OnCancer

Using sample data from 497 anonymized cancer screening patients whose risk levels were known, to create a regression model that will help predict the risk level of a new patient:

• collecting data onto an .xlsx (Excel) spreadsheet
• using Python to read the spreadsheet data and split them into:
  • training data which will form the basis of the models
  • testing data which will see if the models
    • can predict a risk score
    • ...by validating against the actual risk score
• using a model to predict a risk score on a new patient
• categorizing the score with a risk level with that predicted score

Demo

• Streamlit

Code

• GitHub