In the earlier exercises, I asked you to look at the dots and figure out the distance. This gives a hint as to how we need to think of our data. We need to think of our data as coordinates in some imaginary coordinate space. Now, our data won't be just two-dimensional, because it's textual. Instead, it'll be multidimensional. This gives us hints as to how our data will look—slices of numbers representing a coordinate in some arbitrarily large N-dimensional space.
But, first, we'll need to get the data.
To acquire the tweets from the feed, we'll be using Aditya Mukherjee's excellent Anaconda library. To install it, simply run go get -u github.com/ChimeraCoder/Anaconda.
Of course, one can't just grab data from Twitter willy-nilly. We will need to acquire data via the Twitter API. The documentation of Twitter's API is...
