Data Mining For Dummies

Chapter 10

Ferreting Out Public Data Sources

In This Chapter

Fathoming your sources

Recognizing issues

Surveying the public data landscape

When you need data that you don’t already own, look for public sources first. Not only are these sources numerous and diverse, but in many cases, no commercial entity would be able to independently gather the same information. And public data is usually available free or at low cost.

Looking Over the Lay of the Land

Public data is primarily government data. Government agencies collect and share data about people, activities, and resources. In the U.S., you have the right to request information from any part of the federal government (though not all parts are equally responsive). Every state, county, and city collects and maintains data that may be available to you. Countries around the world have their own statistical agencies, as do a number of intergovernmental organizations.

Public data is a by-product of everyday government work; no government collects data for the purpose of sharing it with data miners. Obtaining relevant government data in a form you can use isn’t always easy. You can develop a good sense of what to expect if you make ...