https://github.com/dominodatalab/aihub-project-anomaly-detection

Build and track algorithms to detect anomalies in CPU Utilization streaming data
https://github.com/dominodatalab/aihub-project-anomaly-detection

Last synced: 29 days ago
JSON representation

Build and track algorithms to detect anomalies in CPU Utilization streaming data

• Host: GitHub
• URL: https://github.com/dominodatalab/aihub-project-anomaly-detection
• Owner: dominodatalab
• License: apache-2.0
• Created: 2023-10-06T18:08:54.000Z (about 1 year ago)
• Default Branch: release-1.0.0
• Last Pushed: 2024-02-05T22:12:29.000Z (11 months ago)
• Last Synced: 2024-02-05T23:28:22.631Z (11 months ago)
• Language: Jupyter Notebook
• Size: 2.17 MB
• Stars: 0
• Watchers: 5
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# Anomaly Detection on Time Series Data

A Domino Data Labs reference project showcasing anomaly detection on CPU Utilization data of EC2 Compute Instances

## License

This template is licensed under Apache 2.0 and contains the following components: 

* pandas [BSD 3](https://github.com/pandas-dev/pandas/blob/main/LICENSE)

* scikit-Learn [BSD 3](https://github.com/scikit-learn/scikit-learn/blob/main/COPYING)

* matplotlib [MDT](https://matplotlib.org/stable/users/project/license.html)

* seaborn [BSD 3](https://github.com/mwaskom/seaborn/blob/master/LICENSE.md)

## About this template

This is a reference Domino Project adapted from the Kaggle dataset and notebook found [here](https://www.kaggle.com/code/leomauro/anomaly-detection-streaming-data/input).


This notebook presents a few unsupervised algorithms to detect anomaly in CPU Utilization streaming data.


We are going to experiment Anomaly Detection in [Numenta Anomaly Benchmark (NAB)](https://www.kaggle.com/boltzmannbrain/nab).

## Prerequisities

### Hardware

This template works with a standard small-sized hardware tier, such as the small-k8s tier on all Domino deployments.

### Environment

This template works on any standard Domino Environment, no GPUs are required. The necessary libraries are listed in the `requirements.txt` file.

#### Workspace Tools

The only tool required is Jupyter Notebooks/Lab

## Usage Instructions

List step-by-step instructions for how to use a project created from this template

1. Run Notebook [anomaly-detection-streaming-data.ipynb](https://github.com/dominodatalab/aihub-project-anomaly-detection/blob/main/anomaly-detection-streaming-data.ipynb)

## References

This project was adapted from the dataset found in Kaggle: https://www.kaggle.com/code/leomauro/anomaly-detection-streaming-data/input