Data Science: Analytics - NBA trends project

Hi all,

I’m 50% through with the Data Science: Analytics path and just finished the NBA trends project. I watched the walkthrough video and the instructor didn’t really answer some of the rationalization behind the findings in each question on whether the variables are associated or not, so I thought I’d share mine and see if I can get feedback on this. Hopefully this is helpful. My Markdown answers are also included in the Jupyter Notebook.

I see there are some entries kind of duplicated. Some game id’s are repeated twice, and the info in it is recorded from the point of view of each team respectively, meaning the fran_id and opp_fran are interchanged, same for pts and opp_points.

Does this duplication of entries affect the results obtained through the analysis?