Medical insurance costs dataset research

Hey everyone,
I have completed my first project and have a great fun experience.
Here is the link to portfolio project: Click here!
Kindly ask for a feedback.

With kind regards,


A few thoughts:

  • Solid job of writing functions and using the csv library to navigate around the data set.

  • I would move your Main Questions–which is currently near the bottom–to the top of the notebook so anyone reading it would have a better understanding at the beginning of your analysis.

  • Might be a good idea to round the charges col. to 2 decimal places. Those numbers can be a little bit difficult to read.

  • It’s good that you use comments so the reader can see your thought process as you sift through the data. Data people are objective storytellers and investigators of sorts.

  • Be careful of using subjective language, or language that is considered biased (ie: value judgments). Things like: ‘We see that people with obesity occupy as much as 1/2 of the total number. This indicates an unhealthy state of the body. The saddest thing is that the normal weight is less than 1/5 of all records.’ (I wrote a course suggestion on this very data set awhile back).
    Further, analysts are supposed to be objective, not subjective when analyzing data. So, also be mindful of using words like “fact” in the analysis. This is a sample data set and it’s not like it’s CPS data where each row/entry has a weight factored into it, and
    no statistical testing for significance has taken place so it’s difficult to make statements about the broader population from this analysis at this juncture.

Ohh! Thank you! I will pay attention to this next time!