A collection of datasets for RUL estimation as Lightning Data Modules.
Project description
RUL Datasets
This library contains a collection of common benchmark datasets for remaining useful lifetime (RUL) estimation. They are provided as LightningDataModules to be readily used in PyTorch Lightning.
Currently, four datasets are supported:
- C-MAPSS Turbofan Degradation Dataset
- FEMTO (PRONOSTIA) Bearing Dataset
- XJTU-SY Bearing Dataset
- Dummy A tiny, simple dataset for debugging
All datasets share the same API, so they can be used as drop-in replacements for each other. That means, if an experiment can be run with one of the datasets, it can be run with all of them. No code changes needed.
Aside from the basic ones, this library contains data modules for advanced experiments concerning transfer learning, unsupervised domain adaption and semi-supervised learning. These data modules are designed as higher-order data modules. This means they take one or more of the basic data modules as inputs and adjust them to the desired use case.
Installation
The library is pip-installable. Simply type:
pip install rul-datasets
Contribution
Contributions are always welcome. Whether you want to fix a bug, add a feature or a new dataset, just open an issue and a PR.
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
Hashes for rul_datasets-0.10.5-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6bbb0ba35d791e5dca337593662de50231894c16f70457e44d5b68eb3c124689 |
|
MD5 | ba2b6c320ee78032a196213c80b32ea0 |
|
BLAKE2b-256 | 3e4d84ac67cd8c5f257962086e1c1794b644fd9d0a02f643ce4c8ec6bb41efa7 |