Proposal for Final Project

Deliverable#2

Data Resource

I found my interested dataset in Kaggle, and this dataset is about Nutrition Facts for McDonald’s Food.

Objectives of this Project

___ Since I love eating different kinds of food but also concern about weight, it would be interesting if I can figure out some relationships among fat, protein, carbon, calories and so on. Sometimes, people are really busy that they don’t have time to prepare health food, so it would be helpful if some of these relationships could provide clues while choosing fast food. McDonalds is almost everywhere and easy to find. Therefore, nutrition facts are important if McDonalds is a convenient choice.

___ Packages

• package tidyverse : I plan to have data tables dispalyed with abilities to sort them by different nutrition .
• package shiny: I also want to have some interactive section that can customize filters with changing a few conditions, such as max of fat, max of calories and so on.
• package dplyr: Since this dataset also includes milkshake, which I’m not interested in, I would like to remove it. And I might need to creat some subsets in order to analyze relationships between just two variables.
• package ggplot: I would like to output some histograms, scatter plots, box plots and maybe correlations.
• there might be some other packages I need to use but I haven’t notice that.

___ Ideally, I would like also to compare nutrition facts of Burger King and KFC with McDonald’s, but I cannot find downloadable dataset of these two. If I can find available dataset later, I would like to update my analysis plan.

Attempting Analysis and Visualization

There are several outputs I would like to have from this dataset.

• First of all, I want to output scatter plots for several different nutrition components (fat, carbon, sugar, and protein) versus total calories.
• Second, output histograms of different nutritions.
• Third, correlations between these five (fat, carbon, sugar, protein and calories)
• Forth, create an interactive interface (if I can figure out how “shiny” works), which can customize personal choices with personal nutrition concerns. If possible, it also could show bar charts to display components of each selected food.

From above analysis and visualization, I might be able to reach some conclusions, such as if all food in McDonalds are junk food, or if some food are similar in taste but one is healthier. I believe I can come up more interesting conclusions when I see these charts.