Insights Machine Learning Core APIs
Machine Learning functionality designed and integrated with KX Insights
The KX Insights Machine Learning functionality described here is a centralized location for all things machine learning within Insights. The APIs and functionality defined are intended for use across the microservice and platform offerings of KX Insights.
Central to their design is providing users with the ability to develop machine learning workflows allowing users to:
- Fit models on static/streaming data.
- Update models based on new information provided to the system.
- Store and version models for use in production ML systems.
- Deploy and audit Machine Learning models within a KX Insights ecosystem.
The following outlines the functionality provided within the Machine Learning APIs:
- Analytic functionality (
presently only available with q API)
- Data preprocessing (data encoding, feature hashing, infinity replacement).
- ML models (clustering, regression, classification).
- Stream processor ML-Analytic integrations.
- Model Registry
- Store and version ML models on-prem or within a cloud storage solution.
- A common model retrieval API for deployment of models from various Python/q libraries.
- Storage of information relating to model training/monitoring allowing sysadmins to control the promotion of models to production.
- Enhanced team collaboration oportunities and management oversight by centralising an ML teams work to a common storage location.
These APIs are provided both as q and Python libraries providing users within each language with the ability to make use of the functionality provided by KX with the language of your choice: