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 +1,269 @@
|
|
1
|
+
#ifndef KMEANS_MINIBATCH_HPP
|
2
|
+
#define KMEANS_MINIBATCH_HPP
|
3
|
+
|
4
|
+
#include <vector>
|
5
|
+
#include <algorithm>
|
6
|
+
#include <numeric>
|
7
|
+
#include <cstdint>
|
8
|
+
#include <stdexcept>
|
9
|
+
#include <limits>
|
10
|
+
#include <random>
|
11
|
+
|
12
|
+
#include "Base.hpp"
|
13
|
+
#include "Details.hpp"
|
14
|
+
#include "QuickSearch.hpp"
|
15
|
+
#include "compute_wcss.hpp"
|
16
|
+
#include "is_edge_case.hpp"
|
17
|
+
#include "random.hpp"
|
18
|
+
|
19
|
+
/**
|
20
|
+
* @file MiniBatch.hpp
|
21
|
+
*
|
22
|
+
* @brief Implements the mini-batch algorithm for k-means clustering.
|
23
|
+
*/
|
24
|
+
|
25
|
+
namespace kmeans {
|
26
|
+
|
27
|
+
/**
|
28
|
+
* @brief Implements the mini-batch algorithm for k-means clustering.
|
29
|
+
*
|
30
|
+
* The mini-batch approach is similar to Lloyd's algorithm in that it runs through a set of observations, assigns each to the closest centroid, updates the centroids and repeats.
|
31
|
+
* The key difference is that each iteration is performed with a random subset of observations (i.e., a "mini-batch"), instead of the full set of observations.
|
32
|
+
* This reduces computational time at the cost of some solution quality.
|
33
|
+
* In theory, it can also reduce memory usage, though this is not particularly relevant here as we are already assuming that the data can be fully stored in memory.
|
34
|
+
*
|
35
|
+
* The update procedure for a cluster's centroid involves adjusting the coordinates by the assigned observations in the mini-batch.
|
36
|
+
* The resulting vector can be interpreted as the mean of all observations that have ever been sampled (possibly multiple times) to that cluster.
|
37
|
+
* Thus, the magnitude of the updates will decrease in later iterations as the relative effect of newly sampled points is reduced.
|
38
|
+
* This ensures that the centroids will stabilize at a sufficiently large number of iterations.
|
39
|
+
*
|
40
|
+
* We may stop the algorithm before the maximum number of iterations if only a few observations are reassigned at each iteration.
|
41
|
+
* Specifically, every \f$h\f$ iterations, we compute the proportion of sampled observations for each cluster in the past \f$h\f$ mini-batches that were reassigned to/from that cluster.
|
42
|
+
* If this proportion is less than some threshold \f$p\f$ for all clusters, we consider that the algorithm has converged.
|
43
|
+
*
|
44
|
+
* @tparam DATA_t Floating-point type for the data and centroids.
|
45
|
+
* @tparam CLUSTER_t Integer type for the cluster assignments.
|
46
|
+
* @tparam INDEX_t Integer type for the observation index.
|
47
|
+
*/
|
48
|
+
template<typename DATA_t = double, typename CLUSTER_t = int, typename INDEX_t = int>
|
49
|
+
class MiniBatch : public Refine<DATA_t, CLUSTER_t, INDEX_t> {
|
50
|
+
public:
|
51
|
+
/**
|
52
|
+
* @brief Default parameter values for `MiniBatch`.
|
53
|
+
*/
|
54
|
+
struct Defaults {
|
55
|
+
/**
|
56
|
+
* See `MiniBatch::set_max_iterations()`.
|
57
|
+
*/
|
58
|
+
static constexpr int max_iterations = 100;
|
59
|
+
|
60
|
+
/**
|
61
|
+
* See `MiniBatch::set_batch_size()`.
|
62
|
+
*/
|
63
|
+
static constexpr INDEX_t batch_size = 500;
|
64
|
+
|
65
|
+
/**
|
66
|
+
* See `MiniBatch::set_max_change_proportion()`.
|
67
|
+
*/
|
68
|
+
static constexpr double max_change_proportion = 0.01;
|
69
|
+
|
70
|
+
/**
|
71
|
+
* See `MiniBatch::set_convergence_history()`.
|
72
|
+
*/
|
73
|
+
static constexpr int convergence_history = 10;
|
74
|
+
|
75
|
+
/**
|
76
|
+
* See `MiniBatch::set_seed()`.
|
77
|
+
*/
|
78
|
+
static constexpr uint64_t seed = 1234567890;
|
79
|
+
};
|
80
|
+
|
81
|
+
private:
|
82
|
+
int maxiter = Defaults::max_iterations;
|
83
|
+
|
84
|
+
INDEX_t batch_size = Defaults::batch_size;
|
85
|
+
|
86
|
+
int history = Defaults::convergence_history;
|
87
|
+
|
88
|
+
double max_change = Defaults::max_change_proportion;
|
89
|
+
|
90
|
+
uint64_t seed = Defaults::seed;
|
91
|
+
public:
|
92
|
+
/**
|
93
|
+
* @param i Maximum number of iterations.
|
94
|
+
* More iterations increase the opportunity for convergence at the cost of more computational time.
|
95
|
+
*
|
96
|
+
* @return A reference to this `MiniBatch` object.
|
97
|
+
*/
|
98
|
+
MiniBatch& set_max_iterations(int i = Defaults::max_iterations) {
|
99
|
+
maxiter = i;
|
100
|
+
return *this;
|
101
|
+
}
|
102
|
+
|
103
|
+
/**
|
104
|
+
* @param s Number of observations in the mini-batch.
|
105
|
+
* Larger numbers improve quality at the cost of computational time.
|
106
|
+
*
|
107
|
+
* @return A reference to this `MiniBatch` object.
|
108
|
+
*/
|
109
|
+
MiniBatch& set_batch_size(INDEX_t s = Defaults::batch_size) {
|
110
|
+
batch_size = s;
|
111
|
+
return *this;
|
112
|
+
}
|
113
|
+
|
114
|
+
/**
|
115
|
+
* @param p Maximum proportion of observations in each cluster that can be reassigned when checking for convergence (i.e., \f$p\f$).
|
116
|
+
* Lower values improve the quality of the result at the cost of computational time.
|
117
|
+
*
|
118
|
+
* @return A reference to this `MiniBatch` object.
|
119
|
+
*/
|
120
|
+
MiniBatch& set_max_change_proportion(double p = Defaults::max_change_proportion) {
|
121
|
+
max_change = p;
|
122
|
+
return *this;
|
123
|
+
}
|
124
|
+
|
125
|
+
/**
|
126
|
+
* @param h Number of iterations to remember when checking for convergence (i.e., \f$h\f$).
|
127
|
+
* Larger values improve the quality of the result at the cost of computational time.
|
128
|
+
*
|
129
|
+
* @return A reference to this `MiniBatch` object.
|
130
|
+
*/
|
131
|
+
MiniBatch& set_convergence_history(int h = Defaults::convergence_history) {
|
132
|
+
history = h;
|
133
|
+
return *this;
|
134
|
+
}
|
135
|
+
|
136
|
+
/**
|
137
|
+
* @param s Seed to use for PRNG when sampling observations to use in each mini-batch.
|
138
|
+
*
|
139
|
+
* @return A reference to this `MiniBatch` object.
|
140
|
+
*/
|
141
|
+
MiniBatch& set_seed(uint64_t s = Defaults::seed) {
|
142
|
+
seed = s;
|
143
|
+
return *this;
|
144
|
+
}
|
145
|
+
|
146
|
+
public:
|
147
|
+
/**
|
148
|
+
* @param ndim Number of dimensions.
|
149
|
+
* @param nobs Number of observations.
|
150
|
+
* @param[in] data Pointer to a `ndim`-by-`nobs` array where columns are observations and rows are dimensions.
|
151
|
+
* Data should be stored in column-major order.
|
152
|
+
* @param ncenters Number of cluster centers.
|
153
|
+
* @param[in, out] centers Pointer to a `ndim`-by-`ncenters` array where columns are cluster centers and rows are dimensions.
|
154
|
+
* On input, this should contain the initial centroid locations for each cluster.
|
155
|
+
* Data should be stored in column-major order.
|
156
|
+
* On output, this will contain the final centroid locations for each cluster.
|
157
|
+
* @param[out] clusters Pointer to an array of length `nobs`.
|
158
|
+
* On output, this will contain the cluster assignment for each observation.
|
159
|
+
*
|
160
|
+
* @return `centers` and `clusters` are filled, and a `Details` object is returned containing clustering statistics.
|
161
|
+
* If `ncenters > nobs`, only the first `nobs` columns of the `centers` array will be filled.
|
162
|
+
*/
|
163
|
+
Details<DATA_t, INDEX_t> run(int ndim, INDEX_t nobs, const DATA_t* data, CLUSTER_t ncenters, DATA_t* centers, CLUSTER_t* clusters) {
|
164
|
+
if (is_edge_case(nobs, ncenters)) {
|
165
|
+
return process_edge_case(ndim, nobs, data, ncenters, centers, clusters);
|
166
|
+
}
|
167
|
+
|
168
|
+
int iter = 0, status = 0;
|
169
|
+
std::vector<INDEX_t> total_sampled(ncenters);
|
170
|
+
std::vector<CLUSTER_t> previous(nobs);
|
171
|
+
std::vector<INDEX_t> last_changed(ncenters), last_sampled(ncenters);
|
172
|
+
|
173
|
+
auto actual_batch_size = std::min(batch_size, nobs);
|
174
|
+
int last_updated = 0;
|
175
|
+
std::mt19937_64 eng(seed);
|
176
|
+
|
177
|
+
for (iter = 1; iter <= maxiter; ++iter) {
|
178
|
+
auto chosen = sample_without_replacement(nobs, actual_batch_size, eng);
|
179
|
+
if (iter > 1) {
|
180
|
+
for (auto o : chosen) {
|
181
|
+
previous[o] = clusters[o];
|
182
|
+
}
|
183
|
+
}
|
184
|
+
|
185
|
+
QuickSearch<DATA_t, CLUSTER_t> index(ndim, ncenters, centers);
|
186
|
+
#pragma omp parallel for
|
187
|
+
for (size_t i = 0; i < chosen.size(); ++i) {
|
188
|
+
clusters[chosen[i]] = index.find(data + chosen[i] * ndim);
|
189
|
+
}
|
190
|
+
|
191
|
+
// Updating the means for each cluster.
|
192
|
+
for (auto o : chosen) {
|
193
|
+
const auto c = clusters[o];
|
194
|
+
auto& n = total_sampled[c];
|
195
|
+
++n;
|
196
|
+
|
197
|
+
auto ocopy = data + o * ndim;
|
198
|
+
auto ccopy = centers + c * ndim;
|
199
|
+
for (int d = 0; d < ndim; ++d, ++ocopy, ++ccopy) {
|
200
|
+
(*ccopy) += (*ocopy - *ccopy)/n;
|
201
|
+
}
|
202
|
+
}
|
203
|
+
|
204
|
+
// Checking for updates.
|
205
|
+
if (iter != 1) {
|
206
|
+
for (auto o : chosen) {
|
207
|
+
++(last_sampled[previous[o]]);
|
208
|
+
if (previous[o] != clusters[o]) {
|
209
|
+
++(last_sampled[clusters[o]]);
|
210
|
+
++(last_changed[previous[o]]);
|
211
|
+
++(last_changed[clusters[o]]);
|
212
|
+
}
|
213
|
+
}
|
214
|
+
|
215
|
+
if (iter % history == 1) {
|
216
|
+
bool too_many_changes = false;
|
217
|
+
for (CLUSTER_t c = 0; c < ncenters; ++c) {
|
218
|
+
if (static_cast<double>(last_changed[c]) >= last_sampled[c] * max_change) {
|
219
|
+
too_many_changes = true;
|
220
|
+
break;
|
221
|
+
}
|
222
|
+
}
|
223
|
+
|
224
|
+
if (!too_many_changes) {
|
225
|
+
break;
|
226
|
+
}
|
227
|
+
std::fill(last_sampled.begin(), last_sampled.end(), 0);
|
228
|
+
std::fill(last_changed.begin(), last_changed.end(), 0);
|
229
|
+
}
|
230
|
+
}
|
231
|
+
}
|
232
|
+
|
233
|
+
if (iter == maxiter + 1) {
|
234
|
+
status = 2;
|
235
|
+
}
|
236
|
+
|
237
|
+
// Run through all observations to make sure they have the latest cluster assignments.
|
238
|
+
QuickSearch<DATA_t, CLUSTER_t> index(ndim, ncenters, centers);
|
239
|
+
#pragma omp parallel for
|
240
|
+
for (INDEX_t o = 0; o < nobs; ++o) {
|
241
|
+
clusters[o] = index.find(data + o * ndim);
|
242
|
+
}
|
243
|
+
|
244
|
+
std::fill(total_sampled.begin(), total_sampled.end(), 0);
|
245
|
+
for (INDEX_t o = 0; o < nobs; ++o) {
|
246
|
+
++total_sampled[clusters[o]];
|
247
|
+
}
|
248
|
+
|
249
|
+
for (auto c : total_sampled) {
|
250
|
+
if (c == 0) {
|
251
|
+
status = 1;
|
252
|
+
break;
|
253
|
+
}
|
254
|
+
}
|
255
|
+
|
256
|
+
compute_centroids(ndim, nobs, data, ncenters, centers, clusters, total_sampled);
|
257
|
+
|
258
|
+
return Details<DATA_t, INDEX_t>(
|
259
|
+
std::move(total_sampled),
|
260
|
+
compute_wcss(ndim, nobs, data, ncenters, centers, clusters),
|
261
|
+
iter,
|
262
|
+
status
|
263
|
+
);
|
264
|
+
}
|
265
|
+
};
|
266
|
+
|
267
|
+
}
|
268
|
+
|
269
|
+
#endif
|
@@ -0,0 +1,179 @@
|
|
1
|
+
#ifndef KMEANS_QUICKSEARCH_HPP
|
2
|
+
#define KMEANS_QUICKSEARCH_HPP
|
3
|
+
|
4
|
+
#include <vector>
|
5
|
+
#include <random>
|
6
|
+
#include <limits>
|
7
|
+
#include <cmath>
|
8
|
+
#include <tuple>
|
9
|
+
#include <iostream>
|
10
|
+
|
11
|
+
namespace kmeans {
|
12
|
+
|
13
|
+
/* Adapted from http://stevehanov.ca/blog/index.php?id=130 */
|
14
|
+
template<typename DATA_t = double, typename CLUSTER_t = int>
|
15
|
+
class QuickSearch {
|
16
|
+
private:
|
17
|
+
int num_dim;
|
18
|
+
CLUSTER_t num_obs;
|
19
|
+
const DATA_t* reference;
|
20
|
+
|
21
|
+
static DATA_t normalize(DATA_t x) {
|
22
|
+
return std::sqrt(x);
|
23
|
+
}
|
24
|
+
|
25
|
+
static DATA_t raw_distance(const DATA_t* x, const DATA_t* y, int ndim) {
|
26
|
+
DATA_t output = 0;
|
27
|
+
for (int i = 0; i < ndim; ++i, ++x, ++y) {
|
28
|
+
output += (*x - *y) * (*x - *y);
|
29
|
+
}
|
30
|
+
return output;
|
31
|
+
}
|
32
|
+
|
33
|
+
private:
|
34
|
+
typedef int NodeIndex_t;
|
35
|
+
static const NodeIndex_t LEAF_MARKER=-1;
|
36
|
+
|
37
|
+
// Single node of a VP tree (has a point and radius; left children are closer to point than the radius)
|
38
|
+
struct Node {
|
39
|
+
DATA_t threshold; // radius
|
40
|
+
CLUSTER_t index; // original index of current vantage point
|
41
|
+
NodeIndex_t left; // node index of the next vantage point for all children closer than 'threshold' from the current vantage point
|
42
|
+
NodeIndex_t right; // node index of the next vantage point for all children further than 'threshold' from the current vantage point
|
43
|
+
Node(NodeIndex_t i=0) : threshold(0), index(i), left(LEAF_MARKER), right(LEAF_MARKER) {}
|
44
|
+
};
|
45
|
+
std::vector<Node> nodes;
|
46
|
+
|
47
|
+
typedef std::tuple<CLUSTER_t, const DATA_t*, DATA_t> DataPoint; // internal distances computed using "DATA_t" type, even if output is returned with DISTANCE_t.
|
48
|
+
|
49
|
+
template<class SAMPLER>
|
50
|
+
NodeIndex_t buildFromPoints(NodeIndex_t lower, NodeIndex_t upper, std::vector<DataPoint>& items, SAMPLER& rng) {
|
51
|
+
if (upper == lower) { // indicates that we're done here!
|
52
|
+
return LEAF_MARKER;
|
53
|
+
}
|
54
|
+
|
55
|
+
NodeIndex_t pos = nodes.size();
|
56
|
+
nodes.resize(pos + 1);
|
57
|
+
Node& node=nodes.back();
|
58
|
+
|
59
|
+
int gap = upper - lower;
|
60
|
+
if (gap > 1) { // if we did not arrive at leaf yet
|
61
|
+
|
62
|
+
/* Choose an arbitrary point and move it to the start of the [lower, upper)
|
63
|
+
* interval in 'items'; this is our new vantage point.
|
64
|
+
*
|
65
|
+
* Yes, I know that the modulo method does not provide strictly
|
66
|
+
* uniform values but statistical correctness doesn't really matter
|
67
|
+
* here... but reproducibility across platforms does matter, and
|
68
|
+
* std::uniform_int_distribution is implementation-dependent!
|
69
|
+
*/
|
70
|
+
NodeIndex_t i = static_cast<NodeIndex_t>(rng() % gap + lower);
|
71
|
+
std::swap(items[lower], items[i]);
|
72
|
+
const auto& vantage = items[lower];
|
73
|
+
|
74
|
+
// Compute distances to the new vantage point.
|
75
|
+
const DATA_t* ref = std::get<1>(vantage);
|
76
|
+
for (size_t i = lower + 1; i < upper; ++i) {
|
77
|
+
const DATA_t* loc = std::get<1>(items[i]);
|
78
|
+
std::get<2>(items[i]) = raw_distance(ref, loc, num_dim);
|
79
|
+
}
|
80
|
+
|
81
|
+
// Partition around the median distance from the vantage point.
|
82
|
+
NodeIndex_t median = lower + gap/2;
|
83
|
+
std::nth_element(items.begin() + lower + 1, items.begin() + median, items.begin() + upper,
|
84
|
+
[&](const DataPoint& left, const DataPoint& right) -> bool {
|
85
|
+
return std::get<2>(left) < std::get<2>(right);
|
86
|
+
}
|
87
|
+
);
|
88
|
+
|
89
|
+
// Threshold of the new node will be the distance to the median
|
90
|
+
node.threshold = normalize(std::get<2>(items[median]));
|
91
|
+
|
92
|
+
// Recursively build tree
|
93
|
+
node.index = std::get<0>(vantage);
|
94
|
+
node.left = buildFromPoints(lower + 1, median, items, rng);
|
95
|
+
node.right = buildFromPoints(median, upper, items, rng);
|
96
|
+
} else {
|
97
|
+
node.index = std::get<0>(items[lower]);
|
98
|
+
}
|
99
|
+
|
100
|
+
return pos;
|
101
|
+
}
|
102
|
+
|
103
|
+
private:
|
104
|
+
template<typename INPUT_t>
|
105
|
+
void search_nn(NodeIndex_t curnode_index, const INPUT_t* target, CLUSTER_t& closest, DATA_t& tau) const {
|
106
|
+
if (curnode_index == LEAF_MARKER) { // indicates that we're done here
|
107
|
+
return;
|
108
|
+
}
|
109
|
+
|
110
|
+
// Compute distance between target and current node
|
111
|
+
const auto& curnode=nodes[curnode_index];
|
112
|
+
DATA_t dist = normalize(raw_distance(reference + curnode.index * num_dim, target, num_dim));
|
113
|
+
|
114
|
+
// If current node within radius tau
|
115
|
+
if (dist < tau) {
|
116
|
+
closest = curnode.index;
|
117
|
+
tau = dist;
|
118
|
+
}
|
119
|
+
|
120
|
+
// Return if we arrived at a leaf
|
121
|
+
if (curnode.left == LEAF_MARKER && curnode.right == LEAF_MARKER) {
|
122
|
+
return;
|
123
|
+
}
|
124
|
+
|
125
|
+
// If the target lies within the radius of ball
|
126
|
+
if (dist < curnode.threshold) {
|
127
|
+
if (dist - tau <= curnode.threshold) { // if there can still be neighbors inside the ball, recursively search left child first
|
128
|
+
search_nn(curnode.left, target, closest, tau);
|
129
|
+
}
|
130
|
+
|
131
|
+
if (dist + tau >= curnode.threshold) { // if there can still be neighbors outside the ball, recursively search right child
|
132
|
+
search_nn(curnode.right, target, closest, tau);
|
133
|
+
}
|
134
|
+
|
135
|
+
// If the target lies outsize the radius of the ball
|
136
|
+
} else {
|
137
|
+
if (dist + tau >= curnode.threshold) { // if there can still be neighbors outside the ball, recursively search right child first
|
138
|
+
search_nn(curnode.right, target, closest, tau);
|
139
|
+
}
|
140
|
+
|
141
|
+
if (dist - tau <= curnode.threshold) { // if there can still be neighbors inside the ball, recursively search left child
|
142
|
+
search_nn(curnode.left, target, closest, tau);
|
143
|
+
}
|
144
|
+
}
|
145
|
+
}
|
146
|
+
|
147
|
+
public:
|
148
|
+
QuickSearch(CLUSTER_t ndim, CLUSTER_t nobs, const DATA_t* vals) : num_dim(ndim), num_obs(nobs), reference(vals) {
|
149
|
+
std::vector<DataPoint> items;
|
150
|
+
items.reserve(num_obs);
|
151
|
+
auto ptr = vals;
|
152
|
+
for (CLUSTER_t i = 0; i < num_obs; ++i, ptr += num_dim) {
|
153
|
+
items.push_back(DataPoint(i, ptr, 0));
|
154
|
+
}
|
155
|
+
|
156
|
+
nodes.reserve(num_obs);
|
157
|
+
std::mt19937_64 rand(1234567890); // seed doesn't really matter, we don't need statistical correctness here.
|
158
|
+
buildFromPoints(0, num_obs, items, rand);
|
159
|
+
return;
|
160
|
+
}
|
161
|
+
|
162
|
+
CLUSTER_t find(const DATA_t* query) const {
|
163
|
+
DATA_t tau = std::numeric_limits<DATA_t>::max();
|
164
|
+
CLUSTER_t closest = 0;
|
165
|
+
search_nn(0, query, closest, tau);
|
166
|
+
return closest;
|
167
|
+
}
|
168
|
+
|
169
|
+
std::pair<CLUSTER_t, DATA_t> find_with_distance(const DATA_t* query) const {
|
170
|
+
DATA_t tau = std::numeric_limits<DATA_t>::max();
|
171
|
+
CLUSTER_t closest = 0;
|
172
|
+
search_nn(0, query, closest, tau);
|
173
|
+
return std::make_pair(closest, tau);
|
174
|
+
}
|
175
|
+
};
|
176
|
+
|
177
|
+
}
|
178
|
+
|
179
|
+
#endif
|
@@ -0,0 +1,32 @@
|
|
1
|
+
#ifndef KMEANS_COMPUTE_CENTROIDS_HPP
|
2
|
+
#define KMEANS_COMPUTE_CENTROIDS_HPP
|
3
|
+
|
4
|
+
#include <algorithm>
|
5
|
+
|
6
|
+
namespace kmeans {
|
7
|
+
|
8
|
+
template<typename DATA_t = double, typename INDEX_t = int, typename CLUSTER_t = int, class V>
|
9
|
+
void compute_centroids(int ndim, INDEX_t nobs, const DATA_t* data, CLUSTER_t ncenters, DATA_t* centers, const CLUSTER_t* clusters, const V& sizes) {
|
10
|
+
std::fill(centers, centers + ndim * ncenters, 0);
|
11
|
+
|
12
|
+
for (INDEX_t obs = 0; obs < nobs; ++obs) {
|
13
|
+
auto copy = centers + clusters[obs] * ndim;
|
14
|
+
auto mine = data + obs * ndim;
|
15
|
+
for (int dim = 0; dim < ndim; ++dim, ++copy, ++mine) {
|
16
|
+
*copy += *mine;
|
17
|
+
}
|
18
|
+
}
|
19
|
+
|
20
|
+
for (CLUSTER_t cen = 0; cen < ncenters; ++cen) {
|
21
|
+
if (sizes[cen]) {
|
22
|
+
auto curcenter = centers + cen * ndim;
|
23
|
+
for (int dim = 0; dim < ndim; ++dim, ++curcenter) {
|
24
|
+
*curcenter /= sizes[cen];
|
25
|
+
}
|
26
|
+
}
|
27
|
+
}
|
28
|
+
}
|
29
|
+
|
30
|
+
}
|
31
|
+
|
32
|
+
#endif
|
@@ -0,0 +1,27 @@
|
|
1
|
+
#ifndef KMEANS_COMPUTE_WCSS_HPP
|
2
|
+
#define KMEANS_COMPUTE_WCSS_HPP
|
3
|
+
|
4
|
+
#include <vector>
|
5
|
+
|
6
|
+
namespace kmeans {
|
7
|
+
|
8
|
+
template<typename DATA_t = double, typename INDEX_t = int, typename CLUSTER_t = int>
|
9
|
+
std::vector<DATA_t> compute_wcss(int ndim, INDEX_t nobs, const DATA_t* data, CLUSTER_t ncenters, const DATA_t* centers, const CLUSTER_t* clusters) {
|
10
|
+
std::vector<DATA_t> wcss(ncenters);
|
11
|
+
for (INDEX_t obs = 0; obs < nobs; ++obs) {
|
12
|
+
auto cen = clusters[obs];
|
13
|
+
auto curcenter = centers + cen * ndim;
|
14
|
+
auto& curwcss = wcss[cen];
|
15
|
+
|
16
|
+
auto curdata = data + obs * ndim;
|
17
|
+
for (int dim = 0; dim < ndim; ++dim, ++curcenter, ++curdata) {
|
18
|
+
curwcss += (*curdata - *curcenter) * (*curdata - *curcenter);
|
19
|
+
}
|
20
|
+
}
|
21
|
+
|
22
|
+
return wcss;
|
23
|
+
}
|
24
|
+
|
25
|
+
}
|
26
|
+
|
27
|
+
#endif
|
@@ -0,0 +1,42 @@
|
|
1
|
+
#ifndef KMEANS_IS_EDGE_CASE_HPP
|
2
|
+
#define KMEANS_IS_EDGE_CASE_HPP
|
3
|
+
|
4
|
+
#include <numeric>
|
5
|
+
#include <algorithm>
|
6
|
+
#include "compute_wcss.hpp"
|
7
|
+
#include "compute_centroids.hpp"
|
8
|
+
|
9
|
+
namespace kmeans {
|
10
|
+
|
11
|
+
template<typename INDEX_t = int, typename CLUSTER_t = int>
|
12
|
+
bool is_edge_case(INDEX_t nobs, CLUSTER_t ncenters) {
|
13
|
+
return (ncenters <= 1 || static_cast<INDEX_t>(ncenters) >= nobs);
|
14
|
+
}
|
15
|
+
|
16
|
+
template<typename DATA_t = double, typename INDEX_t = int, typename CLUSTER_t = int>
|
17
|
+
Details<DATA_t, INDEX_t> process_edge_case(int ndim, INDEX_t nobs, const DATA_t* data, CLUSTER_t ncenters, DATA_t* centers, CLUSTER_t* clusters) {
|
18
|
+
if (ncenters == 1) {
|
19
|
+
// All points in cluster 0.
|
20
|
+
std::fill(clusters, clusters + nobs, 0);
|
21
|
+
std::vector<INDEX_t> sizes(1, nobs);
|
22
|
+
compute_centroids(ndim, nobs, data, ncenters, centers, clusters, sizes);
|
23
|
+
auto wcss = compute_wcss(ndim, nobs, data, ncenters, centers, clusters);
|
24
|
+
return Details(std::move(sizes), std::move(wcss), 0, 0);
|
25
|
+
|
26
|
+
} else if (ncenters >= nobs) {
|
27
|
+
// Special case, each observation is a center.
|
28
|
+
std::iota(clusters, clusters + nobs, 0);
|
29
|
+
std::vector<INDEX_t> sizes(ncenters);
|
30
|
+
std::fill(sizes.begin(), sizes.begin() + nobs, 1);
|
31
|
+
compute_centroids(ndim, nobs, data, ncenters, centers, clusters, sizes);
|
32
|
+
auto wcss = compute_wcss(ndim, nobs, data, ncenters, centers, clusters);
|
33
|
+
return Details(std::move(sizes), std::move(wcss), 0, (ncenters > nobs ? 3 : 0));
|
34
|
+
|
35
|
+
} else { //i.e., ncenters == 0, provided is_edge_case is true.
|
36
|
+
return Details<DATA_t, INDEX_t>(0, 3);
|
37
|
+
}
|
38
|
+
}
|
39
|
+
|
40
|
+
}
|
41
|
+
|
42
|
+
#endif
|
@@ -0,0 +1,55 @@
|
|
1
|
+
#ifndef KMEANS_RANDOM_HPP
|
2
|
+
#define KMEANS_RANDOM_HPP
|
3
|
+
|
4
|
+
#include <vector>
|
5
|
+
#include <numeric>
|
6
|
+
#include "aarand/aarand.hpp"
|
7
|
+
|
8
|
+
namespace kmeans {
|
9
|
+
|
10
|
+
template<typename T = int, class ENGINE>
|
11
|
+
std::vector<T> sample_without_replacement(T population, size_t choose, ENGINE& eng) {
|
12
|
+
std::vector<T> sofar;
|
13
|
+
|
14
|
+
if (choose >= population) {
|
15
|
+
sofar.resize(population);
|
16
|
+
std::iota(sofar.begin(), sofar.end(), 0);
|
17
|
+
} else {
|
18
|
+
sofar.reserve(choose);
|
19
|
+
T traversed = 0;
|
20
|
+
|
21
|
+
while (sofar.size() < choose) {
|
22
|
+
if (static_cast<double>(choose - sofar.size()) > static_cast<double>(population - traversed) * aarand::standard_uniform(eng)) {
|
23
|
+
sofar.push_back(traversed);
|
24
|
+
}
|
25
|
+
++traversed;
|
26
|
+
}
|
27
|
+
}
|
28
|
+
|
29
|
+
return sofar;
|
30
|
+
}
|
31
|
+
|
32
|
+
template<typename DATA_t, typename INDEX_t, class ENGINE>
|
33
|
+
INDEX_t weighted_sample(const std::vector<DATA_t>& cumulative, const std::vector<DATA_t>& mindist, INDEX_t nobs, ENGINE& eng) {
|
34
|
+
auto total = cumulative.back();
|
35
|
+
INDEX_t chosen_id = 0;
|
36
|
+
|
37
|
+
do {
|
38
|
+
const DATA_t sampled_weight = total * aarand::standard_uniform(eng);
|
39
|
+
chosen_id = std::lower_bound(cumulative.begin(), cumulative.end(), sampled_weight) - cumulative.begin();
|
40
|
+
|
41
|
+
// We wrap this in a do/while to defend against edge cases where
|
42
|
+
// ties are chosen. The most obvious of these is when you get a
|
43
|
+
// `sampled_weight` of zero _and_ there exists a bunch of zeros at
|
44
|
+
// the start of `cumulative`. One could also get unexpected ties
|
45
|
+
// from limited precision in floating point comparisons, so we'll
|
46
|
+
// just be safe and implement a loop here, in the same vein as
|
47
|
+
// uniform01.
|
48
|
+
} while (chosen_id == nobs || mindist[chosen_id] == 0);
|
49
|
+
|
50
|
+
return chosen_id;
|
51
|
+
}
|
52
|
+
|
53
|
+
}
|
54
|
+
|
55
|
+
#endif
|