LunchBox includes Machine Learning components (LunchBoxML) that make Accord.NET and ML.NET workflows accessible within Grasshopper. These components allow users to train, save, and test machine learning models using a variety of algorithms. This example uses LunchBox’s Regression Trainer alongside Ladybug’s environmental modeling tools to predict incident solar radiation for an irregular surface.
While the status quo for models might be inconsistent or otherwise messy labeling, a utility in LunchBox can simplify label clean up. This article provides step-by-step instructions for preparing a simple Grasshopper script that will swap out a variety of Revit room names with standard labels.
LunchBox's new building massing tools can help you quickly create massing schemes that fit specific boundaries, areas, and number of floors based on your project's unique goals.
Interoperability has been a foundational concept in the formation and continued operations of Proving Ground. In a blog post from 2016, I positioned interoperability as a ‘wicked problem’ for the building design and construction industry that is situated at the intersection of “interdependent issues of the marketplace of tools and our execution processes.” While the … Continue reading Creating Conveyor – Real-World Project Influences
