Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
mastodon.green is one of the many independent Mastodon servers you can use to participate in the fediverse.
Plant trees while you use Mastodon. A server originally for people in the EU, but now open for anyone in the world

Administered by:

Server stats:

1.2K
active users

mastodon.green: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#datascience

65 posts58 participants7 posts today
Public
ResearchBuzz: Firehose

Online Journalism Blog: Google Sheets has a new AI function — how does it perform on classification tasks?. “AI has been built into Google Sheets for some time now in the Clippy-like form of Gemini in Sheets. But Google Sheets’s AI function is different. Available to a limited number of users for now, it allows you to incorporate AI prompts directly into a formula rather than having to […]

https://rbfirehose.com/2025/04/13/online-journalism-blog-google-sheets-has-a-new-ai-function-how-does-it-perform-on-classification-tasks/

ResearchBuzz: Firehose | Individual posts from ResearchBuzz · Online Journalism Blog: Google Sheets has a new AI function — how does it perform on classification tasks? | ResearchBuzz: Firehose
More from ResearchBuzz: Firehose
#ai#aiassisted#datascience
Public
runbikecode

On Tuesday it will be my one year mark of banning alcohol from my life. Today I deleted the "consumed alcohol" question from my Whoop morning journal. Could've done that a year ago 🤷. And yes, looking at the data was what made me quit alcohol. #sober #alcoholispoison #datascience

#Ad: Get a free WHOOP 4.0 and one month free when you join with my link: join.whoop.com/72434810

join.whoop.comJoin WHOOPThe most advanced fitness and health wearable. Get personalized insights on your body's recovery, strain, sleep, and health with in-app coaching features designed to help you unlock your best self.
Public
Frank Lesniak

This week, while at #PSHSummit25, I worked on AutoCategorizerPS. This #PowerShell #datascience tool automatically categorizes text data when you do not know the categories/labels that best characterize the data. Link: github.com/franklesniak/AutoCa #PSHSummit

Use cases: survey analysis, service desk ticket analysis, product review analysis, etc. If this sounds useful to you, check out the talk I gave with Danny Stutz from last year: youtu.be/Z08QCs_y1BU?si=6HRnOY

(If you're wondering, I improved #AzureOpenAI support (now "production ready") and enhanced one of the scripts to support the latest #OpenAI models.)

A series of scripts that perform zero-shot (untrained) data classification using AI. - franklesniak/AutoCategorizerPS
GitHubGitHub - franklesniak/AutoCategorizerPS: A series of scripts that perform zero-shot (untrained) data classification using AI.A series of scripts that perform zero-shot (untrained) data classification using AI. - franklesniak/AutoCategorizerPS
Public
Doug Ortiz

Did you know you can make LLMs solve problems like a mathematician?

Chain-of-Thought prompting transforms AI outputs from guesswork to structured reasoning!

Try this:

Think through this step-by-step:
[Your complex question]

This simple trick forces the model to show its work, dramatically improving accuracy on math, logic, and reasoning tasks.
I've cut errors by 30% using this technique!

#AI#LLM#PromptEngineering
Public
benrutter

Phew! Been a fun week or so for Wimsey (my data testing project), finished building out:

- Handy "validate or test" function (test or build a set of tests from the data)
- New tests for strings (matches regex, maximum/minimum length, category should be in, etc)
- Functionality for arbitrary narwhals expressions

Plus every time I blink Narwhals gets even better, so Pyspark and DuckDB are supported without me doing anything!

github.com/benrutter/wimsey

#python#datascience#data
Public
datatofu

dict is likely the most important built-in Python data structure. A more common name for it is hash map or associative array. It is a flexibly sized collection of key-value pairs, where key and value are Python objects. One approach for creating one is to use curly braces {} and colons to separate keys and values.

(dicT. Please say it properly)

You can access, insert, or set elements using the same syntax as for accessing elements of a list or tuple.

Tags: #python #datascience

ExploreLive feeds
About