PLearn 0.1
Public Member Functions | Static Public Member Functions | Public Attributes | Static Public Attributes | Static Protected Member Functions | Protected Attributes | Private Types | Private Member Functions
PLearn::VMatrixFromDistribution Class Reference

#include <VMatrixFromDistribution.h>

Inheritance diagram for PLearn::VMatrixFromDistribution:
Inheritance graph
[legend]
Collaboration diagram for PLearn::VMatrixFromDistribution:
Collaboration graph
[legend]

List of all members.

Public Member Functions

 VMatrixFromDistribution ()
virtual void build ()
 Simply calls inherited::build() then build_().
virtual void makeDeepCopyFromShallowCopy (CopiesMap &copies)
 Transforms a shallow copy into a deep copy.
virtual string classname () const
virtual OptionListgetOptionList () const
virtual OptionMapgetOptionMap () const
virtual RemoteMethodMapgetRemoteMethodMap () const
virtual VMatrixFromDistributiondeepCopy (CopiesMap &copies) const
virtual real get (int i, int j) const
 This method must be implemented in all subclasses.
virtual void getSubRow (int i, int j, Vec v) const
 It is suggested that this method be implemented in subclasses to speed up accesses (default version repeatedly calls get(i,j) which may have a significant overhead).
virtual void getRow (int i, Vec v) const
 These methods do not usually need to be overridden in subclasses (default versions call getSubRow, which should do just fine)
virtual void getColumn (int i, Vec v) const
 Copies column i into v (which must have appropriate length equal to the VMat's length).
virtual void getMat (int i, int j, Mat m) const
 Copies the submatrix starting at i,j into m (which must have appropriate length and width).
virtual Mat toMat () const
 Returns a Mat with the same data as this VMat.

Static Public Member Functions

static string _classname_ ()
static OptionList_getOptionList_ ()
static RemoteMethodMap_getRemoteMethodMap_ ()
static Object_new_instance_for_typemap_ ()
static bool _isa_ (const Object *o)
static void _static_initialize_ ()
static const PPathdeclaringFile ()

Public Attributes

PP< PDistributiondistr
string mode
int32_t generator_seed
int nsamples
Vec mins
Vec maxs
int samples_per_dim

Static Public Attributes

static StaticInitializer _static_initializer_

Static Protected Member Functions

static void declareOptions (OptionList &ol)
 Declares this class' options.

Protected Attributes

Mat data
 Will hold the data sampled from the distribution.

Private Types

typedef VMatrix inherited

Private Member Functions

void build_ ()
 This does the actual building.

Detailed Description

Definition at line 50 of file VMatrixFromDistribution.h.


Member Typedef Documentation

Reimplemented from PLearn::VMatrix.

Definition at line 55 of file VMatrixFromDistribution.h.


Constructor & Destructor Documentation

PLearn::VMatrixFromDistribution::VMatrixFromDistribution ( )

Definition at line 47 of file VMatrixFromDistribution.cc.

References samples_per_dim.

    :mode("sample"), generator_seed(0), nsamples(0)
    /* ### Initialize all fields to their default value */
{
    samples_per_dim = 10;
}

Member Function Documentation

string PLearn::VMatrixFromDistribution::_classname_ ( ) [static]

Reimplemented from PLearn::VMatrix.

Definition at line 57 of file VMatrixFromDistribution.cc.

OptionList & PLearn::VMatrixFromDistribution::_getOptionList_ ( ) [static]

Reimplemented from PLearn::VMatrix.

Definition at line 57 of file VMatrixFromDistribution.cc.

RemoteMethodMap & PLearn::VMatrixFromDistribution::_getRemoteMethodMap_ ( ) [static]

Reimplemented from PLearn::VMatrix.

Definition at line 57 of file VMatrixFromDistribution.cc.

bool PLearn::VMatrixFromDistribution::_isa_ ( const Object o) [static]

Reimplemented from PLearn::VMatrix.

Definition at line 57 of file VMatrixFromDistribution.cc.

Object * PLearn::VMatrixFromDistribution::_new_instance_for_typemap_ ( ) [static]

Reimplemented from PLearn::Object.

Definition at line 57 of file VMatrixFromDistribution.cc.

StaticInitializer VMatrixFromDistribution::_static_initializer_ & PLearn::VMatrixFromDistribution::_static_initialize_ ( ) [static]

Reimplemented from PLearn::VMatrix.

Definition at line 57 of file VMatrixFromDistribution.cc.

void PLearn::VMatrixFromDistribution::build ( ) [virtual]

Simply calls inherited::build() then build_().

Reimplemented from PLearn::VMatrix.

Definition at line 154 of file VMatrixFromDistribution.cc.

References PLearn::VMatrix::build(), and build_().

Here is the call graph for this function:

void PLearn::VMatrixFromDistribution::build_ ( ) [private]

This does the actual building.

Reimplemented from PLearn::VMatrix.

Definition at line 90 of file VMatrixFromDistribution.cc.

References data, distr, generator_seed, i, PLearn::VMatrix::inputsize_, j, PLearn::VMatrix::length_, maxs, mins, mode, nsamples, PLERROR, PLearn::pow(), PLearn::TMat< T >::resize(), samples_per_dim, PLearn::VMatrix::targetsize_, PLearn::VMatrix::weightsize_, PLearn::TMat< T >::width(), and PLearn::VMatrix::width_.

Referenced by build().

{
    if(distr)
    {
        if(mode=="sample")
        {
            length_ = nsamples;
            width_ = distr->getNPredicted();
            inputsize_ = width_;
            targetsize_ = 0;
            weightsize_ = 0;
            data.resize(length_, width_);
            distr->resetGenerator(generator_seed);
            distr->generateN(data);
        }
        else if(mode=="density" || mode=="log_density")
        {
            length_ = (int)pow(double(samples_per_dim),double(distr->inputsize()));
            width_ = distr->inputsize()+1;
            inputsize_ = distr->inputsize();
            targetsize_ = 0;
            weightsize_ = 1;

            data.resize(length_, width_);
            Vec v(data.width());
            int k=0;
            switch(distr->inputsize())
            {
            case 1:
                for(int j=0;j<samples_per_dim;j++)
                {
                    v[0] = mins[0] + ((real)j / (samples_per_dim-1)) * (maxs[0]-mins[0]);
                    if(mode=="density")
                        v[1] = distr->density(v.subVec(0,1));
                    else // log_density
                        v[1] = distr->log_density(v.subVec(0,1));
                    data(k++)<<v;
                }
                break;
            case 2:
                for(int i=0;i<samples_per_dim;i++)
                {
                    v[0] = mins[0] + ((real)i / (samples_per_dim-1)) * (maxs[0]-mins[0]);
                    for(int j=0;j<samples_per_dim;j++)
                    {
                        v[1] = mins[1] + ((real)j / (samples_per_dim-1)) * (maxs[1]-mins[1]);
                        if(mode=="density")
                            v[2] = distr->density(v.subVec(0,2));
                        else // log_density
                            v[2] = distr->log_density(v.subVec(0,2));
                        data(k++)<<v;
                    }
                }
                break;
            default:
                PLERROR("density and log_density modes only supported for distribution of dimension 1 or 2");break;
            }
        }
        else
            PLERROR("In VMatrixFromDistribution: invalid mode: %s",mode.c_str());
    }
}

Here is the call graph for this function:

Here is the caller graph for this function:

string PLearn::VMatrixFromDistribution::classname ( ) const [virtual]

Reimplemented from PLearn::Object.

Definition at line 57 of file VMatrixFromDistribution.cc.

void PLearn::VMatrixFromDistribution::declareOptions ( OptionList ol) [static, protected]

Declares this class' options.

Reimplemented from PLearn::VMatrix.

Definition at line 59 of file VMatrixFromDistribution.cc.

References PLearn::OptionBase::buildoption, PLearn::declareOption(), PLearn::VMatrix::declareOptions(), distr, generator_seed, maxs, mins, mode, nsamples, and samples_per_dim.

{
    declareOption(ol, "distr", &VMatrixFromDistribution::distr, OptionBase::buildoption,
                  "The distribution this matrix will be generated from\n");

    declareOption(ol, "mode", &VMatrixFromDistribution::mode, OptionBase::buildoption,
                  "mode can be one of:\n"
                  "   \"sample\" : will draw nsamples from the distribution initializing the generator with the generator_seed \n"
                  "   \"density\" : for 1d or 2d distributions, will report the density along a grid of samples_per_dim \n"
                  "                 gridpoints per dimension. The resulting matrix will contain rows of the form [ coordinates density ] \n"
                  "   \"log_density\" : same as density, but reports the log of the density instead. \n"
        );

    declareOption(ol, "generator_seed", &VMatrixFromDistribution::generator_seed, OptionBase::buildoption,
                  "The initial generator_seed to initialize the distribution's generator");

    declareOption(ol, "nsamples", &VMatrixFromDistribution::nsamples, OptionBase::buildoption,
                  "number of samples to draw");

    declareOption(ol, "samples_per_dim", &VMatrixFromDistribution::samples_per_dim, OptionBase::buildoption,
                  "number of samples on each dimensions of the grid");

    declareOption(ol, "mins", &VMatrixFromDistribution::mins, OptionBase::buildoption,
                  "the minimum of the grid on each dimensions");

    declareOption(ol, "maxs", &VMatrixFromDistribution::maxs, OptionBase::buildoption,
                  "the maximum of the grid on each dimensions");

    inherited::declareOptions(ol);
}

Here is the call graph for this function:

static const PPath& PLearn::VMatrixFromDistribution::declaringFile ( ) [inline, static]

Reimplemented from PLearn::VMatrix.

Definition at line 109 of file VMatrixFromDistribution.h.

VMatrixFromDistribution * PLearn::VMatrixFromDistribution::deepCopy ( CopiesMap copies) const [virtual]

Reimplemented from PLearn::VMatrix.

Definition at line 57 of file VMatrixFromDistribution.cc.

real PLearn::VMatrixFromDistribution::get ( int  i,
int  j 
) const [virtual]

This method must be implemented in all subclasses.

Returns element (i,j).

Implements PLearn::VMatrix.

Definition at line 165 of file VMatrixFromDistribution.cc.

References data.

{ return data(i,j); }
void PLearn::VMatrixFromDistribution::getColumn ( int  i,
Vec  v 
) const [virtual]

Copies column i into v (which must have appropriate length equal to the VMat's length).

Reimplemented from PLearn::VMatrix.

Definition at line 168 of file VMatrixFromDistribution.cc.

References PLearn::TMat< T >::column(), and data.

{ v << data.column(i); }

Here is the call graph for this function:

void PLearn::VMatrixFromDistribution::getMat ( int  i,
int  j,
Mat  m 
) const [virtual]

Copies the submatrix starting at i,j into m (which must have appropriate length and width).

Reimplemented from PLearn::VMatrix.

Definition at line 177 of file VMatrixFromDistribution.cc.

References data, PLearn::TMat< T >::length(), PLearn::TMat< T >::subMat(), and PLearn::TMat< T >::width().

{ m << data.subMat(i,j,m.length(),m.width()); }

Here is the call graph for this function:

OptionList & PLearn::VMatrixFromDistribution::getOptionList ( ) const [virtual]

Reimplemented from PLearn::Object.

Definition at line 57 of file VMatrixFromDistribution.cc.

OptionMap & PLearn::VMatrixFromDistribution::getOptionMap ( ) const [virtual]

Reimplemented from PLearn::Object.

Definition at line 57 of file VMatrixFromDistribution.cc.

RemoteMethodMap & PLearn::VMatrixFromDistribution::getRemoteMethodMap ( ) const [virtual]

Reimplemented from PLearn::Object.

Definition at line 57 of file VMatrixFromDistribution.cc.

void PLearn::VMatrixFromDistribution::getRow ( int  i,
Vec  v 
) const [virtual]

These methods do not usually need to be overridden in subclasses (default versions call getSubRow, which should do just fine)

Copies row i into v (which must have appropriate length equal to the VMat's width).

Reimplemented from PLearn::VMatrix.

Definition at line 174 of file VMatrixFromDistribution.cc.

References data.

{ v << data(i); }
void PLearn::VMatrixFromDistribution::getSubRow ( int  i,
int  j,
Vec  v 
) const [virtual]

It is suggested that this method be implemented in subclasses to speed up accesses (default version repeatedly calls get(i,j) which may have a significant overhead).

Fills v with the subrow i lying between columns j (inclusive) and j+v.length() (exclusive).

Reimplemented from PLearn::VMatrix.

Definition at line 171 of file VMatrixFromDistribution.cc.

References data, and PLearn::TVec< T >::length().

{ v << data(i).subVec(j,v.length()); }

Here is the call graph for this function:

void PLearn::VMatrixFromDistribution::makeDeepCopyFromShallowCopy ( CopiesMap copies) [virtual]

Transforms a shallow copy into a deep copy.

Reimplemented from PLearn::VMatrix.

Definition at line 160 of file VMatrixFromDistribution.cc.

References PLearn::VMatrix::makeDeepCopyFromShallowCopy().

Here is the call graph for this function:

Mat PLearn::VMatrixFromDistribution::toMat ( ) const [virtual]

Returns a Mat with the same data as this VMat.

The default version of this method calls toMatCopy(). However this method will typically be overrided by subclasses (such as MemoryVMatrix) whose internal representation is already a Mat in order to return this Mat directly to avoid a new memory allocation and copy of elements. In this case, and in this case only, modifying the elements of the returned Mat will logically result in modified elements in the original VMatrix view of it. If you want to be sure that altering the content of the returned Mat won't modify the data contained in the VMatrix, you should call toMatCopy() instead.

Reimplemented from PLearn::VMatrix.

Definition at line 180 of file VMatrixFromDistribution.cc.

References data.

{ return data; }

Member Data Documentation

Reimplemented from PLearn::VMatrix.

Definition at line 109 of file VMatrixFromDistribution.h.

Will hold the data sampled from the distribution.

Definition at line 60 of file VMatrixFromDistribution.h.

Referenced by build_(), get(), getColumn(), getMat(), getRow(), getSubRow(), and toMat().

Definition at line 68 of file VMatrixFromDistribution.h.

Referenced by build_(), and declareOptions().

Definition at line 72 of file VMatrixFromDistribution.h.

Referenced by build_(), and declareOptions().

Definition at line 76 of file VMatrixFromDistribution.h.

Referenced by build_(), and declareOptions().

Definition at line 76 of file VMatrixFromDistribution.h.

Referenced by build_(), and declareOptions().

Definition at line 69 of file VMatrixFromDistribution.h.

Referenced by build_(), and declareOptions().

Definition at line 73 of file VMatrixFromDistribution.h.

Referenced by build_(), and declareOptions().

Definition at line 77 of file VMatrixFromDistribution.h.

Referenced by build_(), declareOptions(), and VMatrixFromDistribution().


The documentation for this class was generated from the following files:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines