This lecture is just to point you to some data resources so you might be able to get some free data, and do some of analysis, if you don't happen to have any at the organization that you're at. So this website consists of data from a variety of national organizations. So we can start off with the United Nations data sets, which are at this website, and then you can find data that are available from the United States at data.gov. And you can go to this blog post to find a bunch of other cities and states within the United States that have open data. There's also a lot more information on a variety of other countries and this website down here data.gov/opendatasites actually gives information on data sites for other countries all around the world. So that's a good place to start if you don't know if your country has an open government data site. Gapminder is another website that has a lot of data about development in particular in human heath. And so there's a large number of datasets that are available on that website which is Gapminder.org. You can also get survey data from the United States. This website here gives you a lot of information about how do you actually access the surveys and process them in R. So it's actually really nice because the surveys are often very big and unwieldy, and this website gives you a lot of information on how to access them. The Infochimps Marketplace has a bunch of different data sets which you can sort by various different tags, and you can identify data sets that might be of interest to you. Some of them are free, and some of them cost money. Kaggle is another place that you can go to for data sets. So Kaggle is a company that offers data science competitions, and they often have very interesting data sets that they make available as part of those competitions. So they're good for practice, but they're also good for potentially discovering new, interesting things that can help companies solve real problems. There's also some collections that have been put together by famous data scientists. So these are several data scientists. Hilary Mason, Jeff Hammerbacher, and others who have put together data sets that are research quality and that might be useful for you. These all come from this blog post which talks about several other data sets, they're curated by other data scientists as well. There are also a large variety of other, more specialised collections. So for example, the Stanford Large Network Data Archive has a large number of data sets that focus on network data, machine learning, the UCI Machine Learning archive has a variety of data sets that can be used to practice your classification or predictions. The CMU Statlib is one of the most famous canonical sets of data sets that are available. Gene Expression Omnibus is focused on data sets that come from human genomic experiments or other organismal genomics experiments. And then there's data from the ArXiv or public datasets on Amazon web services. Finally, there a large number of APIs that you've now learned how to use, through the course of this class. And so, for example, there's specific packages such as the twitter package which can be used to access the Twitter API, in an easier way than trying to set up a application yourself. You can similarly get access to figshare data or to data from publications like Plos one. rOpenSci has a large number of very nice packages that allow you to access data from a variety of sources that are focused on academics. There's also dedicated R packages for Facebook and Google Maps. All of these mean that there is really no excuse to not be able to find real data to focus on any project that you might be interested in.
