HoloPRO Interface and Vipnway: Difference between pages

From Eigenvector Research Documentation Wiki
(Difference between pages)
Jump to navigation Jump to search
imported>Jeremy
No edit summary
 
imported>Scott
No edit summary
 
Line 1: Line 1:
==Introduction==
===Purpose===


Kaiser Optical Systems' HoloPRO software supports calls into either Solo_Predictor (as of v3.2.0.5) or Matlab. The sections below give some background and basic information on using HoloPRO software with Eigenvector Research products. [http://www.kosi.com Contact Kaiser Optical Systems] for more information on interfacing to Matlab or using the Solo_Predictor interfacing options of HoloPRO.
Calculate Variable Importance in Projection from NPLS model.


==Solo_Predictor Interface==
===Synopsis===
For making predictions using Solo_Predictor, a regression model can be specified and HoloPRO will automatically extract the available information from that model. For best interfacing, it is recommended you build models which include labels on your y-block columns to clearly identify the predicted species.


==Model_Exporter Interface==
:vip_scores = vipnway(model)
To use Eigenvector Research models which have been exported using Model_Exporter, HoloPRO supports calling into Matlab which can be scripted to return results from the model of interest. The Model_Exporter models can be called directly and do not require any additional software beyond Matlab and HoloPRO.


==PLS_Toolbox Interface==
===Description===
To use Eigenvector models with PLS_Toolbox natively (without using Model_Exporter) HoloPRO's Matlab interface can be used along with custom scripts to return results from the model of interest. For assistance with scripting for these situations, [mailto:helpdesk@eigenvector.com contact our Helpdesk].


====Licensing====
Variable Importance in Projection (VIP) scores estimate the importance of each variable in the projection used in a NPLS model and is often used for variable selection. A variable with a VIP Score close to or greater than 1 (one) can be considered important in given model. Variables with VIP scores significantly less than 1 (one) are less important and might be good candidates for exclusion from the model. It works for X n-way and Y up to two-way and it assume samples are in the first mode.


Note that the [http://www.eigenvector.com/software/license_evri.html PLS_Toolbox license] requires that, unless special site licensing arrangements are made, you must obtain a separate PLS_Toolbox license for each instance of any PLS_Toolbox code you wish to deploy. Special licensing options are available. See the [http://www.eigenvector.com Eigenvector Website] for more information.
====Inputs====


====Configuration====
* '''model''' = A NPLS model structure from a NPLS model.
For best performance, it is recommended that you follow these instructions to configure Matlab and PLS_Toolbox:


With Matlab already installed (as per [http://www.mathworks.com The Mathworks installation instructions]), PLS_Toolbox can be copied onto the target computer using any of the available file types as described in the [[Installation|standard installation instructions]]. The primary differences from the standard installation will be that you will create two special files and place these files into the PLS_Toolbox/utilities folder on the target computer:
====Outputs====
# Create a text file named '''evrilicense.lic''' and put your license code (available from the [http://download.eigenvector.com Eigenvector Research download page]) as a single line in that file. You can also obtain a evrilicense.lic file from the [mailto:helpdesk@eigenvector.com Eigenvector Helpdesk].
 
# Create an ''empty'' text file named '''evrinetwork.lic'''. This file will instruct PLS_Toolbox to ignore installation errors and run without warnings (necessary when calling PLS_Toolbox functions from within SiPAT.)
* '''vip_scores''' = a cell array with dimensions of: [modes 2 to n X # of columns in Y]. The first row in the cell array corresponds to VIP Scores for mode 2. The second row corresponds to VIP Scores for mode 3.
 
===See Also===
 
[[selectvars]], [[genalg]], [[ipls]], [[plotloads]], [[pls]], [[plsda]], [[sratio]], [[rpls]], [[vip]]

Revision as of 17:06, 18 December 2018

Purpose

Calculate Variable Importance in Projection from NPLS model.

Synopsis

vip_scores = vipnway(model)

Description

Variable Importance in Projection (VIP) scores estimate the importance of each variable in the projection used in a NPLS model and is often used for variable selection. A variable with a VIP Score close to or greater than 1 (one) can be considered important in given model. Variables with VIP scores significantly less than 1 (one) are less important and might be good candidates for exclusion from the model. It works for X n-way and Y up to two-way and it assume samples are in the first mode.

Inputs

  • model = A NPLS model structure from a NPLS model.

Outputs

  • vip_scores = a cell array with dimensions of: [modes 2 to n X # of columns in Y]. The first row in the cell array corresponds to VIP Scores for mode 2. The second row corresponds to VIP Scores for mode 3.

See Also

selectvars, genalg, ipls, plotloads, pls, plsda, sratio, rpls, vip