Data—Collect, Clean, and Connect - Graph Analysis and Visualization - page 79

CPI Expenditure
Level Weight
+ All
items............................................
100
+ Food and
beverages.................................. 14.792
+
Food...............................................
13.742
+ Food at
home...................................... 7.816
+ Cereals and bakery
products...................... 1.09
+ Cereals and cereal
products..................... 0.35
+ Flour and prepared flour
mixes................. 0.039
+ Breakfast
cereal............................... 0.194
...
See the CPI data set in the Supplementary Materials on this topic's
companion website for an example.
Getting the Data
Identifying the data is only part of the problem—actually getting the data
can be an interesting challenge in some corporate environments.
Techniques for getting data include the following:
• File download —Many of the previously described data sets are
available as downloadable files on the Internet from various sites.
http://data.gov can be a good top-level source for U.S. data.
http://stats.oecd.org or http://data.worldbank.org can be good sources
for data across countries. Social network data can be accessed from a
variety of sites such as http://tweetarchivist.com .
• Report data export —Many reporting software solutions provide a
means to export data as flat files or into spreadsheets.