Blog Plan

[espinosawendy]

Question One: We do not plan for our final project to be an extension of the mid-semester project. Instead, we are going to explore data on the nutritional aspects of various menu items at different popular fast-food restaurants. Questions we generally aim to address are: “What are the healthiest fast food items?” or “How do various fast food items compare to our average daily requirements of nutrition?” or “Which fast food chains are the unhealthiest?” or “Which US states have the highest number of fast-food restaurants?” or “Which states have the most of each specific fast food restaurant?”

We will again be using Kaggle, specifically this dataset: https://www.kaggle.com/datasets/ulrikthygepedersen/fastfood-nutrition, to import the data as a CSV file. Our data contains the nutritional contents of various menu items for the following restaurants: McDonald’s, Sonic, Taco Bell, Arby’s, Subway, Dairy Queen, and Burger King.

We will also use a dataset that contains the locations (by state) of various fast-food restaurants throughout the US: https://www.kaggle.com/datasets/khushishahh/fast-food-restaurants-across-us

Question Two: Our blog aims to have three posts, where each post addresses a different question and is done by a different member of the team.

• “How do various fast food items compare to our average daily requirements of nutrition?”, shown via k-means clustering (unsupervised learning) or an interactive Shiny app that lets you compare various food items.
• “Which fast food chains are the unhealthiest?”, shown via k-means clustering (unsupervised learning). Separating the seven different restaurants into clusters using the elbow method and finding the averages of various nutritional contents for each.
• “Which states have the highest number of fast-food restaurants?”, done using spatial data and leaflet.

Question Three: Mini Update 1 (Wednesday, April 19th): Check in with the group about the status of data wrangling and combining the two data sets Divide up the various blog posts (which group member will work on a specific graph)

Status Update 1 due: Thursday, April 20th: Submit our wrangled data Make changes to our schedule, if necessary

Mini Update 2 (Tuesday, April 25th): Check progress on individual blog posts. Help each other with any bugs that we may be having trouble with.

Status Update 2 due: Thursday, April 27th: Turn in a draft of blog posts with some functional parts and comments of future work to be done

Mini Update 3 (Wednesday, May 3rd): Run through presentations as a group and make sure all components are functional

Presentations (Thursday, May 4th): Before this day, we hope for our blog to be nearly done

Final Blog (Tuesday, May 9th): Look over feedback from presentations and make changes/updates based on the feedback Finalize Blog post and turn it in Finish reflections and turn those in as well.

[katcorr]

Ooooo this sounds so interesting! I like your idea to pivot to studying nutrition (or lack there of) at fast food chains. And your ideas for specific analyses and visualizations sound great. Nice detailed timeline. You may want to consider coding some together (you don't have to do both spatial -and- k-means clustering so could work together on one, although I agree both would be interesting to explore here) but if your approach for more individual components works better for you all given your schedules, then that's fine too. I look forward to your post!

Proposal: 10/10

[cspelke]

Status Update #1: For our checkpoint, we wanted to be done with data wrangling, and we successfully completed this for both the data sets that we are going to use for our blog post. We pushed our code for the wrangled data sets to Git Hub in the RMD file called DataWrangling_Test.RMD. Our final wrangled data sets are nutritioninfo.csv and restmap.csv in the data folder. We think we are in a good place for the rest of our project. By the next checkpoint, we still hope to have a draft of our blog post. We met outside of class to wrangle our data and plan to meet early next week so that we will be able to complete the draft by Thursday.

[katcorr]

Great! Update 1: 5/5

[cspelke]

Status Update #2 By this point, we wanted to have completed a rough draft of our blog project, and we have essentially done this. We have each completed a cluster analysis of three of the fast food restaurants (or in Wendy’s case, two restaurants and the map) in our dataset. The results of our k-means clustering can be found in the files: ‘DQ,MCD,SON_Clusters.Rmd’, ‘SUB_TB_Clusters.Rmd’ and ‘ARB,CHI,BUR.Rmd’. The next steps in our project are to put our cluster visualizations into our blog and then to write analyses of each of our results. We plan to meet next week to compile our code, review our interpretations of our findings, and plan out our presentations.

[katcorr]

Great! Update 2: 5/5