eurybia
Made-With-ML
Our great sponsors
eurybia | Made-With-ML | |
---|---|---|
3 | 51 | |
203 | 35,656 | |
3.0% | - | |
5.1 | 6.8 | |
about 1 month ago | 5 months ago | |
Jupyter Notebook | Jupyter Notebook | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
eurybia
-
State of the Art data drift libraries on Python?
Try out eurybia, from the author of shapash which is a brilliant library as well.
-
Providing ML team with data: normalized or denormalized?
Your data scientists will cook up ugly bits of code to prepare their training data, you'll probably have to rewrite that when they want to ship to prod and also detect and handle discrepancies. In that regard, it sounds like you may enjoy Eurybia to communicate about this data with your data scientists. We made it precisely for that.
-
Advice on a Data Quality framework
So we just trained a model to try and do the same, and then sort of read its entrails through Shapash. The more it can tell the difference, the more your data has changed. We can know which variable has changed the most, and how much it's important to our models. If all else fails (and also if all else works), we can still know (again, this is all quantified in some way, we need numbers, not eyeballings) how much our models predictions have evolved over time, independantly of particular data changes, legit or not. How can our models predictions change if the data is all clean, you ask ? I mean I asked, but you would have too, in my shoes. What lies beyond data engineering ? What is the meaning of life ? The answer is concept drift, and that's where we're starting to work on now that we have a good grasp on data drift. Anyways, the tool is Eurybia. If any part of my ramblings resemble some of your work, please give it a try and chat us up here or through the repo, we are of course very eager to get feedbacks and possibly even contributions, who knows. See ya !
Made-With-ML
-
[D] How do you keep up to date on Machine Learning?
Made With ML
- Open-Source Production Machine Learning Course
-
Advice for switching careers within analytics
- Develop a (simple!) ML project and apply MLOps best practices to it. Ask Chat GPT all of your MLOps questions. I've joined this MLOps community and it has been very helpful to know what path to follow in order to be better at MLOps, thanks to them I arrived at madewithml, but I haven't done it yet. But it covers all the MLOps side.
-
Recommendation for MLOps resources
Hey, I’m also working in ML. Here’s a great resource: https://madewithml.com. Also, check out Noah Gift’s book Practical MLOPs.
- Ask HN: Resource to learn how to train and use ML Models
-
Need help to find resources to learn ml ops
Try replicating this setup: https://madewithml.com/
-
MLops Resources
madewithml
-
Ask HN: How do I get started with MLOps?
There's a really nice website by Goku Mohandas called Made With ML. IMO it is the best practical guide to MLOps out there: https://madewithml.com
Incase you want to dive a little deeper, https://fullstackdeeplearning.com/course/2022/ is also something I have been recommended by folks.
- Resources for Current DE Interested in Learning Data Science
-
Do organizations still need machine learning engineers?
madewithml is pretty sweet, especially the MLOps side of things. It'll give you good skills in how development in Python and deploying ML works.
What are some alternatives?
shapash - 🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
zero-to-mastery-ml - All course materials for the Zero to Mastery Machine Learning and Data Science course.
evidently - Evaluate and monitor ML models from validation to production. Join our Discord: https://discord.com/invite/xZjKRaNp8b
mlops-zoomcamp - Free MLOps course from DataTalks.Club
nannyml - nannyml: post-deployment data science in python
FLAML - A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.
TensorFlow-Examples - TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
mlops-course - Learn how to design, develop, deploy and iterate on production-grade ML applications.
ML-For-Beginners - 12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
practical-mlops-book - [Book-2021] Practical MLOps O'Reilly Book
Copulas - A library to model multivariate data using copulas.
ETCI-2021-Competition-on-Flood-Detection - Experiments on Flood Segmentation on Sentinel-1 SAR Imagery with Cyclical Pseudo Labeling and Noisy Student Training