pdf1d_pdf Class Reference

#include <pdf1d_pdf.h>

Inheritance diagram for pdf1d_pdf:

Inheritance graph
[legend]

List of all members.


Detailed Description

Base class for Univariate Probability Density Function classes.

Functions are available to test the plausibility of a vector or set of parameters, to modify a set of parameters so it is plausible and to choose a threshold of plausibility. Also, for cases where the distributions of parameters are multi-modal, the number and centres of each peak can be recorded. This is particularly useful for non-linear and mixture model representations of the parameter distributions.

Definition at line 26 of file pdf1d_pdf.h.


Public Member Functions

 pdf1d_pdf ()
 Dflt ctor.
virtual ~pdf1d_pdf ()
 Destructor.
double mean () const
 Mean of distribution.
double variance () const
 Variance of each dimension.
virtual int n_peaks () const
 Number of peaks of distribution.
virtual double peak (int) const
 Position of the i'th peak.
virtual double log_p (double x) const =0
 Log of probability density at x.
virtual double operator() (double x) const
 Probability density at x.
virtual double cdf (double x) const
 Cumulative Probability (P(x'<x) for x' drawn from the distribution.
virtual bool cdf_is_analytic () const
 Return true if cdf() uses an analytic implementation.
virtual double inverse_cdf (double P) const
 The inverse cdf.
virtual double gradient (double x, double &p) const =0
 Gradient and value of PDF at x.
virtual pdf1d_samplernew_sampler () const =0
 Create a sampler object on the heap.
virtual double log_prob_thresh (double pass_proportion) const
 Compute threshold for PDF to pass a given proportion.
virtual double nearest_plausible (double x, double log_p_min) const =0
 Compute nearest point to x which has a density above a threshold.
virtual bool is_valid_pdf () const
 Return true if the object represents a valid PDF.
void get_samples (vnl_vector< double > &x) const
 Fill x with samples drawn from distribution.
short version_no () const
 Version number for I/O.
virtual vcl_string is_a () const
 Name of the class.
virtual bool is_class (vcl_string const &s) const
 Does the name of the class match the argument?.
virtual pdf1d_pdfclone () const =0
 Create a copy on the heap and return base class pointer.
virtual void print_summary (vcl_ostream &os) const =0
 Print class to os.
virtual void b_write (vsl_b_ostream &bfs) const =0
 Save class to binary file stream.
virtual void b_read (vsl_b_istream &bfs)=0
 Load class from binary file stream.
bool write_plot_file (const vcl_string &plot_file, double min_x, double max_x, int n) const
 Write values (x,p(x)) to text file suitable for plotting.

Protected Member Functions

void set_mean (double m)
void set_variance (double v)

Private Attributes

double mean_
double var_

Constructor & Destructor Documentation

pdf1d_pdf::pdf1d_pdf (  ) 

Dflt ctor.

Definition at line 24 of file pdf1d_pdf.cxx.

pdf1d_pdf::~pdf1d_pdf (  )  [virtual]

Destructor.

Definition at line 31 of file pdf1d_pdf.cxx.


Member Function Documentation

void pdf1d_pdf::set_mean ( double  m  )  [inline, protected]

Reimplemented in pdf1d_gaussian.

Definition at line 31 of file pdf1d_pdf.h.

void pdf1d_pdf::set_variance ( double  v  )  [inline, protected]

Definition at line 32 of file pdf1d_pdf.h.

double pdf1d_pdf::mean (  )  const [inline]

Mean of distribution.

Definition at line 42 of file pdf1d_pdf.h.

double pdf1d_pdf::variance (  )  const [inline]

Variance of each dimension.

Definition at line 45 of file pdf1d_pdf.h.

virtual int pdf1d_pdf::n_peaks (  )  const [inline, virtual]

Number of peaks of distribution.

Definition at line 48 of file pdf1d_pdf.h.

virtual double pdf1d_pdf::peak ( int   )  const [inline, virtual]

Position of the i'th peak.

Definition at line 51 of file pdf1d_pdf.h.

virtual double pdf1d_pdf::log_p ( double  x  )  const [pure virtual]

double pdf1d_pdf::operator() ( double  x  )  const [virtual]

double pdf1d_pdf::cdf ( double  x0  )  const [virtual]

Cumulative Probability (P(x'<x) for x' drawn from the distribution.

Cumulative Probability (P(x'<x) for x' drawn from the distribution).

By default this can be calculated by drawing random samples from the distribution and computing the number less than x.

Reimplemented in pdf1d_epanech_kernel_pdf, pdf1d_exponential, pdf1d_flat, pdf1d_gaussian, pdf1d_gaussian_kernel_pdf, pdf1d_mixture, and pdf1d_weighted_epanech_kernel_pdf.

Definition at line 45 of file pdf1d_pdf.cxx.

bool pdf1d_pdf::cdf_is_analytic (  )  const [virtual]

Return true if cdf() uses an analytic implementation.

Default is false, as the base implementation is to draw samples from the distribution randomly to estimate cdf(x)

Reimplemented in pdf1d_epanech_kernel_pdf, pdf1d_exponential, pdf1d_flat, pdf1d_gaussian, pdf1d_gaussian_kernel_pdf, pdf1d_mixture, and pdf1d_weighted_epanech_kernel_pdf.

Definition at line 62 of file pdf1d_pdf.cxx.

double pdf1d_pdf::inverse_cdf ( double  P  )  const [virtual]

The inverse cdf.

The inverse cumulative distribution function.

The value of x: P(x'<x) = P for x' drawn from distribution pdf. The default version of this algorithm uses sampling if !cdf_is_analytic(), and Newton-Raphson root finding otherwise.

The value of x: P(x'<x) = P for x' drawn from distribution pdf.

Reimplemented in pdf1d_kernel_pdf.

Definition at line 288 of file pdf1d_pdf.cxx.

virtual double pdf1d_pdf::gradient ( double  x,
double &  p 
) const [pure virtual]

Gradient and value of PDF at x.

Computes gradient of PDF at x, and returns the prob at x in p

Implemented in pdf1d_epanech_kernel_pdf, pdf1d_exponential, pdf1d_flat, pdf1d_gaussian, pdf1d_gaussian_kernel_pdf, pdf1d_mixture, and pdf1d_weighted_epanech_kernel_pdf.

virtual pdf1d_sampler* pdf1d_pdf::new_sampler (  )  const [pure virtual]

Create a sampler object on the heap.

Caller is responsible for deletion.

Implemented in pdf1d_epanech_kernel_pdf, pdf1d_exponential, pdf1d_flat, pdf1d_gaussian, pdf1d_gaussian_kernel_pdf, pdf1d_mixture, and pdf1d_weighted_epanech_kernel_pdf.

double pdf1d_pdf::log_prob_thresh ( double  pass_proportion  )  const [virtual]

Compute threshold for PDF to pass a given proportion.

Reimplemented in pdf1d_exponential, pdf1d_flat, and pdf1d_gaussian.

Definition at line 68 of file pdf1d_pdf.cxx.

virtual double pdf1d_pdf::nearest_plausible ( double  x,
double  log_p_min 
) const [pure virtual]

Compute nearest point to x which has a density above a threshold.

If log_p(x)>log_p_min then x returned unchanged. Otherwise move (typically up the gradient) until log_p(x)>=log_p_min.

Implemented in pdf1d_epanech_kernel_pdf, pdf1d_exponential, pdf1d_flat, pdf1d_gaussian, pdf1d_gaussian_kernel_pdf, pdf1d_mixture, and pdf1d_weighted_epanech_kernel_pdf.

bool pdf1d_pdf::is_valid_pdf (  )  const [virtual]

Return true if the object represents a valid PDF.

This will return false, if n_dims() is 0, for example just ofter default construction.

Reimplemented in pdf1d_mixture.

Definition at line 126 of file pdf1d_pdf.cxx.

void pdf1d_pdf::get_samples ( vnl_vector< double > &  x  )  const

Fill x with samples drawn from distribution.

Utility function. This calls new_sampler() to do the work, then deletes the sampler again. If you intend calling this repeatedly, create a sampler yourself.

Definition at line 132 of file pdf1d_pdf.cxx.

short pdf1d_pdf::version_no (  )  const

vcl_string pdf1d_pdf::is_a (  )  const [virtual]

bool pdf1d_pdf::is_class ( vcl_string const &  s  )  const [virtual]

virtual pdf1d_pdf* pdf1d_pdf::clone (  )  const [pure virtual]

Create a copy on the heap and return base class pointer.

Implemented in pdf1d_epanech_kernel_pdf, pdf1d_exponential, pdf1d_flat, pdf1d_gaussian, pdf1d_gaussian_kernel_pdf, pdf1d_mixture, and pdf1d_weighted_epanech_kernel_pdf.

void pdf1d_pdf::print_summary ( vcl_ostream &  os  )  const [pure virtual]

void pdf1d_pdf::b_write ( vsl_b_ostream bfs  )  const [pure virtual]

void pdf1d_pdf::b_read ( vsl_b_istream bfs  )  [pure virtual]

bool pdf1d_pdf::write_plot_file ( const vcl_string &  plot_file,
double  min_x,
double  max_x,
int  n 
) const

Write values (x,p(x)) to text file suitable for plotting.

Evaluate pdf at n points in range [min_x,max_x] and write a text file, each line of which is {x p(x)}, suitable for plotting with many graph packages

Definition at line 142 of file pdf1d_pdf.cxx.


Member Data Documentation

double pdf1d_pdf::mean_ [private]

Definition at line 28 of file pdf1d_pdf.h.

double pdf1d_pdf::var_ [private]

Definition at line 29 of file pdf1d_pdf.h.


The documentation for this class was generated from the following files:

Generated on Sun Nov 22 06:23:41 2009 for contrib/mul/pdf1d by  doxygen 1.5.5