NYC Schools_Demographic Factors vs SAT Scores Analysis

Hi Team

Thank you for the beautiful structure and design of the course.
Sharing my first project with the Community.
Would appreciate any feedback.

The same can be referred to in GitHub in the link below.
NYC High School SAT Data Analysis for Demographic indicators


1 Like

Hi @nagesh.n16! Thanks for sharing the project with the Community :slight_smile: Your code style is nice, it’s very consistent and easy to read. Have you used Jupyter Lab Formatter?

Anyway, here is my feedback:

  • Your project should tell a story. What’s the goal of it? What do you want to find? You can read An In-Depth Style Guide for Data Science Projects article to learn more about how to create data science project
  • Don’t forget to comment your code here and there. It’ll definitely improve readability and will make its comprehension much easier to the audience (and yourself in a couple of months). The same goes for functions (How to Use Python Docstrings for Effective Code Documentation)
  • Import all necessary packages in the first code cell. It gives us directions on what packages we should install straight from the beginning
  • You can greatly improve your figures by adding a title and axes labels. These articles can be useful: How to Make Your Plots Appealing in Python (a little bit of self-promotion) and What to Consider When Choosing Colors for Data Visualization
  • Great observation about correlation between genders and SAT scores. I’m glad you’ve investigated this issue further with a scatter plot
  • You can expand your explanations on why there is negative correlation of Black and Hispanic races with SAT scores? Is there a reason? Can we improve this situation?

I hope my feedback is helpful! Happy coding :slight_smile:


Hi @artur.sannikov96

Thanks a lot for your feedback. I will incorporate these. FYI, I don’t use Jupyter Lab formatter (have heard of it for the first time).

Love the support from the DQ moderators. Looking forward to your continued help.