Skip to content

GGC-DSA/health-status-prediction

Repository files navigation

Health Status Prediction

Quick Links | Project Deliverables!

Website
Final Notebook
Final Poster
Final Report
Screencast Demo

Table of Contents

Below is a table that will navigate you through the folders we have provided and what files they contain.

Folder Name Files
CLEANED Datasets Contains all 4 pre-processed datasets.
Iteration Presentations Contains 3 iteration presentations that detail the important decisions made throughout the semester, project progress, and overall creative process.
Notebooks Contains all 4 individual Jupyter/Google Collab Notebooks with statistical analysis based on personal dataset.
Raw Datasets Contains all 4 raw datasets taken directly from Kaggle.
Visual Code Contains the files of code for our D3.js and Tableau visuals.
Miscellaneous Files Description
Combined.csv Merged .csv file of all applicable datasets.
TODO.md Document with details pertaining to features we were unable to implement.

Project Overview

Project Description:
Create an exploratory visual that is both engaging and informative to a user about Heart Diease based on selected symptoms!

Project Goal:

  1. Create an interactive visual.
  2. Show the correlation between the most common Heart Disease symptoms and their Heart Health Status.

Implemented Features:

Category Feature
Statistical Complete Regressional Analysis for each of our top contributing risk factors (Age, Cholesterol, Diabetes, Hypertension, Physical Inactivity, and Smoking)
Successful application of PCA to all datasets to narrow down which of the factors have the most impact on heart diease.
Thorough Statistical Analysis and K-Means Clustering for a more in-depth analysis.
Visual Create accurate and engaging visuals for all statistical tests performed on the data.

The Team:

Member Role
Sarah Price Data Analyser, Project Manager
Ruth Whitehouse Data Modeler, Client Liaison
Shababa "May" Kamreen Data Visualizer, Scrum Master
Haley "Lily" Sheppard Data Visualizer, Project Scribe

Technologies:

Name Role
Python Primary Programming Language
Jupyter Notebook Statistics
Tableau Visualization
D3.jS Dynamic Visualization

Instructions for Editing the Website

Our website is hosted/deployed by Netify. The code for the website is located under a branch called newbranch. In order to edit or add any information, you will have to switch to that branch and either edit the code directly in GitHub, or open the code in a text editor on your local machine.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 5