https://lost-stats.github.io/
"LOST is a Rosetta Stone for statistical software"

Or "Rosetta Code". Useful reference either way.

#statistics #datascience

https://econml.azurewebsites.net/spec/spec.html
The EconML Python SDK, developed by the ALICE team at MSR New England, incorporates individual machine learning steps into interpretable causal models.

Pretty cool. Docs feature introduction into the topic and the methods.

#datascience #causalinference #machinelearning

#machinelearning for 4-graders (~10 years old)
https://orangedatamining.com/blog/2022/2022-06-01-blog-minions-new/

Most important points IMO:
- Single simple task: classification with decision trees
- Guide pupils to invent the method themselves on simplified visual and familiar synthetic data
- Show automation on data pupils collected themselves, manually retrace the generated tree
- Discuss issues with data and problems they generate down the line

https://www.singularity-data.com/blog/building-a-cloud-database-from-scratch-why-we-moved-from-cpp-to-rust/

(Another?) Real-World RIIR. Actually pretty sober evaluation of pros and cons after the fact with some sensible advise.

And to entirely different (old) news. Lawrence Paulson is as sharp as ever:

I get the impression (if Twitter is at all reliable) that they see their rivals as set theorists, though I’d be surprised if any set theorists were even aware of their work.

https://lawrencecpaulson.github.io/2022/07/13/Isabelle_influences.html

I hadn’t understood that in intuitionistic type theory, if you wanted a thing, and you didn’t fancy Russell’s “honest toil”, it was perfectly okay to consult your intuition and simply add the thing you wanted. Of course, you had to have the right intuition or your addition would never get the official imprimatur.

He's undeniably old and sarcastic but hits very close to the base. 😏

https://www.kickstarter.com/projects/retrodigital/stalker-shadow-of-the-zone-fan-film/

This might become the best Stalker movie since Tarkovsky. Or even the very best one depending on your tastes.

https://aviatesk.github.io/JET.jl/dev/

(Finally!) A static type-checker for the #julia programming language (based on Abstract Interpretation).

Another better-than-C++ language from the insides of Google: https://github.com/carbon-language/carbon-lang

They pretty much readily admit it's "worse than Rust" but the "killer feature" is bidirectional interoperability with existing C++ code akin to Java-Kotlin or JavaScript-TypeScript. I guess that puts a bar on how much safety they can attain. 😏

But at least they implement sensible modules/packages system, generics à la Rust, type-level programming without templates metaprogramming craziness.

I wonder how much it differs from D? 🤔

Anyway they already contributed Carbon support into Compiler Explorer (aka Godbolt) so anyone can play with it without even installing: https://carbon.compiler-explorer.com/

https://www.youtube.com/watch?v=2d0iJ4lFKFQ

This one is good. A glimpse of Rutger Hauer's brilliance once more...

https://nickch-k.github.io/SomeThoughts/posts/2022-01-23-overdebunked/

How NOT to critique #statistics especially when you know it barely enough to make yourself look stupid (like I do 😁).

https://mixtape.scunning.com/

Another book on #causalinference ! Looks like a hot topic. 😄

Judging by the cover it predominantly describes "classical" methods like matching, regression discontinuity, difference-in-differences and alike. They promise examples and exercises in R (and Stata, but who cares about that?).

https://nickchk.com/robustness.html

A short practical guide on robustness tests in #statistics It even has a "checklist" to fill in! 😄 And a list of misconceptions too.

https://www.markhw.com/blog/causalforestintro

A hands-on overview and tutorial on estimating Heterogeneous Treatment Effects in particular with honest causal forests (R package grf).

#statistics #causalinference

— Добрый день, какая у Вас проблема?
— Голова сегодня не работает...
— Выключите и включите снова!

Почему программисты не боятся дереализации? Потому что мы и так живём в виртуальном мире! 🤣

https://github.com/ibraheemdev/modern-unix
A collection of modern/faster/saner alternatives to common unix commands.

That most of them are written in Rust is pure accident. 😁

This year's JuliaCon is effectively finished yesterday. There were several talks related to compilation and runtime.

New Julia parser in Julia:
https://www.youtube.com/watch?v=CIiGng9Brrk

Metal GPU backend:
https://www.youtube.com/watch?v=IARikXzRU7s

LLVM JIT compiler:
https://www.youtube.com/watch?v=A0VwcXcAz4o

Garbage Collection:
https://www.youtube.com/watch?v=YkcQYJIoaq
https://www.youtube.com/watch?v=2ekwjy60tR0
https://www.youtube.com/watch?v=Ks0p6PQyIPs

John Baez gives hour-long lectures on particular natural numbers! Yep, that's our John. 😁

I'm kidding. I'm pretty sure the lectures talk about symmetries, groups and alike. Go watch these and many others: https://www.youtube.com/playlist?list=PLuAO-1XXEh0ZiJlRKz7EuODAdIOjC5-1l

— ... an algorithm fails...
— ... алгоритм отказывается работать...
— Ну, не то чтобы он отказывался... 😅

Strong JavaScript vibes. Not something I would recommend copying from JS. And no warnings whatsoever. 😒
#julia

https://www.softxjournal.com/
SoftwareX — an (academic) journal publishing papers on (academic) software (artifacts).