An Introduction to Machine Learning for Weather Prediction in Native Ruby

Title :

Forecasting the Future: An Introduction to Machine Learning for Weather Prediction in Native Ruby

Abstract:

Have you ever considered building a machine learning model in Ruby? It may surprise you to learn that you can train, build, and deploy ML models in Ruby. But what are the benefits of using Ruby over other languages?

One of the biggest advantages of using Ruby for machine learning is accessibility. You're no longer limited to specific languages or tools when exploring AI and ML concepts. It's time for Rubyists to dive into the world of machine learning! -

In this talk, we'll build a model that predicts the weather and explore the tools and libraries available for your own native Ruby Machine Learning projects.

Whether you're a seasoned Rubyist or just starting out, don't miss this opportunity to discover the possibilities of machine learning in Ruby.

Transcript

3. Hi I’m Landon 👋‍ Senior Monkey Patcher @testdouble
4. @thedayisntgray Linkedin Mastodon Twitter Senior Software Consultant @testdouble
5. There was a question that plagued me… 🤔
7. • Problem • Collect Data • Data Preparation • Train Model • Make Predictions
8. But before that… 🔨 📚
9. Jupyter Notebook + iruby
12. Libraries 📚
13. require 'numo/narray' require 'daru' require 'rumale'
14. • Problem • Collect Data • Data Preparation • Train Model • Make Predictions
15. 🌩
16. 🌡 Max Temperature
17. • Problem • Collect Data • Data Preparation • Train Model • Make Predictions
20. • Problem • Collect Data • Data Preparation • Train Model • Make Predictions
22. 5 Core Values: PRCP = Precipitation SNOW = Snowfall SNWD = Snow depth TMAX = Maximum temperature TMIN = Minimum temperature
24. Clean Up Data • Handling Missing values • Outliers • Malformed Data • Eliminate duplicate values
25. Clean Up Data
26. Who’s Tired 😪
27. 80/20 Rule
28. • Problem • Collect Data • Data Preparation • Train Model • Make Predictions
29. Split the data Training Test Dataset
31. Linear regression - is an attempt to model the relationship between two variables by fitting a linear equation to the observed data.
32. Y = mx + b
33. f(x) = mx + b
35. Best Fit Line
36. Train Model
37. 🎉
38. • Problem • Collect Data • Data Preparation • Train Model • Make Predictions
40. • Problem • Collect Data • Data Preparation • Train Model • Make Predictions
41. Thank You!
42. 🎁
43. https://tinyurl.com/y8anhkrv Repository