zhen-hw100 / pyphm

Datasets specific to Prognostics and Health Management. Easily download and prepare the data before feature engineering or model training.

Machinery data, made easy

Datasets specific to PHM (prognostics and health management). Use Python to easily download and prepare the data, before feature engineering or model training.

Current datasets:

• UC-Berkeley Milling Dataset: example notebook (open in Colab); dataset source
• IMS Bearing Dataset: dataset source
• Airbus Helicopter Accelerometer Dataset: dataset source
• More coming soon!

Alpha Notice

PyPHM is in active development. Expect considerable changes in the near future.

Our goals are to create:

• A package that implements common data preprocessing methods used by others.
• A package with a coherent and thoughtful API.
• Thorough documentation, with plenty of examples.
• A package that is well tested, with the use of type hints.
• A package built with continuous integration and continuous deployment.

Installation

Install with pip: pip install pyphm

Install from github repository: clone with git clone https://github.com/tvhahn/PyPHM.git. Then run python -m pip install -e . to install the package on your local machine.

Run tests: python -m unittest discover -s tests