Rescale: Difference between revisions

From Eigenvector Research Documentation Wiki
Jump to navigation Jump to search
imported>Jeremy
(Importing text file)
imported>Jeremy
 
(4 intermediate revisions by 2 users not shown)
Line 1: Line 1:
===Purpose===
===Purpose===


Line 6: Line 5:
===Synopsis===
===Synopsis===


:rx = rescale(x,means,''stds,options'')
:rx = rescale(x,means,stds,options)
:rx = rescale(x,means)


===Description===
===Description===


Rescales a matrix x using the means means and standard deviation stds vectors specified. An optional input options is an options structure with the field:
Rescales a matrix <tt>x</tt>, using the means <tt>means</tt> and standard deviation <tt>stds</tt> vectors specified.
 
====Inputs====
 
* '''x''' = matrix of input data
* '''means''' = vector of means to be used for rescaling
* '''stds''' = vector of standard deviations to be used for rescaling
 
If only two input arguments are supplied, the function will correct the means only.


rx = rescale(x,means) rescales a mean centered matrix x using a vector of means.
====Outputs====


rx = rescale(x,means,''stds'') rescales an autoscaled matrix x using a vector of means, and vector of standard deviations stds.
* '''rx''' = rescaled version of the input data '''x'''


===Options===
===Options===


*     '''stdthreshold''': [ 0 ] scalar value or vector of standard deviation threshold values. If a standard deviation is below its corresponding threshold value, the threshold value will be used in lieu of the actual value. A scalar value is used as a threshold for all variables.
options = a structure array with the field:
 
* '''stdthreshold''' = [0] scalar value or vector of standard deviation threshold values. If a standard deviation is below its                   corresponding threshold value, the threshold value will be used in lieu of the actual value. A scalar value is                     used as a threshold for all variables.
 
===Examples===
 
rx = rescale(x,means)
rescales a mean centered matrix <tt>x</tt> using a vector of means <tt>means</tt>.
 
rx = rescale(x,means,stds)
rescales a previously autoscaled matrix <tt>x</tt> using a vector of means <tt>means</tt>, and vector of standard deviations <tt>stds</tt>.


===See Also===
===See Also===


[[auto]], [[medcn]], [[mncn]], [[npreprocess]], [[preprocess]], [[scale]]
[[auto]], [[medcn]], [[mncn]], [[npreprocess]], [[preprocess]], [[scale]]

Latest revision as of 15:54, 22 February 2013

Purpose

Scales data back to original scaling.

Synopsis

rx = rescale(x,means,stds,options)
rx = rescale(x,means)

Description

Rescales a matrix x, using the means means and standard deviation stds vectors specified.

Inputs

  • x = matrix of input data
  • means = vector of means to be used for rescaling
  • stds = vector of standard deviations to be used for rescaling

If only two input arguments are supplied, the function will correct the means only.

Outputs

  • rx = rescaled version of the input data x

Options

options = a structure array with the field:

  • stdthreshold = [0] scalar value or vector of standard deviation threshold values. If a standard deviation is below its corresponding threshold value, the threshold value will be used in lieu of the actual value. A scalar value is used as a threshold for all variables.

Examples

rx = rescale(x,means)

rescales a mean centered matrix x using a vector of means means.

rx = rescale(x,means,stds)

rescales a previously autoscaled matrix x using a vector of means means, and vector of standard deviations stds.

See Also

auto, medcn, mncn, npreprocess, preprocess, scale