A Prophet-based network anomaly detection package
Project description
Propano ๐
A lightweight, open-source network anomaly detection package leveraging Facebook Prophet for time-series modeling.
๐น Key Features:
โ Anomaly detection based on Prophetโs upper/lower confidence bounds
โ Persistence & Proximity Analysis to minimize false positives
โ Optimized for network data: traffic volume, packet loss, DDoS detection
โ Sensitivity options to tune the model
๐ Getting Started
pip install propano
Project Structure
propano/
โโโ src/
โ โโโ propano/
โ โ โโโ __init__.py
โ โ โโโ anomaly_detector.py # Core anomaly detection logic
โ โ โโโ cli.py # Command-line interface (CLI)
โ โ โโโ utils.py # Helper functions (e.g., data preprocessing)
โ โ โโโ visualization.py # Functions for plotting anomalies
โ โโโ tests/
โ โ โโโ test_anomaly_detector.py # Unit tests
โ โ โโโ test_cli.py # Unit tests for CLI
โ โ โโโ test_utils.py
โ โโโ data/
โ โ โโโ raw/ # Raw network traffic data
โ โ โ โโโ sample_network_data.csv
โ โ โโโ processed/ # Preprocessed data files
โ โ โ โโโ cleaned_data.csv
โ โโโ notebooks/
โ โ โโโ anomaly_detection_demo.ipynb # Jupyter notebook example
โโโ examples/
โ โโโ example_usage.py # Example script demonstrating package usage
โโโ docs/
โ โโโ README.md # Project documentation
โ โโโ CONTRIBUTING.md # Guidelines for contributors
โโโ .github/
โ โโโ workflows/
โ โ โโโ ci.yml # GitHub Actions CI/CD workflow
โโโ setup.py # Package setup script
โโโ requirements.txt # Dependencies
โโโ LICENSE # Open-source license
โโโ .gitignore # Ignore unnecessary files
Useful Commands for the Developers
To install the dependencies
pip install -r requirements.txt
To Build and Upload to PyPI
python3 -m build
twine upload dist/*
To Uninstall and Reinstall the prophet-net-anomaly
pip uninstall prophet-net-anomaly -y
pip install .
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file propano-0.1.0.tar.gz.
File metadata
- Download URL: propano-0.1.0.tar.gz
- Upload date:
- Size: 8.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9e641aae3b93112ad02175400e5c7627aeaa2146e4b4febb8e26b15d3e9c4ed2
|
|
| MD5 |
57334f7d80a2a579dad1e05218fc3f82
|
|
| BLAKE2b-256 |
bfde56d12775fa1d5d6138b527fab5ad526dafdae85d7bfb60a41b39941aa5ee
|
File details
Details for the file propano-0.1.0-py3-none-any.whl.
File metadata
- Download URL: propano-0.1.0-py3-none-any.whl
- Upload date:
- Size: 9.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a5583111ef9a2ba019b1e80abbe846ed70c6205057bae6c5b0898295f745d6c4
|
|
| MD5 |
78e45ad88cff09d91832c01eecec2c5a
|
|
| BLAKE2b-256 |
9ec64c4788cd01c22cc6b8011bd27f6f49cbb1479bf95ad2a17a2117898fe28e
|