Welcome to Kelvin SDK - App Samples

This repository contains sample applications that demonstrate how to use the Kelvin SDK.

We recommend that you start first by reading the official Kelvin Documentation on https://docs.kelvin.ai.

Applications

Application	Type	Level	Description
Azure Data Lake Gen2 Uploader	Data Uploader	Intermediate	Uploads streaming data to Azure Data Lake Storage Gen2.
Casting Defect Detection using Computer Vision	Computer Vision	Intermediate	Leverages computer vision and a Tensorflow-based model to identify and analyze manufacturing defects in casting processes.
CSV Stream Publisher	CSV Stream Publisher	Beginner	Ingests Data from a CSV file and publishes it to the Kelvin platform.
Databricks Delta Table Uploader	Data Uploader	Intermediate	Uploads streaming data to Databricks Delta Table.
Databricks Volume Uploader	Data Uploader	Intermediate	Uploads streaming data to Databricks Volume.
Event Detection	Event Detection	Beginner	Monitors streaming data to detect and respond to events exceeding pre-set thresholds by emitting a Control Change output.
Event Detection (Complex)	Event Detection	Intermediate	Monitors streaming data to detect and respond to events exceeding pre-set thresholds by emitting a Control Change or Recommendation output. This example also leverages Asset Parameters and App Configuration to make the application more dynamic.
Multi-Objective Optimization ML	Machine Learning	Intermediate	Implements a multi-objective optimization problem using machine learning techniques.
Rolling Window DataFrame	Rolling Window	Beginner	Demonstrates the creation of a rolling window using Pandas to manage and analyze time-series data effectively.

Contributing

1. Fork the project.
2. Create your feature branch (git checkout -b feature/YourFeature).
3. Commit your changes (git commit -m 'Add some feature').
4. Push to the branch (git push origin feature/YourFeature).
5. Open a pull request.