pkdfnn.10.10.01.c File Reference

False Nearest Neighbor method: A parallel kd-tree approach based on top-down searching. More...

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <limits.h>
#include <math.h>
#include "tsa.h"
#include "tdkdtree.h"
#include "mpi.h"

Include dependency graph for pkdfnn.10.10.01.c:

Go to the source code of this file.

Defines
#define	WID_STR
Functions
static void	show_options ()
static void	scan_options ()
static double	standarddeviation ()
static void	makedelayvectors ()
int	main (int argc, char **argv)
	Main function.
static double	standarddeviation (double *x, int N)
	Computing standar deviation from a time series.
static void	makedelayvectors (int n, int d, double **y)
static void	scan_options (int argc, char **argv)
	Scanning program options from the command line.
static void	show_options (char *progname)
	Showing options of the command line.
Variables
static FILE *	prgerr = NULL
	Program error stream.
static FILE *	prgout = NULL
	Program output stream.
static unsigned long	N = ULONG_MAX
	Time series length.
static int	med = 1
	Minimal embedding dimension.
static int	m = 5
	Maximal embedding dimension.
static int	tau = 1
	Delay time.
static double	R_tol = 10.0
	Tolerance factor.
static unsigned long	exclude = 0
	Scalar values that would be exclude.
static unsigned int	column = 1
	Input file columns to be reading.
static char *	outfile = NULL
	Output file name pointer.
static char *	infile = NULL
	Input file name pointer.
static unsigned int	verbosity = 0xff
	Verbose level.
static double *	x = NULL
	Time series.

Detailed Description

False Nearest Neighbor method: A parallel kd-tree approach based on top-down searching.

Version:: 10.10.01

Author:: Julio José Águila Guerrero

Date:: October 20th, 2010

This program implements the False Nearest Neighbor (FNN) method introduced by Kennel et al. (1991). The goal of the method is to obtain the minimal embeding dimension of a dynamical system from a time series.
In this case, the implementation is based on a kd-tree data structure and the nearest neighbors searching is performed using a top-down algorithm. The kd-tree build function produces an unbalanced tree.

Note:: Last change was in October 22nd, 2010.

Definition in file pkdfnn.10.10.01.c.

Define Documentation

#define WID_STR

Value:

"Computing minimal embedding dimension using a\n" \
   "        false nearest neighbors method by Kennel et al. (1991).\n" \
   "        This program is a kd-tree data structure approach\n" \
   "        based on a top-down search algorithm."

Definition at line 326 of file pkdfnn.10.10.01.c.

Function Documentation

int main	(	int	argc,
		char **	argv
	)

Main function.

Parameters:

	argc	Arguments counter.
	argv	Arguments vector.

Returns:: If there is not error the function returns 0. Anything else in other case.

Definition at line 100 of file pkdfnn.10.10.01.c.

Here is the call graph for this function:

static void makedelayvectors	(	int	n,
		int	d,
		double **	y
	)			`[static]`

Definition at line 250 of file pkdfnn.10.10.01.c.

static void makedelayvectors ( ) [static]

Here is the caller graph for this function:

static void scan_options	(	int	argc,
		char **	argv
	)			`[static]`

Scanning program options from the command line.

Parameters:

	argc	Arguments counter.
	argv	Arguments vector.

Returns:: None.

Definition at line 276 of file pkdfnn.10.10.01.c.

static void scan_options ( ) [static]

Here is the caller graph for this function:

static void show_options ( char * progname ) [static]

Showing options of the command line.

Parameters:

progname

Program name.

Returns:: None.

Definition at line 339 of file pkdfnn.10.10.01.c.

static void show_options ( ) [static]

Here is the caller graph for this function:

static double standarddeviation	(	double *	x,
		int	N
	)			`[static]`

Computing standar deviation from a time series.

Parameters:

	x	Time series.
	N	Time series length.

Returns:: Standar deviation of the time series x.

Definition at line 223 of file pkdfnn.10.10.01.c.

static double standarddeviation ( ) [static]

Here is the caller graph for this function:

Variable Documentation

unsigned int column = 1 [static]

Input file columns to be reading.

Definition at line 72 of file pkdfnn.10.10.01.c.

unsigned long exclude = 0 [static]

Scalar values that would be exclude.

Definition at line 68 of file pkdfnn.10.10.01.c.

char* infile = NULL [static]

Input file name pointer.

Definition at line 80 of file pkdfnn.10.10.01.c.

int m = 5 [static]

Maximal embedding dimension.

Definition at line 56 of file pkdfnn.10.10.01.c.

int med = 1 [static]

Minimal embedding dimension.

Definition at line 52 of file pkdfnn.10.10.01.c.

unsigned long N = ULONG_MAX [static]

Time series length.

Definition at line 48 of file pkdfnn.10.10.01.c.

char* outfile = NULL [static]

Output file name pointer.

Definition at line 76 of file pkdfnn.10.10.01.c.

FILE* prgerr = NULL [static]

Program error stream.

Definition at line 40 of file pkdfnn.10.10.01.c.

FILE* prgout = NULL [static]

Program output stream.

Definition at line 44 of file pkdfnn.10.10.01.c.

double R_tol = 10.0 [static]

Tolerance factor.

Definition at line 64 of file pkdfnn.10.10.01.c.

int tau = 1 [static]

Delay time.

Definition at line 60 of file pkdfnn.10.10.01.c.

unsigned int verbosity = 0xff [static]

Verbose level.

Definition at line 84 of file pkdfnn.10.10.01.c.

double* x = NULL [static]

Time series.

Definition at line 88 of file pkdfnn.10.10.01.c.

pkdfnn.10.10.01.c File Reference

Defines

Functions

Variables

Detailed Description

Define Documentation

Function Documentation

Variable Documentation