Forecasting the Future: An Introduction to Machine Learning for Weather Prediction in Native Ruby
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?
Landon Gray
Test Double, Senior Software Consultant
Attendees
- All
| Relevancy | Interesting |
|---|---|
| 4 | 5 |
Notes
Ultimately this talk felt very incomplete and not relevant. It really just touched on a few ideas and showed some possibliities. It didn't really go into any depth on anything.
Wants to do machine learning in ruby, not python.
Tools
Jupyter Notebook + iruby Execute Ruby. Can do visualization using python.
Libraries
numo/narray-> Equivalent to python numpy -> GitHub - ruby-numo/numo-narray: Ruby/Numo::NArray - New NArray class librarydaru-> Equivalent to python pandas -> Data Frame -> GitHub - SciRuby/daru: Data Analysis in Rubyrumale-> ML algorithms -> GitHub - yoshoku/rumale: Rumale is a machine learning library in Ruby
Problem
Predict weather and max temp
Collect Data
National Center for Environment Information has tons of weather data Weather data for the Atlanta airport.
Data Preparation
Import into Jupyter notebook Duplicate, don't manipulate source
Look at the top 5 values of each desired category.
Clean up
- Handling Missing values
- Outliers
- Malformed Data
- Eliminate duplicate values 80/20 rule.
Train Model
Split the data set.
- 80% is training
- Trains the model
- 20% is testing
- Validates the training
Linear regression - is an attempt to model the relationship between two variables by fitting
Y = mx + b
f(x) = mx + b
Best fit line.