Contact Sales: (619) 330-0780

Solutions for Python Users

Python scikit-learn

Rapid Deployment and Real-time Scoring for Python Users

Python has achieved broad acceptance as a capable programming language and, in combination with scikit-learn, has achieved widespread adoption among data scientists as an efficient tool for machine learning. Even when data scientists utilize this powerful machine learning library for data analysis, they still confront the challenge of rapidly deploying predictive models from their desktop development environment into an operational IT environment.

Zementis solutions support batch, real-time and streaming analytics, offering a highly efficient, versatile and cost-effective approach to executing models developed in scikit-learn.

ADAPA and UPPI utilize PMML, the Predictive Model Markup Language, which is the industry standard for representing predictive models. PMML allows models to be developed in one application and deployed within another, as long as both applications are PMML-compliant. Since both Zementis solutions are compatible with PMML, scikit-learn users benefit by gaining both extreme speed and extreme agility across the predictive model lifecycle.

From model development, to test, to deployment and to ongoing operation in a production environment, Zementis delivers more efficient data science to Python users.

 

Immediate Benefits of Using ADAPA or UPPI

Once a model built in scikit-learn is saved as a PMML file, it can be directly deployed in ADAPA or in UPPI for scoring in whatever production environment the business utilizes. With ADAPA and UPPI, you can:

  • Execute your scikit-learn models on any target platform, without the need for a Python-based deployment engine or special Python enhancements
  • Support a wide breadth of modeling approaches (e.g. model ensembles, segmentation, chaining, cascade)
  • Overcome memory and speed limitations that Python imposes on model execution performance
  • Support real-time scoring for high-volume transactions
  • Deploy your Python models in minutes, not months (no need for recoding models into production)
  • Make one or many predictive models operational at once
  • Ensure consistent model performance by removing dependency on the Python environment

 
With ADAPA, you can:

  • Execute models on-demand, for individual real-time transactions or batch scoring applications
  • Manage models via Web Services or a Web console
  • Tap into all the advantages of cloud computing with ADAPA in the Cloud

 
With UPPI, you can:

  • Execute your models in-database, close to where your data resides with UPPI In-database (Greenplum/Pivotal, IBM PureData for Analytics (Netezza), IBM z Systems mainframes, SAP Sybase IQ and Teradata Aster)
  • Tap into the advantages of big data infrastructure components and applications within the Hadoop ecosystem, using Hive, Spark and Storm for batch and real-time streaming analytics, as well as Datameer for advanced business intelligence

 

Python PMML Support

Python offers support for PMML through the Py2PMML converter available from Zementis. This package allows for great flexibility to export your scikit-learn models and transformations into PMML.

  • Py2PMML Converter: Read this introduction to learn more about the Zementis Py2PMML Converter
  • Python Support Forums: Our support forums offer multiple examples of Python commands that allow you to build a model in scikit-learn and export the model in PMML. Browse through our Python PMML Support Forums for details.

 

A Common Industry Standard

PMML allows for the decoupling of two very important data mining tasks: model development and operational model deployment. With PMML, data scientists can focus on data analysis and model building using best-of-breed model development tools, whereas ADAPA and UPPI make operational deployment and actual use of the model extremely fast and simple.

 

Python into ADAPA UPPI

 

For example, if a data scientist develops a Random Forest Model using the scikit-learn RandomForestClassifier class, effectively deploying the model operationally only requires saving it as a PMML file using the Zementis Py2PMML converter and then deploying it either in ADAPA or UPPI for scoring.

Once deployed, the model is available for all to use. ADAPA makes models available for scoring on-premise through ADAPA On-site or in the cloud through ADAPA in the Cloud. UPPI makes models available for scoring in-database or in Hadoop.

PMML allows for the model development environment to be used just for that, model development. Scoring, in real-time or for batch jobs, is handled by ADAPA or UPPI.

To speak with a Zementis representative and get more information about our predictive analytics solutions, please contact us.

 

Copyright © 2017 Zementis / Software AG. All Rights Reserved.