A machine learning project for predicting the chances of having a stroke

1. Create a 3.10 python environment

1. Use the requirements.txt file to install the necessary packages pip install -r requirements.txt. The file is found in the root project folder.
2. Use your new environment to execute the main.py file. NOTA: Be sure that you execute the file form the root project folder.
3. Wait until the automated pipeline is executed and the best model is proposed. NOTA: This could take several minutes.

The result is a model predicting a stroke with a 85% accuracy.

The main.py script makes a ML pipeline on the Stroke data set by using sklearn with python.

The main script contains only the deployment of the ML pipeline, we are going to skip the data analysis part with all its graphics, as it is better to show it in the Jupyter Notebook.

The jupyter notebook with all the logic and analysis followed, can be found in the root/notebook folder.

The strokes data is found in the root/data folder

GNU GENERAL PUBLIC LICENSE, see LICENSE file for more information.