Add results from clustering

[starcalibre]

Now that we're approaching the stage that we'll be incorporating the results from clustering the images, we need to think of how these should be presented. Ideas discussed in the meeting today were:

• Finding centroid samples and displaying them. Some clustering algorithms will explicitly choose centroids (KMeans, DBSCAN) while others we'll need to find the centroid ourselves.
• Average feature vectors.
• Highlighting features that do interesting things across the dataset -- maybe high variance features? The nice thing about the new feature documents collection is we can associate such statistics to each feature so the UI can easily display these.

[jni]

Re: centroids, we k-means gives you a "virtual" centroid, not one that necessarily corresponds to any sample. What we want is to display the sample that is closest to this centroid.

Re: interesting features, all the features by construction have mean 0 and variance 1, but what we might see is features that have higher variance across the cluster centroids. In a sense, these might capture the biological variance between the different clusters.