statsmodel פשוט רץ במשך נצח ומתישהו הרמתי ידיים. אפילו לא הייתי בטוח לחלוטין שמה שאני עושה שם נכון עם הדוקומנטציה המוזרה שלהם.
בזמן שפתחתי את R והתחלתי לכתוב את הרגרסיה השיערוך הגס שלי למקדמי t בsklearn סיים לרוץ, ואז ויתרתי על האופציה, אבל באמת שR בנויה כל כך הרבה יותר לדברים האלו מפייתון.
בזמן שפתחתי את R והתחלתי לכתוב את הרגרסיה השיערוך הגס שלי למקדמי t בsklearn סיים לרוץ, ואז ויתרתי על האופציה, אבל באמת שR בנויה כל כך הרבה יותר לדברים האלו מפייתון.
October 22, 2025 at 3:05 PM
statsmodel פשוט רץ במשך נצח ומתישהו הרמתי ידיים. אפילו לא הייתי בטוח לחלוטין שמה שאני עושה שם נכון עם הדוקומנטציה המוזרה שלהם.
בזמן שפתחתי את R והתחלתי לכתוב את הרגרסיה השיערוך הגס שלי למקדמי t בsklearn סיים לרוץ, ואז ויתרתי על האופציה, אבל באמת שR בנויה כל כך הרבה יותר לדברים האלו מפייתון.
בזמן שפתחתי את R והתחלתי לכתוב את הרגרסיה השיערוך הגס שלי למקדמי t בsklearn סיים לרוץ, ואז ויתרתי על האופציה, אבל באמת שR בנויה כל כך הרבה יותר לדברים האלו מפייתון.
Minor update on regMMD:
cran.r-project.org/web/packages...
includes more outputs on GD/SGD for sanity checks.
Future plans: include more models (mixtures, etc) and write a Python version in the sklearn style.
I take the opportunity: if you have time to help us on this, you are more than welcome!
cran.r-project.org/web/packages...
includes more outputs on GD/SGD for sanity checks.
Future plans: include more models (mixtures, etc) and write a Python version in the sklearn style.
I take the opportunity: if you have time to help us on this, you are more than welcome!
October 16, 2025 at 8:19 AM
Minor update on regMMD:
cran.r-project.org/web/packages...
includes more outputs on GD/SGD for sanity checks.
Future plans: include more models (mixtures, etc) and write a Python version in the sklearn style.
I take the opportunity: if you have time to help us on this, you are more than welcome!
cran.r-project.org/web/packages...
includes more outputs on GD/SGD for sanity checks.
Future plans: include more models (mixtures, etc) and write a Python version in the sklearn style.
I take the opportunity: if you have time to help us on this, you are more than welcome!
What a banger is skrub @skrub-data.bsky.social !
Big thumbs up for the sklearn team & the maintainer of this package
Big thumbs up for the sklearn team & the maintainer of this package
October 1, 2025 at 8:24 AM
What a banger is skrub @skrub-data.bsky.social !
Big thumbs up for the sklearn team & the maintainer of this package
Big thumbs up for the sklearn team & the maintainer of this package
Right timing as we finish our introduction to sklearn in Jena for @helmholtzai.bsky.social !
Game on! 👾 for @scikit-learn.bsky.social
experts only: the ✨boss level✨ has arrived 🚀
For seasoned pros ready to master ML:
🔹 Custom algorithms
🔹 MLOps & deployment
🔹 Align ML with business projects
Be among the first to get certified! 👉https://eu1.hubs.ly/H0dZ18x0
#machinelearning #datascience
experts only: the ✨boss level✨ has arrived 🚀
For seasoned pros ready to master ML:
🔹 Custom algorithms
🔹 MLOps & deployment
🔹 Align ML with business projects
Be among the first to get certified! 👉https://eu1.hubs.ly/H0dZ18x0
#machinelearning #datascience
November 27, 2024 at 10:40 AM
Right timing as we finish our introduction to sklearn in Jena for @helmholtzai.bsky.social !
Yes all the time. If I have a feature extraction pipeline that is running over my training data and I want it to be consistent and be free to update sklearn. Particularly for steps like kmeans or PCA.
November 28, 2024 at 7:33 PM
Yes all the time. If I have a feature extraction pipeline that is running over my training data and I want it to be consistent and be free to update sklearn. Particularly for steps like kmeans or PCA.
And of course the User Guide and linked examples are a typical sklearn treasure trove of knowledge scikit-learn.org/stable/modul...
3.3. Tuning the decision threshold for class prediction
Classification is best divided into two parts: the statistical problem of learning a model to predict, ideally, class probabilities;, the decision problem to take concrete action based on those pro...
scikit-learn.org
May 29, 2024 at 11:34 AM
And of course the User Guide and linked examples are a typical sklearn treasure trove of knowledge scikit-learn.org/stable/modul...
29. I think the unified "sklearn-style" API for modeling is good
July 27, 2025 at 5:50 PM
29. I think the unified "sklearn-style" API for modeling is good
ניסיתי למצוא מה הטוקנים (פיצ'רים) הכי משפיעים לניבוי בינארי של משהו בציוץ, אם אני הולך פשוט על המקדמים זה מביא לי את הפיצ'רים הכי נידחים בעולם כי כמובן שהם אלו שהכי ישפיעו, אז חשבתי ללכת על מובהקות, רק שאין בsklearn מובהקות וstatsmodels לא אהבו אותי.
(בפועל גם בדיקת מקדמי t הביאה תוצאות מפוקפקות)
(בפועל גם בדיקת מקדמי t הביאה תוצאות מפוקפקות)
October 22, 2025 at 2:06 PM
ניסיתי למצוא מה הטוקנים (פיצ'רים) הכי משפיעים לניבוי בינארי של משהו בציוץ, אם אני הולך פשוט על המקדמים זה מביא לי את הפיצ'רים הכי נידחים בעולם כי כמובן שהם אלו שהכי ישפיעו, אז חשבתי ללכת על מובהקות, רק שאין בsklearn מובהקות וstatsmodels לא אהבו אותי.
(בפועל גם בדיקת מקדמי t הביאה תוצאות מפוקפקות)
(בפועל גם בדיקת מקדמי t הביאה תוצאות מפוקפקות)
"People underestimate how impactful sklearn continues to be" — @fchollet.bsky.social
December 16, 2023 at 4:51 PM
"People underestimate how impactful sklearn continues to be" — @fchollet.bsky.social
Sklearn에 있는 DBSCAN 여기저기 써먹을수있을줄 알았는데 분자간 거리가 짧은 멀티 분자 시스템 분자동역학 해석하기엔 별로구만.
August 16, 2023 at 9:11 AM
Sklearn에 있는 DBSCAN 여기저기 써먹을수있을줄 알았는데 분자간 거리가 짧은 멀티 분자 시스템 분자동역학 해석하기엔 별로구만.
Reescrevemos o plano:
• 1 curso fundamental
• Python (escolha dele)
• Pandas + Sklearn
• 1 projeto real por mês
[6/7]
• 1 curso fundamental
• Python (escolha dele)
• Pandas + Sklearn
• 1 projeto real por mês
[6/7]
May 22, 2025 at 11:38 AM
Reescrevemos o plano:
• 1 curso fundamental
• Python (escolha dele)
• Pandas + Sklearn
• 1 projeto real por mês
[6/7]
• 1 curso fundamental
• Python (escolha dele)
• Pandas + Sklearn
• 1 projeto real por mês
[6/7]
Translating Cython to Mojo, a first attempt https://fnands.com/blog/2025/sklearn-mojo-dbscan-inner/ (https://news.ycombinator.com/item?id=45495738)
Translating Cython to Mojo, a first attempt
fnands.com
October 7, 2025 at 4:15 AM
Translating Cython to Mojo, a first attempt https://fnands.com/blog/2025/sklearn-mojo-dbscan-inner/ (https://news.ycombinator.com/item?id=45495738)
Some highlights:
• It doesn't need training (because the entire historical dataset is fed into the model as "context"; just like how LLMs use large context windows at inference time).
• The model is super-easy to use. It's implemented as a Python package and exposes the same API as sklearn.
2/4
• It doesn't need training (because the entire historical dataset is fed into the model as "context"; just like how LLMs use large context windows at inference time).
• The model is super-easy to use. It's implemented as a Python package and exposes the same API as sklearn.
2/4
January 13, 2025 at 12:08 PM
Some highlights:
• It doesn't need training (because the entire historical dataset is fed into the model as "context"; just like how LLMs use large context windows at inference time).
• The model is super-easy to use. It's implemented as a Python package and exposes the same API as sklearn.
2/4
• It doesn't need training (because the entire historical dataset is fed into the model as "context"; just like how LLMs use large context windows at inference time).
• The model is super-easy to use. It's implemented as a Python package and exposes the same API as sklearn.
2/4
October 6, 2025 at 10:00 PM
Me diz uma coisa? Você verifica o estrato seu target de treino/teste na hora de aplicar um estimador?
Essa é uma brincadeira que aprendi lendo o 'Hands on ML' e acho MUITO válido compartilhar. Chega aí que eu explico.
⚠️Esse fio exige conhecimento prévio básico em ML e sklearn
#studytech
🧶
Essa é uma brincadeira que aprendi lendo o 'Hands on ML' e acho MUITO válido compartilhar. Chega aí que eu explico.
⚠️Esse fio exige conhecimento prévio básico em ML e sklearn
#studytech
🧶
September 3, 2024 at 11:46 PM
Me diz uma coisa? Você verifica o estrato seu target de treino/teste na hora de aplicar um estimador?
Essa é uma brincadeira que aprendi lendo o 'Hands on ML' e acho MUITO válido compartilhar. Chega aí que eu explico.
⚠️Esse fio exige conhecimento prévio básico em ML e sklearn
#studytech
🧶
Essa é uma brincadeira que aprendi lendo o 'Hands on ML' e acho MUITO válido compartilhar. Chega aí que eu explico.
⚠️Esse fio exige conhecimento prévio básico em ML e sklearn
#studytech
🧶
sklearn is powerful and cool i just, don't really like it
November 1, 2023 at 9:57 PM
sklearn is powerful and cool i just, don't really like it
Apparently the #fuckItFriday chaos muppet is ruling again tonight.
I'm all out of ML/python/sklearn mojo but 🧶brain was really keen to start ANOTHER sock because finishing ONE #sockdown challenge a month is not challenge enough?
ravel.me/johannab/mm
I'm all out of ML/python/sklearn mojo but 🧶brain was really keen to start ANOTHER sock because finishing ONE #sockdown challenge a month is not challenge enough?
ravel.me/johannab/mm
johannab's Miss Marple’s Subtlety
Late CO for another missed mystery
ravel.me
June 28, 2025 at 1:36 AM
Apparently the #fuckItFriday chaos muppet is ruling again tonight.
I'm all out of ML/python/sklearn mojo but 🧶brain was really keen to start ANOTHER sock because finishing ONE #sockdown challenge a month is not challenge enough?
ravel.me/johannab/mm
I'm all out of ML/python/sklearn mojo but 🧶brain was really keen to start ANOTHER sock because finishing ONE #sockdown challenge a month is not challenge enough?
ravel.me/johannab/mm
Watch it be a Python script with import sklearn lol
January 15, 2025 at 1:51 AM
Watch it be a Python script with import sklearn lol
I don't believe Econ should do too much to familiarize people with classic ML libraries like sklearn unless it's specifically a Data Science or ML module. For the rest I believe there are better alternatives.
June 4, 2025 at 11:30 AM
I don't believe Econ should do too much to familiarize people with classic ML libraries like sklearn unless it's specifically a Data Science or ML module. For the rest I believe there are better alternatives.
`statsmodels`と`sklearn`でのロジスティック回帰の挙動の違いについて
https://zenn.dev/0_u0/articles/6a43ff43b02399
https://zenn.dev/0_u0/articles/6a43ff43b02399
`statsmodels`と`sklearn`でのロジスティック回帰の挙動の違いについて
zenn.dev
July 14, 2024 at 12:47 AM
`statsmodels`と`sklearn`でのロジスティック回帰の挙動の違いについて
https://zenn.dev/0_u0/articles/6a43ff43b02399
https://zenn.dev/0_u0/articles/6a43ff43b02399
The tensorflow syntax is more like sklearn and feels more home than pyTorch.
February 27, 2025 at 10:48 AM
The tensorflow syntax is more like sklearn and feels more home than pyTorch.
我sklearn用得更多，但它的统计功能真是bare minimum
October 2, 2023 at 12:16 AM
我sklearn用得更多，但它的统计功能真是bare minimum
This Sklearn Tool for Feature Selection Is a Must-Know for Every ML and Data Science Professional by The Insight Loop
This Sklearn Tool for Feature Selection Is a Must-Know for Every ML and Data Science Professional
While working on a machine learning project, I came across an exciting Python library designed to identify the most important features in a…
code.likeagirl.io
August 7, 2025 at 1:18 PM
This Sklearn Tool for Feature Selection Is a Must-Know for Every ML and Data Science Professional by The Insight Loop