Random Forest Regression to Predict Cancer Rates Base on Data from the OECD

Introduciton

My name is Levi. This is the capstone project for my Masters in Data Anlytics.

In this project I will explore data gathered from The Organization for Economic Cooperation and Development (OECD) to build a machine learning model that can predict cancer rates based on Country, Year, and type of cancer.

Data was dowloaded from https://data-explorer.oecd.org/vis?fs[0]=Topic%2C0%7CHealth%23HEA%23&pg=0&fc=Topic&bp=true&snb=36&df[ds]=dsDisseminateFinalDMZ&df[id]=DSD_HEALTH_STAT%40DF_C&df[ag]=OECD.ELS.HD&df[vs]=1.0&pd=2000%2C&dq=.A...........&ly[rw]=REF_AREA&ly[cl]=TIME_PERIOD&ly[rs]=SEX%2CCANCER_SITE&to[TIME_PERIOD]=false

Project Report can be viewed here: https://www.overleaf.com/read/bryndtbswyhk#c2f711

Steps in Process

Collect Data

Explore and Clean Data

Develop and Test Model

Visulize Model

Analyze Data

Requirements for this Project

Github to fork repo

Jupyter Lab

Python (3.12.1)

VSCode (not necessary, but it is what I used to organize and code)

Project Libraries

Pandas

Numpy

Matplotlib

Seaborn

SciKit-Learn

Project Files

Capstone Cleaning and EDA.ipynb: Jupyter notebook Cleaning and exploration of the dataset

Capstone Models.ipynb: Notebook with the models and visulizations

OECDHEALTHDATA.csv: Original Data file downloaded from the OECD website

OECD_Final.csv: CSV generated after first round of cleaning

OECD_MN.csv: CSV generated after second round of cleaning. Contains only cancer rates for "Malignant neoplasms" cancer site

OECD_NOMN.csv: CSV generated after second round of cleaning. Does not contain cancer rates for "Malignant neoplasms" cancer site.

Resources

These are the resources used for research and coding

https://datascience.cancer.gov/training/learn-data-science/clean-data-basics

https://statisticsbyjim.com/regression/interpret-r-squared-regression/

https://machinelearningmastery.com/regression-metrics-for-machine-learning/

https://www.cancer.gov/about-cancer/causes-prevention/risk/age#:~:text=According%20to%20the%20most%20recent,in%20people%20above%20this%20age

https://platform.openai.com/models/gpt-3.5

https://github.com/PlayingNumbers/ds_salary_proj/blob/master/model_building.py

https://pandas.pydata.org/pandas-docs/stable/index.html