Learning Path
Get started with the Semantic Data Science API
In our example, we used the Semantic Data Science API for feature engineering of a public data set that is related to COVID-19 and has the following columns:
- Date
- Longitude
- Latitude
- Province/State
- Country/Region
- Recovered
- Confirmed
- Deaths.
The Semantic Data Science API extracted the most salient concepts related to the data, such as “COVID,” which is not explicitly mentioned but inferred by the mapping component. The Semantic Data Science API then found new features that were related to the available concepts, some of which can be directly computed. For example, the Semantic Data Science API suggested computing “confirmed_percent” and “deaths_percent” from Country/Region and either Confirmed or Deaths, respectively.
Others features cannot necessarily be computed from the given data. For instance, the Semantic Data Science API identified an epidemiology model that described the spread of a disease as a potentially related feature, although it doesn’t suggest how to compute or incorporate this information. The Semantic Data Science API lets you explore the sources behind the concepts and features it identifies, providing more insight and assistance than current tools.
Summary
This article explained how the Semantic Data Science API can be used to extract the most salient concepts related to the data, and how it helps you look at the sources behind the concepts, providing more insight and assistance.