I currently complete another machine learning project here.
Right now, this is still work in progress.
My plan is to fit a simple model to heart failure data from Kaggle and to predict patient survival.
Can be found in 02-exploratory_data_analysis.ipynb.
Optimize features for training a model.
- Model Training
- Evaluation
- Potentially deployment (depending of if this makes any sense for this project)
- Final documentation (blog post)
A quick overview of the main sources I used while working on this project.
Raw data is a dataset about heart failure and patient survival from a study by Chicco et al., I acquired from Kaggle.
Davide Chicco, Giuseppe Jurman: Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone. BMC Medical Informatics and Decision Making 20, 16 (2020)
https://www.kaggle.com/datasets/andrewmvd/heart-failure-clinical-data
FIXME: Transform this list of bullet points to a proper resource.
- I got a lot of inspiration and knowledge from Aurélien Géron's book Hands-On ML (insert citation here, can be found in book)
- Countless websites for tutorials (cannot all be mentioned, but most relevant ones are mentioned or linked in the notebooks when they are used)
- The Data Camp Podcast with Nick Singh: How to build a DS portfolio
FIXME: Transform this list of bullet points to a proper resource.
- Python
- Pandas
- Scikit-learn
- Kaggle