Talks
Speakers
Events
Topics
Sign in
Home
Talks
Speakers
Events
Topics
Leaderboard
Use
Analytics
Sign in
Suggest modification to this talk
Title
Description
Forecasting the Future: An Introduction to Machine Learning for Weather Prediction in Native Ruby. Landon Gray @thedayisntgray asked "Why aren't people doing Machine Learning in Native Ruby?" and decided to take action. This engaging talk shares his ideas and thoughts and culminates in an ML project using Ruby with Jupyter + iruby. @BlueRidgeRuby @thedayisntgray
Date
Summarized using AI?
If this talk's summary was generated by AI, please check this box. A "Summarized using AI" badge will be displayed in the summary tab to indicate that the summary was generated using AI.
Show "Summarized using AI" badge on summary page
Summary
Markdown supported
In the video titled "Forecasting the Future: An Intro to Machine Learning with Ruby," Landon Gray, a Senior Software Engineer, explores the application of machine learning in native Ruby, particularly for weather prediction. This talk aims to address the question of why Ruby is not more commonly used for machine learning, focusing on a practical machine learning project developed in Ruby. Key points discussed include: - **Introduction to Machine Learning with Ruby**: Gray explains his motivation for using Ruby instead of more widely used languages such as Python, C++, or R. - **Tools and Libraries**: He introduces Jupyter Notebook with the IRuby kernel as the development environment and mentions essential Ruby libraries like Numo::NArray, Daru, and Rali used for data processing and modeling. - **Project Goal**: The main objective is to predict weather, specifically maximum temperatures, using historical datasets. - **Data Collection and Preparation**: Gray details how he accessed weather datasets from the National Centers for Environmental Information, focusing on data cleaning processes, including handling missing values and outliers. - **Feature Engineering**: He emphasizes the importance of preparing data properly, such as using previous day's temperature as a feature to predict the current day's maximum temperature, in line with the 80/20 rule of data science. - **Model Training**: The training process involves splitting data into sets for training and testing, and Gray uses linear regression as the modeling technique, illustrating how the model establishes a best-fit line to make predictions. - **Project Repository and Resources**: Gray provides a link to the project repository for viewers to access the code and experiment with different algorithms, enhancing their understanding of the process. In conclusion, Gray encourages viewers to explore machine learning with Ruby and highlights that although Ruby is less popular than Python in this field, it can still be a viable option for developing machine learning models. He acknowledges the community's hesitance toward using Ruby and asserts that there are opportunities to grow this interest in data science within the Ruby ecosystem. The video ends with an invitation for questions from the audience, reinforcing the interactive nature of such discussions in the programming community.
Suggest modifications
Cancel
