Leveraging new coders behaviour in finding the best markets for to advertise an e-learning product

One of the things I was unsure of when working on this project is if it was ok to sample a sample data, so i did not use the pd.sample() metod in any of my analyis. The outlier amounts, I decided to drop all of them because regardless of how long the coders have been programming the outlier amount were way above what is spent monthly by people who attend bootcamps.

Here is the link to my last mission screen

fcc_survey.ipynb (271.5 KB)

Click here to view the jupyter notebook file in a new tab


Hi @abomayesan

Your project stands out for its simplicity, concise narrative and stylized plots! :+1:

I would suggest a few suggestions:

  • Proofread your narrative; there are several spelling mistakes.
  • A beautiful plot seems incomplete with well-structured/ detailed Titles (or sub-titles etc).
    You have three boxplots. Show the difference between them by adding some context to their titles. For example:
    • Money spent… As is
    • Money spent… (exorbitant outliers removed)
    • Money spent… (Bootcamp outliers removed)
      Not exactly these words but something that describes how you have treated the dataset to reach that distribution and how is it different from the original data.
      Not necessarily, but I may just glance at the plots and try to understand your analysis!
  • Use the markdowns effectively. I had to double-take as to why you included Australia and not Poland, Brazil or Germany. I kind of skipped Top 5 English Countries. It would have forced me to read it (more) thoroughly.

Cool project overall :ok_hand:

1 Like

Thank you so much for your feed back. I’m working on correcting those errors and getting better. Thank you very much.

1 Like