PMML (Predictive Model Markup Language) is the de facto standard used to represent and share predictive analytic solutions between applications. It enables data mining scientists and users alike to easily build, visualize, and deploy their solutions using different platforms and systems.
In addition to offering powerful, PMML-based applications in the form of ADAPA and UPPI, Zementis offers a variety of PMML tools and packages that support the creation of PMML-based models. With these PMML tools, you can build PMML-based models in R or Python, as well as generate PMML for data pre- and post-processing. These tools also serve as useful guides for learning PMML.
The tools include:
- PMML export for R through the pmml and pmmlTransformations packages
- Python to PMML Converter
- Transformations Generator
Zementis invites you to benefit from PMML fully and deploy your predictive solutions in minutes using ADAPA for real-time scoring and UPPI for big data scoring.
Python to PMML Converter (Py2PMML)
More and more data scientists are using Python to build their models. In particular, they are using a machine learning library called “scikit-learn”. This library offers a host of modeling techniques, which cover classification, regression and clustering. Given its popularity and the need to have models built in Python exported into PMML format, Zementis is now offering a Python to PMML Converter, or Py2PMML for short. It works by reading in a text file generated in python containing the model parameters and by giving back a PMML file equivalent of your model built in Python.
Py2PMML is super easy to use and the best part is that you can deploy your models directly inside ADAPA for real-time scoring or UPPI for Big Data scoring. Feel free to contact us to find out more or take a look at our support forums.
To learn more, click HERE
PMML Transformations Generator
The “Transformations Generator” tool is the result of our continuing commitment to the success and adoption of the PMML standard. This tool, companion to the book: “PMML in Action”, provides an interactive, hands-on approach to the generation of data transformations.
PMML provides a variety of data transformations, including value mapping, normalization, and discretization. It also offers several built-in functions as well as arithmetic and logical operators which can be combined to represent complex pre-processing steps. With the “Transformations Generator” tool, one can graphically design a transformation and obtain the respective PMML code.
The figure below shows the “Value Mapping” transformation as represented by the transformations generator tool. The left side shows the graphical representation of the mapping of primary colors to numbers. The left side shows the corresponding PMML code generated by the tool.
To give it a try, click HERE