Hackathon: Heart Disease Prediction
Last updated
Last updated
This module is the last part of our journey to data and AI. In this module, we will put everything we have learned so far to use by creating a predictor which determines whether a patient has heart disease.
To help you get started, we have put together a notebook that performs the data science basics for you and trains a simple machine learning model for you.
Your task is to improve each section of this notebook, thus improving your final model's accuracy. The more accurate your models' predictions are on unseen data, the better your model is performing.
Remember: Your best tool to figure out how to perform the idea you have in mind is a simple online search.
Log in to Cloud Pak for Data as a Service
Select your project from the Projects section of the hamburger menu (☰)
In your project, click Add to project and choose Notebook
Choose New notebook From URL. Give your notebook a name, select the smallest runtime, copy the following URL, and click `Create.
Spend some time looking through the sections of the notebook to get an overview. A notebook is composed of text (markdown or heading) cells and code cells. The markdown cells provide comments on what the code is designed to do.
You will run cells individually by highlighting each cell, then either click the Run button at the top of the notebook or hitting the keyboard shortcut to run the cell (Shift + Enter but can vary based on platform). While the cell is running, an asterisk ([*]) will show up to the cell's left. When that cell has finished executing, a sequential number will show up (i.e., [17]).
To submit your results, fill in the last cell of this notebook which includes your name, email address, and your model's accuracy, which you wish to submit.
Once you have submitted your notebook, we will review your notebook and score your model by using it to predict patients' heart disease in a new dataset. Your model's accuracy to correctly predict whether those new patients had heart disease is used to determine your ranking.
A few notes:
Each participant can submit as many notebooks as they wish. We will, however, consider only the best of your last three submissions.
The submission window closes on the morning of March 24th.
Make sure to include your name and email so we can identify you.
Make sure to keep the last cell's format as is and only replace your new model in it.
If you have any issues (for example, if you run out of computing power), please contact us.
