All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
- Added new dataset versioning system, you can work with multiple versions of the same dataset during creation
- Added new in-Python download system, you can download a specific version of the dataset during initialization
- Refactored dataset indexing system, a dedicated directory will be created for the index database during initialization
- Refactored preprocessing cache system, a dedicated directory will be created and a faster version for cache coherence check has been implemented
- Refactored logging system
- Update package requirements
- Update README
- Deprecated Makefile
- Updated README
- HOTFIX Remove incosistent extra channel in TUH EEG Abnormal
- DOI reference link using Zenodo
- @dataclass decorator to datadabase tables ORM
- Install instruction for Python 3.6 dataclasses
- Renamed JoinedPreprocessor to ForkedPreprocessor
- Renamed JoinDataFrames to ToMergedDataframes
- Renamed SinglePickleCache to PickleCache
- Python 3.6 full support due to @dataclass (workaround: python3.6 -m pip install dataclasses)
- Conda environment.yml configuration file
- ChunksPickleCache cache manager
- VerticalPipeline pipeline executor
- TextMiner textual analysis
- Add min_value and max_value for each file Metadata
- Add min_value and max_value in pipeline environment variables
- Update MinMaxNormalization and MinMaxCenteredNormalization to min/max value across samples
- Environment variables injection in TUH EEG Abnormal dataset
- The CHANGELOG file.
- Initial documentation at https://pyeeglab.readthedocs.io.
- Online code editing by clicking on the GitPod badge in README.
- Travis CI support for multiple os/python configurations, including:
- Ubuntu 16.04 Xenial / Python 3.6.0.
- Ubuntu 18.04 Bionic / Python 3.7.0.
- Ubuntu 18.04 Bionic / Python 3.8.0.
- OSX 10.14 / Python 3.7.4.
- Windows 10 / Python 3.8.0.
- Min-Max zero-centered normalization preprocessor