Here’s my work on the project so far. I’ve done what I could think of, but to be honest I’m a bit at a loss for what else I might do. So, I’m happy to take suggestions, and do further work.
I wanted to run a 1-sample T-test to see if the high Endangerment rate was significant for birds and mammals (as I recall this project doing before the Data Science course update turned it into a Portfolio Project), but I’m having a hard time thinking about how to conceive of an ‘expected average’ for this kind of data.
In any case, here are links to the GitHub repository and Repl.it:
GitHub: GitHub - gatlinbredeson/Biodiversity-in-National-Parks: Biodiversity in National Parks Portfolio Project for Codecademy
Repl: https://repl.it/@GatlinBredeson/Biodiversity-in-National-Parks#Biodiversity_in_National_Parks.py
Is this on the DS path? Do you have a link to it?
I did this project a couple years ago and I thought there were specific instructions?
I thought that the portfolio required one to use numpy, scipy, math in addition to pandas, seaborn and matplotlib?
You’re right–This project was a ‘Capstone’ or a ‘Challenge’ project in the older Data Science course. I remember doing it; but since they updated the course, they turned it into a Portfolio project with way fewer instructions (which is fine, being able to do it on our own is the point). And now I don’t seem to have access to the former project and its instructions.
I feel my project here is incomplete and I’d like to do more, but I’m having trouble thinking of things. I’ve really stalled on my progress through the course because of this, so I decided to ask for some inspiration from my colleagues (as I might do in a job) to help me along!
A suggestion: something that would be helpful is if the user could see the outcomes of your various code block in the cells. (right now we don’t see the output of the code cells). It’s also helpful to use text cells to describe what you’re doing in Jupyter (or Colab) so whoever is looking at the notebook can see/understand your thought process as you go along investigating the data.
So, you did or didn’t do the previous project off-platform and have that Jupyter Notebook saved somewhere?
Some of the questions from the previous version of the project were:
- How many unique scientific names?
- How many unique species categories?
(And then I grouped by the col. ‘conservation status’ and unique scientific name to see how many were in each status. (I think you did that?))
- You could fill in the NULLS with something like, ‘No Intervention.’
Perhaps you can make some charts that separate out the ‘No Intervention/Not Protected’ vs. 'Protected" in the same categories, so you could calculate the percent protected in each category. And from that you could see what category is more endangered b/c of their level of protection(?)
The previous project also asked the learner to run a chi square test between birds and mammals and their protection status to see if there was a statistically significant difference. (Chi square b/c they’re categorical variables) to do that you’d have to import from scipy.stats import chi2_contingency
You would also need to include Numpy in your imports as well.
I hope that helps!
1 Like
Thanks so much! This is helpful.
1 Like