https://github.com/hayesall/diabetes-time-series
Re-implementation of the UCI Diabetes Dataset from AIM 1994
https://github.com/hayesall/diabetes-time-series
dataset diabetes time-series uci-machine-learning
Last synced: 8 months ago
JSON representation
Re-implementation of the UCI Diabetes Dataset from AIM 1994
- Host: GitHub
- URL: https://github.com/hayesall/diabetes-time-series
- Owner: hayesall
- License: cc-by-4.0
- Created: 2022-02-11T19:43:36.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-03-30T17:58:49.000Z (over 3 years ago)
- Last Synced: 2025-03-02T02:46:26.905Z (8 months ago)
- Topics: dataset, diabetes, time-series, uci-machine-learning
- Language: Python
- Homepage:
- Size: 348 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
This directory contain a data set prepared for the use of participants
for the 1994 AAAI Spring Symposium on Artificial Intelligence in Medicine.
* diabetes-data.tar.Z contains the distribution for 70 sets of data recorded
on diabetes patients (several weeks' to months' worth of glucose, insulin,
and lifestyle data per patient + a description of the problem domain).
Archived using tar and compressed.
Extract the data files from the archive. On a Unix system, type
'tar xvf icu-data.tar'. This will create a new directory named ICU-Data
and extract all data files into that directory. Very occasionally
this may not work; in that case try 'tar xvof' instead of 'tar xvf'.
## License
This dataset is adapted from the
[Diabetes dataset from the UCI Machine Learning Repository](https://archive.ics.uci.edu/ml/datasets/diabetes)
under the terms of the
Creative Commons Attribution 4.0 International (CC BY 4.0) license.
### Statement of Changes
- The `Diabetes-Data` directory has similar structure to the unzipped
version from the UCI repository.
- Fixes "*corrupted data*" where multiple files (`data-20`,
`data-22`, `data-27`) contained lines that did not match the
"day, time, type, quantity" structure. Some of these involved
Alexander Hayes's judgements for what the correct value should be,
many of which are documented in `hayesall-notes`.
- Adds some quality-of-life improvements to make the data easier
to analyze. This work is ongoing.
This work is licensed under a Creative Commons Attribution 4.0 International License.