I started this project in October, and took a few months’ break because life got hectic. I came back to it yesterday, and finished it just now. I think I found some interesting correlations–do you agree with the conclusions, and are the methods clear?
Thanks!
Hi Gavin,
Nice work. The project was well structured, and made it easy to understand each step along the way.
In cell In[22] you used the following code:
conservationCategory = species_info[species_info.conservation_status != “No Intervention”]
.groupby([“conservation_status”, “category”])[‘scientific_name’]
.count().unstack()
print(conservationCategory)
Another way to create the same table is to use the following code:
conservationCategory = pd.crosstab(index=species_trouble.conservation_status, columns=species_trouble.category)
print(conservationCategory)
In doing so, you would get zeros instead of NaN-values. Moreover, the code would be shorter.
One small remark: the threshold you used for statistical significance was 5%. The term used was p-value, but it’s called the alpha value according to my understanding.
Best Regards,
Robin