Peer review

[anjoru]

Hi Malika! Nice job! I had no issues running the code and was able to find everything I needed. I do have some minor suggestions to improve your project.

Template files still in code folders While I was able to find the files relevant for this project, there are some that should be removed. For example, in the process-code folder, the original templates are still there. This was the case for the other code folders as well. To make sure users open the correct file, remove the ones you are not using.

README files I did not see any of the README that had been updated for this project. README files should be updated to provide users insight into your process, file structure, etc.

Clarity I understand that for this phase of the project, we should just be getting into the analysis, but I peeked at your files and have comments. I had some issues with understanding this plot: p2 Customer_Segment, it was not explained in the statistical-analysis_superstoreRFM.R file. It appears again in the manuscript with some explanation. The caption says that "approximately 25 percentage of the customers are grouped as Valued Customers". The y-axis is count and the values customers are coded as 0/1. It is not immediately clear what that means. Adding descriptive labels would improve this plot. Also consider changing the y-axis or creating a stacked bar graph.

I think that the R file would be easier to follow as a qmd. I am sure that is your next step.

There are some code chunks that have very few comments. It might be helpful to add descriptions on what exactly you are doing. For example:

# Aggregate the total sales per country
# by grouping the data by 'Country' and then calculating the sum of 'InvoiceValue'
p5 <- mydata %>%
  group_by(Country) %>%
  summarise(TotalSales = sum(InvoiceValue)) %>%
  # Create a bar chart with ggplot2 where:
  # - Countries are ordered by TotalSales for clarity in presentation
  # - TotalSales is on the y-axis
  # - The bars are filled with colors corresponding to the Country
  ggplot(aes(x = reorder(Country, TotalSales), y = TotalSales, fill = Country)) + 
  geom_bar(stat = "identity") +  # Use geom_bar to represent TotalSales as bars
  coord_flip() +  # Flip the coordinates to make the chart horizontal
  theme(legend.position = "none")  # Remove the legend to declutter the plot

Housekeeping Remove Notes heading from the end of the eda qmd.

Your processing qmd might benefit from some subheadings. Also, line 100 of that file has what looks like should be a paragraph as a header.

Overall, I think you are in good shape for this stage of the project. My advice to make this more user-friendly is to use more descriptive dataframe names, label axes on plot carefully, remove unneccessary files. Finally, begin filling in the README files.

Sufficient | Submission is (almost) complete, contains enough information to allow assessment of feasibility of proposed project. Fully reproducible. 3/3

[Madhak1]

Hey Andrew, Thanks for pointing out the unclear aspects of the plots and data analysis. I will be sure to address these issues and aim for greater clarity. I have also noticed there is quite a bit of organizing to do on my end. I am working towards making these improvements. I really appreciate your feedback and suggestions.

[anjoru]

I am in the exact same position. I have quite a lot of organizing to do to meet the minimum standards for this assignment. Have a great weekend!

On Fri, Mar 22, 2024 at 7:06 PM Madhak1 @.***> wrote:

Hey Andrew, Thanks for pointing out the unclear aspects of the plots and data analysis. I will be sure to address these issues and aim for greater clarity. I have also noticed there is quite a bit of organizing to do on my end. I am working towards making these improvements. I really appreciate your feedback and suggestions.

— Reply to this email directly, view it on GitHub https://github.com/Madhak1/Dhakhwa-MADA-project/issues/5#issuecomment-2016067048, or unsubscribe https://github.com/notifications/unsubscribe-auth/AZVEVYJ3VORGSZ3C2MXFYFTYZS2PJAVCNFSM6AAAAABFCINDIKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAMJWGA3DOMBUHA . You are receiving this because you authored the thread.Message ID: @.***>