- data/vendor/umappp/neighbor_similarities.hpp +136 -0
- data/vendor/umappp/optimize_layout.hpp +285 -0
- data/vendor/umappp/spectral_init.hpp +181 -0
- data/vendor/umappp/umappp.hpp +13 -0
- metadata +465 -0
@@ -0,0 +1,309 @@
|
|
1
|
+
#ifndef KMEANS_INITIALIZE_PCA_PARTITION_HPP
|
2
|
+
#define KMEANS_INITIALIZE_PCA_PARTITION_HPP
|
3
|
+
|
4
|
+
#include <iostream>
|
5
|
+
#include <random>
|
6
|
+
#include <vector>
|
7
|
+
#include <cmath>
|
8
|
+
#include <algorithm>
|
9
|
+
#include <numeric>
|
10
|
+
|
11
|
+
#include "aarand/aarand.hpp"
|
12
|
+
#include "powerit/PowerIterations.hpp"
|
13
|
+
#include "Base.hpp"
|
14
|
+
|
15
|
+
/**
|
16
|
+
* @file InitializePCAPartition.hpp
|
17
|
+
*
|
18
|
+
* @brief Class for k-means initialization with PCA partitioning.
|
19
|
+
*/
|
20
|
+
namespace kmeans {
|
21
|
+
|
22
|
+
/**
|
23
|
+
* @brief Implements the PCA partitioning method of Su and Dy (2007).
|
24
|
+
*
|
25
|
+
* This approach involves the selection of starting points via iterative partitioning based on principal components analysis.
|
26
|
+
* The aim is to obtain well-separated starting points for refinement with algorithms like Hartigan-Wong or Lloyd.
|
27
|
+
* This is achieved by selecting the most dispersed cluster for further partitioning.
|
28
|
+
*
|
29
|
+
* We start from a single cluster containing all points.
|
30
|
+
* At each iteration, we select the cluster with the largest within-cluster sum of squares (WCSS);
|
31
|
+
* we identify the first principal component within that cluster;
|
32
|
+
* and we split the cluster at its center along that axis to obtain two new clusters.
|
33
|
+
* This is repeated until the desired number of clusters is obtained, and the centers and cluster identifiers are then reported.
|
34
|
+
*
|
35
|
+
* The original algorithm favors selection and partitioning of the largest cluster, which has the greatest chance of having the highest WCSS.
|
36
|
+
* For more fine-grained control, we modify the procedure to adjust the effective number of observations contributing to the WCSS.
|
37
|
+
* Specifically, we choose the cluster to partition based on the product of $N$ and the mean squared difference within each cluster,
|
38
|
+
* where $N$ is the cluster size raised to some user-specified power (i.e., the "size adjustment") between 0 and 1.
|
39
|
+
* An adjustment of 1 recapitulates the original algorithm, while smaller values of the size adjustment will reduce the preference towards larger clusters.
|
40
|
+
* A value of zero means that the cluster size is completely ignored, though this seems unwise as it causes excessive splitting of small clusters with unstable WCSS.
|
41
|
+
*
|
42
|
+
* This method is not completely deterministic as a randomization step is used in the PCA.
|
43
|
+
* Nonetheless, the stochasticity is likely to have a much smaller effect than in the other initialization methods.
|
44
|
+
*
|
45
|
+
* @tparam DATA_t Floating-point type for the data and centroids.
|
46
|
+
* @tparam CLUSTER_t Integer type for the cluster index.
|
47
|
+
* @tparam INDEX_t Integer type for the observation index.
|
48
|
+
*
|
49
|
+
* @seealso
|
50
|
+
* Su, T. and Dy, J. G. (2007).
|
51
|
+
* In Search of Deterministic Methods for Initializing K-Means and Gaussian Mixture Clustering,
|
52
|
+
* _Intelligent Data Analysis_ 11, 319-338.
|
53
|
+
*/
|
54
|
+
template<typename DATA_t = double, typename CLUSTER_t = int, typename INDEX_t = int>
|
55
|
+
class InitializePCAPartition : public Initialize<DATA_t, CLUSTER_t, INDEX_t> {
|
56
|
+
public:
|
57
|
+
/**
|
58
|
+
* @brief Default parameter settings.
|
59
|
+
*/
|
60
|
+
struct Defaults {
|
61
|
+
/**
|
62
|
+
* See `set_size_adjustment()` for more details.
|
63
|
+
*/
|
64
|
+
static constexpr DATA_t size_adjustment = 1;
|
65
|
+
|
66
|
+
/**
|
67
|
+
* See `set_seed()` for more details.
|
68
|
+
*/
|
69
|
+
static constexpr uint64_t seed = 6523u;
|
70
|
+
};
|
71
|
+
|
72
|
+
public:
|
73
|
+
/**
|
74
|
+
* @param i Maximum number of power iterations to use in `powerit::PowerIterations::set_iterations()`.
|
75
|
+
* @return A reference to this `InitializePCAPartition` object.
|
76
|
+
*/
|
77
|
+
InitializePCAPartition& set_iterations(int i = powerit::PowerIterations::Defaults::iterations) {
|
78
|
+
iters = i;
|
79
|
+
return *this;
|
80
|
+
}
|
81
|
+
|
82
|
+
/**
|
83
|
+
* @param t Convergence threshold to use in `powerit::PowerIterations::set_tolerance()`.
|
84
|
+
* @return A reference to this `InitializePCAPartition` object.
|
85
|
+
*/
|
86
|
+
InitializePCAPartition& set_tolerance(DATA_t t = powerit::PowerIterations::Defaults::tolerance) {
|
87
|
+
tol = t;
|
88
|
+
return *this;
|
89
|
+
}
|
90
|
+
|
91
|
+
/**
|
92
|
+
* @param s Size adjustment value, should lie in [0, 1].
|
93
|
+
* @return A reference to this `InitializePCAPartition` object.
|
94
|
+
*/
|
95
|
+
InitializePCAPartition& set_size_adjustment(DATA_t s = Defaults::size_adjustment) {
|
96
|
+
adjust = s;
|
97
|
+
return *this;
|
98
|
+
}
|
99
|
+
|
100
|
+
/**
|
101
|
+
* @param Random seed to use to construct the PRNG for the power method.
|
102
|
+
* @return A reference to this `InitializePCAPartition` object.
|
103
|
+
*/
|
104
|
+
InitializePCAPartition& set_seed(uint64_t s = Defaults::seed) {
|
105
|
+
seed = s;
|
106
|
+
return *this;
|
107
|
+
}
|
108
|
+
private:
|
109
|
+
int iters = powerit::PowerIterations::Defaults::iterations;
|
110
|
+
DATA_t tol = powerit::PowerIterations::Defaults::tolerance;
|
111
|
+
DATA_t adjust = Defaults::size_adjustment;
|
112
|
+
uint64_t seed = Defaults::seed;
|
113
|
+
|
114
|
+
public:
|
115
|
+
/**
|
116
|
+
* @cond
|
117
|
+
*/
|
118
|
+
static DATA_t normalize(int ndim, DATA_t* x) {
|
119
|
+
DATA_t ss = 0;
|
120
|
+
for (int d = 0; d < ndim; ++d) {
|
121
|
+
ss += x[d] * x[d];
|
122
|
+
}
|
123
|
+
|
124
|
+
if (ss) {
|
125
|
+
ss = std::sqrt(ss);
|
126
|
+
for (int d = 0; d < ndim; ++d) {
|
127
|
+
x[d] /= ss;
|
128
|
+
}
|
129
|
+
}
|
130
|
+
return ss;
|
131
|
+
}
|
132
|
+
|
133
|
+
template<class Rng>
|
134
|
+
std::vector<DATA_t> compute_pc1(int ndim, const std::vector<INDEX_t>& chosen, const DATA_t* data, const DATA_t* center, Rng& eng) const {
|
135
|
+
std::vector<DATA_t> delta(ndim);
|
136
|
+
std::vector<DATA_t> cov(ndim * ndim);
|
137
|
+
|
138
|
+
// Computing the lower triangle of the covariance matrix.
|
139
|
+
for (auto i : chosen) {
|
140
|
+
auto dptr = data + i * ndim;
|
141
|
+
for (int j = 0; j < ndim; ++j) {
|
142
|
+
delta[j] = dptr[j] - center[j];
|
143
|
+
}
|
144
|
+
for (int j = 0; j < ndim; ++j) {
|
145
|
+
for (int k = 0; k <= j; ++k) {
|
146
|
+
cov[j * ndim + k] += delta[j] * delta[k];
|
147
|
+
}
|
148
|
+
}
|
149
|
+
}
|
150
|
+
|
151
|
+
// Filling in the other side of the matrix, to enable cache-efficient multiplication.
|
152
|
+
for (size_t j = 0; j < ndim; ++j) {
|
153
|
+
for (size_t k = j + 1; k < ndim; ++k) {
|
154
|
+
cov[j * ndim + k] = cov[k * ndim + j];
|
155
|
+
}
|
156
|
+
}
|
157
|
+
|
158
|
+
powerit::PowerIterations power;
|
159
|
+
power.set_iterations(iters).set_tolerance(tol);
|
160
|
+
|
161
|
+
std::vector<DATA_t> output(ndim);
|
162
|
+
power.run(ndim, cov.data(), output.data(), eng);
|
163
|
+
return output;
|
164
|
+
}
|
165
|
+
|
166
|
+
static void compute_center(int ndim, INDEX_t nobs, const DATA_t* data, DATA_t* center) {
|
167
|
+
std::fill(center, center + ndim, 0);
|
168
|
+
for (size_t i = 0; i < nobs; ++i) {
|
169
|
+
auto dptr = data + i * ndim;
|
170
|
+
for (int d = 0; d < ndim; ++d) {
|
171
|
+
center[d] += dptr[d];
|
172
|
+
}
|
173
|
+
}
|
174
|
+
for (int d = 0; d < ndim; ++d) {
|
175
|
+
center[d] /= nobs;
|
176
|
+
}
|
177
|
+
}
|
178
|
+
|
179
|
+
static void compute_center(int ndim, const std::vector<INDEX_t>& chosen, const DATA_t* data, DATA_t* center) {
|
180
|
+
std::fill(center, center + ndim, 0);
|
181
|
+
for (auto i : chosen) {
|
182
|
+
auto dptr = data + i * ndim;
|
183
|
+
for (int d = 0; d < ndim; ++d) {
|
184
|
+
center[d] += dptr[d];
|
185
|
+
}
|
186
|
+
}
|
187
|
+
for (int d = 0; d < ndim; ++d) {
|
188
|
+
center[d] /= chosen.size();
|
189
|
+
}
|
190
|
+
}
|
191
|
+
|
192
|
+
static DATA_t update_mrse(int ndim, const std::vector<INDEX_t>& chosen, const DATA_t* data, DATA_t* center) {
|
193
|
+
compute_center(ndim, chosen, data, center);
|
194
|
+
|
195
|
+
DATA_t curmrse = 0;
|
196
|
+
for (auto i : chosen) {
|
197
|
+
auto dptr = data + i * ndim;
|
198
|
+
for (int d = 0; d < ndim; ++d) {
|
199
|
+
DATA_t delta = dptr[d] - center[d];
|
200
|
+
curmrse += delta * delta;
|
201
|
+
}
|
202
|
+
}
|
203
|
+
|
204
|
+
return curmrse / chosen.size();
|
205
|
+
}
|
206
|
+
/**
|
207
|
+
* @endcond
|
208
|
+
*/
|
209
|
+
public:
|
210
|
+
/*
|
211
|
+
* @param ndim Number of dimensions.
|
212
|
+
* @param nobs Number of observations.
|
213
|
+
* @param data Pointer to an array where the dimensions are rows and the observations are columns.
|
214
|
+
* Data should be stored in column-major format.
|
215
|
+
* @param ncenters Number of centers to pick.
|
216
|
+
* @param[out] centers Pointer to a `ndim`-by-`ncenters` array where columns are cluster centers and rows are dimensions.
|
217
|
+
* On output, this will contain the final centroid locations for each cluster.
|
218
|
+
* Data should be stored in column-major order.
|
219
|
+
* @param clusters Pointer to an array of length `nobs`.
|
220
|
+
* This is used as a buffer and the contents on output should not be used.
|
221
|
+
*
|
222
|
+
* @return `centers` is filled with the new cluster centers.
|
223
|
+
* The number of filled centers is returned, see `Initializer::run()`.
|
224
|
+
*/
|
225
|
+
CLUSTER_t run(int ndim, INDEX_t nobs, const DATA_t* data, CLUSTER_t ncenters, DATA_t* centers, CLUSTER_t* clusters) {
|
226
|
+
if (nobs == 0) {
|
227
|
+
return 0;
|
228
|
+
}
|
229
|
+
|
230
|
+
std::mt19937_64 rng(seed);
|
231
|
+
std::vector<DATA_t> mrse(ncenters);
|
232
|
+
std::vector<std::vector<INDEX_t> > assignments(ncenters);
|
233
|
+
|
234
|
+
// Setting up the zero'th cluster. (No need to actually compute the
|
235
|
+
// MRSE at this point, as there's nothing to compare it to.)
|
236
|
+
compute_center(ndim, nobs, data, centers);
|
237
|
+
assignments[0].resize(nobs);
|
238
|
+
std::iota(assignments.front().begin(), assignments.front().end(), 0);
|
239
|
+
std::fill(clusters, clusters + nobs, 0);
|
240
|
+
|
241
|
+
for (CLUSTER_t cluster = 1; cluster < ncenters; ++cluster) {
|
242
|
+
DATA_t worst_ss = 0;
|
243
|
+
INDEX_t worst_cluster = 0;
|
244
|
+
for (CLUSTER_t i = 0; i < cluster; ++i) {
|
245
|
+
DATA_t multiplier = assignments[i].size();
|
246
|
+
if (adjust != 1) {
|
247
|
+
multiplier = std::pow(static_cast<DATA_t>(multiplier), adjust);
|
248
|
+
}
|
249
|
+
|
250
|
+
DATA_t pseudo_ss = mrse[i] * multiplier;
|
251
|
+
if (pseudo_ss > worst_ss) {
|
252
|
+
worst_ss = pseudo_ss;
|
253
|
+
worst_cluster = i;
|
254
|
+
}
|
255
|
+
}
|
256
|
+
|
257
|
+
// Extracting the principal component for this bad boy.
|
258
|
+
auto worst_center = centers + worst_cluster * ndim;
|
259
|
+
auto& worst_assignments = assignments[worst_cluster];
|
260
|
+
auto pc1 = compute_pc1(ndim, worst_assignments, data, worst_center, rng);
|
261
|
+
|
262
|
+
// Projecting all points in this cluster along PC1. The center lies
|
263
|
+
// at zero, so everything positive (on one side of the hyperplane
|
264
|
+
// orthogonal to PC1 and passing through the center) gets bumped to
|
265
|
+
// the next cluster.
|
266
|
+
std::vector<INDEX_t>& new_assignments = assignments[cluster];
|
267
|
+
std::vector<INDEX_t> worst_assignments2;
|
268
|
+
for (auto i : worst_assignments) {
|
269
|
+
auto dptr = data + i * ndim;
|
270
|
+
DATA_t proj = 0;
|
271
|
+
for (int d = 0; d < ndim; ++d) {
|
272
|
+
proj += (dptr[d] - worst_center[d]) * pc1[d];
|
273
|
+
}
|
274
|
+
|
275
|
+
if (proj > 0) {
|
276
|
+
new_assignments.push_back(i);
|
277
|
+
} else {
|
278
|
+
worst_assignments2.push_back(i);
|
279
|
+
}
|
280
|
+
}
|
281
|
+
|
282
|
+
// If one or the other is empty, then this entire procedure short
|
283
|
+
// circuits as all future iterations will just re-select this
|
284
|
+
// cluster (which won't get partitioned properly anyway). In the
|
285
|
+
// bigger picture, the quick exit out of the iterations is correct
|
286
|
+
// as we should only fail to partition in this manner if all points
|
287
|
+
// within each remaining cluster are identical.
|
288
|
+
if (new_assignments.empty() || worst_assignments2.empty()) {
|
289
|
+
return cluster;
|
290
|
+
}
|
291
|
+
|
292
|
+
for (auto i : new_assignments) {
|
293
|
+
clusters[i] = cluster;
|
294
|
+
}
|
295
|
+
worst_assignments.swap(worst_assignments2);
|
296
|
+
|
297
|
+
// Computing centers and MRSE.
|
298
|
+
auto new_center = centers + cluster * ndim;
|
299
|
+
mrse[cluster] = update_mrse(ndim, new_assignments, data, new_center);
|
300
|
+
mrse[worst_cluster] = update_mrse(ndim, worst_assignments, data, worst_center);
|
301
|
+
}
|
302
|
+
|
303
|
+
return ncenters;
|
304
|
+
}
|
305
|
+
};
|
306
|
+
|
307
|
+
}
|
308
|
+
|
309
|
+
#endif
|
@@ -0,0 +1,91 @@
|
|
1
|
+
#ifndef KMEANS_INITIALIZE_RANDOM_HPP
|
2
|
+
#define KMEANS_INITIALIZE_RANDOM_HPP
|
3
|
+
|
4
|
+
#include <algorithm>
|
5
|
+
#include <cstdint>
|
6
|
+
#include <random>
|
7
|
+
|
8
|
+
#include "Base.hpp"
|
9
|
+
#include "random.hpp"
|
10
|
+
|
11
|
+
/**
|
12
|
+
* @file InitializeRandom.hpp
|
13
|
+
*
|
14
|
+
* @brief Class for random initialization.
|
15
|
+
*/
|
16
|
+
|
17
|
+
namespace kmeans {
|
18
|
+
|
19
|
+
/**
|
20
|
+
* @cond
|
21
|
+
*/
|
22
|
+
template<class V, typename DATA_t>
|
23
|
+
void copy_into_array(const V& chosen, int ndim, const DATA_t* in, DATA_t* out) {
|
24
|
+
for (auto c : chosen) {
|
25
|
+
auto ptr = in + c * ndim;
|
26
|
+
std::copy(ptr, ptr + ndim, out);
|
27
|
+
out += ndim;
|
28
|
+
}
|
29
|
+
return;
|
30
|
+
}
|
31
|
+
/**
|
32
|
+
* @endcond
|
33
|
+
*/
|
34
|
+
|
35
|
+
/**
|
36
|
+
* @brief Initialize starting points by sampling random observations without replacement.
|
37
|
+
*
|
38
|
+
* @tparam DATA_t Floating-point type for the data and centroids.
|
39
|
+
* @tparam CLUSTER_t Integer type for the cluster index.
|
40
|
+
* @tparam INDEX_t Integer type for the observation index.
|
41
|
+
*/
|
42
|
+
template<typename DATA_t = double, typename CLUSTER_t = int, typename INDEX_t = int>
|
43
|
+
class InitializeRandom : public Initialize<DATA_t, CLUSTER_t, INDEX_t> {
|
44
|
+
public:
|
45
|
+
/**
|
46
|
+
* @brief Default parameter settings.
|
47
|
+
*/
|
48
|
+
struct Defaults {
|
49
|
+
/**
|
50
|
+
* See `set_seed()` for more details.
|
51
|
+
*/
|
52
|
+
static constexpr uint64_t seed = 6523u;
|
53
|
+
};
|
54
|
+
|
55
|
+
/**
|
56
|
+
* @param Random seed to use to construct the PRNG prior to sampling.
|
57
|
+
*
|
58
|
+
* @return A reference to this `InitializeRandom` object.
|
59
|
+
*/
|
60
|
+
InitializeRandom& set_seed(uint64_t s = Defaults::seed) {
|
61
|
+
seed = s;
|
62
|
+
return *this;
|
63
|
+
}
|
64
|
+
private:
|
65
|
+
uint64_t seed = Defaults::seed;
|
66
|
+
public:
|
67
|
+
/*
|
68
|
+
* @param ndim Number of dimensions.
|
69
|
+
* @param nobs Number of observations.
|
70
|
+
* @param data Pointer to an array where the dimensions are rows and the observations are columns.
|
71
|
+
* Data should be stored in column-major format.
|
72
|
+
* @param ncenters Number of centers to pick.
|
73
|
+
* @param[out] centers Pointer to a `ndim`-by-`ncenters` array where columns are cluster centers and rows are dimensions.
|
74
|
+
* On output, this will contain the final centroid locations for each cluster.
|
75
|
+
* Data should be stored in column-major order.
|
76
|
+
* @param clusters Ignored in this method.
|
77
|
+
*
|
78
|
+
* @return `centers` is filled with the new cluster centers.
|
79
|
+
* The number of filled centers is returned, see `Initializer::run()`.
|
80
|
+
*/
|
81
|
+
CLUSTER_t run(int ndim, INDEX_t nobs, const DATA_t* data, CLUSTER_t ncenters, DATA_t* centers, CLUSTER_t* clusters) {
|
82
|
+
std::mt19937_64 eng(seed);
|
83
|
+
auto chosen = sample_without_replacement(nobs, ncenters, eng);
|
84
|
+
copy_into_array(chosen, ndim, data, centers);
|
85
|
+
return chosen.size();
|
86
|
+
}
|
87
|
+
};
|
88
|
+
|
89
|
+
}
|
90
|
+
|
91
|
+
#endif
|
@@ -0,0 +1,161 @@
|
|
1
|
+
#ifndef KMEANS_KMEANS_HPP
|
2
|
+
#define KMEANS_KMEANS_HPP
|
3
|
+
|
4
|
+
#include "Base.hpp"
|
5
|
+
#include "HartiganWong.hpp"
|
6
|
+
#include "InitializeKmeansPP.hpp"
|
7
|
+
#include "Details.hpp"
|
8
|
+
#include <random>
|
9
|
+
|
10
|
+
/**
|
11
|
+
* @file Kmeans.hpp
|
12
|
+
*
|
13
|
+
* @brief Implements the full k-means clustering procedure.
|
14
|
+
*/
|
15
|
+
|
16
|
+
namespace kmeans {
|
17
|
+
|
18
|
+
/**
|
19
|
+
* @brief Top-level class to run k-means clustering.
|
20
|
+
*
|
21
|
+
* k-means clustering aims to partition a dataset of `nobs` observations into `ncenters` clusters where `ncenters` is specified in advance.
|
22
|
+
* Each observation is assigned to its closest cluster based on the distance to the cluster centroids.
|
23
|
+
* The cluster centroids themselves are chosen to minimize the sum of squared Euclidean distances from each observation to its assigned cluster.
|
24
|
+
* This procedure involves some heuristics to choose a good initial set of centroids (see `weighted_initialization()` for details)
|
25
|
+
* and to converge to a local minimum (see `HartiganWong`, `Lloyd` or `MiniBatch` for details).
|
26
|
+
*
|
27
|
+
* @tparam DATA_t Floating-point type for the data and centroids.
|
28
|
+
* @tparam CLUSTER_t Integer type for the cluster assignments.
|
29
|
+
* @tparam INDEX_t Integer type for the observation index.
|
30
|
+
* This should have a maximum positive value that is at least 50 times greater than the maximum expected number of observations.
|
31
|
+
*/
|
32
|
+
template<typename DATA_t = double, typename CLUSTER_t = int, typename INDEX_t = int>
|
33
|
+
class Kmeans {
|
34
|
+
public:
|
35
|
+
/**
|
36
|
+
* @brief Default parameter values for `Kmeans`.
|
37
|
+
*/
|
38
|
+
struct Defaults {
|
39
|
+
/**
|
40
|
+
* See `set_seed()` for more details.
|
41
|
+
*/
|
42
|
+
static constexpr uint64_t seed = 5489u;
|
43
|
+
};
|
44
|
+
|
45
|
+
private:
|
46
|
+
uint64_t seed = Defaults::seed;
|
47
|
+
|
48
|
+
public:
|
49
|
+
/**
|
50
|
+
* @param s Seed to use for PRNG.
|
51
|
+
* Defaults to default seed for the `std::mt19937_64` constructor.
|
52
|
+
*
|
53
|
+
* @return A reference to this `Kmeans` object.
|
54
|
+
*
|
55
|
+
* This seed is only used for the default `refiner` and `initializer` instances in `run()`.
|
56
|
+
* Otherwise, the seed from individual instances is respected.
|
57
|
+
*/
|
58
|
+
Kmeans& set_seed(uint64_t s = 5489u) {
|
59
|
+
seed = s;
|
60
|
+
return *this;
|
61
|
+
}
|
62
|
+
|
63
|
+
public:
|
64
|
+
/**
|
65
|
+
* @param ndim Number of dimensions.
|
66
|
+
* @param nobs Number of observations.
|
67
|
+
* @param[in] data Pointer to a `ndim`-by-`nobs` array where columns are observations and rows are dimensions.
|
68
|
+
* Data should be stored in column-major order.
|
69
|
+
* @param ncenters Number of cluster centers.
|
70
|
+
* @param[in, out] centers Pointer to a `ndim`-by-`ncenters` array where columns are cluster centers and rows are dimensions.
|
71
|
+
* On input, this should contain the initial centroid locations for each cluster if `set_initialization_method()` is `NONE`, otherwise it is ignored.
|
72
|
+
* On output, this will contain the final centroid locations for each cluster.
|
73
|
+
* Data should be stored in column-major order.
|
74
|
+
* @param[in, out] clusters Pointer to an array of length `nobs`.
|
75
|
+
* On input, this should contain the identity of the closest cluster for each observation if `set_initialization_method()` is `REINIT_PRECOMPUTED`, otherwise it is ignored.
|
76
|
+
* On output, this will contain the (0-indexed) cluster assignment for each observation.
|
77
|
+
* @param initializer Pointer to a `Initialize` object containing the desired k-means initialization method, e.g., `InitializeNone`, `InitializeRandom`, `InitializeKmeansPP`.
|
78
|
+
* If `NULL`, this defaults to a default-constructed `InitializeKmeansPP` instance.
|
79
|
+
* @param refiner Pointer to a `Refine` object containing the desired k-means refinement algorithm, e.g., `HartiganWong`, `Lloyd`, `MiniBatch`.
|
80
|
+
* If `NULL`, this defaults to a default-constructed `HartiganWong` instance.
|
81
|
+
*
|
82
|
+
* @return `centers` and `clusters` are filled, and a `Details` object is returned containing clustering statistics.
|
83
|
+
* Note that the actual number of clusters may be less than `ncenters` in pathological cases -
|
84
|
+
* check the length of `Details::sizes` and the value of `Details::status`.
|
85
|
+
*/
|
86
|
+
Details<DATA_t, INDEX_t> run(int ndim, INDEX_t nobs, const DATA_t* data, CLUSTER_t ncenters, DATA_t* centers, CLUSTER_t* clusters,
|
87
|
+
Initialize<DATA_t, CLUSTER_t, INDEX_t>* initializer = NULL, Refine<DATA_t, CLUSTER_t, INDEX_t>* refiner = NULL)
|
88
|
+
{
|
89
|
+
if (initializer == NULL) {
|
90
|
+
InitializeKmeansPP<DATA_t, CLUSTER_t, INDEX_t> init;
|
91
|
+
ncenters = init.run(ndim, nobs, data, ncenters, centers, clusters);
|
92
|
+
} else {
|
93
|
+
ncenters = initializer->run(ndim, nobs, data, ncenters, centers, clusters);
|
94
|
+
}
|
95
|
+
|
96
|
+
if (refiner == NULL) {
|
97
|
+
HartiganWong<DATA_t, CLUSTER_t, INDEX_t> hw;
|
98
|
+
return hw.run(ndim, nobs, data, ncenters, centers, clusters);
|
99
|
+
} else {
|
100
|
+
return refiner->run(ndim, nobs, data, ncenters, centers, clusters);
|
101
|
+
}
|
102
|
+
}
|
103
|
+
|
104
|
+
public:
|
105
|
+
/**
|
106
|
+
* @brief Full statistics from k-means clustering.
|
107
|
+
*/
|
108
|
+
struct Results {
|
109
|
+
/**
|
110
|
+
* @cond
|
111
|
+
*/
|
112
|
+
Results(int ndim, INDEX_t nobs, CLUSTER_t ncenters) : centers(ndim * ncenters), clusters(nobs) {}
|
113
|
+
/**
|
114
|
+
* @endcond
|
115
|
+
*/
|
116
|
+
|
117
|
+
/**
|
118
|
+
* A column-major `ndim`-by-`ncenters` array containing per-cluster centroid coordinates.
|
119
|
+
*/
|
120
|
+
std::vector<DATA_t> centers;
|
121
|
+
|
122
|
+
/**
|
123
|
+
* An array of length `nobs` containing 0-indexed cluster assignments for each observation.
|
124
|
+
*/
|
125
|
+
std::vector<CLUSTER_t> clusters;
|
126
|
+
|
127
|
+
/**
|
128
|
+
* Further details from the chosen k-means algorithm.
|
129
|
+
*/
|
130
|
+
Details<DATA_t, INDEX_t> details;
|
131
|
+
};
|
132
|
+
|
133
|
+
/**
|
134
|
+
* @param ndim Number of dimensions.
|
135
|
+
* @param nobs Number of observations.
|
136
|
+
* @param[in] data Pointer to a `ndim`-by-`nobs` array where columns are observations and rows are dimensions.
|
137
|
+
* Data should be stored in column-major order.
|
138
|
+
* @param ncenters Number of cluster centers.
|
139
|
+
* @param initializer Pointer to a `Initialize` object containing the desired k-means initialization method.
|
140
|
+
* If `NULL`, this defaults to a default-constructed `InitializeKmeansPP` instance.
|
141
|
+
* @param refiner Pointer to a `Refine` object containing the desired k-means refinement algorithm.
|
142
|
+
* If `NULL`, this defaults to a default-constructed `HartiganWong` instance.
|
143
|
+
*
|
144
|
+
* @return `centers` and `clusters` are filled, and a `Results` object is returned containing clustering statistics.
|
145
|
+
* See `run()` for more details.
|
146
|
+
*
|
147
|
+
* For this method, it would be unwise to initialize with any methods that use information from the existing cluster centers.
|
148
|
+
* We suggest using only `InitializeRandom` or InitializeKmeansPP` here.
|
149
|
+
*/
|
150
|
+
Results run(int ndim, INDEX_t nobs, const DATA_t* data, CLUSTER_t ncenters,
|
151
|
+
Initialize<DATA_t, CLUSTER_t, INDEX_t>* initializer = NULL, Refine<DATA_t, CLUSTER_t, INDEX_t>* refiner = NULL)
|
152
|
+
{
|
153
|
+
Results output(ndim, nobs, ncenters);
|
154
|
+
output.details = run(ndim, nobs, data, ncenters, output.centers.data(), output.clusters.data(), initializer, refiner);
|
155
|
+
return output;
|
156
|
+
}
|
157
|
+
};
|
158
|
+
|
159
|
+
}
|
160
|
+
|
161
|
+
#endif
|
@@ -0,0 +1,134 @@
|
|
1
|
+
#ifndef KMEANS_LLOYD_HPP
|
2
|
+
#define KMEANS_LLOYD_HPP
|
3
|
+
|
4
|
+
#include <vector>
|
5
|
+
#include <algorithm>
|
6
|
+
#include <numeric>
|
7
|
+
#include <cstdint>
|
8
|
+
#include <stdexcept>
|
9
|
+
#include <limits>
|
10
|
+
|
11
|
+
#include "Base.hpp"
|
12
|
+
#include "Details.hpp"
|
13
|
+
#include "QuickSearch.hpp"
|
14
|
+
#include "is_edge_case.hpp"
|
15
|
+
#include "compute_centroids.hpp"
|
16
|
+
#include "compute_wcss.hpp"
|
17
|
+
|
18
|
+
/**
|
19
|
+
* @file Lloyd.hpp
|
20
|
+
*
|
21
|
+
* @brief Implements the Lloyd algorithm for k-means clustering.
|
22
|
+
*/
|
23
|
+
|
24
|
+
namespace kmeans {
|
25
|
+
|
26
|
+
/**
|
27
|
+
* @brief Implements the Lloyd algorithm for k-means clustering.
|
28
|
+
*
|
29
|
+
* The Lloyd algorithm is the simplest k-means clustering algorithm,
|
30
|
+
* involving several iterations of batch assignments and center calculations.
|
31
|
+
* Specifically, we assign each observation to its closest cluster, and once all points are assigned, we recompute the cluster centroids.
|
32
|
+
* This is repeated until there are no reassignments or the maximum number of iterations is reached.
|
33
|
+
*
|
34
|
+
* @tparam DATA_t Floating-point type for the data and centroids.
|
35
|
+
* @tparam CLUSTER_t Integer type for the cluster assignments.
|
36
|
+
* @tparam INDEX_t Integer type for the observation index.
|
37
|
+
*
|
38
|
+
* @see
|
39
|
+
* Lloyd, S. P. (1982).
|
40
|
+
* Least squares quantization in PCM.
|
41
|
+
* _IEEE Transactions on Information Theory_ 28, 128-137.
|
42
|
+
*/
|
43
|
+
template<typename DATA_t = double, typename CLUSTER_t = int, typename INDEX_t = int>
|
44
|
+
class Lloyd : public Refine<DATA_t, CLUSTER_t, INDEX_t> {
|
45
|
+
public:
|
46
|
+
/**
|
47
|
+
* @brief Default parameter values for `Lloyd`.
|
48
|
+
*/
|
49
|
+
struct Defaults {
|
50
|
+
/**
|
51
|
+
* See `Lloyd::set_max_iterations()`.
|
52
|
+
*/
|
53
|
+
static constexpr int max_iterations = 10;
|
54
|
+
};
|
55
|
+
|
56
|
+
private:
|
57
|
+
int maxiter = Defaults::max_iterations;
|
58
|
+
|
59
|
+
public:
|
60
|
+
/**
|
61
|
+
* @param m Maximum number of iterations.
|
62
|
+
* More iterations increase the opportunity for convergence at the cost of more computational time.
|
63
|
+
*
|
64
|
+
* @return A reference to this `Lloyd` object.
|
65
|
+
*/
|
66
|
+
Lloyd& set_max_iterations(int m = Defaults::max_iterations) {
|
67
|
+
maxiter = m;
|
68
|
+
return *this;
|
69
|
+
}
|
70
|
+
|
71
|
+
public:
|
72
|
+
Details<DATA_t, INDEX_t> run(int ndim, INDEX_t nobs, const DATA_t* data, CLUSTER_t ncenters, DATA_t* centers, CLUSTER_t* clusters) {
|
73
|
+
if (is_edge_case(nobs, ncenters)) {
|
74
|
+
return process_edge_case(ndim, nobs, data, ncenters, centers, clusters);
|
75
|
+
}
|
76
|
+
|
77
|
+
int iter = 0, status = 0;
|
78
|
+
std::vector<INDEX_t> sizes(ncenters);
|
79
|
+
std::vector<CLUSTER_t> copy(nobs);
|
80
|
+
|
81
|
+
for (iter = 1; iter <= maxiter; ++iter) {
|
82
|
+
// Nearest-neighbor search to assign to the closest cluster.
|
83
|
+
// Note that we move the `updated` check outside of this loop
|
84
|
+
// so that, in the future, this is more easily parallelized.
|
85
|
+
QuickSearch<DATA_t, CLUSTER_t> index(ndim, ncenters, centers);
|
86
|
+
#pragma omp parallel for
|
87
|
+
for (INDEX_t obs = 0; obs < nobs; ++obs) {
|
88
|
+
copy[obs] = index.find(data + obs * ndim);
|
89
|
+
}
|
90
|
+
|
91
|
+
bool updated = false;
|
92
|
+
for (INDEX_t obs = 0; obs < nobs; ++obs) {
|
93
|
+
if (copy[obs] != clusters[obs]) {
|
94
|
+
updated = true;
|
95
|
+
break;
|
96
|
+
}
|
97
|
+
}
|
98
|
+
if (!updated) {
|
99
|
+
break;
|
100
|
+
}
|
101
|
+
std::copy(copy.begin(), copy.end(), clusters);
|
102
|
+
|
103
|
+
// Counting the number in each cluster.
|
104
|
+
std::fill(sizes.begin(), sizes.end(), 0);
|
105
|
+
for (INDEX_t obs = 0; obs < nobs; ++obs) {
|
106
|
+
++sizes[clusters[obs]];
|
107
|
+
}
|
108
|
+
|
109
|
+
for (CLUSTER_t c = 0; c < ncenters; ++ c) {
|
110
|
+
if (!sizes[c]) {
|
111
|
+
status = 1;
|
112
|
+
break;
|
113
|
+
}
|
114
|
+
}
|
115
|
+
|
116
|
+
compute_centroids(ndim, nobs, data, ncenters, centers, clusters, sizes);
|
117
|
+
}
|
118
|
+
|
119
|
+
if (iter == maxiter + 1) {
|
120
|
+
status = 2;
|
121
|
+
}
|
122
|
+
|
123
|
+
return Details<DATA_t, INDEX_t>(
|
124
|
+
std::move(sizes),
|
125
|
+
compute_wcss(ndim, nobs, data, ncenters, centers, clusters),
|
126
|
+
iter,
|
127
|
+
status
|
128
|
+
);
|
129
|
+
}
|
130
|
+
};
|
131
|
+
|
132
|
+
}
|
133
|
+
|
134
|
+
#endif
|