all of classes and functions are contained in the shogun namespace 更多...

组合类型
class	CParallel
	Class Parallel provides helper functions for multithreading. 更多...
class	CSGObject
	Class SGObject is the base class of all shogun objects. 更多...
class	CVersion
	Class Version provides version information. 更多...
class	CClassifier
	A generic classifier interface. 更多...
class	CDistanceMachine
	A generic DistanceMachine interface. 更多...
class	CKernelMachine
	A generic KernelMachine interface. 更多...
class	CKernelPerceptron
	Class KernelPerceptron - currently unfinished implementation of a Kernel Perceptron. 更多...
class	CKNN
	Class KNN, an implementation of the standard k-nearest neigbor classifier. 更多...
class	CLDA
	Class LDA implements regularized Linear Discriminant Analysis. 更多...
class	CLinearClassifier
	Class LinearClassifier is a generic interface for all kinds of linear classifiers. 更多...
class	CLPBoost
	Class LPBoost trains a linear classifier called Linear Programming Machine, i.e. a SVM using a $\ell_1$ norm regularizer. 更多...
class	CLPM
	Class LPM trains a linear classifier called Linear Programming Machine, i.e. a SVM using a $\ell_1$ norm regularizer. 更多...
class	CMKL
	Multiple Kernel Learning. 更多...
class	CMKLClassification
	Multiple Kernel Learning for two-class-classification. 更多...
class	CMKLMultiClass
	MKLMultiClass is a class for L1-norm multiclass MKL. 更多...
class	MKLMultiClassGLPK
	MKLMultiClassGLPK is a helper class for MKLMultiClass. 更多...
class	MKLMultiClassGradient
	MKLMultiClassGradient is a helper class for MKLMultiClass. 更多...
class	MKLMultiClassOptimizationBase
	MKLMultiClassOptimizationBase is a helper class for MKLMultiClass. 更多...
class	CMKLOneClass
	Multiple Kernel Learning for one-class-classification. 更多...
class	CPerceptron
	Class Perceptron implements the standard linear (online) perceptron. 更多...
class	CPluginEstimate
	class PluginEstimate 更多...
class	CSubGradientLPM
	Class SubGradientSVM trains a linear classifier called Linear Programming Machine, i.e. a SVM using a $\ell_1$ norm regularizer. 更多...
class	CCPLEXSVM
	CplexSVM a SVM solver implementation based on cplex (unfinished). 更多...
class	CDomainAdaptationSVM
	class DomainAdaptiveSVM 更多...
class	CGMNPLib
	class GMNPLib Library of solvers for Generalized Minimal Norm Problem (GMNP). 更多...
class	CGMNPSVM
	Class GMNPSVM implements a one vs. rest MultiClass SVM. 更多...
class	CGNPPLib
	class GNPPLib, a Library of solvers for Generalized Nearest Point Problem (GNPP). 更多...
class	CGNPPSVM
	class GNPPSVM 更多...
class	CGPBTSVM
	class GPBTSVM 更多...
class	CLaRank
class	CLibLinear
	class to implement LibLinear 更多...
class	CLibSVM
	LibSVM. 更多...
class	CLibSVMMultiClass
	class LibSVMMultiClass 更多...
class	CLibSVMOneClass
	class LibSVMOneClass 更多...
class	CMPDSVM
	class MPDSVM 更多...
class	CMultiClassSVM
	class MultiClassSVM 更多...
class	CQPBSVMLib
	class QPBSVMLib 更多...
class	CScatterSVM
	ScatterSVM - Multiclass SVM. 更多...
class	CSubGradientSVM
	class SubGradientSVM 更多...
class	CSVM
	A generic Support Vector Machine Interface. 更多...
class	CSVMLin
	class SVMLin 更多...
class	CSVMOcas
	class SVMOcas 更多...
class	CSVMSGD
	class SVMSGD 更多...
class	CWDSVMOcas
	class WDSVMOcas 更多...
class	CHierarchical
	Agglomerative hierarchical single linkage clustering. 更多...
class	CKMeans
	KMeans clustering, partitions the data into k (a-priori specified) clusters. 更多...
class	CBrayCurtisDistance
	class Bray-Curtis distance 更多...
class	CCanberraMetric
	class CanberraMetric 更多...
class	CCanberraWordDistance
	class CanberraWordDistance 更多...
class	CChebyshewMetric
	class ChebyshewMetric 更多...
class	CChiSquareDistance
	class ChiSquareDistance 更多...
class	CCosineDistance
	class CosineDistance 更多...
class	CDistance
	class Distance 更多...
class	CEuclidianDistance
	class EuclidianDistance 更多...
class	CGeodesicMetric
	class GeodesicMetric 更多...
class	CHammingWordDistance
	class HammingWordDistance 更多...
class	CJensenMetric
	class JensenMetric 更多...
class	CManhattanMetric
	class ManhattanMetric 更多...
class	CManhattanWordDistance
	class ManhattanWordDistance 更多...
class	CMinkowskiMetric
	class MinkowskiMetric 更多...
class	CRealDistance
	class RealDistance 更多...
class	CSimpleDistance
	template class SimpleDistance 更多...
class	CSparseDistance
	template class SparseDistance 更多...
class	CSparseEuclidianDistance
	class SparseEucldianDistance 更多...
class	CStringDistance
	template class StringDistance 更多...
class	CTanimotoDistance
	class Tanimoto coefficient 更多...
class	CDistribution
	Base class Distribution from which all methods implementing a distribution are derived. 更多...
class	CGHMM
	class GHMM - this class is non-functional and was meant to implement a Generalize Hidden Markov Model (aka Semi Hidden Markov HMM). 更多...
class	CHistogram
	Class Histogram computes a histogram over all 16bit unsigned integers in the features. 更多...
class	CModel
	class Model 更多...
class	CHMM
	Hidden Markov Model. 更多...
class	CLinearHMM
	The class LinearHMM is for learning Higher Order Markov chains. 更多...
class	CPerformanceMeasures
	Class to implement various performance measures. 更多...
class	CAlphabet
	The class Alphabet implements an alphabet and alphabet utility functions. 更多...
class	CAttributeFeatures
	Implements attributed features, that is in the simplest case a number of (attribute, value) pairs. 更多...
class	CCombinedDotFeatures
	Features that allow stacking of a number of DotFeatures. 更多...
class	CCombinedFeatures
	The class CombinedFeatures is used to combine a number of of feature objects into a single CombinedFeatures object. 更多...
class	CDotFeatures
	Features that support dot products among other operations. 更多...
class	CDummyFeatures
	The class DummyFeatures implements features that only know the number of feature objects (but don't actually contain any). 更多...
class	CExplicitSpecFeatures
	Features that compute the Spectrum Kernel feature space explicitly. 更多...
class	CFeatures
	The class Features is the base class of all feature objects. 更多...
class	CFKFeatures
	The class FKFeatures implements Fischer kernel features obtained from two Hidden Markov models. 更多...
class	CHashedWDFeatures
	Features that compute the Weighted Degreee Kernel feature space explicitly. 更多...
class	CHashedWDFeaturesTransposed
	Features that compute the Weighted Degreee Kernel feature space explicitly. 更多...
class	CImplicitWeightedSpecFeatures
	Features that compute the Weighted Spectrum Kernel feature space explicitly. 更多...
class	CLabels
	The class Labels models labels, i.e. class assignments of objects. 更多...
class	CPolyFeatures
	implement DotFeatures for the polynomial kernel 更多...
class	CRealFileFeatures
	The class RealFileFeatures implements a dense double-precision floating point matrix from a file. 更多...
class	CSimpleFeatures
	The class SimpleFeatures implements dense feature matrices. 更多...
class	CSNPFeatures
	Features that compute the Weighted Degreee Kernel feature space explicitly. 更多...
class	CSparseFeatures
	Template class SparseFeatures implements sparse matrices. 更多...
class	CSparsePolyFeatures
	implement DotFeatures for the polynomial kernel 更多...
class	CStringFeatures
	Template class StringFeatures implements a list of strings. 更多...
class	CStringFileFeatures
	File based string features. 更多...
class	CTOPFeatures
	The class TOPFeatures implements TOP kernel features obtained from two Hidden Markov models. 更多...
class	CWDFeatures
	Features that compute the Weighted Degreee Kernel feature space explicitly. 更多...
class	CSignalModel
	class SignalModel 更多...
class	CTrainPredMaster
	class TrainPredMaster 更多...
class	CAUCKernel
	The AUC kernel can be used to maximize the area under the receiver operator characteristic curve (AUC) instead of margin in SVM training. 更多...
class	CAvgDiagKernelNormalizer
	Normalize the kernel by either a constant or the average value of the diagonal elements (depending on argument c of the constructor). 更多...
class	CChi2Kernel
	The Chi2 kernel operating on realvalued vectors computes the chi-squared distance between sets of histograms. 更多...
class	CCombinedKernel
	The Combined kernel is used to combine a number of kernels into a single CombinedKernel object by linear combination. 更多...
class	CCommUlongStringKernel
	The CommUlongString kernel may be used to compute the spectrum kernel from strings that have been mapped into unsigned 64bit integers. 更多...
class	CCommWordStringKernel
	The CommWordString kernel may be used to compute the spectrum kernel from strings that have been mapped into unsigned 16bit integers. 更多...
class	CConstKernel
	The Constant Kernel returns a constant for all elements. 更多...
class	CCustomKernel
	The Custom Kernel allows for custom user provided kernel matrices. 更多...
class	CDiagKernel
	The Diagonal Kernel returns a constant for the diagonal and zero otherwise. 更多...
class	CDiceKernelNormalizer
	DiceKernelNormalizer performs kernel normalization inspired by the Dice coefficient (see http://en.wikipedia.org/wiki/Dice's_coefficient). 更多...
class	CDistanceKernel
	The Distance kernel takes a distance as input. 更多...
class	CFirstElementKernelNormalizer
	Normalize the kernel by a constant obtained from the first element of the kernel matrix, i.e. $c=k({\bf x},{\bf x})$ . 更多...
class	CFixedDegreeStringKernel
	The FixedDegree String kernel takes as input two strings of same size and counts the number of matches of length d. 更多...
class	CGaussianKernel
	The well known Gaussian kernel (swiss army knife for SVMs) on dense real valued features. 更多...
class	CGaussianMatchStringKernel
	The class GaussianMatchStringKernel computes a variant of the Gaussian kernel on strings of same length. 更多...
class	CGaussianShiftKernel
	An experimental kernel inspired by the WeightedDegreePositionStringKernel and the Gaussian kernel. 更多...
class	CGaussianShortRealKernel
	The well known Gaussian kernel (swiss army knife for SVMs) on dense short-real valued features. 更多...
class	CHistogramWordStringKernel
	The HistogramWordString computes the TOP kernel on inhomogeneous Markov Chains. 更多...
class	CIdentityKernelNormalizer
	Identity Kernel Normalization, i.e. no normalization is applied. 更多...
struct	K_THREAD_PARAM
class	CKernel
	The Kernel base class. 更多...
class	CKernelNormalizer
	The class Kernel Normalizer defines a function to post-process kernel values. 更多...
class	CLinearByteKernel
	Computes the standard linear kernel on dense byte valued features. 更多...
class	CLinearKernel
	Computes the standard linear kernel on dense real valued features. 更多...
class	CLinearStringKernel
	Computes the standard linear kernel on dense char valued features. 更多...
class	CLinearWordKernel
	Computes the standard linear kernel on dense word (2-byte) valued features. 更多...
class	CLocalAlignmentStringKernel
	The LocalAlignmentString kernel compares two sequences through all possible local alignments between the two sequences. 更多...
class	CLocalityImprovedStringKernel
	The LocalityImprovedString kernel is inspired by the polynomial kernel. Comparing neighboring characters it puts emphasize on local features. 更多...
class	CMatchWordStringKernel
	The class MatchWordStringKernel computes a variant of the polynomial kernel on strings of same length converted to a word alphabet. 更多...
class	CMultitaskKernelMaskNormalizer
	The MultitaskKernel allows Multitask Learning via a modified kernel function. 更多...
class	CMultitaskKernelMaskPairNormalizer
	The MultitaskKernel allows Multitask Learning via a modified kernel function. 更多...
class	CMultitaskKernelMklNormalizer
	Base-class for parameterized Kernel Normalizers. 更多...
class	CMultitaskKernelNormalizer
	The MultitaskKernel allows Multitask Learning via a modified kernel function. 更多...
class	CMultitaskKernelPlifNormalizer
	The MultitaskKernel allows learning a piece-wise linear function (PLIF) via MKL. 更多...
class	CNode
	A CNode is an element of a CTaxonomy, which is used to describe hierarchical structure between tasks. 更多...
class	CTaxonomy
	CTaxonomy is used to describe hierarchical structure between tasks. 更多...
class	CMultitaskKernelTreeNormalizer
	The MultitaskKernel allows Multitask Learning via a modified kernel function based on taxonomy. 更多...
class	COligoStringKernel
	This class offers access to the Oligo Kernel introduced by Meinicke et al. in 2004. 更多...
class	CPolyKernel
	Computes the standard polynomial kernel on dense real valued features. 更多...
class	CPolyMatchStringKernel
	The class PolyMatchStringKernel computes a variant of the polynomial kernel on strings of same length. 更多...
class	CPolyMatchWordStringKernel
	The class PolyMatchWordStringKernel computes a variant of the polynomial kernel on word-features. 更多...
class	CPyramidChi2
	Pyramid Kernel over Chi2 matched histograms. 更多...
class	CRegulatoryModulesStringKernel
	The Regulaty Modules kernel, based on the WD kernel, as published in Schultheiss et al., Bioinformatics (2009) on regulatory sequences. 更多...
class	CRidgeKernelNormalizer
	Normalize the kernel by adding a constant term to its diagonal. This aids kernels to become positive definite (even though they are not - often caused by numerical problems). 更多...
class	CSalzbergWordStringKernel
	The SalzbergWordString kernel implements the Salzberg kernel. 更多...
class	CScatterKernelNormalizer
class	CSigmoidKernel
	The standard Sigmoid kernel computed on dense real valued features. 更多...
class	CSimpleKernel
	Template class SimpleKernel is the base class for kernels working on Simple features. 更多...
class	CSimpleLocalityImprovedStringKernel
	SimpleLocalityImprovedString kernel, is a ``simplified'' and better performing version of the Locality improved kernel. 更多...
class	CSNPStringKernel
	The class SNPStringKernel computes a variant of the polynomial kernel on strings of same length. 更多...
class	CSparseGaussianKernel
	The well known Gaussian kernel (swiss army knife for SVMs) on sparse real valued features. 更多...
class	CSparseKernel
	Template class SparseKernel, is the base class of kernels working on sparse features. 更多...
class	CSparseLinearKernel
	Computes the standard linear kernel on sparse real valued features. 更多...
class	CSparsePolyKernel
	Computes the standard polynomial kernel on sparse real valued features. 更多...
struct	joint_list_struct
class	CSpectrumMismatchRBFKernel
class	CSpectrumRBFKernel
class	CSqrtDiagKernelNormalizer
	SqrtDiagKernelNormalizer divides by the Square Root of the product of the diagonal elements. 更多...
class	CStringKernel
	Template class StringKernel, is the base class of all String Kernels. 更多...
class	CTanimotoKernelNormalizer
	TanimotoKernelNormalizer performs kernel normalization inspired by the Tanimoto coefficient (see http://en.wikipedia.org/wiki/Jaccard_index ). 更多...
class	CTensorProductPairKernel
	Computes the Tensor Product Pair Kernel (TPPK). 更多...
class	CVarianceKernelNormalizer
	VarianceKernelNormalizer divides by the ``variance''. 更多...
class	CWeightedCommWordStringKernel
	The WeightedCommWordString kernel may be used to compute the weighted spectrum kernel (i.e. a spectrum kernel for 1 to K-mers, where each k-mer length is weighted by some coefficient $\beta_k$ ) from strings that have been mapped into unsigned 16bit integers. 更多...
class	CWeightedDegreePositionStringKernel
	The Weighted Degree Position String kernel (Weighted Degree kernel with shifts). 更多...
class	CWeightedDegreeRBFKernel
class	CWeightedDegreeStringKernel
	The Weighted Degree String kernel. 更多...
class	CArray
	Template class Array implements a dense one dimensional array. 更多...
class	CArray2
	Template class Array2 implements a dense two dimensional array. 更多...
class	CArray3
	Template class Array3 implements a dense three dimensional array. 更多...
class	CAsciiFile
	A Ascii File access class. 更多...
class	CBinaryFile
	A Binary file access class. 更多...
class	CBinaryStream
	memory mapped emulation via binary streams (files) 更多...
class	CBitString
	a string class embedding a string in a compact bit representation 更多...
class	CCache
	Template class Cache implements a simple cache. 更多...
class	CCompressor
class	CCplex
	Class CCplex to encapsulate access to the commercial cplex general purpose optimizer. 更多...
class	CDynamicArray
	Template Dynamic array class that creates an array that can be used like a list or an array. 更多...
class	CDynInt
	integer type of dynamic size 更多...
class	CFile
	A File access base class. 更多...
class	CGCArray
	Template class GCArray implements a garbage collecting static array. 更多...
class	CHash
	Collection of Hashing Functions. 更多...
class	CHDF5File
	A HDF5 File access class. 更多...
class	CIndirectObject
	an array class that accesses elements indirectly via an index array. 更多...
class	CIO
	Class IO, used to do input output operations throughout shogun. 更多...
class	CListElement
	Class ListElement, defines how an element of the the list looks like. 更多...
class	CList
	Class List implements a doubly connected list for low-level-objects. 更多...
class	CMath
	Class which collects generic mathematical functions. 更多...
class	CMemoryMappedFile
	memory mapped file 更多...
class	CRange
struct	TParameter
class	CParameter
class	CSet
	Template Set class. 更多...
class	ShogunException
	Class ShogunException defines an exception which is thrown whenever an error inside of shogun occurs. 更多...
class	CSignal
	Class Signal implements signal handling to e.g. allow ctrl+c to cancel a long running process. 更多...
class	CSimpleFile
	Template class SimpleFile to read and write from files. 更多...
class	CTime
	Class Time that implements a stopwatch based on either cpu time or wall clock time. 更多...
class	CTrie
	Template class Trie implements a suffix trie, i.e. a tree in which all suffixes up to a certain length are stored. 更多...
class	CDecompressString
	Preprocessor that decompresses compressed strings. 更多...
class	CLogPlusOne
	Preprocessor LogPlusOne does what the name says, it adds one to a dense real valued vector and takes the logarithm of each component of it. 更多...
class	CNormDerivativeLem3
	Preprocessor NormDerivativeLem3, performs the normalization used in Lemma3 in Jaakola Hausslers Fischer Kernel paper currently not implemented 更多...
class	CNormOne
	Preprocessor NormOne, normalizes vectors to have norm 1. 更多...
class	CPCACut
	Preprocessor PCACut performs principial component analysis on the input vectors and keeps only the n eigenvectors with eigenvalues above a certain threshold. 更多...
class	CPreProc
	Class PreProc defines a preprocessor interface. 更多...
class	CPruneVarSubMean
	Preprocessor PruneVarSubMean will substract the mean and remove features that have zero variance. 更多...
class	CSimplePreProc
	Template class SimplePreProc, base class for preprocessors (cf. CPreProc) that apply to CSimpleFeatures (i.e. rectangular dense matrices). 更多...
class	CSortUlongString
	Preprocessor SortUlongString, sorts the indivual strings in ascending order. 更多...
class	CSortWordString
	Preprocessor SortWordString, sorts the indivual strings in ascending order. 更多...
class	CSparsePreProc
	Template class SparsePreProc, base class for preprocessors (cf. CPreProc) that apply to CSparseFeatures. 更多...
class	CStringPreProc
	Template class StringPreProc, base class for preprocessors (cf. CPreProc) that apply to CStringFeatures (i.e. strings of variable length). 更多...
class	CKRR
	Class KRR implements Kernel Ridge Regression - a regularized least square method for classification and regression. 更多...
class	CLibSVR
	Class LibSVR, performs support vector regression using LibSVM. 更多...
class	CMKLRegression
	Multiple Kernel Learning for regression. 更多...
struct	segment_loss_struct
	segment loss 更多...
class	CDynProg
	Dynamic Programming Class. 更多...
class	CIntronList
	class IntronList 更多...
class	CPlif
	class Plif 更多...
class	CPlifArray
	class PlifArray 更多...
class	CPlifBase
	class PlifBase 更多...
class	CPlifMatrix
	store plif arrays for all transitions in the model 更多...
class	CSegmentLoss
	class IntronList 更多...
类型定义
typedef float64_t	KERNELCACHE_ELEM
typedef int64_t	KERNELCACHE_IDX
typedef CDynInt< uint64_t, 3 >	uint192_t
typedef CDynInt< uint64_t, 3 >	uint256_t
typedef CDynInt< uint64_t, 3 >	uint512_t
typedef CDynInt< uint64_t, 3 >	uint1024_t
HMM specific types

typedef float64_t	T_ALPHA_BETA_TABLE
	type for alpha/beta caching table
typedef uint8_t	T_STATES
typedef T_STATES *	P_STATES
枚举
enum	EClassifierType { CT_NONE = 0, CT_LIGHT = 10, CT_LIBSVM = 20, CT_LIBSVMONECLASS = 30, CT_LIBSVMMULTICLASS = 40, CT_MPD = 50, CT_GPBT = 60, CT_CPLEXSVM = 70, CT_PERCEPTRON = 80, CT_KERNELPERCEPTRON = 90, CT_LDA = 100, CT_LPM = 110, CT_LPBOOST = 120, CT_KNN = 130, CT_SVMLIN = 140, CT_KRR = 150, CT_GNPPSVM = 160, CT_GMNPSVM = 170, CT_SUBGRADIENTSVM = 180, CT_SUBGRADIENTLPM = 190, CT_SVMPERF = 200, CT_LIBSVR = 210, CT_SVRLIGHT = 220, CT_LIBLINEAR = 230, CT_KMEANS = 240, CT_HIERARCHICAL = 250, CT_SVMOCAS = 260, CT_WDSVMOCAS = 270, CT_SVMSGD = 280, CT_MKLMULTICLASS = 290, CT_MKLCLASSIFICATION = 300, CT_MKLONECLASS = 310, CT_MKLREGRESSION = 320, CT_SCATTERSVM = 330, CT_DASVM = 340, CT_LARANK = 350 }
enum	ESolverType { ST_AUTO = 0, ST_CPLEX = 1, ST_GLPK = 2, ST_NEWTON = 3, ST_DIRECT = 4, ST_ELASTICNET = 5 }
enum	LIBLINEAR_SOLVER_TYPE { L2R_LR, L2R_L2LOSS_SVC_DUAL, L2R_L2LOSS_SVC, L2R_L1LOSS_SVC_DUAL, MCSVM_CS, L1R_L2LOSS_SVC, L1R_LR }
enum	LIBSVM_SOLVER_TYPE { LIBSVM_C_SVC = 1, LIBSVM_NU_SVC = 2 }
enum	EMultiClassSVM { ONE_VS_REST, ONE_VS_ONE }
enum	E_QPB_SOLVER { QPB_SOLVER_SCA, QPB_SOLVER_SCAS, QPB_SOLVER_SCAMV, QPB_SOLVER_PRLOQO, QPB_SOLVER_CPLEX, QPB_SOLVER_GS, QPB_SOLVER_GRADDESC }
enum	E_SVM_TYPE { SVM_OCAS = 0, SVM_BMRM = 1 }
enum	EDistanceType { D_UNKNOWN = 0, D_MINKOWSKI = 10, D_MANHATTAN = 20, D_CANBERRA = 30, D_CHEBYSHEW = 40, D_GEODESIC = 50, D_JENSEN = 60, D_MANHATTANWORD = 70, D_HAMMINGWORD = 80, D_CANBERRAWORD = 90, D_SPARSEEUCLIDIAN = 100, D_EUCLIDIAN = 110, D_CHISQUARE = 120, D_TANIMOTO = 130, D_COSINE = 140, D_BRAYCURTIS = 150 }
enum	BaumWelchViterbiType { BW_NORMAL, BW_TRANS, BW_DEFINED, VIT_NORMAL, VIT_DEFINED }
enum	EAlphabet { DNA = 0, RAWDNA = 1, RNA = 2, PROTEIN = 3, BINARY = 4, ALPHANUM = 5, CUBE = 6, RAWBYTE = 7, IUPAC_NUCLEIC_ACID = 8, IUPAC_AMINO_ACID = 9, NONE = 10, DIGIT = 11, DIGIT2 = 12, RAWDIGIT = 13, RAWDIGIT2 = 14, UNKNOWN = 15, SNP = 16, RAWSNP = 17 }
	Alphabet of charfeatures/observations. 更多...
enum	EFeatureType { F_UNKNOWN = 0, F_BOOL = 5, F_CHAR = 10, F_BYTE = 20, F_SHORT = 30, F_WORD = 40, F_INT = 50, F_UINT = 60, F_LONG = 70, F_ULONG = 80, F_SHORTREAL = 90, F_DREAL = 100, F_LONGREAL = 110, F_ANY = 1000 }
	shogun feature type 更多...
enum	EFeatureClass { C_UNKNOWN = 0, C_SIMPLE = 10, C_SPARSE = 20, C_STRING = 30, C_COMBINED = 40, C_COMBINED_DOT = 60, C_WD = 70, C_SPEC = 80, C_WEIGHTEDSPEC = 90, C_POLY = 100, C_ANY = 1000 }
	shogun feature class 更多...
enum	EFeatureProperty { FP_NONE = 0, FP_DOT = 1 }
	shogun feature properties 更多...
enum	EOptimizationType { FASTBUTMEMHUNGRY, SLOWBUTMEMEFFICIENT }
enum	EKernelType { K_UNKNOWN = 0, K_LINEAR = 10, K_SPARSELINEAR = 11, K_POLY = 20, K_GAUSSIAN = 30, K_SPARSEGAUSSIAN = 31, K_GAUSSIANSHIFT = 32, K_GAUSSIANMATCH = 33, K_HISTOGRAM = 40, K_SALZBERG = 41, K_LOCALITYIMPROVED = 50, K_SIMPLELOCALITYIMPROVED = 60, K_FIXEDDEGREE = 70, K_WEIGHTEDDEGREE = 80, K_WEIGHTEDDEGREEPOS = 81, K_WEIGHTEDDEGREERBF = 82, K_WEIGHTEDCOMMWORDSTRING = 90, K_POLYMATCH = 100, K_ALIGNMENT = 110, K_COMMWORDSTRING = 120, K_COMMULONGSTRING = 121, K_SPECTRUMMISMATCHRBF = 122, K_COMBINED = 140, K_AUC = 150, K_CUSTOM = 160, K_SIGMOID = 170, K_CHI2 = 180, K_DIAG = 190, K_CONST = 200, K_DISTANCE = 220, K_LOCALALIGNMENT = 230, K_PYRAMIDCHI2 = 240, K_OLIGO = 250, K_MATCHWORD = 260, K_TPPK = 270, K_REGULATORYMODULES = 280 }
enum	EKernelProperty { KP_NONE = 0, KP_LINADD = 1, KP_KERNCOMBINATION = 2, KP_BATCHEVALUATION = 4 }
enum	ENormalizerType { N_REGULAR = 0, N_MULTITASK = 1 }
enum	EWDKernType { E_WD = 0, E_EXTERNAL = 1, E_BLOCK_CONST = 2, E_BLOCK_LINEAR = 3, E_BLOCK_SQPOLY = 4, E_BLOCK_CUBICPOLY = 5, E_BLOCK_EXP = 6, E_BLOCK_LOG = 7, E_BLOCK_EXTERNAL = 8 }
enum	E_COMPRESSION_TYPE { UNCOMPRESSED, LZO, GZIP, BZIP2, LZMA }
enum	E_PROB_TYPE { E_LINEAR, E_QP }
enum	SGDataType { DT_UNDEFINED = 0, DT_SCALAR_BOOL = 100, DT_SCALAR_BYTE, DT_SCALAR_CHAR, DT_SCALAR_INT, DT_SCALAR_UINT, DT_SCALAR_LONG, DT_SCALAR_ULONG, DT_SCALAR_REAL, DT_SCALAR_SHORTREAL, DT_SCALAR_LONGREAL, DT_SCALAR_SHORT, DT_SCALAR_WORD, DT_VECTOR_BOOL = 200, DT_VECTOR_BYTE, DT_VECTOR_CHAR, DT_VECTOR_INT, DT_VECTOR_UINT, DT_VECTOR_LONG, DT_VECTOR_ULONG, DT_VECTOR_REAL, DT_VECTOR_SHORTREAL, DT_VECTOR_LONGREAL, DT_VECTOR_SHORT, DT_VECTOR_WORD, DT_DENSE_BOOL = 300, DT_DENSE_BYTE, DT_DENSE_CHAR, DT_DENSE_INT, DT_DENSE_UINT, DT_DENSE_LONG, DT_DENSE_ULONG, DT_DENSE_REAL, DT_DENSE_SHORTREAL, DT_DENSE_LONGREAL, DT_DENSE_SHORT, DT_DENSE_WORD, DT_NDARRAY_BOOL = 400, DT_NDARRAY_BYTE, DT_NDARRAY_CHAR, DT_NDARRAY_INT, DT_NDARRAY_UINT, DT_NDARRAY_LONG, DT_NDARRAY_ULONG, DT_NDARRAY_REAL, DT_NDARRAY_SHORTREAL, DT_NDARRAY_LONGREAL, DT_NDARRAY_SHORT, DT_NDARRAY_WORD, DT_SPARSE_BOOL = 500, DT_SPARSE_BYTE, DT_SPARSE_CHAR, DT_SPARSE_INT, DT_SPARSE_UINT, DT_SPARSE_LONG, DT_SPARSE_ULONG, DT_SPARSE_REAL, DT_SPARSE_SHORTREAL, DT_SPARSE_LONGREAL, DT_SPARSE_SHORT, DT_SPARSE_WORD, DT_STRING_BOOL = 600, DT_STRING_BYTE, DT_STRING_CHAR, DT_STRING_INT, DT_STRING_UINT, DT_STRING_LONG, DT_STRING_ULONG, DT_STRING_REAL, DT_STRING_SHORTREAL, DT_STRING_LONGREAL, DT_STRING_SHORT, DT_STRING_WORD, DT_ATTR_STRUCT = 700, DT_SHOGUN_OBJECT = 1000 }
enum	EMessageType { MSG_GCDEBUG, MSG_DEBUG, MSG_INFO, MSG_NOTICE, MSG_WARN, MSG_ERROR, MSG_CRITICAL, MSG_ALERT, MSG_EMERGENCY, MSG_MESSAGEONLY }
enum	EPreProcType { P_UNKNOWN = 0, P_NORMONE = 10, P_LOGPLUSONE = 20, P_SORTWORDSTRING = 30, P_SORTULONGSTRING = 40, P_SORTWORD = 50, P_PRUNEVARSUBMEAN = 60, P_DECOMPRESSCHARSTRING = 70, P_DECOMPRESSBYTESTRING = 80, P_DECOMPRESSWORDSTRING = 90, P_DECOMPRESSULONGSTRING = 100 }
enum	ERegressionType { RT_NONE = 0, RT_LIGHT = 10, RT_LIBSVM = 20 }
enum	ETransformType { T_LINEAR, T_LOG, T_LOG_PLUS1, T_LOG_PLUS3, T_LINEAR_PLUS3 }
函数
void	init_shogun (void(print_message)(FILE target, const char str), void(print_warning)(FILE target, const char str), void(print_error)(FILE target, const char str), void(cancel_computations)(bool &delayed, bool &immediately))
void	exit_shogun ()
void	set_global_io (CIO *io)
CIO *	get_global_io ()
void	set_global_parallel (CParallel *parallel)
CParallel *	get_global_parallel ()
void	set_global_version (CVersion *version)
CVersion *	get_global_version ()
void	set_global_math (CMath *math)
CMath *	get_global_math ()
int32_t	InnerProjector (int32_t method, int32_t n, int32_t iy, float64_t e, float64_t qk, float64_t l, float64_t u, float64_t *x, float64_t &lambda)
int32_t	gvpm (int32_t Projector, int32_t n, float32_t vecA, float64_t b, float64_t c, float64_t e, int32_t iy, float64_t x, float64_t tol, int32_t ls, int32_t proj)
int32_t	FletcherAlg2A (int32_t Projector, int32_t n, float32_t vecA, float64_t b, float64_t c, float64_t e, int32_t iy, float64_t x, float64_t tol, int32_t ls, int32_t proj)
int32_t	gpm_solver (int32_t Solver, int32_t Projector, int32_t n, float32_t A, float64_t b, float64_t c, float64_t e, int32_t iy, float64_t x, float64_t tol, int32_t ls, int32_t proj)
float64_t	ProjectR (float64_t x, int32_t n, float64_t lambda, int32_t a, float64_t b, float64_t *c, float64_t l, float64_t u)
int32_t	ProjectDai (int32_t n, int32_t a, float64_t b, float64_t c, float64_t l, float64_t u, float64_t *x, float64_t &lam_ext)
float64_t	quick_select (float64_t *arr, int32_t n)
int32_t	Pardalos (int32_t n, int32_t iy, float64_t e, float64_t qk, float64_t low, float64_t up, float64_t *x)
static void *	xmalloc (int32_t n)
static void *	xrealloc (void *ptr, int32_t n)
static larank_kcache_t *	larank_kcache_create (CKernel *kernelfunc)
static void	xtruncate (larank_kcache_t *self, int32_t k, int32_t nlen)
static void	xpurge (larank_kcache_t *self)
static void	larank_kcache_set_maximum_size (larank_kcache_t *self, int64_t entries)
static void	larank_kcache_destroy (larank_kcache_t *self)
static void	xminsize (larank_kcache_t *self, int32_t n)
static int32_t *	larank_kcache_r2i (larank_kcache_t *self, int32_t n)
static void	xextend (larank_kcache_t *self, int32_t k, int32_t nlen)
static void	xswap (larank_kcache_t *self, int32_t i1, int32_t i2, int32_t r1, int32_t r2)
static void	larank_kcache_swap_rr (larank_kcache_t *self, int32_t r1, int32_t r2)
static void	larank_kcache_swap_ri (larank_kcache_t *self, int32_t r1, int32_t i2)
static float64_t	xquery (larank_kcache_t *self, int32_t i, int32_t j)
static float64_t	larank_kcache_query (larank_kcache_t *self, int32_t i, int32_t j)
static void	larank_kcache_set_buddy (larank_kcache_t self, larank_kcache_t buddy)
static float32_t *	larank_kcache_query_row (larank_kcache_t *self, int32_t i, int32_t len)
static const void *	get_col (uint32_t i)
static float64_t	get_time ()
ocas_return_value_T	svm_ocas_solver (float64_t C, uint32_t nData, float64_t TolRel, float64_t TolAbs, float64_t QPBound, uint32_t _BufSize, uint8_t Method, void(compute_W)(float64_t , float64_t , float64_t , uint32_t, void ), float64_t(update_W)(float64_t, void ), void(add_new_cut)(float64_t , uint32_t , uint32_t, uint32_t, void ), void(compute_output)(float64_t , void ), void(sort)(float64_t , uint32_t , uint32_t), void user_data)
void	nrerror (char error_text[])
bool	choldc (float64_t a, int32_t n, float64_t p)
void	cholsb (float64_t a[], int32_t n, float64_t p[], float64_t b[], float64_t x[])
void	chol_forward (float64_t a[], int32_t n, float64_t p[], float64_t b[], float64_t x[])
void	chol_backward (float64_t a[], int32_t n, float64_t p[], float64_t b[], float64_t x[])
bool	solve_reduced (int32_t n, int32_t m, float64_t h_x[], float64_t h_y[], float64_t a[], float64_t x_x[], float64_t x_y[], float64_t c_x[], float64_t c_y[], float64_t workspace[], int32_t step)
void	matrix_vector (int32_t n, float64_t m[], float64_t x[], float64_t y[])
int32_t	pr_loqo (int32_t n, int32_t m, float64_t c[], float64_t h_x[], float64_t a[], float64_t b[], float64_t l[], float64_t u[], float64_t primal[], float64_t dual[], int32_t verb, float64_t sigfig_max, int32_t counter_max, float64_t margin, float64_t bound, int32_t restart)
int8_t	qpssvm_solver (const void (get_col)(uint32_t), float64_t diag_H, float64_t f, float64_t b, uint16_t I, float64_t x, uint32_t n, uint32_t tmax, float64_t tolabs, float64_t tolrel, float64_t QP, float64_t QD, uint32_t verb)
void	ssl_train (struct data Data, struct options Options, struct vector_double Weights, struct vector_double Outputs)
int32_t	CGLS (const struct data Data, const struct options Options, const struct vector_int Subset, struct vector_double Weights, struct vector_double *Outputs)
int32_t	L2_SVM_MFN (const struct data Data, struct options Options, struct vector_double Weights, struct vector_double Outputs, int32_t ini)
float64_t	line_search (float64_t w, float64_t w_bar, float64_t lambda, float64_t o, float64_t o_bar, float64_t Y, float64_t C, int32_t d, int32_t l)
int32_t	TSVM_MFN (const struct data Data, struct options Options, struct vector_double Weights, struct vector_double Outputs)
int32_t	switch_labels (float64_t Y, float64_t o, int32_t *JU, int32_t u, int32_t S)
int32_t	DA_S3VM (struct data Data, struct options Options, struct vector_double Weights, struct vector_double Outputs)
int32_t	optimize_w (const struct data Data, const float64_t p, struct options Options, struct vector_double Weights, struct vector_double *Outputs, int32_t ini)
void	optimize_p (const float64_t g, int32_t u, float64_t T, float64_t r, float64_t p)
float64_t	transductive_cost (float64_t normWeights, float64_t Y, float64_t Outputs, int32_t m, float64_t lambda, float64_t lambda_u)
float64_t	entropy (const float64_t *p, int32_t u)
float64_t	KL (const float64_t p, const float64_t q, int32_t u)
float64_t	norm_square (const vector_double *A)
void	initialize (struct vector_double *A, int32_t k, float64_t a)
void	initialize (struct vector_int *A, int32_t k)
void	GetLabeledData (struct data D, const struct data Data)
void *	sqdist_thread_func (void *P)
void	wrap_dsyev (char jobz, char uplo, int n, double a, int lda, double w, int *info)
void	wrap_dgesvd (char jobu, char jobvt, int m, int n, double a, int lda, double sing, double u, int ldu, double vt, int ldvt, int *info)
bool	read_real_valued_sparse (TSparse< float64_t > *&matrix, int32_t &num_feat, int32_t &num_vec)
bool	write_real_valued_sparse (const TSparse< float64_t > *matrix, int32_t num_feat, int32_t num_vec)
bool	read_real_valued_dense (float64_t *&matrix, int32_t &num_feat, int32_t &num_vec)
bool	write_real_valued_dense (const float64_t *matrix, int32_t num_feat, int32_t num_vec)
bool	read_char_valued_strings (T_STRING< char > *&strings, int32_t &num_str, int32_t &max_string_len)
bool	write_char_valued_strings (const T_STRING< char > *strings, int32_t num_str)
变量
CParallel *	sg_parallel = NULL
CIO *	sg_io = NULL
CVersion *	sg_version = NULL
CMath *	sg_math = NULL
void(*	sg_print_message )(FILE target, const char str) = NULL
	function called to print normal messages
void(*	sg_print_warning )(FILE target, const char str) = NULL
	function called to print warning messages
void(*	sg_print_error )(FILE target, const char str) = NULL
	function called to print error messages
void(*	sg_cancel_computations )(bool &delayed, bool &immediately) = NULL
	function called to cancel things
uint32_t	Randnext
static const uint32_t	QPSolverMaxIter = 10000000
static float64_t *	H
static uint32_t	BufSize

详细描述

all of classes and functions are contained in the shogun namespace

类型定义文档

typedef float64_t KERNELCACHE_ELEM

在文件Kernel.h第30行定义。

typedef int64_t KERNELCACHE_IDX

在文件Kernel.h第38行定义。

typedef T_STATES * P_STATES

在文件HMM.h第66行定义。

typedef float64_t T_ALPHA_BETA_TABLE

type for alpha/beta caching table

在文件HMM.h第37行定义。

typedef uint16_t T_STATES

type that is used for states. Probably uint8_t is enough if you have at most 256 states, however uint16_t/long/... is also possible although you might quickly run into memory problems

在文件HMM.h第64行定义。

typedef CDynInt<uint64_t,3> uint1024_t

在文件DynInt.h第565行定义。

typedef CDynInt<uint64_t,3> uint192_t

convenience typedefs

在文件DynInt.h第562行定义。

typedef CDynInt<uint64_t,3> uint256_t

在文件DynInt.h第563行定义。

typedef CDynInt<uint64_t,3> uint512_t

在文件DynInt.h第564行定义。

枚举类型文档

enum BaumWelchViterbiType

枚举值:

BW_NORMAL
BW_TRANS
BW_DEFINED
VIT_NORMAL
VIT_DEFINED

在文件HMM.h第70行定义。

enum E_COMPRESSION_TYPE

枚举值:

UNCOMPRESSED
LZO
GZIP
BZIP2
LZMA

在文件Compressor.h第25行定义。

enum E_PROB_TYPE

枚举值:

E_LINEAR
E_QP

在文件Cplex.h第29行定义。

enum E_QPB_SOLVER

枚举值:

QPB_SOLVER_SCA
QPB_SOLVER_SCAS
QPB_SOLVER_SCAMV
QPB_SOLVER_PRLOQO
QPB_SOLVER_CPLEX
QPB_SOLVER_GS
QPB_SOLVER_GRADDESC

在文件qpbsvmlib.h第30行定义。

enum E_SVM_TYPE

枚举值:

SVM_OCAS
SVM_BMRM

在文件SVMOcas.h第22行定义。

enum EAlphabet

Alphabet of charfeatures/observations.

枚举值:

DNA	DNA - letters A,C,G,T.
RAWDNA	RAWDNA - letters 0,1,2,3.
RNA	RNA - letters A,C,G,U.
PROTEIN	PROTEIN - letters a-z.
BINARY
ALPHANUM	ALPHANUM - [0-9a-z].
CUBE	CUBE - [1-6].
RAWBYTE	RAW BYTE - [0-255].
IUPAC_NUCLEIC_ACID	IUPAC_NUCLEIC_ACID.
IUPAC_AMINO_ACID	IUPAC_AMINO_ACID.
NONE	NONE - type has no alphabet.
DIGIT	DIGIT - letters 0-9.
DIGIT2	DIGIT2 - letters 0-2.
RAWDIGIT	RAWDIGIT - 0-9.
RAWDIGIT2	RAWDIGIT2 - 0-2.
UNKNOWN	unknown alphabet
SNP	SNP - letters A,C,G,T,0.
RAWSNP	RAWSNP - letters 0,1,2,3,4.

在文件Alphabet.h第21行定义。

enum EClassifierType

枚举值:

CT_NONE
CT_LIGHT
CT_LIBSVM
CT_LIBSVMONECLASS
CT_LIBSVMMULTICLASS
CT_MPD
CT_GPBT
CT_CPLEXSVM
CT_PERCEPTRON
CT_KERNELPERCEPTRON
CT_LDA
CT_LPM
CT_LPBOOST
CT_KNN
CT_SVMLIN
CT_KRR
CT_GNPPSVM
CT_GMNPSVM
CT_SUBGRADIENTSVM
CT_SUBGRADIENTLPM
CT_SVMPERF
CT_LIBSVR
CT_SVRLIGHT
CT_LIBLINEAR
CT_KMEANS
CT_HIERARCHICAL
CT_SVMOCAS
CT_WDSVMOCAS
CT_SVMSGD
CT_MKLMULTICLASS
CT_MKLCLASSIFICATION
CT_MKLONECLASS
CT_MKLREGRESSION
CT_SCATTERSVM
CT_DASVM
CT_LARANK

在文件Classifier.h第27行定义。

enum EDistanceType

枚举值:

D_UNKNOWN
D_MINKOWSKI
D_MANHATTAN
D_CANBERRA
D_CHEBYSHEW
D_GEODESIC
D_JENSEN
D_MANHATTANWORD
D_HAMMINGWORD
D_CANBERRAWORD
D_SPARSEEUCLIDIAN
D_EUCLIDIAN
D_CHISQUARE
D_TANIMOTO
D_COSINE
D_BRAYCURTIS

在文件Distance.h第31行定义。

enum EFeatureClass

shogun feature class

枚举值:

C_UNKNOWN
C_SIMPLE
C_SPARSE
C_STRING
C_COMBINED
C_COMBINED_DOT
C_WD
C_SPEC
C_WEIGHTEDSPEC
C_POLY
C_ANY

在文件FeatureTypes.h第35行定义。

enum EFeatureProperty

shogun feature properties

枚举值:

FP_NONE
FP_DOT

在文件FeatureTypes.h第51行定义。

enum EFeatureType

shogun feature type

枚举值:

F_UNKNOWN
F_BOOL
F_CHAR
F_BYTE
F_SHORT
F_WORD
F_INT
F_UINT
F_LONG
F_ULONG
F_SHORTREAL
F_DREAL
F_LONGREAL
F_ANY

在文件FeatureTypes.h第16行定义。

enum EKernelProperty

枚举值:

KP_NONE
KP_LINADD
KP_KERNCOMBINATION
KP_BATCHEVALUATION

在文件Kernel.h第87行定义。

enum EKernelType

枚举值:

K_UNKNOWN
K_LINEAR
K_SPARSELINEAR
K_POLY
K_GAUSSIAN
K_SPARSEGAUSSIAN
K_GAUSSIANSHIFT
K_GAUSSIANMATCH
K_HISTOGRAM
K_SALZBERG
K_LOCALITYIMPROVED
K_SIMPLELOCALITYIMPROVED
K_FIXEDDEGREE
K_WEIGHTEDDEGREE
K_WEIGHTEDDEGREEPOS
K_WEIGHTEDDEGREERBF
K_WEIGHTEDCOMMWORDSTRING
K_POLYMATCH
K_ALIGNMENT
K_COMMWORDSTRING
K_COMMULONGSTRING
K_SPECTRUMMISMATCHRBF
K_COMBINED
K_AUC
K_CUSTOM
K_SIGMOID
K_CHI2
K_DIAG
K_CONST
K_DISTANCE
K_LOCALALIGNMENT
K_PYRAMIDCHI2
K_OLIGO
K_MATCHWORD
K_TPPK
K_REGULATORYMODULES

在文件Kernel.h第47行定义。

enum EMessageType

The io libs output [DEBUG] etc in front of every message 'higher' messages filter output depending on the loglevel, i.e. CRITICAL messages will print all MSG_CRITICAL TO MSG_EMERGENCY messages.

枚举值:

MSG_GCDEBUG
MSG_DEBUG
MSG_INFO
MSG_NOTICE
MSG_WARN
MSG_ERROR
MSG_CRITICAL
MSG_ALERT
MSG_EMERGENCY
MSG_MESSAGEONLY

在文件io.h第40行定义。

enum EMultiClassSVM

枚举值:

ONE_VS_REST
ONE_VS_ONE

在文件MultiClassSVM.h第21行定义。

enum ENormalizerType

normalizer type

枚举值:

N_REGULAR
N_MULTITASK

在文件KernelNormalizer.h第20行定义。

enum EOptimizationType

枚举值:

FASTBUTMEMHUNGRY
SLOWBUTMEMEFFICIENT

在文件Kernel.h第41行定义。

enum EPreProcType

枚举值:

P_UNKNOWN
P_NORMONE
P_LOGPLUSONE
P_SORTWORDSTRING
P_SORTULONGSTRING
P_SORTWORD
P_PRUNEVARSUBMEAN
P_DECOMPRESSCHARSTRING
P_DECOMPRESSBYTESTRING
P_DECOMPRESSWORDSTRING
P_DECOMPRESSULONGSTRING

在文件PreProc.h第26行定义。

enum ERegressionType

枚举值:

RT_NONE
RT_LIGHT
RT_LIBSVM

在文件Regression.h第16行定义。

enum ESolverType

枚举值:

ST_AUTO
ST_CPLEX
ST_GLPK
ST_NEWTON
ST_DIRECT
ST_ELASTICNET

在文件Classifier.h第67行定义。

enum ETransformType

枚举值:

T_LINEAR
T_LOG
T_LOG_PLUS1
T_LOG_PLUS3
T_LINEAR_PLUS3

在文件Plif.h第21行定义。

enum EWDKernType

枚举值:

E_WD
E_EXTERNAL
E_BLOCK_CONST
E_BLOCK_LINEAR
E_BLOCK_SQPOLY
E_BLOCK_CUBICPOLY
E_BLOCK_EXP
E_BLOCK_LOG
E_BLOCK_EXTERNAL

在文件WeightedDegreeStringKernel.h第29行定义。

enum LIBLINEAR_SOLVER_TYPE

liblinar solver type

枚举值:

L2R_LR	L2 regularized linear logistic regression.
L2R_L2LOSS_SVC_DUAL	L2 regularized SVM with L2-loss using dual coordinate descent.
L2R_L2LOSS_SVC	L2 regularized SVM with L2-loss using newton in the primal.
L2R_L1LOSS_SVC_DUAL	L2 regularized linear SVM with L1-loss using dual coordinate descent.
MCSVM_CS	linear multi-class svm by Crammer and Singer
L1R_L2LOSS_SVC	L1 regularized SVM with L2-loss using dual coordinate descent.
L1R_LR	L1 regularized logistic regression.

在文件LibLinear.h第25行定义。

enum LIBSVM_SOLVER_TYPE

枚举值:

LIBSVM_C_SVC
LIBSVM_NU_SVC

在文件LibSVM.h第20行定义。

enum SGDataType

枚举值:

DT_UNDEFINED
DT_SCALAR_BOOL	simple scalar/string types
DT_SCALAR_BYTE
DT_SCALAR_CHAR
DT_SCALAR_INT
DT_SCALAR_UINT
DT_SCALAR_LONG
DT_SCALAR_ULONG
DT_SCALAR_REAL
DT_SCALAR_SHORTREAL
DT_SCALAR_LONGREAL
DT_SCALAR_SHORT
DT_SCALAR_WORD
DT_VECTOR_BOOL	vector type
DT_VECTOR_BYTE
DT_VECTOR_CHAR
DT_VECTOR_INT
DT_VECTOR_UINT
DT_VECTOR_LONG
DT_VECTOR_ULONG
DT_VECTOR_REAL
DT_VECTOR_SHORTREAL
DT_VECTOR_LONGREAL
DT_VECTOR_SHORT
DT_VECTOR_WORD
DT_DENSE_BOOL	dense matrices
DT_DENSE_BYTE
DT_DENSE_CHAR
DT_DENSE_INT
DT_DENSE_UINT
DT_DENSE_LONG
DT_DENSE_ULONG
DT_DENSE_REAL
DT_DENSE_SHORTREAL
DT_DENSE_LONGREAL
DT_DENSE_SHORT
DT_DENSE_WORD
DT_NDARRAY_BOOL	dense nd arrays
DT_NDARRAY_BYTE
DT_NDARRAY_CHAR
DT_NDARRAY_INT
DT_NDARRAY_UINT
DT_NDARRAY_LONG
DT_NDARRAY_ULONG
DT_NDARRAY_REAL
DT_NDARRAY_SHORTREAL
DT_NDARRAY_LONGREAL
DT_NDARRAY_SHORT
DT_NDARRAY_WORD
DT_SPARSE_BOOL	sparse matrices
DT_SPARSE_BYTE
DT_SPARSE_CHAR
DT_SPARSE_INT
DT_SPARSE_UINT
DT_SPARSE_LONG
DT_SPARSE_ULONG
DT_SPARSE_REAL
DT_SPARSE_SHORTREAL
DT_SPARSE_LONGREAL
DT_SPARSE_SHORT
DT_SPARSE_WORD
DT_STRING_BOOL	strings of arbitrary type
DT_STRING_BYTE
DT_STRING_CHAR
DT_STRING_INT
DT_STRING_UINT
DT_STRING_LONG
DT_STRING_ULONG
DT_STRING_REAL
DT_STRING_SHORTREAL
DT_STRING_LONGREAL
DT_STRING_SHORT
DT_STRING_WORD
DT_ATTR_STRUCT	structures
DT_SHOGUN_OBJECT	shogun objects

在文件DataType.h第16行定义。

函数文档

int32_t shogun::CGLS	(	const struct data *	Data,
		const struct options *	Options,
		const struct vector_int *	Subset,
		struct vector_double *	Weights,
		struct vector_double *	Outputs
	)

在文件ssl.cpp第76行定义。

void shogun::chol_backward	(	float64_t	a[],
		int32_t	n,
		float64_t	p[],
		float64_t	b[],
		float64_t	x[]
	)

在文件pr_loqo.cpp第169行定义。

void shogun::chol_forward	(	float64_t	a[],
		int32_t	n,
		float64_t	p[],
		float64_t	b[],
		float64_t	x[]
	)

在文件pr_loqo.cpp第156行定义。

bool shogun::choldc	(	float64_t *	a,
		int32_t	n,
		float64_t *	p
	)

在文件pr_loqo.cpp第61行定义。

void shogun::cholsb	(	float64_t	a[],
		int32_t	n,
		float64_t	p[],
		float64_t	b[],
		float64_t	x[]
	)

在文件pr_loqo.cpp第132行定义。

int32_t shogun::DA_S3VM	(	struct data *	Data,
		struct options *	Options,
		struct vector_double *	Weights,
		struct vector_double *	Outputs
	)

在文件ssl.cpp第567行定义。

float64_t shogun::entropy	(	const float64_t *	p,
		int32_t	u
	)

在文件ssl.cpp第1028行定义。

void exit_shogun ( )

This function must be called when one stops using libshogun. It will perform a number of cleanups

int32_t shogun::FletcherAlg2A	(	int32_t	Projector,
		int32_t	n,
		float32_t *	vecA,
		float64_t *	b,
		float64_t	c,
		float64_t	e,
		int32_t *	iy,
		float64_t *	x,
		float64_t	tol,
		int32_t *	ls,
		int32_t *	proj
	)

在文件gpm.cpp第448行定义。

static const void* shogun::get_col ( uint32_t i ) [static]

在文件libocas.cpp第43行定义。

CIO * get_global_io ( )

get the global io object

返回:: io object

CMath * get_global_math ( )

get the global math object

返回:: math object

CParallel * get_global_parallel ( )

get the global parallel object

返回:: parallel object

CVersion * get_global_version ( )

get the global version object

返回:: version object

static float64_t shogun::get_time ( ) [static]

在文件libocas.cpp第51行定义。

void shogun::GetLabeledData	(	struct data *	D,
		const struct data *	Data
	)

在文件ssl.cpp第1094行定义。

int32_t gpm_solver	(	int32_t	Solver,
		int32_t	Projector,
		int32_t	n,
		float32_t *	A,
		float64_t *	b,
		float64_t	c,
		float64_t	e,
		int32_t *	iy,
		float64_t *	x,
		float64_t	tol,
		int32_t *	ls,
		int32_t *	proj
	)

int32_t shogun::gvpm	(	int32_t	Projector,
		int32_t	n,
		float32_t *	vecA,
		float64_t *	b,
		float64_t	c,
		float64_t	e,
		int32_t *	iy,
		float64_t *	x,
		float64_t	tol,
		int32_t *	ls,
		int32_t *	proj
	)

在文件gpm.cpp第110行定义。

void init_shogun	(	void()(FILE target, const char *str)	print_message = `NULL`,
		void()(FILE target, const char *str)	print_warning = `NULL`,
		void()(FILE target, const char *str)	print_error = `NULL`,
		void(*)(bool &delayed, bool &immediately)	cancel_computations = `NULL`
	)

This function must be called before libshogun is used. Usually shogun does not provide any output messages (neither debugging nor error; apart from exceptions). This function allows one to specify customized output callback functions and a callback function to check for exceptions:

参数:

	print_message	function pointer to print a message
	print_warning	function pointer to print a warning message
	print_error	function pointer to print an error message (this will be printed before shogun throws an exception)
	cancel_computations	function pointer to check for exception

void shogun::initialize	(	struct vector_double *	A,
		int32_t	k,
		float64_t	a
	)

在文件ssl.cpp第1074行定义。

void shogun::initialize	(	struct vector_int *	A,
		int32_t	k
	)

在文件ssl.cpp第1084行定义。

int32_t InnerProjector	(	int32_t	method,
		int32_t	n,
		int32_t *	iy,
		float64_t	e,
		float64_t *	qk,
		float64_t	l,
		float64_t	u,
		float64_t *	x,
		float64_t &	lambda
	)

在文件gpm.cpp第1221行定义。

float64_t shogun::KL	(	const float64_t *	p,
		const float64_t *	q,
		int32_t	u
	)

在文件ssl.cpp第1041行定义。

int32_t shogun::L2_SVM_MFN	(	const struct data *	Data,
		struct options *	Options,
		struct vector_double *	Weights,
		struct vector_double *	Outputs,
		int32_t	ini
	)

在文件ssl.cpp第195行定义。

static larank_kcache_t* shogun::larank_kcache_create ( CKernel * kernelfunc ) [static]

在文件LaRank.cpp第82行定义。

static void shogun::larank_kcache_destroy ( larank_kcache_t * self ) [static]

在文件LaRank.cpp第151行定义。

static float64_t shogun::larank_kcache_query	(	larank_kcache_t *	self,
		int32_t	i,
		int32_t	j
	)			`[static]`

在文件LaRank.cpp第342行定义。

static float32_t* shogun::larank_kcache_query_row	(	larank_kcache_t *	self,
		int32_t	i,
		int32_t	len
	)			`[static]`

在文件LaRank.cpp第374行定义。

static int32_t* shogun::larank_kcache_r2i	(	larank_kcache_t *	self,
		int32_t	n
	)			`[static]`

在文件LaRank.cpp第215行定义。

static void shogun::larank_kcache_set_buddy	(	larank_kcache_t *	self,
		larank_kcache_t *	buddy
	)			`[static]`

在文件LaRank.cpp第351行定义。

static void shogun::larank_kcache_set_maximum_size	(	larank_kcache_t *	self,
		int64_t	entries
	)			`[static]`

在文件LaRank.cpp第143行定义。

static void shogun::larank_kcache_swap_ri	(	larank_kcache_t *	self,
		int32_t	r1,
		int32_t	i2
	)			`[static]`

在文件LaRank.cpp第308行定义。

static void shogun::larank_kcache_swap_rr	(	larank_kcache_t *	self,
		int32_t	r1,
		int32_t	r2
	)			`[static]`

在文件LaRank.cpp第302行定义。

float64_t shogun::line_search	(	float64_t *	w,
		float64_t *	w_bar,
		float64_t	lambda,
		float64_t *	o,
		float64_t *	o_bar,
		float64_t *	Y,
		float64_t *	C,
		int32_t	d,
		int32_t	l
	)

在文件ssl.cpp第356行定义。

void shogun::matrix_vector	(	int32_t	n,
		float64_t	m[],
		float64_t	x[],
		float64_t	y[]
	)

在文件pr_loqo.cpp第270行定义。

float64_t shogun::norm_square ( const vector_double * A )

在文件ssl.cpp第1063行定义。

void shogun::nrerror ( char error_text[] )

在文件pr_loqo.cpp第45行定义。

void shogun::optimize_p	(	const float64_t *	g,
		int32_t	u,
		float64_t	T,
		float64_t	r,
		float64_t *	p
	)

在文件ssl.cpp第929行定义。

int32_t shogun::optimize_w	(	const struct data *	Data,
		const float64_t *	p,
		struct options *	Options,
		struct vector_double *	Weights,
		struct vector_double *	Outputs,
		int32_t	ini
	)

在文件ssl.cpp第650行定义。

int32_t shogun::Pardalos	(	int32_t	n,
		int32_t *	iy,
		float64_t	e,
		float64_t *	qk,
		float64_t	low,
		float64_t	up,
		float64_t *	x
	)

在文件gpm.cpp第1052行定义。

int32_t pr_loqo	(	int32_t	n,
		int32_t	m,
		float64_t	c[],
		float64_t	h_x[],
		float64_t	a[],
		float64_t	b[],
		float64_t	l[],
		float64_t	u[],
		float64_t	primal[],
		float64_t	dual[],
		int32_t	verb,
		float64_t	sigfig_max,
		int32_t	counter_max,
		float64_t	margin,
		float64_t	bound,
		int32_t	restart
	)

int32_t shogun::ProjectDai	(	int32_t	n,
		int32_t *	a,
		float64_t	b,
		float64_t *	c,
		float64_t	l,
		float64_t	u,
		float64_t *	x,
		float64_t &	lam_ext
	)

在文件gpm.cpp第860行定义。

float64_t shogun::ProjectR	(	float64_t *	x,
		int32_t	n,
		float64_t	lambda,
		int32_t *	a,
		float64_t	b,
		float64_t *	c,
		float64_t	l,
		float64_t	u
	)

在文件gpm.cpp第832行定义。

int8_t qpssvm_solver	(	const void ()(uint32_t)	get_col,
		float64_t *	diag_H,
		float64_t *	f,
		float64_t	b,
		uint16_t *	I,
		float64_t *	x,
		uint32_t	n,
		uint32_t	tmax,
		float64_t	tolabs,
		float64_t	tolrel,
		float64_t *	QP,
		float64_t *	QD,
		uint32_t	verb
	)

float64_t shogun::quick_select	(	float64_t *	arr,
		int32_t	n
	)

在文件gpm.cpp第992行定义。

bool shogun::read_char_valued_strings	(	T_STRING< char > *&	strings,
		int32_t &	num_str,
		int32_t &	max_string_len
	)

read char string features, simple ascii format e.g. foo bar ACGTACGTATCT

two strings

参数:

	strings	strings to read into
	num_str	number of strings
	max_string_len	length of longest string

返回:: if reading was successful

bool shogun::read_real_valued_dense	(	float64_t *&	matrix,
		int32_t &	num_feat,
		int32_t &	num_vec
	)

read dense real valued features, simple ascii format e.g. 1.0 1.1 0.2 2.3 3.5 5

a matrix that consists of 3 vectors with each of 2d

参数:

	matrix	matrix to read into
	num_feat	number of features for each vector
	num_vec	number of vectors in matrix

返回:: if reading was successful

bool shogun::read_real_valued_sparse	(	TSparse< float64_t > *&	matrix,
		int32_t &	num_feat,
		int32_t &	num_vec
	)

read sparse real valued features in svm light format e.g. -1 1:10.0 2:100.2 1000:1.3 with -1 == (optional) label and dim 1 - value 10.0 dim 2 - value 100.2 dim 1000 - value 1.3

参数:

	matrix	matrix to read into
	num_feat	number of features for each vector
	num_vec	number of vectors in matrix

返回:: if reading was successful

void set_global_io ( CIO * io )

set the global io object

参数:

io

io object to use

void set_global_math ( CMath * math )

set the global math object

参数:

math

math object to use

void set_global_parallel ( CParallel * parallel )

set the global parallel object

参数:

parallel

parallel object to use

void set_global_version ( CVersion * version )

set the global version object

参数:

version

version object to use

bool shogun::solve_reduced	(	int32_t	n,
		int32_t	m,
		float64_t	h_x[],
		float64_t	h_y[],
		float64_t	a[],
		float64_t	x_x[],
		float64_t	x_y[],
		float64_t	c_x[],
		float64_t	c_y[],
		float64_t	workspace[],
		int32_t	step
	)

在文件pr_loqo.cpp第207行定义。

void* shogun::sqdist_thread_func ( void * P )

在文件KMeans.cpp第96行定义。

void shogun::ssl_train	(	struct data *	Data,
		struct options *	Options,
		struct vector_double *	Weights,
		struct vector_double *	Outputs
	)

在文件ssl.cpp第33行定义。

ocas_return_value_T shogun::svm_ocas_solver	(	float64_t	C,
		uint32_t	nData,
		float64_t	TolRel,
		float64_t	TolAbs,
		float64_t	QPBound,
		uint32_t	_BufSize,
		uint8_t	Method,
		void()(float64_t , float64_t , float64_t , uint32_t, void *)	compute_W,
		float64_t()(float64_t, void )	update_W,
		void()(float64_t , uint32_t , uint32_t, uint32_t, void )	add_new_cut,
		void()(float64_t , void *)	compute_output,
		void()(float64_t , uint32_t *, uint32_t)	sort,
		void *	user_data
	)

在文件libocas.cpp第63行定义。

int32_t shogun::switch_labels	(	float64_t *	Y,
		float64_t *	o,
		int32_t *	JU,
		int32_t	u,
		int32_t	S
	)

在文件ssl.cpp第522行定义。

float64_t shogun::transductive_cost	(	float64_t	normWeights,
		float64_t *	Y,
		float64_t *	Outputs,
		int32_t	m,
		float64_t	lambda,
		float64_t	lambda_u
	)

在文件ssl.cpp第1008行定义。

int32_t shogun::TSVM_MFN	(	const struct data *	Data,
		struct options *	Options,
		struct vector_double *	Weights,
		struct vector_double *	Outputs
	)

FIXME Clear(Data_Labeled);

在文件ssl.cpp第434行定义。

void wrap_dgesvd	(	char	jobu,
		char	jobvt,
		int	m,
		int	n,
		double *	a,
		int	lda,
		double *	sing,
		double *	u,
		int	ldu,
		double *	vt,
		int	ldvt,
		int *	info
	)

void wrap_dsyev	(	char	jobz,
		char	uplo,
		int	n,
		double *	a,
		int	lda,
		double *	w,
		int *	info
	)

bool shogun::write_char_valued_strings	(	const T_STRING< char > *	strings,
		int32_t	num_str
	)

write char string features, simple ascii format

参数:

	strings	strings to write
	num_str	number of strings

返回:: if writing was successful

bool shogun::write_real_valued_dense	(	const float64_t *	matrix,
		int32_t	num_feat,
		int32_t	num_vec
	)

write dense real valued features, simple ascii format

参数:

	matrix	matrix to write
	num_feat	number of features for each vector
	num_vec	number of vectros in matrix

返回:: if writing was successful

bool shogun::write_real_valued_sparse	(	const TSparse< float64_t > *	matrix,
		int32_t	num_feat,
		int32_t	num_vec
	)

write sparse real valued features in svm light format

参数:

	matrix	matrix to write
	num_feat	number of features for each vector
	num_vec	number of vectros in matrix

返回:: if writing was successful

static void shogun::xextend	(	larank_kcache_t *	self,
		int32_t	k,
		int32_t	nlen
	)			`[static]`

在文件LaRank.cpp第221行定义。

static void* shogun::xmalloc ( int32_t n ) [static]

在文件LaRank.cpp第63行定义。

static void shogun::xminsize	(	larank_kcache_t *	self,
		int32_t	n
	)			`[static]`

在文件LaRank.cpp第184行定义。

static void shogun::xpurge ( larank_kcache_t * self ) [static]

在文件LaRank.cpp第129行定义。

static float64_t shogun::xquery	(	larank_kcache_t *	self,
		int32_t	i,
		int32_t	j
	)			`[static]`

在文件LaRank.cpp第314行定义。

static void* shogun::xrealloc	(	void *	ptr,
		int32_t	n
	)			`[static]`

在文件LaRank.cpp第71行定义。

static void shogun::xswap	(	larank_kcache_t *	self,
		int32_t	i1,
		int32_t	i2,
		int32_t	r1,
		int32_t	r2
	)			`[static]`

在文件LaRank.cpp第240行定义。

static void shogun::xtruncate	(	larank_kcache_t *	self,
		int32_t	k,
		int32_t	nlen
	)			`[static]`

在文件LaRank.cpp第103行定义。

变量文档

uint32_t BufSize [static]

在文件libocas.cpp第38行定义。

float64_t* H [static]

在文件libocas.cpp第37行定义。

const uint32_t QPSolverMaxIter = 10000000 [static]

在文件libocas.cpp第35行定义。

uint32_t Randnext

void(* sg_cancel_computations)(bool &delayed, bool &immediately) = NULL

function called to cancel things

在文件init.cpp第38行定义。

CIO * sg_io = NULL

在文件init.cpp第21行定义。

CMath * sg_math = NULL

在文件init.cpp第23行定义。

CParallel * sg_parallel = NULL

在文件init.cpp第20行定义。

void(* sg_print_error)(FILE *target, const char *str) = NULL

function called to print error messages

在文件init.cpp第35行定义。

void(* sg_print_message)(FILE *target, const char *str) = NULL

function called to print normal messages

在文件init.cpp第29行定义。

void(* sg_print_warning)(FILE *target, const char *str) = NULL

function called to print warning messages

在文件init.cpp第32行定义。

CVersion * sg_version = NULL

在文件init.cpp第22行定义。

shogun名字空间参考

组合类型

类型定义

枚举

函数

变量

详细描述

类型定义文档

枚举类型文档

函数文档

变量文档