zach-nabavian.bsky.social
Data analyst with a focus on demand forecasting and automation.
LinkedIn: https://www.linkedin.com/in/zachary-nabavian/
GitHub: https://github.com/Zach-Nabavian
152 posts
176 followers
501 following
Regular Contributor
Active Commenter
comment in response to
post
Also, there is a potential limitation to this dataset. There was only 1 earthquake recorded in each of 2011 and 2012, while hundreds were recorded in subsequent years. This makes me wonder if the dataset is incomplete. I don't think it's likely that those early years had one earthquake each.
comment in response to
post
It was fun to experiment with this kind of graph, anyway. Here's my github: github.com/Zach-Nabavia... Thanks to @libbyheeren.bsky.social for curating this week's dataset.
comment in response to
post
With dual axis graphs, it's easy to adjust the y axes to give the illusion of any relationship you want. They are pretty clunky to implement in ggplot(), but I don't think they are universally bad.
comment in response to
post
This is awesome. I think we all needed a dataset like this after last week’s. Looking forward to exploring this one.
comment in response to
post
Oh also, I've been experimenting with a custom theme for these plots.
comment in response to
post
My GitHub: github.com/Zach-Nabavia...
comment in response to
post
Finally, I had this pretty crazy beeswarm plot for traffic fatalities. Colors correspond to days of the week. I'm not sure how useful this kind of plot is, but I thought it was worth experimenting with.
comment in response to
post
I have another box plot by months of the year. There isn't as much variation here, though January, February, and March tended to be safer.
comment in response to
post
A few weeks ago, we looked at car crash fatalities. I was interested in seeing which days of the week and months of the year had the most car crashes.
comment in response to
post
This helps a lot!
comment in response to
post
Well now I know what’s next on my reading list.
comment in response to
post
Thanks to @libbyheeren.bsky.social for hosting the mini-hackathon today. It was a lot of fun working on this together.
comment in response to
post
My GitHub github.com/Zach-Nabavia...
comment in response to
post
Link to the TidyTuesday GitHub repo github.com/rfordatascie...
comment in response to
post
Thanks for hosting! This was a really tough dataset to dive into.
comment in response to
post
If they did, then these tariffs would have never happened.
comment in response to
post
What a disgrace.
comment in response to
post
NO WAY. That’s really cool. I hope someone creates something similar for Python too.
comment in response to
post
It’s a great strategy if your goal is to help everyone in except America.
comment in response to
post
There are so many ways to analyze this dataset. I feel like I need more than a week.
comment in response to
post
My github: github.com/Zach-Nabavia...
comment in response to
post
Thanks to @emilhvitfeldt.bsky.social for the evolutions dataset gist.github.com/EmilHvitfeld...
comment in response to
post
The original Pokemon dataset: github.com/rfordatascie...
comment in response to
post
brb I need to update my graph for fully evolved Pokémon.
comment in response to
post
comment in response to
post
I guess $80 is the norm now.
comment in response to
post
I wasn’t a fan of the new design at first but Bananza has really sold me on it.
comment in response to
post
This book is the GOAT. Every college data science program should use it. It has a version for Python too.
comment in response to
post
He couldn’t even leave the penguins out of it!?
comment in response to
post
Now that’s an extinction event I could get behind.
comment in response to
post
Trump has been able to get away with making shit up for way too long.
comment in response to
post
Really great stuff, Andrew. We need to fill the void somehow.