Public Member Functions | Static Public Member Functions | Public Attributes | Protected Member Functions | Static Protected Member Functions

CStatistics Class Reference

Detailed Description

Class that contains certain functions related to statistics, such as probability/cumulative distribution functions, different statistics, etc.

Definition at line 30 of file Statistics.h.

Inheritance diagram for CStatistics:
Inheritance graph
[legend]

List of all members.

Public Member Functions

virtual const char * get_name () const
virtual CSGObject * shallow_copy () const
virtual CSGObject * deep_copy () const
virtual bool is_generic (EPrimitiveType *generic) const
template<class T >
void set_generic ()
void unset_generic ()
virtual void print_serializable (const char *prefix="")
virtual bool save_serializable (CSerializableFile *file, const char *prefix="", int32_t param_version=VERSION_PARAMETER)
virtual bool load_serializable (CSerializableFile *file, const char *prefix="", int32_t param_version=VERSION_PARAMETER)
DynArray< TParameter * > * load_file_parameters (const SGParamInfo *param_info, int32_t file_version, CSerializableFile *file, const char *prefix="")
DynArray< TParameter * > * load_all_file_parameters (int32_t file_version, int32_t current_version, CSerializableFile *file, const char *prefix="")
void map_parameters (DynArray< TParameter * > *param_base, int32_t &base_version, DynArray< const SGParamInfo * > *target_param_infos)
void set_global_io (SGIO *io)
SGIO * get_global_io ()
void set_global_parallel (Parallel *parallel)
Parallel * get_global_parallel ()
void set_global_version (Version *version)
Version * get_global_version ()
SGStringList< char > get_modelsel_names ()
void print_modsel_params ()
char * get_modsel_param_descr (const char *param_name)
index_t get_modsel_param_index (const char *param_name)
void build_parameter_dictionary (CMap< TParameter *, CSGObject * > &dict)

Static Public Member Functions

static float64_t mean (SGVector< float64_t > values)
static float64_t median (SGVector< float64_t > values, bool modify=false, bool in_place=false)
static float64_t matrix_median (SGMatrix< float64_t > values, bool modify=false, bool in_place=false)
static float64_t variance (SGVector< float64_t > values)
static float64_t std_deviation (SGVector< float64_t > values)
static SGVector< float64_t > matrix_mean (SGMatrix< float64_t > values, bool col_wise=true)
static SGVector< float64_t > matrix_variance (SGMatrix< float64_t > values, bool col_wise=true)
static SGVector< float64_t > matrix_std_deviation (SGMatrix< float64_t > values, bool col_wise=true)
static SGMatrix< float64_t > covariance_matrix (SGMatrix< float64_t > observations, bool in_place=false)
static float64_t confidence_intervals_mean (SGVector< float64_t > values, float64_t alpha, float64_t &conf_int_low, float64_t &conf_int_up)
static float64_t inverse_student_t (int32_t k, float64_t p)
static float64_t inverse_incomplete_beta (float64_t a, float64_t b, float64_t y)
static float64_t incomplete_beta (float64_t a, float64_t b, float64_t x)
static float64_t inverse_normal_cdf (float64_t y0)
static float64_t inverse_normal_cdf (float64_t y0, float64_t mean, float64_t std_dev)
static float64_t lgamma (float64_t x)
static floatmax_t lgammal (floatmax_t x)
static float64_t tgamma (float64_t x)
static float64_t incomplete_gamma (float64_t a, float64_t x)
static float64_t incomplete_gamma_completed (float64_t a, float64_t x)
static float64_t gamma_cdf (float64_t x, float64_t a, float64_t b)
static float64_t inverse_gamma_cdf (float64_t p, float64_t a, float64_t b)
static float64_t inverse_incomplete_gamma_completed (float64_t a, float64_t y0)
static float64_t normal_cdf (float64_t x, float64_t std_dev=1)
static float64_t error_function (float64_t x)
static float64_t error_function_complement (float64_t x)
static float64_t mutual_info (float64_t *p1, float64_t *p2, int32_t len)
static float64_t relative_entropy (float64_t *p, float64_t *q, int32_t len)
static float64_t entropy (float64_t *p, int32_t len)
static SGVector< float64_t > fishers_exact_test_for_multiple_2x3_tables (SGMatrix< float64_t > tables)
static float64_t fishers_exact_test_for_2x3_table (SGMatrix< float64_t > table)
static SGVector< int32_t > sample_indices (int32_t sample_size, int32_t N)
static float64_t dlgamma (float64_t x)

Public Attributes

SGIO * io
Parallel * parallel
Version * version
Parameter * m_parameters
Parameter * m_model_selection_parameters
ParameterMap * m_parameter_map
uint32_t m_hash

Protected Member Functions

virtual TParameter * migrate (DynArray< TParameter * > *param_base, const SGParamInfo *target)
virtual void one_to_one_migration_prepare (DynArray< TParameter * > *param_base, const SGParamInfo *target, TParameter *&replacement, TParameter *&to_migrate, char *old_name=NULL)
virtual void load_serializable_pre () throw (ShogunException)
virtual void load_serializable_post () throw (ShogunException)
virtual void save_serializable_pre () throw (ShogunException)
virtual void save_serializable_post () throw (ShogunException)
virtual bool update_parameter_hash ()

Static Protected Member Functions

static float64_t ibetaf_incompletebetaps (float64_t a, float64_t b, float64_t x, float64_t maxgam)
static float64_t ibetaf_incompletebetafe (float64_t a, float64_t b, float64_t x, float64_t big, float64_t biginv)
static float64_t ibetaf_incompletebetafe2 (float64_t a, float64_t b, float64_t x, float64_t big, float64_t biginv)
static bool equal (float64_t a, float64_t b)
static bool not_equal (float64_t a, float64_t b)
static bool less (float64_t a, float64_t b)
static bool less_equal (float64_t a, float64_t b)
static bool greater (float64_t a, float64_t b)
static bool greater_equal (float64_t a, float64_t b)

Member Function Documentation

void build_parameter_dictionary ( CMap< TParameter *, CSGObject * > &  dict  )  [inherited]

Builds a dictionary of all parameters in SGObject as well of those of SGObjects that are parameters of this object. Dictionary maps parameters to the objects that own them.

Parameters:
dict dictionary of parameters to be built.

Definition at line 1201 of file SGObject.cpp.

float64_t confidence_intervals_mean ( SGVector< float64_t >  values,
float64_t  alpha,
float64_t &  conf_int_low,
float64_t &  conf_int_up 
) [static]

Calculates the sample mean of a given set of samples and also computes the confidence interval for the actual mean for a given p-value, assuming that the actual variance and mean are unknown (These are estimated by the samples). Based on Student's t-distribution.

Only for normally distributed data

Parameters:
values vector of values that are used for calculations
alpha actual mean lies in confidence interval with (1-alpha)*100%
conf_int_low lower confidence interval border is written here
conf_int_up upper confidence interval border is written here
Returns:
sample mean

Definition at line 333 of file Statistics.cpp.

SGMatrix< float64_t > covariance_matrix ( SGMatrix< float64_t >  observations,
bool  in_place = false 
) [static]

Computes the empirical estimate of the covariance matrix of the given data which is organized as num_cols variables with num_rows observations.

Data is centered before matrix is computed. May be done in place. In this case, the observation matrix is changed (centered).

Given sample matrix $X$, first, column mean is removed to create $\bar X$. Then $\text{cov}(X)=(X-\bar X)^T(X - \bar X)$ is returned.

Needs SHOGUN to be compiled with LAPACK.

Parameters:
observations data matrix organized as one variable per column
in_place optional, if set to true, observations matrix will be centered, if false, a copy will be created an centered.
Returns:
covariance matrix empirical estimate

Definition at line 309 of file Statistics.cpp.

virtual CSGObject* deep_copy (  )  const [virtual, inherited]

A deep copy. All the instance variables will also be copied.

Definition at line 131 of file SGObject.h.

float64_t dlgamma ( float64_t  x  )  [static]

Derivative of the log gamma function.

Taken from likT.m from the GPML toolbox.

Parameters:
x input
Returns:
derivative of the log gamma input

Definition at line 1945 of file Statistics.cpp.

float64_t entropy ( float64_t *  p,
int32_t  len 
) [static]
Returns:
entropy of $p$ which is given in logspace

Definition at line 1910 of file Statistics.cpp.

static bool equal ( float64_t  a,
float64_t  b 
) [static, protected]

method to make ALGLIB integration easier

Definition at line 481 of file Statistics.h.

float64_t error_function ( float64_t  x  )  [static]

Error function

The integral is

\[ \text{error\_function}(x)= \frac{2}{\sqrt{pi}}\int_0^x \exp (-t^2) dt \]

For $0 \leq |x| < 1, \text{error\_function}(x) = x \frac{P4(x^2)}{Q5(x^2)}$ otherwise $\text{error\_function}(x) = 1 - \text{error\_function\_complement}(x)$.

Taken from ALGLIB under gpl2+

Definition at line 1684 of file Statistics.cpp.

float64_t error_function_complement ( float64_t  x  )  [static]

Complementary error function

\[ 1 - \text{error\_function}(x) = \text{error\_function\_complement}(x)= \frac{2}{\sqrt{\pi}}\int_x^\infty \exp\left(-t^2 \right)dt \]

For small $x$, $\text{error\_function\_complement}(x) = 1 - \text{error\_function}(x)$; otherwise rational approximations are computed.

Taken from ALGLIB under gpl2+

Definition at line 1723 of file Statistics.cpp.

float64_t fishers_exact_test_for_2x3_table ( SGMatrix< float64_t >  table  )  [static]

fisher's test for 2x3 table

Parameters:
table 

Definition at line 1781 of file Statistics.cpp.

SGVector< float64_t > fishers_exact_test_for_multiple_2x3_tables ( SGMatrix< float64_t >  tables  )  [static]

fisher's test for multiple 2x3 tables

Parameters:
tables 

Definition at line 1766 of file Statistics.cpp.

float64_t gamma_cdf ( float64_t  x,
float64_t  a,
float64_t  b 
) [static]

Evaluates the CDF of the gamma distribution with given parameters $a, b$ at $x$. Based on Wikipedia definition and ALGLIB routines.

Parameters:
x position to evaluate
a shape parameter
b scale parameter
Returns:
gamma CDF at $x$

Definition at line 1506 of file Statistics.cpp.

SGIO * get_global_io (  )  [inherited]

get the io object

Returns:
io object

Definition at line 224 of file SGObject.cpp.

Parallel * get_global_parallel (  )  [inherited]

get the parallel object

Returns:
parallel object

Definition at line 259 of file SGObject.cpp.

Version * get_global_version (  )  [inherited]

get the version object

Returns:
version object

Definition at line 272 of file SGObject.cpp.

SGStringList< char > get_modelsel_names (  )  [inherited]
Returns:
vector of names of all parameters which are registered for model selection

Definition at line 1108 of file SGObject.cpp.

char * get_modsel_param_descr ( const char *  param_name  )  [inherited]

Returns description of a given parameter string, if it exists. SG_ERROR otherwise

Parameters:
param_name name of the parameter
Returns:
description of the parameter

Definition at line 1132 of file SGObject.cpp.

index_t get_modsel_param_index ( const char *  param_name  )  [inherited]

Returns index of model selection parameter with provided index

Parameters:
param_name name of model selection parameter
Returns:
index of model selection parameter with provided name, -1 if there is no such

Definition at line 1145 of file SGObject.cpp.

virtual const char* get_name (  )  const [virtual]
Returns:
object name

Implements CSGObject.

Definition at line 441 of file Statistics.h.

static bool greater ( float64_t  a,
float64_t  b 
) [static, protected]

method to make ALGLIB integration easier

Definition at line 493 of file Statistics.h.

static bool greater_equal ( float64_t  a,
float64_t  b 
) [static, protected]

method to make ALGLIB integration easier

Definition at line 496 of file Statistics.h.

float64_t ibetaf_incompletebetafe ( float64_t  a,
float64_t  b,
float64_t  x,
float64_t  big,
float64_t  biginv 
) [static, protected]

Continued fraction expansion #1 for incomplete beta integral

Taken from ALGLIB under gpl2+

Definition at line 1173 of file Statistics.cpp.

float64_t ibetaf_incompletebetafe2 ( float64_t  a,
float64_t  b,
float64_t  x,
float64_t  big,
float64_t  biginv 
) [static, protected]

Continued fraction expansion #2 for incomplete beta integral

Taken from ALGLIB under gpl2+

Definition at line 1276 of file Statistics.cpp.

float64_t ibetaf_incompletebetaps ( float64_t  a,
float64_t  b,
float64_t  x,
float64_t  maxgam 
) [static, protected]

Power series for incomplete beta integral. Use when $bx$ is small and $x$ not too close to $1$.

Taken from ALGLIB under gpl2+

Definition at line 1119 of file Statistics.cpp.

float64_t incomplete_beta ( float64_t  a,
float64_t  b,
float64_t  x 
) [static]

Incomplete beta integral

Returns incomplete beta integral of the arguments, evaluated from zero to $x$. The function is defined as

\[ \frac{\Gamma(a+b)}{\Gamma(a)\Gamma(b)}\int_0^x t^{a-1} (1-t)^{b-1} dt. \]

The domain of definition is $0 \leq x \leq 1$. In this implementation $a$ and $b$ are restricted to positive values. The integral from $x$ to $1$ may be obtained by the symmetry relation

\[ 1-\text{incomplete\_beta}(a,b,x)=\text{incomplete\_beta}(b,a,1-x). \]

The integral is evaluated by a continued fraction expansion or, when $b\cdot x$ is small, by a power series.

Taken from ALGLIB under gpl2+

Definition at line 860 of file Statistics.cpp.

float64_t incomplete_gamma ( float64_t  a,
float64_t  x 
) [static]

Incomplete gamma integral

Given $p$, the function finds $x$ such that

\[ \text{incomplete\_gamma}(a,x)=\frac{1}{\Gamma(a)}}\int_0^x e^{-t} t^{a-1} dt. \]

In this implementation both arguments must be positive. The integral is evaluated by either a power series or continued fraction expansion, depending on the relative values of $a$ and $x$.

Taken from ALGLIB under gpl2+

Definition at line 1381 of file Statistics.cpp.

float64_t incomplete_gamma_completed ( float64_t  a,
float64_t  x 
) [static]

Complemented incomplete gamma integral

The function is defined by

\[ \text{incomplete\_gamma\_completed}(a,x)=1-\text{incomplete\_gamma}(a,x) = \frac{1}{\Gamma (a)}\int_x^\infty e^{-t} t^{a-1} dt \]

In this implementation both arguments must be positive. The integral is evaluated by either a power series or continued fraction expansion, depending on the relative values of $a$ and $x$.

Taken from ALGLIB under gpl2+

Definition at line 1422 of file Statistics.cpp.

float64_t inverse_gamma_cdf ( float64_t  p,
float64_t  a,
float64_t  b 
) [static]

Evaluates the inverse CDF of the gamma distribution with given parameters $a$, $b$ at $x$, such that result equals $\text{gamma\_cdf}(x,a,b)$.

Parameters:
p position to evaluate
a shape parameter
b scale parameter
Returns:
$x$ such that result equals $\text{gamma\_cdf}(x,a,b)$.

Definition at line 1512 of file Statistics.cpp.

float64_t inverse_incomplete_beta ( float64_t  a,
float64_t  b,
float64_t  y 
) [static]

Inverse of imcomplete beta integral

Given $y$, the function finds $x$ such that

$\text{inverse\_incomplete\_beta}( a, b, x ) = y .$

The routine performs interval halving or Newton iterations to find the root of $\text{inverse\_incomplete\_beta}( a, b, x )-y=0.$

Taken from ALGLIB under gpl2+

Definition at line 408 of file Statistics.cpp.

float64_t inverse_incomplete_gamma_completed ( float64_t  a,
float64_t  y0 
) [static]

Inverse of complemented imcomplete gamma integral

Given $p$, the function finds $x$ such that

$\text{inverse\_incomplete\_gamma\_completed}( a, x ) = p.$

Starting with the approximate value $ x=a t^3$, where $ t = 1 - d - \text{ndtri}(p) \sqrt{d} $ and $ d = \frac{1}{9}a $

The routine performs up to 10 Newton iterations to find the root of $ \text{inverse\_incomplete\_gamma\_completed}( a, x )-p=0$

Taken from ALGLIB under gpl2+

Definition at line 1520 of file Statistics.cpp.

float64_t inverse_normal_cdf ( float64_t  y0  )  [static]

Inverse of Normal distribution function

Returns the argument, $x$, for which the area under the Gaussian probability density function (integrated from minus infinity to $x$) is equal to $y$.

For small arguments $0 < y < \exp(-2)$, the program computes $z = \sqrt{ -2.0 \log(y) }$; then the approximation is $x = z - \frac{log(z)}{z} - \frac{1}{z} \frac{P(\frac{1}{z})}{ Q(\frac{1}{z}}$. There are two rational functions $\frac{P}{Q}$, one for $0 < y < \exp(-32)$ and the other for $y$ up to $\exp(-2)$. For larger arguments, $w = y - 0.5$, and $\frac{x}{\sqrt{2\pi}} = w + w^3 R(\frac{w^2)}{S(w^2)})$.

Taken from ALGLIB under gpl2+

Definition at line 1002 of file Statistics.cpp.

float64_t inverse_normal_cdf ( float64_t  y0,
float64_t  mean,
float64_t  std_dev 
) [static]

same as other version, but with custom mean and variance

Definition at line 996 of file Statistics.cpp.

float64_t inverse_student_t ( int32_t  k,
float64_t  p 
) [static]

Functional inverse of Student's t distribution

Given probability $p$, finds the argument $t$ such that $\text{student\_t}(k,t)=p$

Taken from ALGLIB under gpl2+

Definition at line 360 of file Statistics.cpp.

bool is_generic ( EPrimitiveType *  generic  )  const [virtual, inherited]

If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.

Parameters:
generic set to the type of the generic if returning TRUE
Returns:
TRUE if a class template.

Definition at line 278 of file SGObject.cpp.

static bool less ( float64_t  a,
float64_t  b 
) [static, protected]

method to make ALGLIB integration easier

Definition at line 487 of file Statistics.h.

static bool less_equal ( float64_t  a,
float64_t  b 
) [static, protected]

method to make ALGLIB integration easier

Definition at line 490 of file Statistics.h.

static float64_t lgamma ( float64_t  x  )  [static]
Returns:
natural logarithm of the gamma function of input

Definition at line 264 of file Statistics.h.

static floatmax_t lgammal ( floatmax_t  x  )  [static]
Returns:
natural logarithm of the gamma function of input for large numbers

Definition at line 271 of file Statistics.h.

DynArray< TParameter * > * load_all_file_parameters ( int32_t  file_version,
int32_t  current_version,
CSerializableFile *  file,
const char *  prefix = "" 
) [inherited]

maps all parameters of this instance to the provided file version and loads all parameter data from the file into an array, which is sorted (basically calls load_file_parameter(...) for all parameters and puts all results into a sorted array)

Parameters:
file_version parameter version of the file
current_version version from which mapping begins (you want to use VERSION_PARAMETER for this in most cases)
file file to load from
prefix prefix for members
Returns:
(sorted) array of created TParameter instances with file data

Definition at line 679 of file SGObject.cpp.

DynArray< TParameter * > * load_file_parameters ( const SGParamInfo *  param_info,
int32_t  file_version,
CSerializableFile *  file,
const char *  prefix = "" 
) [inherited]

loads some specified parameters from a file with a specified version The provided parameter info has a version which is recursively mapped until the file parameter version is reached. Note that there may be possibly multiple parameters in the mapping, therefore, a set of TParameter instances is returned

Parameters:
param_info information of parameter
file_version parameter version of the file, must be <= provided parameter version
file file to load from
prefix prefix for members
Returns:
new array with TParameter instances with the attached data

Definition at line 523 of file SGObject.cpp.

bool load_serializable ( CSerializableFile *  file,
const char *  prefix = "",
int32_t  param_version = VERSION_PARAMETER 
) [virtual, inherited]

Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!

Parameters:
file where to load from
prefix prefix for members
param_version (optional) a parameter version different to (this is mainly for testing, better do not use)
Returns:
TRUE if done, otherwise FALSE

Reimplemented in CModelSelectionParameters.

Definition at line 354 of file SGObject.cpp.

void load_serializable_post (  )  throw (ShogunException) [protected, virtual, inherited]

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_POST is called.

Exceptions:
ShogunException Will be thrown if an error occurres.

Reimplemented in CLinearHMM, CAlphabet, CANOVAKernel, CCircularKernel, CExponentialKernel, CGaussianKernel, CInverseMultiQuadricKernel, CKernel, CWeightedDegreePositionStringKernel, and CList.

Definition at line 1033 of file SGObject.cpp.

void load_serializable_pre (  )  throw (ShogunException) [protected, virtual, inherited]

Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_PRE is called.

Exceptions:
ShogunException Will be thrown if an error occurres.

Definition at line 1028 of file SGObject.cpp.

void map_parameters ( DynArray< TParameter * > *  param_base,
int32_t &  base_version,
DynArray< const SGParamInfo * > *  target_param_infos 
) [inherited]

Takes a set of TParameter instances (base) with a certain version and a set of target parameter infos and recursively maps the base level wise to the current version using CSGObject::migrate(...). The base is replaced. After this call, the base version containing parameters should be of same version/type as the initial target parameter infos. Note for this to work, the migrate methods and all the internal parameter mappings have to match

Parameters:
param_base set of TParameter instances that are mapped to the provided target parameter infos
base_version version of the parameter base
target_param_infos set of SGParamInfo instances that specify the target parameter base

Definition at line 717 of file SGObject.cpp.

SGVector< float64_t > matrix_mean ( SGMatrix< float64_t >  values,
bool  col_wise = true 
) [static]

Calculates mean of given values. Given $\{x_1, ..., x_m\}$, this is $\frac{1}{m}\sum_{i=1}^m x_i$

Computes the mean for each row/col of matrix

Parameters:
values vector of values
col_wise if true, every column vector will be used, row vectors otherwise
Returns:
mean of given values

Definition at line 216 of file Statistics.cpp.

float64_t matrix_median ( SGMatrix< float64_t >  values,
bool  modify = false,
bool  in_place = false 
) [static]

Calculates median of given values. Matrix is seen as a long vector for this. The median is the value that one gets when the input vector is sorted and then selects the middle value.

This method is just a wrapper for median(). See this method for license of QuickSelect and Torben.

Parameters:
values vector of values
modify if false, array is modified while median is computed (Using QuickSelect). If true, median is computed without modifications, which is slower. There are two methods to choose from.
in_place if set false, the vector is copied and then computed using QuickSelect. If set true, median is computed in-place using Torben method.
Returns:
median of given values

Definition at line 190 of file Statistics.cpp.

SGVector< float64_t > matrix_std_deviation ( SGMatrix< float64_t >  values,
bool  col_wise = true 
) [static]

Calculates unbiased empirical standard deviation estimator of given values. Given $\{x_1, ..., x_m\}$, this is $\sqrt{\frac{1}{m-1}\sum_{i=1}^m (x-\bar{x})^2}$ where $\bar x=\frac{1}{m}\sum_{i=1}^m x_i$

Computes the variance for each row/col of matrix

Parameters:
values vector of values
col_wise if true, every column vector will be used, row vectors otherwise
Returns:
variance of given values

Definition at line 298 of file Statistics.cpp.

SGVector< float64_t > matrix_variance ( SGMatrix< float64_t >  values,
bool  col_wise = true 
) [static]

Calculates unbiased empirical variance estimator of given values. Given $\{x_1, ..., x_m\}$, this is $\frac{1}{m-1}\sum_{i=1}^m (x-\bar{x})^2$ where $\bar x=\frac{1}{m}\sum_{i=1}^m x_i$

Computes the variance for each row/col of matrix

Parameters:
values vector of values
col_wise if true, every column vector will be used, row vectors otherwise
Returns:
variance of given values

Definition at line 253 of file Statistics.cpp.

float64_t mean ( SGVector< float64_t >  values  )  [static]

Calculates mean of given values. Given $\{x_1, ..., x_m\}$, this is $\frac{1}{m}\sum_{i=1}^m x_i$

Parameters:
values vector of values
Returns:
mean of given values

Definition at line 26 of file Statistics.cpp.

float64_t median ( SGVector< float64_t >  values,
bool  modify = false,
bool  in_place = false 
) [static]

Calculates median of given values. The median is the value that one gets when the input vector is sorted and then selects the middle value.

QuickSelect method copyright: This Quickselect routine is based on the algorithm described in "Numerical recipes in C", Second Edition, Cambridge University Press, 1992, Section 8.5, ISBN 0-521-43108-5 This code by Nicolas Devillard - 1998. Public domain.

Torben method copyright: The following code is public domain. Algorithm by Torben Mogensen, implementation by N. Devillard. Public domain.

Both methods adapted to SHOGUN by Heiko Strathmann.

Parameters:
values vector of values
modify if false, array is modified while median is computed (Using QuickSelect). If true, median is computed without modifications, which is slower. There are two methods to choose from.
in_place if set false, the vector is copied and then computed using QuickSelect. If set true, median is computed in-place using Torben method.
Returns:
median of given values

Definition at line 38 of file Statistics.cpp.

TParameter * migrate ( DynArray< TParameter * > *  param_base,
const SGParamInfo *  target 
) [protected, virtual, inherited]

creates a new TParameter instance, which contains migrated data from the version that is provided. The provided parameter data base is used for migration, this base is a collection of all parameter data of the previous version. Migration is done FROM the data in param_base TO the provided param info Migration is always one version step. Method has to be implemented in subclasses, if no match is found, base method has to be called.

If there is an element in the param_base which equals the target, a copy of the element is returned. This represents the case when nothing has changed and therefore, the migrate method is not overloaded in a subclass

Parameters:
param_base set of TParameter instances to use for migration
target parameter info for the resulting TParameter
Returns:
a new TParameter instance with migrated data from the base of the type which is specified by the target parameter

Definition at line 923 of file SGObject.cpp.

float64_t mutual_info ( float64_t *  p1,
float64_t *  p2,
int32_t  len 
) [static]
Returns:
mutual information of $p$ which is given in logspace where $p,q$ are given in logspace

Definition at line 1889 of file Statistics.cpp.

float64_t normal_cdf ( float64_t  x,
float64_t  std_dev = 1 
) [static]

Normal distribution function

Returns the area under the Gaussian probability density function, integrated from minus infinity to $x$:

\[ \text{normal\_cdf}(x)=\frac{1}{\sqrt{2\pi}} \int_{-\infty}^x \exp \left( -\frac{t^2}{2} \right) dt = \frac{1+\text{error\_function}(z) }{2} \]

where $ z = \frac{x}{\sqrt{2} \sigma}$ and $ \sigma $ is the standard deviation. Computation is via the functions $\text{error\_function}$ and $\text{error\_function\_completement}$.

Taken from ALGLIB under gpl2+ Custom variance added by Heiko Strathmann

Definition at line 1679 of file Statistics.cpp.

static bool not_equal ( float64_t  a,
float64_t  b 
) [static, protected]

method to make ALGLIB integration easier

Definition at line 484 of file Statistics.h.

void one_to_one_migration_prepare ( DynArray< TParameter * > *  param_base,
const SGParamInfo *  target,
TParameter *&  replacement,
TParameter *&  to_migrate,
char *  old_name = NULL 
) [protected, virtual, inherited]

This method prepares everything for a one-to-one parameter migration. One to one here means that only ONE element of the parameter base is needed for the migration (the one with the same name as the target). Data is allocated for the target (in the type as provided in the target SGParamInfo), and a corresponding new TParameter instance is written to replacement. The to_migrate pointer points to the single needed TParameter instance needed for migration. If a name change happened, the old name may be specified by old_name. In addition, the m_delete_data flag of to_migrate is set to true. So if you want to migrate data, the only thing to do after this call is converting the data in the m_parameter fields. If unsure how to use - have a look into an example for this. (base_migration_type_conversion.cpp for example)

Parameters:
param_base set of TParameter instances to use for migration
target parameter info for the resulting TParameter
replacement (used as output) here the TParameter instance which is returned by migration is created into
to_migrate the only source that is used for migration
old_name with this parameter, a name change may be specified

Definition at line 864 of file SGObject.cpp.

void print_modsel_params (  )  [inherited]

prints all parameter registered for model selection and their type

Definition at line 1084 of file SGObject.cpp.

void print_serializable ( const char *  prefix = ""  )  [virtual, inherited]

prints registered parameters out

Parameters:
prefix prefix for members

Definition at line 290 of file SGObject.cpp.

float64_t relative_entropy ( float64_t *  p,
float64_t *  q,
int32_t  len 
) [static]
Returns:
relative entropy $H(P||Q)$ where $p,q$ are given in logspace

Definition at line 1900 of file Statistics.cpp.

SGVector< int32_t > sample_indices ( int32_t  sample_size,
int32_t  N 
) [static]

sample indices

Parameters:
sample_size size of sample to pick
N total number of indices

Definition at line 1920 of file Statistics.cpp.

bool save_serializable ( CSerializableFile *  file,
const char *  prefix = "",
int32_t  param_version = VERSION_PARAMETER 
) [virtual, inherited]

Save this object to file.

Parameters:
file where to save the object; will be closed during returning if PREFIX is an empty string.
prefix prefix for members
param_version (optional) a parameter version different to (this is mainly for testing, better do not use)
Returns:
TRUE if done, otherwise FALSE

Reimplemented in CModelSelectionParameters.

Definition at line 296 of file SGObject.cpp.

void save_serializable_post (  )  throw (ShogunException) [protected, virtual, inherited]

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_POST is called.

Exceptions:
ShogunException Will be thrown if an error occurres.

Reimplemented in CKernel.

Definition at line 1043 of file SGObject.cpp.

void save_serializable_pre (  )  throw (ShogunException) [protected, virtual, inherited]

Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_PRE is called.

Exceptions:
ShogunException Will be thrown if an error occurres.

Reimplemented in CKernel.

Definition at line 1038 of file SGObject.cpp.

void set_generic< floatmax_t > (  )  [inherited]

set generic type to T

void set_global_io ( SGIO *  io  )  [inherited]

set the io object

Parameters:
io io object to use

Definition at line 217 of file SGObject.cpp.

void set_global_parallel ( Parallel *  parallel  )  [inherited]

set the parallel object

Parameters:
parallel parallel object to use

Definition at line 230 of file SGObject.cpp.

void set_global_version ( Version *  version  )  [inherited]

set the version object

Parameters:
version version object to use

Definition at line 265 of file SGObject.cpp.

virtual CSGObject* shallow_copy (  )  const [virtual, inherited]

A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.

Reimplemented in CGaussianKernel.

Definition at line 122 of file SGObject.h.

float64_t std_deviation ( SGVector< float64_t >  values  )  [static]

Calculates unbiased empirical standard deviation estimator of given values. Given $\{x_1, ..., x_m\}$, this is $\sqrt{\frac{1}{m-1}\sum_{i=1}^m (x-\bar{x})^2}$ where $\bar x=\frac{1}{m}\sum_{i=1}^m x_i$

Parameters:
values vector of values
Returns:
variance of given values

Definition at line 293 of file Statistics.cpp.

static float64_t tgamma ( float64_t  x  )  [static]
Returns:
gamma function of input

Definition at line 281 of file Statistics.h.

void unset_generic (  )  [inherited]

unset generic type

this has to be called in classes specializing a template class

Definition at line 285 of file SGObject.cpp.

bool update_parameter_hash (  )  [protected, virtual, inherited]

Updates the hash of current parameter combination.

Returns:
bool if parameter combination has changed since last update.

Definition at line 237 of file SGObject.cpp.

float64_t variance ( SGVector< float64_t >  values  )  [static]

Calculates unbiased empirical variance estimator of given values. Given $\{x_1, ..., x_m\}$, this is $\frac{1}{m-1}\sum_{i=1}^m (x-\bar{x})^2$ where $\bar x=\frac{1}{m}\sum_{i=1}^m x_i$

Parameters:
values vector of values
Returns:
variance of given values

Definition at line 202 of file Statistics.cpp.

Member Data Documentation

SGIO* io [inherited]

io

Definition at line 462 of file SGObject.h.

uint32_t m_hash [inherited]

Hash of parameter values

Definition at line 480 of file SGObject.h.

Parameter* m_model_selection_parameters [inherited]

model selection parameters

Definition at line 474 of file SGObject.h.

ParameterMap* m_parameter_map [inherited]

map for different parameter versions

Definition at line 477 of file SGObject.h.

Parameter* m_parameters [inherited]

parameters

Definition at line 471 of file SGObject.h.

Parallel* parallel [inherited]

parallel

Definition at line 465 of file SGObject.h.

Version* version [inherited]

version

Definition at line 468 of file SGObject.h.

The documentation for this class was generated from the following files:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines
SHOGUN Machine Learning Toolbox - Documentation