Modular data Integration for Predictive Healthcare Analytics
Project description
MIPHA
Modular data Integration for Predictive Healthcare Analytics
MIPHA is a framework allowing for the creation of reusable, transferable and highly-customizable machine learning models for disease prediction. Its key features are:
- Flexible architecture allowing for the study of any disease
- Ability to include data from various sources
- Modular architecture designed for reusability
This framework is being worked on as part of my PhD research on disease prediction using machine learning. Development is still in its early stages! Documentation of the library will be updated over time.
Release summary
[0.1.1] Initial prototype - 2024-07-25
Summary
This very first development allows for the instantiation of a disease prediction model, and will be built upon in subsequent iterations.
Added
- Initialize project
- Implement the core components of the framework
- Allow for saving, loading and reusing components of the framework
- Introduce unit tests and test utilities
- Set up continuous integration tools
Fixed
- Bumped up version number for proper release on PyPi
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
File details
Details for the file mipha-0.1.1.tar.gz
.
File metadata
- Download URL: mipha-0.1.1.tar.gz
- Upload date:
- Size: 11.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.0 CPython/3.12.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2734aa57e6d7effa60a557fe10097ee292ba223b5c99d781d63df0edfcf4f459 |
|
MD5 | f2f727414528bf7ee58bf668d809a227 |
|
BLAKE2b-256 | 4cb1877fca47c82a7e0ff18fef9be21989b5c1511a4e42c5b8de4f48f7ffb6fc |
File details
Details for the file mipha-0.1.1-py3-none-any.whl
.
File metadata
- Download URL: mipha-0.1.1-py3-none-any.whl
- Upload date:
- Size: 8.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.0 CPython/3.12.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 422b6ab1592570da999b5f9c42d85967030bd351085d5fd653bec2ee3f0ea86e |
|
MD5 | b726fa36a75ca611e2842feee914db2a |
|
BLAKE2b-256 | ea7c8b7413052f4362b7f7c497b4b6b9d0a348079171d6eaac0522c5dac844c8 |