Clustering

1. Clustering Ram Akella Lecture 6 February 23, 2011 1290& 280I University of California Berkeley Silicon Valley Center/SC

2. Class Outline • Clustering Introduction • Mechanics • Recommender Systems

3. Inter-cluster distances are maximized Intra-cluster distances are minimized What is Cluster Analysis? • Finding groups of objects such that the objects in a group will be similar (or related) to one another and different from (or unrelated to) the objects in other groups

4. Potential Applications • Numerical Taxonomy • Differentiation between different species of animals or plants according to their physical similarities • Fifty plants from3 different species were collected and some measurements were taken such as: sepal length, sepal width, petal length and petal width.

5. Potential Applications • Market Segmentation • The market is divided into smaller groups that are more homogeneous needs and wants of the market place

6. Objectives of cluster analysis • Address the heterogenity in the data • Divide the data into more homogeneous groups • Find the natural modality of data • Determine whether the data contains naturally occurring, homogeneous subsets

7. Measures of distance, dissimilarity and density • To measure of proximity of data we can use • Direct assessment of proximity • Derived measure of proximity or similarity

8. Distance Measurements Euclidean Distance This is usually applied to standardized data to give the same weight to all the metrics (except when the input is the Principal Components)

9. Distance Measurements Minkowski Metric • The Euclidean distance is a especial case when p=2 • When p=1 it is called city-block metric because it is like walking from point A to point B in a city laid out with a grid of streets

10. Mahalanobis Distance This distance takes into account the covariance patterns of the data Where Σ is the population covariance matrix of the data matrix X The Mahalanobis distance captures the fact that a point A and a point B are equally likely to have been drawn from a multivariate normal distribution

11. Agglomerative Clustering • Start with the points as individual clusters • At each step, merge the closest pair of clusters until only one cluster (or k clusters) left • More popular hierarchical clustering technique • Key operation is the computation of the proximity of two clusters • Different approaches to defining the distance between clusters distinguish the different algorithms

12. Agglomerative Clustering Algorithm Basic algorithm is : • Compute the proximity matrix • Let each data point be a cluster • Repeat • Merge the two closest clusters • Update the proximity matrix • Until only a single cluster remains

13. p1 p2 p3 p4 p5 . . . p1 p2 p3 p4 p5 . . . Starting Situation Start with clusters of individual points and a proximity matrix Proximity Matrix

14. C1 C2 C3 C4 C5 C1 C2 C3 C4 C5 Intermediate Situation After some merging steps, we have some clusters C3 C4 C1 Proximity Matrix C5 C2

15. C1 C2 C3 C4 C5 C1 C2 C3 C4 C5 Intermediate Situation We want to merge the two closest clusters (C2 and C5) and update the proximity matrix. C3 C4 Proximity Matrix C1 C5 C2

16. C2 U C5 C1 C3 C4 C1 ? ? ? ? ? C2 U C5 C3 ? ? C4 After Merging The question is: “How do we update the proximity matrix?” C3 C4 Proximity Matrix C1 C2 U C5

17. p1 p2 p3 p4 p5 . . . Similarity? p1 p2 p3 p4 p5 . . . How to Define Inter-Cluster Similarity • MIN • MAX • Group Average • Distance Between Centroids • Ward’s Method Proximity Matrix

18. p1 p2 p3 p4 p5 . . . p1 p2 p3 p4 p5 . . . How to Define Inter-Cluster Similarity • MIN • MAX • Group Average • Distance Between Centroids • Ward’s Method Proximity Matrix

19. p1 p2 p3 p4 p5 . . . p1 p2 p3 p4 p5 . . . How to Define Inter-Cluster Similarity • MIN • MAX • Group Average • Distance Between Centroids • Ward’s Method Proximity Matrix

20. p1 p2 p3 p4 p5 . . . p1 p2 p3 p4 p5 . . . How to Define Inter-Cluster Similarity • MIN • MAX • Group Average • Distance Between Centroids • Ward’s Method Proximity Matrix

21.   p1 p2 p3 p4 p5 . . . p1 p2 p3 p4 p5 . . . How to Define Inter-Cluster Similarity • MIN • MAX • Group Average • Distance Between Centroids • Ward’s Method Proximity Matrix

22. Ward’s Method • Similarity of two clusters is based on the increase in squared error when two clusters are merged • Less susceptible to noise and outliers • Biased towards globular clusters • Hierarchical analogue of K-means • Can be used to initialize K-means

23. K-means Clustering • Partitional clustering approach • Each cluster is associated with a centroid (center point) • Each point is assigned to the cluster with the closest centroid • Number of clusters, K, must be specified • The basic algorithm is very simple

24. K-means Clustering – Details • Initial centroids are often chosen randomly. • Clusters produced vary from one run to another. • The centroid is (typically) the mean of the points in the cluster. • ‘Closeness’ is measured by Euclidean distance, cosine similarity, correlation, etc. • K-means will converge for common similarity measures mentioned above. • Most of the convergence happens in the first few iterations. • Often the stopping condition is changed to ‘Until relatively few points change clusters’

25. Optimal Clustering Sub-optimal Clustering Two different K-means Clustering Original Points

26. Importance of Choosing Initial Centroids

27. How many clusters • To decide the appropriate number of clusters • Run the analysis for different values of k and compare the solutions with the pseudo-F statistic given by Where B is the inter-cluster sum of squares matrix, W is the intra-cluster sum of squares, K is the number of clusters and n the number of data points The larger the pseudo-F statistic, the more efficient the clustering is

28. Evaluating K-means Clusters • Most common measure is Sum of Squared Error (SSE) • For each point, the error is the distance to the nearest cluster • To get SSE, we square these errors and sum them. • x is a data point in cluster Ci and mi is the representative point for cluster Ci • micorresponds to the center (mean) of the cluster • Given two clusters, we can choose the one with the smallest error • One easy way to reduce SSE is to increase K, the number of clusters • A good clustering with smaller K can have a lower SSE than a poor clustering with higher K

29. Problems with Selecting Initial Points • If there are K ‘real’ clusters then the chance of selecting one centroid from each cluster is small. • Chance is relatively small when K is large • If clusters are the same size, n, then • For example, if K = 10, then probability = 10!/1010 = 0.00036 • Sometimes the initial centroids will readjust themselves in ‘right’ way, and sometimes they don’t • Consider an example of five pairs of clusters

30. Solutions to Initial Centroids Problem • Multiple runs • Helps, but probability is not on your side • Sample and use hierarchical clustering to determine initial centroids • Select more than k initial centroids and then select among these initial centroids • Select most widely separated • Post-processing • Bisecting K-means • Not as susceptible to initialization issues

31. Handling Empty Clusters • Basic K-means algorithm can yield empty clusters • Several strategies • Choose the point that contributes most to SSE • Choose a point from the cluster with the highest SSE • If there are several empty clusters, the above can be repeated several times.

32. Updating Centers Incrementally • In the basic K-means algorithm, centroids are updated after all points are assigned to a centroid • An alternative is to update the centroids after each assignment (incremental approach) • Each assignment updates zero or two centroids • More expensive • Introduces an order dependency • Never get an empty cluster • Can use “weights” to change the impact

33. Pre-processing and Post-processing • Pre-processing • Normalize the data • Eliminate outliers • Post-processing • Eliminate small clusters that may represent outliers • Split ‘loose’ clusters, i.e., clusters with relatively high SSE • Merge clusters that are ‘close’ and that have relatively low SSE • Can use these steps during the clustering process • ISODATA

34. Bisecting K-means • Bisecting K-means algorithm • Variant of K-means that can produce a partitional or a hierarchical clustering