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 +1,193 @@
|
|
1
|
+
#ifndef KNNCOLLE_ANNOYBASE_HPP
|
2
|
+
#define KNNCOLLE_ANNOYBASE_HPP
|
3
|
+
|
4
|
+
#include <cstdint>
|
5
|
+
|
6
|
+
#include "../utils/Base.hpp"
|
7
|
+
|
8
|
+
#include "annoy/annoylib.h"
|
9
|
+
#include "annoy/kissrandom.h"
|
10
|
+
|
11
|
+
/**
|
12
|
+
* @file Annoy.hpp
|
13
|
+
*
|
14
|
+
* @brief Implements an approximate nearest neighbor search with Annoy.
|
15
|
+
*/
|
16
|
+
|
17
|
+
namespace knncolle {
|
18
|
+
|
19
|
+
/**
|
20
|
+
* @brief Perform an approximate nearest neighbor search with Annoy.
|
21
|
+
*
|
22
|
+
* In the Approximate Nearest Neighbors Oh Yeah (Annoy) algorithm, a tree is constructed where a random hyperplane splits the points into two subsets at each internal node.
|
23
|
+
* Leaf nodes are defined when the number of points in a subset falls below a threshold (close to twice the number of dimensions for the settings used here).
|
24
|
+
* Multiple trees are constructed in this manner, each of which is different due to the random choice of hyperplanes.
|
25
|
+
* For a given query point, each tree is searched to identify the subset of all points in the same leaf node as the query point.
|
26
|
+
* The union of these subsets across all trees is exhaustively searched to identify the actual nearest neighbors to the query.
|
27
|
+
*
|
28
|
+
* @see
|
29
|
+
* Bernhardsson E (2018).
|
30
|
+
* Annoy.
|
31
|
+
* https://github.com/spotify/annoy
|
32
|
+
*
|
33
|
+
* @tparam DISTANCE An **Annoy**-derived class to compute the distance between vectors.
|
34
|
+
* Note that this is not the same as the classes in `distances.hpp`.
|
35
|
+
* @tparam INDEX_t Integer type for the indices.
|
36
|
+
* @tparam DISTANCE_t Floating point type for the distances.
|
37
|
+
* @tparam INTERNAL_INDEX_t Integer type for the internal indices.
|
38
|
+
* @tparam INTERNAL_DATA_t Floating point type for the internal data store.
|
39
|
+
* This uses a `float` instead of a `double` to sacrifice some accuracy for performance.
|
40
|
+
*/
|
41
|
+
template<class DISTANCE, typename INDEX_t = int, typename DISTANCE_t = double, typename QUERY_t = DISTANCE_t, typename INTERNAL_INDEX_t = int32_t, typename INTERNAL_DATA_t = float>
|
42
|
+
class Annoy : public Base<INDEX_t, DISTANCE_t, QUERY_t> {
|
43
|
+
public:
|
44
|
+
INDEX_t nobs() const {
|
45
|
+
return annoy_index.get_n_items();
|
46
|
+
}
|
47
|
+
|
48
|
+
INDEX_t ndim() const {
|
49
|
+
return num_dim;
|
50
|
+
}
|
51
|
+
|
52
|
+
|
53
|
+
public:
|
54
|
+
/**
|
55
|
+
* Defaults for the constructor parameters.
|
56
|
+
*/
|
57
|
+
struct Defaults {
|
58
|
+
/**
|
59
|
+
* See `ntrees` in the `Annoy()` constructor.
|
60
|
+
*/
|
61
|
+
static constexpr int ntrees = 50;
|
62
|
+
|
63
|
+
/**
|
64
|
+
* See `search_mult` in the `Annoy()` constructor.
|
65
|
+
*/
|
66
|
+
static constexpr double search_mult = -1;
|
67
|
+
};
|
68
|
+
|
69
|
+
public:
|
70
|
+
/**
|
71
|
+
* @param ndim Number of dimensions.
|
72
|
+
* @param nobs Number of observations.
|
73
|
+
* @param vals Pointer to an array of length `ndim * nobs`, corresponding to a dimension-by-observation matrix in column-major format,
|
74
|
+
* i.e., contiguous elements belong to the same observation.
|
75
|
+
* @param ntrees Number of trees to construct.
|
76
|
+
* Larger values improve accuracy at the cost of index size (i.e., memory usage), see [here](https://github.com/spotify/annoy#tradeoffs) for details.
|
77
|
+
* @param search_mult Factor that is multiplied by the number of neighbors `k` to determine the number of nodes to search in `find_nearest_neighbors()`.
|
78
|
+
* Larger values improve accuracy at the cost of runtime, see [here](https://github.com/spotify/annoy#tradeoffs) for details.
|
79
|
+
* If set to -1, it defaults to `ntrees`.
|
80
|
+
*
|
81
|
+
* @tparam INPUT Floating-point type of the input data.
|
82
|
+
*/
|
83
|
+
template<typename INPUT>
|
84
|
+
Annoy(INDEX_t ndim, INDEX_t nobs, const INPUT* vals, int ntrees = Defaults::ntrees, double search_mult = Defaults::search_mult) :
|
85
|
+
annoy_index(ndim), num_dim(ndim), search_k_mult(search_mult)
|
86
|
+
{
|
87
|
+
if constexpr(std::is_same<INPUT, INTERNAL_DATA_t>::value) {
|
88
|
+
for (INDEX_t i=0; i < nobs; ++i, vals += ndim) {
|
89
|
+
annoy_index.add_item(i, vals);
|
90
|
+
}
|
91
|
+
} else {
|
92
|
+
std::vector<INTERNAL_DATA_t> incoming(ndim);
|
93
|
+
for (INDEX_t i=0; i < nobs; ++i, vals += ndim) {
|
94
|
+
std::copy(vals, vals + ndim, incoming.begin());
|
95
|
+
annoy_index.add_item(i, incoming.data());
|
96
|
+
}
|
97
|
+
}
|
98
|
+
annoy_index.build(ntrees);
|
99
|
+
return;
|
100
|
+
}
|
101
|
+
|
102
|
+
std::vector<std::pair<INDEX_t, DISTANCE_t> > find_nearest_neighbors(INDEX_t index, int k) const {
|
103
|
+
std::vector<INTERNAL_INDEX_t> indices;
|
104
|
+
std::vector<INTERNAL_DATA_t> distances;
|
105
|
+
annoy_index.get_nns_by_item(index, k + 1, get_search_k(k + 1), &indices, &distances); // +1, as it forgets to discard 'self'.
|
106
|
+
|
107
|
+
bool self_found = false;
|
108
|
+
const INTERNAL_INDEX_t self = index;
|
109
|
+
std::vector<std::pair<INDEX_t, DISTANCE_t> > output;
|
110
|
+
output.reserve(k);
|
111
|
+
for (size_t i = 0; i < indices.size(); ++i) {
|
112
|
+
if (!self_found && indices[i] == self) {
|
113
|
+
self_found=true;
|
114
|
+
} else {
|
115
|
+
output.emplace_back(indices[i], distances[i]);
|
116
|
+
}
|
117
|
+
}
|
118
|
+
|
119
|
+
// Just in case we're full of ties at duplicate points, such that 'c'
|
120
|
+
// is not in the set. Note that, if self_found=false, we must have at
|
121
|
+
// least 'K+2' points for 'c' to not be detected as its own neighbor.
|
122
|
+
// Thus there is no need to worry whether we are popping off a non-'c'
|
123
|
+
// element at the end of the vector.
|
124
|
+
if (!self_found) {
|
125
|
+
output.pop_back();
|
126
|
+
}
|
127
|
+
|
128
|
+
return output;
|
129
|
+
}
|
130
|
+
|
131
|
+
std::vector<std::pair<INDEX_t, DISTANCE_t> > find_nearest_neighbors(const QUERY_t* query, int k) const {
|
132
|
+
std::vector<INTERNAL_INDEX_t> indices;
|
133
|
+
indices.reserve(k);
|
134
|
+
std::vector<INTERNAL_DATA_t> distances;
|
135
|
+
distances.reserve(k);
|
136
|
+
|
137
|
+
if constexpr(std::is_same<INTERNAL_DATA_t, QUERY_t>::value) {
|
138
|
+
annoy_index.get_nns_by_vector(query, k, get_search_k(k), &indices, &distances);
|
139
|
+
} else {
|
140
|
+
std::vector<INTERNAL_DATA_t> tmp(query, query + num_dim);
|
141
|
+
annoy_index.get_nns_by_vector(tmp.data(), k, get_search_k(k), &indices, &distances);
|
142
|
+
}
|
143
|
+
|
144
|
+
std::vector<std::pair<INDEX_t, DISTANCE_t> > output;
|
145
|
+
output.reserve(k);
|
146
|
+
for (size_t i = 0; i < indices.size(); ++i) {
|
147
|
+
output.emplace_back(indices[i], distances[i]);
|
148
|
+
}
|
149
|
+
return output;
|
150
|
+
}
|
151
|
+
|
152
|
+
const QUERY_t* observation(INDEX_t index, QUERY_t* buffer) const {
|
153
|
+
if constexpr(std::is_same<QUERY_t, INTERNAL_DATA_t>::value) {
|
154
|
+
annoy_index.get_item(index, buffer);
|
155
|
+
} else {
|
156
|
+
std::vector<INTERNAL_DATA_t> tmp(num_dim);
|
157
|
+
annoy_index.get_item(index, tmp.data());
|
158
|
+
std::copy(tmp.begin(), tmp.end(), buffer);
|
159
|
+
}
|
160
|
+
return buffer;
|
161
|
+
}
|
162
|
+
|
163
|
+
using Base<INDEX_t, DISTANCE_t, QUERY_t>::observation;
|
164
|
+
|
165
|
+
private:
|
166
|
+
::Annoy::AnnoyIndex<INTERNAL_INDEX_t, INTERNAL_DATA_t, DISTANCE, ::Annoy::Kiss64Random, ::Annoy::AnnoyIndexSingleThreadedBuildPolicy> annoy_index;
|
167
|
+
INDEX_t num_dim;
|
168
|
+
double search_k_mult;
|
169
|
+
|
170
|
+
int get_search_k(int k) const {
|
171
|
+
if (search_k_mult < 0) {
|
172
|
+
return -1;
|
173
|
+
} else {
|
174
|
+
return search_k_mult * k + 0.5; // rounded up.
|
175
|
+
}
|
176
|
+
}
|
177
|
+
};
|
178
|
+
|
179
|
+
/**
|
180
|
+
* Perform an Annoy search with Euclidean distances.
|
181
|
+
*/
|
182
|
+
template<typename INDEX_t = int, typename DISTANCE_t = double, typename QUERY_t = DISTANCE_t, typename INTERNAL_INDEX_t = int32_t, typename INTERNAL_DATA_t = float>
|
183
|
+
using AnnoyEuclidean = Annoy<::Annoy::Euclidean, INDEX_t, DISTANCE_t, QUERY_t, INTERNAL_INDEX_t, INTERNAL_DATA_t>;
|
184
|
+
|
185
|
+
/**
|
186
|
+
* Perform an Annoy search with Manhattan distances.
|
187
|
+
*/
|
188
|
+
template<typename INDEX_t = int, typename DISTANCE_t = double, typename QUERY_t = DISTANCE_t, typename INTERNAL_INDEX_t = int32_t, typename INTERNAL_DATA_t = float>
|
189
|
+
using AnnoyManhattan = Annoy<::Annoy::Manhattan, INDEX_t, DISTANCE_t, QUERY_t, INTERNAL_INDEX_t, INTERNAL_DATA_t>;
|
190
|
+
|
191
|
+
}
|
192
|
+
|
193
|
+
#endif
|
@@ -0,0 +1,120 @@
|
|
1
|
+
#ifndef KNNCOLLE_BRUTEFORCE_HPP
|
2
|
+
#define KNNCOLLE_BRUTEFORCE_HPP
|
3
|
+
|
4
|
+
#include "../utils/distances.hpp"
|
5
|
+
#include "../utils/NeighborQueue.hpp"
|
6
|
+
#include "../utils/Base.hpp"
|
7
|
+
|
8
|
+
#include <vector>
|
9
|
+
#include <type_traits>
|
10
|
+
|
11
|
+
/**
|
12
|
+
* @file BruteForce.hpp
|
13
|
+
*
|
14
|
+
* @brief Implements a brute-force search for nearest neighbors.
|
15
|
+
*/
|
16
|
+
|
17
|
+
namespace knncolle {
|
18
|
+
|
19
|
+
/**
|
20
|
+
* @brief Perform a brute-force nearest neighbor search.
|
21
|
+
*
|
22
|
+
* The brute-force search computes all pairwise distances between data and query points to identify nearest neighbors of the latter.
|
23
|
+
* It has quadratic complexity and is theoretically the worst-performing method;
|
24
|
+
* however, it has effectively no overhead from constructing or querying indexing structures,
|
25
|
+
* potentially making it faster in cases where indexing provides little benefit (e.g., few data points, high dimensionality).
|
26
|
+
*
|
27
|
+
* @tparam DISTANCE Class to compute the distance between vectors, see `distance::Euclidean` for an example.
|
28
|
+
* @tparam INDEX_t Integer type for the indices.
|
29
|
+
* @tparam DISTANCE_t Floating point type for the distances.
|
30
|
+
* @tparam QUERY_t Floating point type for the query data.
|
31
|
+
* @tparam INTERNAL_t Floating point type for the internal calculations.
|
32
|
+
*/
|
33
|
+
template<class DISTANCE, typename INDEX_t = int, typename DISTANCE_t = double, typename QUERY_t = DISTANCE_t, typename INTERNAL_t = double>
|
34
|
+
class BruteForce : public Base<INDEX_t, DISTANCE_t, QUERY_t> {
|
35
|
+
private:
|
36
|
+
INDEX_t num_dim;
|
37
|
+
INDEX_t num_obs;
|
38
|
+
|
39
|
+
public:
|
40
|
+
INDEX_t nobs() const { return num_obs; }
|
41
|
+
|
42
|
+
INDEX_t ndim() const { return num_dim; }
|
43
|
+
|
44
|
+
private:
|
45
|
+
std::vector<INTERNAL_t> store;
|
46
|
+
|
47
|
+
public:
|
48
|
+
/**
|
49
|
+
* @param ndim Number of dimensions.
|
50
|
+
* @param nobs Number of observations.
|
51
|
+
* @param vals Pointer to an array of length `ndim * nobs`, corresponding to a dimension-by-observation matrix in column-major format,
|
52
|
+
* i.e., contiguous elements belong to the same observation.
|
53
|
+
*
|
54
|
+
* @tparam INPUT Floating-point type of the input data.
|
55
|
+
*/
|
56
|
+
template<typename INPUT>
|
57
|
+
BruteForce(INDEX_t ndim, INDEX_t nobs, const INPUT* vals) : num_dim(ndim), num_obs(nobs), store(vals, vals + ndim * nobs) {}
|
58
|
+
|
59
|
+
std::vector<std::pair<INDEX_t, DISTANCE_t> > find_nearest_neighbors(INDEX_t index, int k) const {
|
60
|
+
NeighborQueue<INDEX_t, INTERNAL_t> nearest(k, index);
|
61
|
+
search_nn(store.data() + index * num_dim, nearest);
|
62
|
+
|
63
|
+
auto output = nearest.template report<DISTANCE_t>();
|
64
|
+
normalize(output);
|
65
|
+
return output;
|
66
|
+
}
|
67
|
+
|
68
|
+
std::vector<std::pair<INDEX_t, DISTANCE_t> > find_nearest_neighbors(const QUERY_t* query, int k) const {
|
69
|
+
NeighborQueue<INDEX_t, INTERNAL_t> nearest(k);
|
70
|
+
search_nn(query, nearest);
|
71
|
+
auto output = nearest.template report<DISTANCE_t>();
|
72
|
+
normalize(output);
|
73
|
+
return output;
|
74
|
+
}
|
75
|
+
|
76
|
+
const QUERY_t* observation(INDEX_t index, QUERY_t* buffer) const {
|
77
|
+
auto candidate = store.data() + num_dim * index;
|
78
|
+
if constexpr(std::is_same<QUERY_t, INTERNAL_t>::value) {
|
79
|
+
return candidate;
|
80
|
+
} else {
|
81
|
+
std::copy(candidate, candidate + num_dim, buffer);
|
82
|
+
return buffer;
|
83
|
+
}
|
84
|
+
}
|
85
|
+
|
86
|
+
using Base<INDEX_t, DISTANCE_t, QUERY_t>::observation;
|
87
|
+
|
88
|
+
private:
|
89
|
+
template<class QUEUE>
|
90
|
+
void search_nn(const QUERY_t* query, QUEUE& nearest) const {
|
91
|
+
auto copy = store.data();
|
92
|
+
for (INDEX_t i = 0; i < num_obs; ++i, copy += num_dim) {
|
93
|
+
nearest.add(i, DISTANCE::template raw_distance<INTERNAL_t>(query, copy, num_dim));
|
94
|
+
}
|
95
|
+
return;
|
96
|
+
}
|
97
|
+
|
98
|
+
void normalize(std::vector<std::pair<INDEX_t, DISTANCE_t> >& results) const {
|
99
|
+
for (auto& d : results) {
|
100
|
+
d.second = DISTANCE::normalize(d.second);
|
101
|
+
}
|
102
|
+
return;
|
103
|
+
}
|
104
|
+
};
|
105
|
+
|
106
|
+
/**
|
107
|
+
* Perform a brute-force search with Euclidean distances.
|
108
|
+
*/
|
109
|
+
template<typename INDEX_t = int, typename DISTANCE_t = double, typename QUERY_t = DISTANCE_t, typename INTERNAL_t = double>
|
110
|
+
using BruteForceEuclidean = BruteForce<distances::Euclidean, INDEX_t, DISTANCE_t, QUERY_t, INTERNAL_t>;
|
111
|
+
|
112
|
+
/**
|
113
|
+
* Perform a brute-force search with Manhattan distances.
|
114
|
+
*/
|
115
|
+
template<typename INDEX_t = int, typename DISTANCE_t = double, typename QUERY_t = DISTANCE_t, typename INTERNAL_t = double>
|
116
|
+
using BruteForceManhattan = BruteForce<distances::Manhattan, INDEX_t, DISTANCE_t, QUERY_t, INTERNAL_t>;
|
117
|
+
|
118
|
+
}
|
119
|
+
|
120
|
+
#endif
|
@@ -0,0 +1,225 @@
|
|
1
|
+
#ifndef KNNCOLLE_HNSW_HPP
|
2
|
+
#define KNNCOLLE_HNSW_HPP
|
3
|
+
|
4
|
+
#include "../utils/Base.hpp"
|
5
|
+
#include "../utils/NeighborQueue.hpp"
|
6
|
+
|
7
|
+
#include "hnswlib/hnswalg.h"
|
8
|
+
#include <cmath>
|
9
|
+
|
10
|
+
/**
|
11
|
+
* @file Hnsw.hpp
|
12
|
+
*
|
13
|
+
* @brief Implements an approximate nearest neighbor search with HNSW.
|
14
|
+
*/
|
15
|
+
|
16
|
+
namespace knncolle {
|
17
|
+
|
18
|
+
/**
|
19
|
+
* @brief Perform an approximate nearest neighbor search with HNSW.
|
20
|
+
*
|
21
|
+
* In the HNSW algorithm (Malkov and Yashunin, 2016), each point is a node in a "nagivable small world" graph.
|
22
|
+
* The nearest neighbor search proceeds by starting at a node and walking through the graph to obtain closer neighbors to a given query point.
|
23
|
+
* Nagivable small world graphs are used to maintain connectivity across the data set by creating links between distant points.
|
24
|
+
* This speeds up the search by ensuring that the algorithm does not need to take many small steps to move from one cluster to another.
|
25
|
+
* The HNSW algorithm extends this idea by using a hierarchy of such graphs containing links of different lengths,
|
26
|
+
* which avoids wasting time on small steps in the early stages of the search where the current node position is far from the query.
|
27
|
+
*
|
28
|
+
* @see
|
29
|
+
* Malkov YA, Yashunin DA (2016).
|
30
|
+
* Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs.
|
31
|
+
* _arXiv_.
|
32
|
+
* https://arxiv.org/abs/1603.09320
|
33
|
+
*
|
34
|
+
*
|
35
|
+
* @tparam DISTANCE An **hnswlib**-derived class to compute the distance between vectors.
|
36
|
+
* Note that this is not the same as the classes in `distances.hpp`.
|
37
|
+
* @tparam INDEX_t Integer type for the indices.
|
38
|
+
* @tparam DISTANCE_t Floating point type for the distances.
|
39
|
+
*/
|
40
|
+
template<class SPACE, typename INDEX_t = int, typename DISTANCE_t = double, typename QUERY_t = DISTANCE_t>
|
41
|
+
class Hnsw : public Base<INDEX_t, DISTANCE_t, QUERY_t> {
|
42
|
+
typedef float INTERNAL_DATA_t; // floats are effectively hard-coded into hnswlib, given that L2Space only uses floats.
|
43
|
+
|
44
|
+
public:
|
45
|
+
INDEX_t nobs() const {
|
46
|
+
return num_obs;
|
47
|
+
}
|
48
|
+
|
49
|
+
INDEX_t ndim() const {
|
50
|
+
return num_dim;
|
51
|
+
}
|
52
|
+
|
53
|
+
public:
|
54
|
+
/**
|
55
|
+
* Defaults for the constructor parameters.
|
56
|
+
*/
|
57
|
+
struct Defaults {
|
58
|
+
/**
|
59
|
+
* See `nlinks` in the `Hnsw()` constructor.
|
60
|
+
*/
|
61
|
+
static constexpr int nlinks = 16;
|
62
|
+
|
63
|
+
/**
|
64
|
+
* See `ef_construction` in the `Hnsw()` constructor.
|
65
|
+
*/
|
66
|
+
static constexpr int ef_construction = 200;
|
67
|
+
|
68
|
+
/**
|
69
|
+
* See `ef_search` in the `Hnsw()` constructor.
|
70
|
+
*/
|
71
|
+
static constexpr int ef_search = 10;
|
72
|
+
};
|
73
|
+
|
74
|
+
public:
|
75
|
+
/**
|
76
|
+
* @param ndim Number of dimensions.
|
77
|
+
* @param nobs Number of observations.
|
78
|
+
* @param vals Pointer to an array of length `ndim * nobs`, corresponding to a dimension-by-observation matrix in column-major format,
|
79
|
+
* i.e., contiguous elements belong to the same observation.
|
80
|
+
* @param nlinks Number of bidirectional links for each node.
|
81
|
+
* This is equivalent to the `M` parameter in the underlying **hnswlib** library, see [here](https://github.com/nmslib/hnswlib/blob/master/ALGO_PARAMS.md#construction-parameters) for details.
|
82
|
+
* @param ef_construction Size of the dynamic list of nearest neighbors during index construction.
|
83
|
+
* This controls the trade-off between indexing time and accuracy and is equivalent to the `ef_construct` parameter in the underlying **hnswlib** library,
|
84
|
+
* see [here](https://github.com/nmslib/hnswlib/blob/master/ALGO_PARAMS.md#construction-parameters) for details.
|
85
|
+
* @param ef_search Size of the dynamic list of nearest neighbors during searching.
|
86
|
+
* This controls the trade-off between search speed and accuracy and is equivalent to the `ef` parameter in the underlying **hnswlib** library,
|
87
|
+
* see [here](https://github.com/nmslib/hnswlib/blob/master/ALGO_PARAMS.md#search-parameters) for details.
|
88
|
+
*
|
89
|
+
* @tparam INPUT Floating-point type of the input data.
|
90
|
+
*/
|
91
|
+
template<typename INPUT>
|
92
|
+
Hnsw(INDEX_t ndim, INDEX_t nobs, const INPUT* vals, int nlinks = Defaults::nlinks, int ef_construction = Defaults::ef_construction, int ef_search = Defaults::ef_search) :
|
93
|
+
space(ndim), hnsw_index(&space, nobs, nlinks, ef_construction), num_dim(ndim), num_obs(nobs)
|
94
|
+
{
|
95
|
+
if constexpr(std::is_same<INPUT, INTERNAL_DATA_t>::value) {
|
96
|
+
for (INDEX_t i=0; i < nobs; ++i, vals += ndim) {
|
97
|
+
hnsw_index.addPoint(vals, i);
|
98
|
+
}
|
99
|
+
} else {
|
100
|
+
std::vector<INTERNAL_DATA_t> copy(ndim);
|
101
|
+
for (INDEX_t i=0; i < nobs; ++i, vals += ndim) {
|
102
|
+
std::copy(vals, vals + ndim, copy.begin());
|
103
|
+
hnsw_index.addPoint(copy.data(), i);
|
104
|
+
}
|
105
|
+
}
|
106
|
+
hnsw_index.setEf(ef_search);
|
107
|
+
return;
|
108
|
+
}
|
109
|
+
|
110
|
+
std::vector<std::pair<INDEX_t, DISTANCE_t> > find_nearest_neighbors(INDEX_t index, int k) const {
|
111
|
+
auto V = hnsw_index.getDataByLabel<INTERNAL_DATA_t>(index);
|
112
|
+
auto Q = hnsw_index.searchKnn(V.data(), k+1);
|
113
|
+
auto output = harvest_queue<INDEX_t, DISTANCE_t>(Q, true, index);
|
114
|
+
normalize(output);
|
115
|
+
return output;
|
116
|
+
}
|
117
|
+
|
118
|
+
std::vector<std::pair<INDEX_t, DISTANCE_t> > find_nearest_neighbors(const QUERY_t* query, int k) const {
|
119
|
+
if constexpr(std::is_same<QUERY_t, INTERNAL_DATA_t>::value) {
|
120
|
+
auto Q = hnsw_index.searchKnn(query, k);
|
121
|
+
auto output = harvest_queue<INDEX_t, DISTANCE_t>(Q);
|
122
|
+
normalize(output);
|
123
|
+
return output;
|
124
|
+
} else {
|
125
|
+
std::vector<INTERNAL_DATA_t> copy(query, query + num_dim);
|
126
|
+
auto Q = hnsw_index.searchKnn(copy.data(), k);
|
127
|
+
auto output = harvest_queue<INDEX_t, DISTANCE_t>(Q);
|
128
|
+
normalize(output);
|
129
|
+
return output;
|
130
|
+
}
|
131
|
+
}
|
132
|
+
|
133
|
+
const QUERY_t* observation(INDEX_t index, QUERY_t* buffer) const {
|
134
|
+
auto V = hnsw_index.getDataByLabel<INTERNAL_DATA_t>(index);
|
135
|
+
std::copy(V.begin(), V.begin() + num_dim, buffer);
|
136
|
+
return buffer;
|
137
|
+
}
|
138
|
+
|
139
|
+
std::vector<QUERY_t> observation(INDEX_t index) const {
|
140
|
+
if constexpr(std::is_same<QUERY_t, INTERNAL_DATA_t>::value) {
|
141
|
+
return hnsw_index.getDataByLabel<QUERY_t>(index);
|
142
|
+
} else {
|
143
|
+
auto V = hnsw_index.getDataByLabel<INTERNAL_DATA_t>(index);
|
144
|
+
return std::vector<QUERY_t>(V.begin(), V.end());
|
145
|
+
}
|
146
|
+
}
|
147
|
+
|
148
|
+
private:
|
149
|
+
SPACE space;
|
150
|
+
hnswlib::HierarchicalNSW<INTERNAL_DATA_t> hnsw_index;
|
151
|
+
INDEX_t num_dim, num_obs;
|
152
|
+
|
153
|
+
static void normalize(std::vector<std::pair<INDEX_t, DISTANCE_t> >& results) {
|
154
|
+
for (auto& d : results) {
|
155
|
+
d.second = SPACE::normalize(d.second);
|
156
|
+
}
|
157
|
+
return;
|
158
|
+
}
|
159
|
+
};
|
160
|
+
|
161
|
+
namespace hnsw_distances {
|
162
|
+
|
163
|
+
class Manhattan : public hnswlib::SpaceInterface<float> {
|
164
|
+
size_t data_size_;
|
165
|
+
size_t dim_;
|
166
|
+
public:
|
167
|
+
Manhattan(size_t ndim) : data_size_(ndim * sizeof(float)), dim_(ndim) {}
|
168
|
+
|
169
|
+
~Manhattan() {}
|
170
|
+
|
171
|
+
size_t get_data_size() {
|
172
|
+
return data_size_;
|
173
|
+
}
|
174
|
+
|
175
|
+
hnswlib::DISTFUNC<float> get_dist_func() {
|
176
|
+
return L1;
|
177
|
+
}
|
178
|
+
|
179
|
+
void * get_dist_func_param() {
|
180
|
+
return &dim_;
|
181
|
+
}
|
182
|
+
|
183
|
+
static float L1(const void *pVect1v, const void *pVect2v, const void *qty_ptr) {
|
184
|
+
//return *((float*)pVect2);
|
185
|
+
const float* pVect1=static_cast<const float*>(pVect1v);
|
186
|
+
const float* pVect2=static_cast<const float*>(pVect2v);
|
187
|
+
size_t qty = *((size_t *) qty_ptr);
|
188
|
+
float res = 0;
|
189
|
+
for (; qty > 0; --qty, ++pVect1, ++pVect2) {
|
190
|
+
res += std::fabs(*pVect1 - *pVect2);
|
191
|
+
}
|
192
|
+
return res;
|
193
|
+
}
|
194
|
+
|
195
|
+
static float normalize(float raw) {
|
196
|
+
return raw;
|
197
|
+
}
|
198
|
+
};
|
199
|
+
|
200
|
+
class Euclidean : public hnswlib::L2Space {
|
201
|
+
public:
|
202
|
+
Euclidean(size_t ndim) : hnswlib::L2Space(ndim) {}
|
203
|
+
|
204
|
+
static float normalize(float raw) {
|
205
|
+
return std::sqrt(raw);
|
206
|
+
}
|
207
|
+
};
|
208
|
+
|
209
|
+
}
|
210
|
+
|
211
|
+
/**
|
212
|
+
* Perform an Hnsw search with Euclidean distances.
|
213
|
+
*/
|
214
|
+
template<typename INDEX_t = int, typename DISTANCE_t = double, typename QUERY_t = DISTANCE_t>
|
215
|
+
using HnswEuclidean = Hnsw<hnsw_distances::Euclidean, INDEX_t, DISTANCE_t, QUERY_t>;
|
216
|
+
|
217
|
+
/**
|
218
|
+
* Perform an Hnsw search with Manhattan distances.
|
219
|
+
*/
|
220
|
+
template<typename INDEX_t = int, typename DISTANCE_t = double, typename QUERY_t = DISTANCE_t>
|
221
|
+
using HnswManhattan = Hnsw<hnsw_distances::Manhattan, INDEX_t, DISTANCE_t, QUERY_t>;
|
222
|
+
|
223
|
+
}
|
224
|
+
|
225
|
+
#endif
|