I'm going to need to see success rating for each groundhog. How often do they correctly predict the weather?

Also how often did their right or wrong predictions contradict the majority?

> How often do they correctly predict the weather?

I mentioned this in another comment, but accuracy data is basically impossible to get. You have to get weather data year by year for different regions of the country and then compare them to historical ranges. Means a pretty huge amount of trawling through data, not a lot of payoff.

> Also how often did their right or wrong predictions contradict the majority?

This one, you can get a little more easily. Check out the predictions page to see them grouped by year: https://groundhog-day.com/predictions

If you are looking up a specific groundhog, you can see how often they align/differ from the plurality.

NOAA's already done it.

https://www.noaa.gov/stories/everyones-favorite-groundhog-pr...

40% accurate, so you're better off inverting Phil's prediction, but not by much.

This topic isn’t something I care about, but I did want to say, great work on the design — I have a thing for minimalist designs like this.

Thanks! It was a fun project for sure: no ads and nobody trying to get me to make it look more conventional.

Finally, somebody found a good use for the internet. Love the idea.

Edit: The only thing I'm missing is some pictures of real groundhogs.

> Includes enterprise-grade API for corporate use cases.

Lmao, brilliant.

It's good, but I kinda hoped it would be findings from the movie Groundhog Day. :-)

You know, with ever more details, upper bound, lower bounds of days, confidence levels, statistical modelling, comparisons against world events that day and psychological profiles of all participants.

The pictures of real groundhogs are all there in the individual profiles, it just turns out that half of them are stuffed.

Made my own map:

    brew install datasette sqlite-utils

    curl 'https://groundhog-day.com/api/v1/predictions?year=2023' | \
      jq .predictions | \
      sqlite-utils insert day.db groundhogs - --flatten

    sqlite-utils convert day.db groundhogs \
      groundhog_coordinates --multi 'return {
      "latitude": value.split(",")[0],
      "longitude": value.split(",")[1]
    }'

    datasette install datasette-cluster-map
    datasette day.db

Screenshot of the map here: https://fedi.simonwillison.net/@simon/109796889732947452

sqlite-utils docs here: https://sqlite-utils.datasette.io/en/stable/cli.html

Now this is a happy thing to find. The internet just got incrementally better. There's hope for us all. :) Thank you!

Having a viewport issue with the tables. "Groundhogs" runs over the right margin on desk and mobile. I can zoom it out to see the whole thing on desktop, but not mobile (zooms in but not out). My browser fonts are set to "large." Desktop, Macbook 2017, 1280px wide: https://paste.pics/2756a626c59b8c309e43fa4b7b67d16c Mobile, Pixel 4XL, 412px wide: https://paste.pics/e58e17c7c05b9d404f74367d3fbb6c48

Perhaps the left menu bar could be narrower (lot of horiz whitespace there)? Or the column widths could be narrower?

"Predictions" table looks good on desktop, but cuts off last 2 columns on mobile.

Everything else looks great. I love the map.

Remarkable how in the 1910s and 1920s we had uninterrupted stretches of extra winters decades in a row, but now early spring dominates. Clear evidence of global warming.

That's a huge insight to take away. Nevertheless, we still have climate-denier groundhogs consistently predicting winter and being wrong about it (cough Phil cough).

Hopefully, this site helps shine a light on these unscientific groundhogs.

If I'm not mistaken, Phil's "predictions" are just written down ahead of time, while other groundhogs have to actually move towards a sign that says "early spring" or "long winter".

I wonder if there is an easy way to tell which groundhog uses which method and if the groundhogs are more accurate about climate change than the humans.

Can you reactivate the Google form to add a groundhog? I had a pet woodchuck (Winnie the Woodchuck) who would like to contribute :)

https://groundhog-day.com/add-groundhog

Yes sir. Not sure how it ended up there.

Really nice!

I'm confused though. The placard says 'early spring' for 2023, but clicking on it, the split is 26/29 early spring vs long winter. Am I reading this wrong or is the placard wrong?

You, sir, have identified a bug. Just pushed an update to fix this.

If you look at the past 3 years, they have all been "early spring": https://groundhog-day.com/predictions

So the logic that was there didn't actually work properly, but I never noticed it before.

I didn't know there were multiple groundhogs. Very eclectic idea.

I didn't know there were so many, and I also didn't know that so many of them aren't real groundhogs.

Same here, I mostly know about the event because of the Bill Murray movie.

Weird omen : Fred la marmotte, Quebec's groundhog for groundhog day, was found dead thursday morning and could not make his prediction.

Great work: I think this is missing some data crunching on past predictions. Were the predictions correct or not?

Accuracy data is basically impossible to get. You have to get weather data year by year for different regions of the country and then compare them to historical ranges. It will basically mean 10x the work I've done already. It's open-source though, so it could be that someone wants to collaborate with me in future :D

Curious fact: In St. Petersburg, Russia, the groundhogs just died shortly before the day this year.

Uh-oh, so did Quebec's Fred la Marmotte. https://www.cbc.ca/news/canada/montreal/fred-la-marmotte-die...

Should I be worried?

Both the tragedies seem a very bad omen, don't they? I generally am not prone to superstitions but this (also given the whole mess taking place in the world during the recent years, cold gloomy weather and excess of stress this week) really feels spooky.

The good news, if you can call it that, is that both critters were presumably found dead just before Groundhog's Day, having died quietly at some time earlier in their hibernation.

Well well well, that is what I call a service.

There is an API for this extremely useful data?

Absolutely: https://groundhog-day.com/api

This is great, but I wish I could filter out all the plush animals.

Interesting point, I've got a page up that is the reverse of that here: https://groundhog-day.com/alternative-groundhogs

On the other hand, there is an API as well, so you can build a custom groundhog dashboard if you like.

Really nice! Next level would be to see correctness of the prediction. I guess something like onset of 5 or 7-day moving average temperature above freezing for each locale

Congratulations on the launch! I noticed however that all the image responses from the API appear to navigate to 404ing URLs :( Otherwise love the project!

Fixed! Thanks for pointing it out. Bath pathname.

It's interesting how few groundhogs there are west of the Mississippi. I guess here out west the weather doesn't matter as much.

I know, and not only are they fewer, but they are also mostly not real, alive groundhogs once you get that far.

We don't have a lot of groundhogs out here. :) I know in Oregon they use a Beaver instead.

Seems long winters being the norm died in the 80s

I have a pet theory on this.

I think, as a local councillor/politician, you show up to a Groundhog Day event and there are like 50 people there hoping you say it's gonna be spring soon, and so you just tell them that it will be.

However, it doesn't seem to be holding for this year, where most have said longer winter so far: https://groundhog-day.com/predictions/2023

Does groundhogs not exists outside of North America (or more specifically, Canada and the US) or is the data just harder to gather?

Not naturally no, according to Wikipedia. Plenty of other marmots though (like Murmeltiere in the European Alps), although I don't think those can predict the seasons.

Nobody else seems to do this outside of the US and Canada.

I live in Buffalo and I’ve never even heard of Buffalo Bert (I live 5 minutes from him apparently). Great job!

Wait, Groundhog Day is today for real? Or is it like in the T. Hanks movie and every day is Groundhog Day?

Groundhog Day is on Feb 2nd! Depends on your timezone when the site rolls over though.

Weird, when I visited the site it was already Feb 3rd in my time zone (Europe/Oslo), and the local time in my time zone was 6:15 am, but it said that it was Groundhog Day.

When I visited the site again now, a few hours later but still Feb 3rd in my time zone, with the current time being 12:12 pm (middle of the day), now it says instead when the next Groundhog Day is (“364 DAYS UNTIL GROUNDHOG DAY 2024”).

Not sure if it is intended exactly like that in terms of time zones or not.

Regardless, cool site and it was interesting to learn a bit more about Groundhog Day. Thank you :)

Bill Murray movie, but possibly

Interestingly I just watched the German-dubbed version last night and my gf (native German speaker, hence the weird viewing choice) pointed out that Bill Murray actually speaks with Tom Hanks' voice (same dubbing actor).

A new DB: actor2germanvoiceactor.com

"Tom Hanks and Bill Murray are the same person" was an interesting finding :-)

One groundhog won't be reporting in - https://www.cbc.ca/news/canada/montreal/fred-la-marmotte-die...

When Chekhov saw the long winter, he saw a winter bleak and dark and bereft of hope. Yet we know that winter is just another step in the cycle of life.

RIP Fred la marmotte

This happened last year in NJ: https://www.nj.com/news/2022/01/njs-weather-predicting-groun...

The organizers claimed they had a replacement lined up for today, but blame an unnamed state statue for not actually being able to use them: https://www.nj.com/news/2023/01/groundhog-day-to-be-without-...

note for others confused by "statue", the organizers are blaming an unspecified state _statute_ for not being able to use their new groundhog