Mpca and Release Notes Version 6 7: Difference between pages

From Eigenvector Research Documentation Wiki
(Difference between pages)
Jump to navigation Jump to search
imported>Mathias
 
imported>Scott
 
Line 1: Line 1:
===Purpose===


Multi-way (unfold) principal components analysis.


===Synopsis===
Version 6.7 of PLS_Toolbox and Solo was released in March, 2012.
:mpca - Launches an analysis window with MPCA as the selected method.
:model = mpca(mwa,ncomp,''options'')
:model = mpca(mwa,ncomp,preprostring)
:pred = mpca(mwa,model,''options'')


===Description===
For general product information, see [http://www.eigenvector.com/software/pls_toolbox.htm PLS_Toolbox Product Page]. For information on Solo, see [http://www.eigenvector.com/software/solo.htm Solo Product Page].


Principal Components Analysis of multi-way data using unfolding to a 2-way matrix followed by conventional PCA.
(back to [[Release Notes PLS Toolbox and Solo]])


Inputs to MPCA are the multi-way array mwa (class "double" or "dataset") and the number of components to use in the model nocomp. To make predictions with new data the inputs are the multi-way array mwa and the MPCA model model. Optional input ''options'' is discussed below.
==NEW FEATURES==


For assistance in preparing batch data for use in MPCA please see [[bspcgui]].
===Design Of Experients (DOE) Tools===
* bla


The output model is a structure array with the following fields:
===Other Method Improvements===
* bla
 
===Preprocessing===
* bla
 
===Import / Export===
* bla
 
===DataSet Editor===
* bla


* '''modeltype''': 'MPCA',
===Plot Controls===
* Selectable plot themes. [[Image:Figbg_color.gif|thumb|| ]]
* bla


* '''datasource''': structure array with information about the x-block,
===[[AnalysisWindow_Layout|Analysis Window]]===
* Show CV results for confusion table when available.
* Improved [[modelcache]] performance and string handling.


* '''date''': date of creation,
===[[WorkspaceBrowser_Layout|Workspace Browser]] ===
* Drag Drop - Enable dragging and dropping of system files onto the Browser window as well as to Analysis window. Enhanced highlighting of drop location.


* '''time''': time of creation,
===Command-line Tool Changes===
* bla


* '''info''': additional model information,


* '''loads''': 1 by 2 cell array with model loadings for each mode/dimension,
==NEW FUNCTIONS AND FILES==


* '''pred''': cell array with model predictions for each input data block (this is empty if options.blockdetail = 'normal'),
*''Full Support for Matlab R2012a''


* '''tsqs''': cell array with T<sup>2</sup> values for each mode,
===Misc New Functions===
:[[autoexport]] - Exports a DataSet object to a file of the specified format.
:[[classsummary]] - List class and axisscale distributions for a DataSet.
:[[figuretheme]] - Resets a figure background and axes to a specified color.
:[[meantrimmed]] - Trimmed mean.
:[[mediantrimmed]] - Trimmed median.
:[[windowfilter]] - Spectral filtering.


* '''ssqresiduals''': cell array with sum of squares residuals for each mode,
===Design of Analysis Tools===
:[[anovadoe]]        - Function to perform ANOVA for 2^k factorial model X, Y data


* '''description''': cell array with text description of model, and
===Other Changes===


* '''detail''': sub-structure with additional model details and results.
:[[crossval]] - improved display of classification results, improved integration with model input
 
===Options===
 
'''options''' = a structure array with the following fields.
 
* '''display''': [ 'off' | {'on'} ]  governs level of display to command window,
 
* '''plots''': [ 'none' | {'final'} ] governs level of plotting,
 
* '''outputversion''': [ 2 | {3} ] governs output format,
 
* '''preprocessing''': { [] }  preprocessing structure, {default is mean centering i.e. options.preprocessing = preprocess('default', 'mean center')} (see PREPROCESS),
 
* '''algorithm''': [ {'svd'} | 'maf' | 'robustpca' ], algorithm for decomposition, Algorithm 'maf' requires Eigenvector's MIA_Toolbox.
 
* '''confidencelimit''': [ {'0.95'} ], confidence level for Q and T2 limits. A value of zero (0) disables calculation of confidencelimits.
 
* '''roptions''': structure of options to pass to robpca (robust PCA engine from the Libra Toolbox).
 
* '''blockdetails''': [ 'compact' | {'standard'} | 'all' ]  extent of detail in predictions and residuals included in model structure ('standard' results in sum of squared residuals, and 'all' gives all x-block residuals), and
 
* '''samplemode''': [ {3} ]  mode (dimension) to use as the sample mode e.g. if it is 3 then it is assumed that mode 3 is the sample/object dimension i.e. if mwa is 7x9x10 then the scores model.loads{1} will have 10 rows (it will be 10xncomp).
 
The default options can be retreived using: options = mpca('options');.
 
It is also possible to input just the preprocessing option as an ordinary string in place of ''options'' and have the remainder of options filled in with the defaults from above. The following strings are valid:
 
: ''''none'''': no scaling,
 
: ''''auto'''': unfolds array then applies autoscaling,
 
: ''''mncn'''': unfolds array then applies mean centering, or
 
: ''''grps'''': {default} unfolds array then group/block scales each variable, i.e. the same variance scaling is used for each variable along its time trajectory (see GSCALE).
 
MPCA will work with arrays of order 3 and higher. For higher order arrays, the last order is assumed to be the sample order, ''i.e.'' for an array of order ''n'' with the dimension of order ''n'' being ''m'', the unfolded matrix will have ''m'' samples. For arrays of higher order the group scaling option will group together all data with the same order 2 index, for multiway array mwa, each mwa(:,j,:, ... ,:) will be scaled as a group.
 
===See Also===
 
[[analysis]], [[bspcgui]], [[evolvfa]], [[ewfa]], [[explode]], [[parafac]], [[pca]], [[preprocess]]

Revision as of 10:36, 7 March 2012


Version 6.7 of PLS_Toolbox and Solo was released in March, 2012.

For general product information, see PLS_Toolbox Product Page. For information on Solo, see Solo Product Page.

(back to Release Notes PLS Toolbox and Solo)

NEW FEATURES

Design Of Experients (DOE) Tools

  • bla

Other Method Improvements

  • bla

Preprocessing

  • bla

Import / Export

  • bla

DataSet Editor

  • bla

Plot Controls

Analysis Window

  • Show CV results for confusion table when available.
  • Improved modelcache performance and string handling.

Workspace Browser

  • Drag Drop - Enable dragging and dropping of system files onto the Browser window as well as to Analysis window. Enhanced highlighting of drop location.

Command-line Tool Changes

  • bla


NEW FUNCTIONS AND FILES

  • Full Support for Matlab R2012a

Misc New Functions

autoexport - Exports a DataSet object to a file of the specified format.
classsummary - List class and axisscale distributions for a DataSet.
figuretheme - Resets a figure background and axes to a specified color.
meantrimmed - Trimmed mean.
mediantrimmed - Trimmed median.
windowfilter - Spectral filtering.

Design of Analysis Tools

anovadoe - Function to perform ANOVA for 2^k factorial model X, Y data

Other Changes

crossval - improved display of classification results, improved integration with model input
Retrieved from "https://www.wiki.eigenvector.com/index.php?title=Mpca&oldid=8087"