Detect anomalies in an IoT dataset
Use a scikit-learn model hosted in a Watson Machine Learning service
In this code pattern you will learn how to detect anomalies within a IBM Maximo Asset Monitor dataset using a scikit-learn model that is externally hosted in a Watson Machine Learning service. You will also learn how to visualize correlations between anomalies via time-series graphs.
The intended audiences for this code pattern are developers and data scientists who would like to analyze their data in Watson IoT Platform Analytics with customized machine learning models that are hosted externally.
Upon completion of this code pattern, you will be able to:
- Load asset data into Watson IoT Platform Analytics.
- Forward data to external services via REST HTTP call.
- Build a dashboard using Maximo Asset Monitor to monitor, visualize, and analyze IOT asset data.
- Generate alerts when certain results are received.
Follow these steps to set up and run this code pattern.
- Provision cloud services
- Setup your Python development environment
- Leverage Python scripts to register entity, function, and ML model
- Deploy Function
- Add alerts
- Add Dashboard Visualizations
For more detailed information, read the code pattern’s README file on GitHub.