Feel free to check out and give feedback to my submission for the Biodiversity in NP submission (as part of the Data Science path).
- I quite enjoyed the project. It touched on the scoping, cleaning, visualising and statistical analysis side of things, so it was a really good summation of the course imo.
- Probably put at least up to 5-6 hours, including slides.
- Link to repo here: GitHub - TollyVellis/bio_diversity_in_national_parks
I have read your notebook and there are lots of useful visualizations! Here are some suggestions:
- You might add some more overall information such as numbers of species. Therefore, readers can compare the other pieces of information with it.
- Transform numeric values in order to make it easier to interpret (the number of observations is quite high so the graph’s y label has the unit ‘1e6’ which is equal to a million) For example, present it with ‘thousands’ unit.
- The visualization of number of species by conservation status for each category (the cropped one) is a good idea but as the number of species which are least concern outnumbered the rest. It’s a wee bit hard to read the graph. Also, the amphibian category was not properly shown.
I have learned some interesting visualization and hypothesis testing from you. Thanks! Hope there is some suggestion useful.