AIMSS Data Pre-Processing Workshop

Hi everyone! Welcome to the AI in Medicine Student Society's Intro to Data Pre-Processing workshop.

This repository stores the data we are going to be using and the steps to set up the Colab notebook.

First steps

We need somewhere to keep the data and the code:

• Visit https://drive.google.com/drive/my-drive
• Create folder aimss_data_workshop

Download Data

Because we're going to be using many different datasets, I made them available in a .zip file.

• Above, click ⭳ Code > Download ZIP, and save zip file above to your local machine
• Unzip file to extract data
• Upload all newly-extracted files to aimss_data_workshop in your Google Drive

Prepare Notebook

In order to edit the demo notebook, you must save your own copy on your drive.

• Visit https://colab.research.google.com/drive/1J9osIwMhiFeuf_XfQnK06NScdhTvysL0?usp=sharing
• Follow File > Save a Copy In Drive
• OPTIONAL: On your copy, follow File > Locate in Drive. Move notebook to aimss_data_workshop. (If this is not done, it will be in a new folder in your Drive called Colab Notebooks)

Slides

The slides that are shared during the presentation can be found here for your reference: https://docs.google.com/presentation/d/1--nUUAL-1UUa9Ecr4y_hpF0LBME3B0EmmLTx60_oqtE/edit?usp=sharing

All Data Sources

Here are all the original links for the datasets (plus some extra!)

https://www.kaggle.com/mirichoi0218/insurance
https://www.kaggle.com/kmader/siim-medical-images
https://www.kaggle.com/tboyle10/medicaltranscriptions
https://www.kaggle.com/jboysen/mri-and-alzheimers
https://gdc.cancer.gov/about-data/publications/pancanatlas
https://data.world/associatedpress/covid-impact-survey-public-data
https://www.kaggle.com/ymirsky/medical-deepfakes-lung-cancer
http://archive.ics.uci.edu/ml/datasets/breast+cancer+wisconsin+%28diagnostic%29