David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Data Mining (and machine learning) DM Lecture 5: Clustering

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Today (unsupervised) Clustering –What and why –A good first step towards understanding your data –Discover patterns and structure in data –Which then guides further data mining –Helps to spot problems and outliers –Identifies `market segments’, e.g. specific types of customers or users ; this is called segmentation or market segmentation How to do it: – Choose distance measure or a similarity measure –Run a (usually) simple algorithm –We will cover the two main algorithms

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: What is Clustering? Why do it? SubscriberCalls per dayMonthly bill Consider these data: Made up; maybe they are 17 subscribers to a mobile phone services company, and show the mean calls per day and the mean monthly bill for each customer Do you spot any patterns or Structure ??

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: What is Clustering? Why do it? Here is a plot of the data, with calls as X and bills as Y Now do you spot any patterns or structure ??

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: What is Clustering? Why do it? Clearly there are two clusters -- two distinct types of customer Top left: few calls but highish bills; bottom right: many calls, low bills

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: So, clustering is all about plotting/visualising and noting distinct groups by eye, right? Not really, because: We can only spot patterns by eye (i.e. with our brains) if the data is 1D, 2D or 3D. Most data of interest is much higher dimensional – e.g. 10D, 20D, 1000D. Sometimes the clusters are not so obvious as a bunch of data all in the same place – we will see examples. So: we need automated algorithms which can do what you just did (find distinct groups in the data), but which can do this for any number of dimensions, and for perhaps more complex kinds of groups.

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: OK, so when we apply an automated clustering algorithm to data, the result is a collection of groups, which tells us potentially useful things about our data – e.g. if we are doing this with supermarket baskets, each group is a collection of typical baskets, which may relate to “general housekeeping”, “late night dinner”, “quick lunchtime shopper”, and perhaps other types that we are not expecting Yes

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Quality of a clustering? Why is this: Better than this?

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Quality of a clustering? A `good clustering’ has the following properties: Items in the same cluster tend to be close to each other Items in different clusters tend to be far from each other It is not hard to come up with a metric – an easily calculated value – that can be used to give a score to any clustering. There are many such metrics. E.g. S = the mean distance between pairs of items in the same cluster D = the mean distance between pairs of items in different clusters Measure of cluster quality is: D/S -- the higher the better.

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Let’s try that S = [AB + AD + AF + AH + BD + BF + BH + DF + DH + FH + CE + CG + EG] / 13 = 44/ D = [ AC + AE + AG + BC + BE + BG + DC + DE + DG + FC + FE + FG + HC + HE + HG ]/15 = 40/15 = 2.67 Cluster Quality = D/S = 0.77 A B C D E F G H

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Let’s try that again S = [AB + AC + AD + BC+ BD + CD + EF + EG + EH + FG + FH + GH ] / 12 = 20/12 = 1.67 D = [ AE + AF + AG + AH + BE + BF + BG + BH + CE + CF + CG + CH + DE + DF + DG + DH]/16 = 68/16 = 4.25 Cluster Quality = D/S = 2.54 A B C D E F G H

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: But what about this? S = [AB + CD + EF + EG + EH + FG + FH + GH ] / 8 = 12/8 = 1.5 D = [ AC + AD + AE + AF + AG + AH + BC + BD + BE + BF + BG + BH + CE + CF + CG + CH + DE + DF + DG + DH]/20 = = 72/20= 3.6 Cluster Quality = D/S = 2.40 A B C D E F G H

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Some important notes There is usually no `correct’ clustering. Clustering algorithms (whether or not they work with cluster quality metrics) always use some kind of distance or similarity measure -- the result of the clustering process will depend on the chosen distance measure. Choice of algorithm, and/or distance measure, will depend on the kind of cluster shapes you might expect in the data. Our D/S measure for cluster quality will not work well in lots of cases

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Examples: sometimes groups are not simple to spot, even in 2D Slide credit: Julia Handl

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Examples: sometimes groups are not simple to spot, even in 2D Slide credit: Julia Handl

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Brain Training Think about why D/S is not a useful cluster quality measure in the general case Try to design a cluster quality metric that will work well in the cases of the previous slides (not very difficult)

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: In many problems the clusters are more `conventional’ – but maybe fuzzy and unclear Slide credit: Julia Handl

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: And there is a different kind of clustering that can be done, which avoids the issue of deciding the number of clusters in advance Slide credit: Elias Raftopoulos Prof. Maria Papadopouli

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: How to do it The most commonly used methods: K-Means Hierarchical Agglomerative Clustering

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: K-Means If you want to see K clusters, then run K-means. I.e. you need to choose in advance the number of clusters. Say K=3 -- run 3-means and the result is a `good ’ grouping of the data into 3 clusters. It works by generating K points (in a way, these are made-up records in the data); each point is the centre (or centroid) of one cluster. As the algorithm iterates, the points adjust their positions until they stabilise. Very simple, fairly fast, very common; a few drawbacks.

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Let’s see it

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Here is the data; we choose k = 2 and run 2-means

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: We choose two cluster centres -- randomly

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Step 1: decide which cluster each point is in – the one whose centre is closest

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Step 2: We now have two clusters – recompute the centre of each cluster

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: These are the new centres

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Step 1: decide which cluster each point is in – the one whose centre is closest

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: This one has to be reassigned:

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Step 2: We now have two new clusters – recompute the centre of each cluster

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Centres now slightly moved

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Step 1: decide which cluster each point is in – the one whose centre is closest

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: In this case, nothing gets reassigned to a new cluster – so the algorithm is finished

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: The K-Means Algorithm Choose k 1. Randomly choose k points, labelled {1, 2, …, k} to be the initial cluster centroids. 2.For each datum, let its cluster ID be the label of its closest centroid. 3.For each cluster, recalculate its actual centre. 4.Go back to Step 2, stop when step 2 does not change the cluster ID of any point

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Simple but often not ideal Variable results with noisy data and outliers Very large or very small values can skew the centroid positions, and give poor clusterings Only suitable for the cases where we can expect clusters to be `clumps ’ that are close together – e.g. terrible in the two-spirals and similar cases

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Hierarchical Agglomerative Clustering Before we discuss this: We need to know how to work out the distance between two points:

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Hierarchical Agglomerative Clustering Before we discuss this: And the distance between a point and a cluster ?

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Hierarchical Agglomerative Clustering Before we discuss this: And the distance between two clusters ?

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Hierarchical Agglomerative Clustering Before we discuss this: There are many options for all of these things; we will discuss them in a later lecture. ?

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Hierarchical Agglomerative Clustering Is very commonly used Very different from K-means Provides a much richer structuring of the data No need to choose k But, quite sensitive to the various ways of working out distance (different results for different ways)

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Let’s see it

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Initially, each point is a cluster

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Find closest pair of clusters, and merge them into one cluster

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Find closest pair of clusters, and merge them into one cluster

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Find closest pair of clusters, and merge them into one cluster

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Find closest pair of clusters, and merge them into one cluster

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Find closest pair of clusters, and merge them into one cluster

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Find closest pair of clusters, and merge them into one cluster

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Find closest pair of clusters, and merge them into one cluster

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Find closest pair of clusters, and merge them into one cluster

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Now all one cluster, so stop

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: The thing on the right is a dendrogram – it contains the information for us to group the data into clusters in various ways

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: E.g. 2 clusters

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: E.g. 3 clusters

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: In a proper dendrogram … The height of a bar indicates how different the items are A dendrogram is also called a binary tree The data points are the leaves of the tree Each node represents a cluster – all the leaves of its subtree

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: The Agglomerative Hierarchical Clustering Algorithm Decide on how to work out distance between two clusters Initialise: each of the N data items is a cluster Repeat N-1 times: –Find the closest pair of clusters; merge them into a single cluster (and update your tree representation)

David Corne, and Nick Taylor, Heriot-Watt University - These slides and related resources: Next time Correlation – what are the important fields in your dataset?