Peer review

[nidhi-dhupati]

• Peer review by: Down to Earth Goats

• Names of team members that participated in this review: Nidhi Dhupati, Nate Xiao, Kelly Huang, Colin Song

• Describe the goal of the project.

The goal of the project is not stated in the written report. However, in the project proposal, it is stated that the goal of the project is to figure out what can predict chocolate ratings, when using chocolate ratings as an indication of the chocolate's likability.

• Describe the data used or collected, if any. If the proposal does not include the use of a specific dataset, comment on whether the project would be strengthened by the inclusion of a dataset.

The dataset used have a review of general characteristics for different chocolate bars including information such as the country of bean origin, percentage of cocoa, and ingredients within each bar. The data was collected over time, from 2006 to 2021. A specific dataset is included.

• Describe the approaches, tools, and methods that will be used.

The methods used here were exploratory data analyses with univariate and bivariate plots, as well as maps for variables that had a geospatial aspect (namely, the country of origin for the bean). A more in-depth analysis was done with the ratings vs. cocoa percent, ingredients, and most memorable characteristics by making a recipe and using cross-validation across 5 folds.

• Is there anything that is unclear from the proposal?

The graph of "Distribution of Cocoa Percent versus Chocolate Rating" might have a mislabeled axis, since one of the axes is labeled as "Chocolate Rating" and the other axis is labeled as "Rating". Additionally, it could be useful to add commentary about the methods that will be used, as this had to be discerned from the code written and the graphs displayed (there was no writeup about the methods that would be used or justification about why these methods were chosen). Additionally, the written report currently does not include an introduction or the research question written. Though we were able to find this in the project proposal, including this in the report could make things more clear.

• Provide constructive feedback on how the team might be able to improve their project. Make sure your feedback includes at least one comment on the statistical modeling aspect of the project, but do feel free to comment on aspects beyond the modeling.

I really enjoyed reading through this project! The exploratory data analysis covered a lot of ground and seemed to utilize many unique types of graphs. In addition to including information from the 5-fold cross validation, the statistical modeling aspect of the project could be improved by fitting and displaying the model that was chosen. I liked how you described the process of choosing the first model, but being able to display the results of this first model and comment about what you learn from the model could help improve the strength of the statistical modeling. Beyond the modeling, I think it could be useful to add more commentary dispersed through the written report to help the readers also see the same takeaways that you were able to find from the graphs.

• What aspect of this project are you most interested in and would like to see highlighted in the presentation.

I am interested in the "most memorable" characteristics of chocolate. I think the graph of these characteristics compared to the rating was interesting to see in the exploratory data analysis section, and it is interesting because it is not something I would generally think about when reviewing chocolate. It was fun to read through the options of the "most memorable" characteristic, and showed that the dataset included some interesting types of chocolate such as "cinnamon" and "blackberry"!

• Provide constructive feedback on any issues with file and/or code organization.

I think the organization of the report seemed to be pretty easy-to-follow, though I would suggest to add the introduction and research question to the top of the report to add context before diving into exploratory data analysis. I also think including a conclusions or takeaways section at the end of the report could help us understand what you learned from the whole analysis, in addition to wrapping up the report nicely.

• (Optional) Any further comments or feedback?