Model_Exporter

Export, Integrate, Deploy…. Easy

Model_Exporter provides a unique and powerful means to add fast and flexible model prediction capability to any third-party software package without the need for outside libraries or toolboxes. Model_Exporter, an add-on product for PLS_Toolbox and Solo, exports models into a stand-alone “predictor” script which includes a simple-to-implement formula to perform a model prediction. Add the power of multivariate modeling to your proprietary application or simply apply models in Python, Java, .NET languages (C# etc), MathWorks’ MATLAB®, Octave, or LabView®, without the need for costly 3rd party toolboxes or libraries.

Free Interpreters Included

Model_Exporter includes the Model_Interpreter, a freely distributable predictor engine that can be used by your application without any licensing fees. The interpreter comes as source code for Java or C# (compilable on Windows or Linux) and as a .NET binary. Use these in your own code and distribute unlimited models in a wide range of applications.

Example Applications

• Handheld or embedded-computation devices high-throughput applications requiring high-speed data manipulation and calculations.
• Distributed applications in MathWorks’ MATLAB or Octave software.
• On-line predictions using MATLAB or LabView software.

Model_Exporter allows you to be self-sufficient and run all the calculations in your own environment.

Let Eigenvector Do the Math!

Don’t reinvent the mathematical steps and translate complicated proprietary file formats. Model_Exporter will provide all the model parameters and numerical calculations you need to make a prediction for a wide range of models including PCA models, regression models (PLS, PCR, MLR, CLS, SVM, and ANN) and classification models (PLSDA and SVMC), including all the preprocessing!

Generic XML format: The XML output format can be parsed by the supplied C# or Java interpreters, or you can translate those engines for your own environment. All you need to provide is the ability to parse XML, manage matrices, and do several simple mathematical operations. Model_Exporter handles everything else.

LabView and MATLAB applications: Predictors exported to m-file formats can be used in LabView or MATLAB. These predictors can be run without the need for any additional toolboxes or purchased libraries. The MATLAB m-file script will even run in the free Octave package.

Plug-in modular design: By using a modular, self-describing script format, you can easily update models without the need to recompile your application; Simply make a new XML or m-file available to your program and the new model will automatically be used. You need know nothing about the new model — it handles all the numerical variations.

More Information and Purchasing

Want to know more about Model Exporter? See the Model_Exporter User’s Guide. If you have any technical questions, contact us at helpdesk@eigenvector.com.

NEW LICENSES: You can purchase a copy of Model_Exporter using our on-line order form. For information on site-licenses and OEM options, contact us by phone (509.662.9213) or email (sales@eigenvector.com).

Product Support

Eigenvector Research offers user support for Model_Exporter by e-mail at helpdesk@eigenvector.com. Questions are almost always answered within 24 hours (and usually much less). Updates and bug fixes will be available for users to download from our web site. For information on other support options, see our technical support page.

Note: Unlike our other products, a paid Model_Exporter license does not provide access to the source m-code. For more information, please write us at helpdesk@eigenvector.com.

System Requirements

Model_Exporter requires PLS_Toolbox or Solo to create exported model predictors. Predictor requirements depend on the parsing language, application, and data requirements. See documentation for more details.