New Google APIs: Prediction, Fusion Tables, and Books
Google announced Prediction API a year ago, but it was reserved to a limited audience. At I/O 2011 they announced the availability of that RESTful cloud service to all customers, having a number of enhancements:
- Streaming training data that allows for rapid adaptation to real-time data and allows refinement of predictive models.
- Improved user interface that provides consistent prediction scores, error reporting, and simplified formatting.
- 99.9% uptime service level agreement for additional assurance.
- Gallery of pre-built third party prediction models (coming soon) that will enable the immediate deployment of established models without the need for original development, beginning with these demo models.
Prediction API can be used to predict new results from historic data such as “user sentiment analysis, language identification, product recommendation, message routing, gene expression, and fraud detection”. Ford will demonstrate during Smart App Design at I/O 2011 how they use Predictive API to optimize energy efficiency for their new hybrid electric vehicles by providing alternative routes to choose from and to optimize driving controls to conserve energy.
Prediction API is included within API Console, a single control point for managing API usage across all Google API services used by a customer.
Google Fusion Tables is a free service useful for uploading data to be stored in tables and shared with selected persons or the general public, data being visualized in several ways: table, map, chart (bar, line, etc.), motion, timeline, or storyline. Some examples of public tables are available here. Data can be imported into Fusion Tables from CSV files (up to 100MB), spreadsheets (Excel, OpenOffice – 1MB), Google spreadsheets, and KML files (100MB).
The project is not new but Google has announced at I/O 2011 that now it has an API for programmatic access to Fusion data Tables. The API enables developers to populate a table with data, to query tables using a subset of SQL, to download selected data and to synchronize local copies of the data with the online version.
Similarly I have been looking at Fusion Tables API since past few weeks and again appears to have a huge potential for visualizing and sharing data on Cloud. It's integration with Google Maps API makes it quite a powerful combination