stataholic

Data Scientist, Forbes.
Research about application of Machine Learning in Sports.

[stataholic @stataholic]

Every {}, "field", :, and comma in JSON becomes tokens.
LLMs tokenize JSON poorly, inflating both latency and API cost.

TOON removes the noise and keeps only the meaning.

#ToonStream

[stataholic @stataholic]

LLMs aren’t expensive.
Your JSON is.

Switching from JSON → TOON cuts token usage by:

55% on flat data

38% on arrays

15% on nested objects

Here’s why this matters — and how much you can save. 👇

#LLM #AI #AGENTS #RAG

[stataholic @stataholic]

Meet Toonstream, the library that implementing
TOON (Token-Oriented Object Notation) —
a serialization format built to make structured LLM inputs far more token-efficient than JSON.

! pip install toonstream

#LLM #AiAgents

[Hudl Statsbomb @Statsbomb]

Update: 49/52 shots have an xG value of 7% or less

[stataholic @stataholic]

Tuesday is the new friday.

[Morissa Schwartz 📚 (Dr. Rissy) @MorissaSchwartz]

Wowwwwww 🤩 https://t.co/y19UP4Fuay

[stataholic @stataholic]

I have a classification problem, and XGBOOST is the best model.
I have calibrated the model outputs as well and saved both the models.

Say, I am creating a pipeline to predict for future values.
Which model should I use?
Normal or calibrated model ?
@tunguz
#DataScience

[Leif Denby @leifdenby]

`plt.subplot_mosaic(...)` is the single-most amazing @matplotlib function I'd never heard of 😍🤓🌍 Can't believe I've used Python for more than a decade and only just discovered it! Subplots will never be the same again 🌟 https://t.co/EBN4ndA6HL

[stataholic @stataholic]

@haltakov evaluation metric is totally depend on the type of data we have.
If it's balanced data, we can use accuracy.
If it's imbalance, we can either use precision or recall depends on the use case.

[stataholic @stataholic]

@tunguz How to become a Data Scientist in one month ?

[stataholic @stataholic]

@StatsBomb Are you guys doing it virtual .?

[Thibault Clérice (ponteineptique on Ciel Bleu ) @PonteIneptique]

Python 3.10 is out, every damn programmer is in love with the new structural pattern matching.
But for anyone teaching python out there, the new error messages are what's up. (Before/After)

[stataholic @stataholic]

How to convert Multi-Class text classification to Multi-label text Classification??

#DataScience
#NLP #Deeplearning

[stataholic @stataholic]

Is there any pre-trained model or library for Entity based / aspect based sentiment analysis?
#NLP #DataScience #MachineLearning

[stataholic @stataholic]

@micaleel yes. kinda

[stataholic @stataholic]

Is there anyway to calculate sentiment score other than Text Blob, vader, Flair?
#NLP #MachineLearning #Python

[stataholic @stataholic]

Ecstatic to announce that I have joined Forbes as a Data Scientist.
I am blessed to have landed in 5 offers (Data Scientist, MLE) from 1000+ applications, 30+ recruiter calls, 20+ technical interviews, 15+ Online assessments & 10+ final rounds.
#DataScience #machinelearning

[Carrie Ann @barelycarrie]

slacking a coworker during a meeting and watching them have to suppress a laugh is my absolute greatest joy

[stataholic @stataholic]

how to do regression with only categorical variables python ??
#MachineLearning #DataScience

[Siddarth Pai @siddarthpaim]

He had such a good hand writing #Physics #CVRaman