🚀 QPython User Guide: Processing Quantexa Assets Release

The Education Services Team is pleased to announce the release of the QPython User Guide: Module 1 (Processing Quantexa Assets).

The User Guide, built in close collaboration with R&D and made available on the Community Platform, is an introductory resource for data scientists and engineers who wish to leverage the QPython library to harness the power of Quantexa.

This is pure Python. No Scala programming is required!

What’s in the QPython User Guide?

The User Guide covers the complete QPython suite and is split into three Modules.

• Module 1 - Processing Quantexa Assets (Released now)
• Module 2 - The Quantexa Knowledge Graph - to be released Q1 FY27
• Module 3 - Scorecard Tuning with QPython - to be released Q1 FY27

The module is designed using the Quantexa Platform 2.8.x and Python 3.11.x.

What can you learn from Module 1?

Module 1 covers using QPython to process the outputs from the Batch Quantexa Platform.

1. Starting with the Quantexa Batch Resolver, you can process the results of Entity Resolution.
2. Moving downstream to the Graph Generation stage, you can access the graphs in the Quantexa Scoring Graph.
3. Finally, you can analyze the Scoring and Re-Alerting outputs.

You will explore the key QPython library objects, giving you full access to the outputs from the Quantexa Pipeline. You will also learn how to use elements of PySpark and Pandas.

QPython library objects

BatchResolver()
Entity()
DocumentEntityEdges()
ScoringGraph()
Score()
CheckpointReader()
ScorecardReader()
Realerting()

How do I enroll in the program?

No enrollments are necessary! The QPython User Guide is a Community resource freely available to registered users (Customers, Partners, and Quantexans) as part of the Community Training Program.

Feel free to use it as a handy reference to support your project work or upskilling.

Please follow the link below to access the User Guide: QPython User Guide: Module 1 (Processing Quantexa Assets)

Special thanks!

We would like to express our gratitude to the project SMEs who generously supported us in the development of this content, and in particular, Felix_Hoddinott​ , Ben_Houghton​, and Tejan_Shah​ .