---
title: "readme"
author: "Chris Fraher"
date: "July 1, 2018"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

# Project Predicting Heart Disease Mortality
The purpose of this machine learning compeition was to analyze and develop a model to predict heart disease mortality based on demographic, economic, and health related data points. Data was provided at the county level across all 50 states with the US. 

## Packages
Analysis was performed using R with the following packages:
- caret
- mice
- tidyverse
- here
- lubridate
- randomForest
- RANN
- jtools
- doSNOW
- plotly
- corrplot,
- VIM
- lime

## Results
As the outcome was a regression model, RMSE was used to measure the accuracy of the predicted values. After training a value of 31.54727 was obtained while a compeition of best score of 32.6040 was calculated indicating some overfitting to the model. Further work should be performed for a more accurate predictor system.