Cool Government Data Sets
Contributed by Karl Smith
Data is the beginning of any data science project. Sometimes an interesting data source can be an inspiration for a new or inventive data science project. I found this great government site with tons of interesting and unusual data sets.
While many are mundane (like the Grain Transportation Report for Importers of Soybeans, *YAWN*), there are some intriguing datasets, such as:
- US Baby Names. Wondering what the most popular baby names are? Look no further, as the government has compiled a list of the most popular ones based on the applications for social security that they receive. Data set contains name, sex of child, and number of children given that name in that year for every year between 1880 and 2013.
- There is also another data set for baby names specifically in New York City, which contains, not only the number of children given that name and sex of the child, but also the ethnicity of the mother and the rank of that name overall that year.
- Average daily traffic counts (ADT) of the City of Chicago. Effectively a census count of traffic for the city of Chicago.
- Consumer Expenditure Report. How much did US citizens making 30k-40k a year on average spend on cereals? This data set will you tell you that and much more. (The answer is $159 on average in 2011.)
- American Time Use Survey. “The American Time Use Survey (ATUS) measures the amount of time people spend doing various activities, such as paid work, childcare, volunteering, and socializing.” The files are in SPS format. Looks like promising data sets, though formatting is weird and will most likely need a lot of cleaning for most uses.
- Flight delays and reasons for delays. Can filter by origin/destination city, airline, flight number, and date. Will give the delay reason, cancellation reason, and other statistics like taxi time, etc.
Those are just a few of the data sets that caught my eye on the site. The site certainly has much much more, so check it out.