Pattern analysis and machine intelligence use is increasingly applied to images, audio and video signals, and natural language text. But it is not much applied to computer program source code. This is seen by many as a missed opportunity. This interesting information came to us from Phys.org in their article, “AI for code encourages collaborative, open scientific discovery.”
Data science programs are a special kind of computer code full of semantically rich content that specifies a sequence of data transformation, analysis, modeling, and interpretation operations. By using data analysis, all of the functions that are called in the analysis can be captured. Those functions can be connected to a data science ontology to produce a semantic flow graph representation of the program. This results in a graph flow from an analysis of data.
If you think of the semantic flow graph as a single data point on which to perform further higher-level tasks, several useful functionalities can be enabled for practicing data scientists, including intelligent search and auto-completion of analyses.
Melody K. Smith
Sponsored by Access Innovations, the world leader in taxonomies, metadata, and semantic enrichment to make your content findable.