Lecture 3 Clustering

January 21, 2003

Data Mining: Concepts and Techniques

What is Cluster Analysis?

Cluster: a collection of data objects High intra-class similarity Low inter-class similarity How to measure similarity? => quality depends Clustering is unsupervised classification: no predefined classes Typical applications As a stand-alone tool to get insight into data distribution As a preprocessing step for other algorithms

General Applications of Clustering

Pattern Recognition Spatial Data Analysis create thematic maps in GIS by clustering feature spaces detect spatial clusters and explain them in spatial data mining Image Processing Economic Science (especially market research) WWW Document classification Cluster Weblog data to discover groups of similar access patterns
Data Mining: Concepts and Techniques 3

January 21, 2003

Data Structures
Data matrix (two modes)
x 11 ... x i1 ... x n1 ... ... ... ... ... x 1f ... x if ... x nf ... ... ... ... ... x 1p ... x ip ... x np

Dissimilarity matrix (one mode)

0 d(2,1) d(3,1 ) : d ( n ,1)

0 d ( 3,2 ) : d ( n ,2 )

0 : ...

... 0
4

January 21, 2003

Data Mining: Concepts and Techniques

Measure the Quality of Clustering

Dissimilarity/Similarity metric: Similarity is expressed in terms of a distance function, which is typically metric: d(i, j) There is a separate quality function that measures the goodness of a cluster. The definitions of distance functions are usually very different for interval-scaled, boolean, categorical, ordinal and ratio variables. Weights should be associated with different variables based on applications and data semantics. It is hard to define similar enough or good enough the answer is typically highly subjective.
Data Mining: Concepts and Techniques 5

January 21, 2003

Similarity and Dissimilarity Between Objects

Distances are normally used to measure the similarity or dissimilarity between two data objects Some popular ones include: Minkowski distance: where i = (xi1, xi2, , xip) and j = (xj1, xj2, , xjp) are two p-dimensional data objects, and q is a positive integer
d (i, j) = q (| x x |q + | x x |q +...+ | x x |q ) i1 j1 i2 j2 ip jp

If q = 1, d is Manhattan distance

d(i, j) =| x x | +| x x | +...+| x x | i1 j1 i2 j2 ip jp
January 21, 2003 Data Mining: Concepts and Techniques 6

Similarity and Dissimilarity Between Objects (Cont.)

If q = 2, d is Euclidean distance:

Properties

d (i, j) = (| x x |2 + | x x |2 +...+ | x x |2 ) i1 j1 i2 j2 ip jp

d(i,j) 0 d(i,i) = 0 d(i,j) = d(j,i) d(i,j) d(i,k) + d(k,j)

Also one can use weighted distance, parametric Pearson product moment correlation, or other disimilarity measures.
Data Mining: Concepts and Techniques 7

January 21, 2003

Type of data in clustering analysis

Interval-scaled variables: Binary variables: Nominal, ordinal, and ratio variables: Variables of mixed types:

January 21, 2003

Data Mining: Concepts and Techniques

Interval-valued variables

Standardize data

Calculate the mean absolute deviation:

sf = 1 n (| x1 f m f | + | x2 f m f | +...+ | xnf m f |)

where

mf = 1 n (x1 f + x2 f

+ ... +

xnf )

Calculate the standardized measurement (z-score)

xif m f zif = sf

January 21, 2003

Data Mining: Concepts and Techniques

Binary Variables

A contingency table for binary data

Object j

1
Object i

sum a +b c+d p

1 a b 0 c d sum a + c b + d

Simple matching coefficient (invariant, if the binary b+c variable is symmetric): d (i, j ) = a+b+c+d Jaccard coefficient (noninvariant if the binary variable is b+c asymmetric rarely the value is ): d ( i , j ) = a+b+c
Data Mining: Concepts and Techniques 10

January 21, 2003

Dissimilarity between Binary Variables

Example
Name Jack Mary Jim

Gender M F M

Fever Y Y Y

Cough N N P

Test-1 P P N

Test-2 N N N

Test-3 N P N

Test-4 N N N

gender is a symmetric attribute the remaining attributes are asymmetric binary let the values Y and P be set to 1, and the value N be set to 0
0 + 1 = 0 . 33 2 + 0 + 1 1 + 1 = 0 . 67 d ( jack , jim ) = 1 + 1 + 1 1 + 2 = 0 . 75 d ( jim , mary ) = 1 + 1 + 2 d ( jack , mary ) =

January 21, 2003

Data Mining: Concepts and Techniques

11

Nominal Variables

A generalization of the binary variable in that it can take more than 2 states, e.g., red, yellow, blue, green Method 1: Simple matching

m: # of matches, p: total # of variables

m d (i, j ) = p p

Method 2: use a large number of binary variables

creating a new binary variable for each of the M nominal states

Data Mining: Concepts and Techniques 12

January 21, 2003

Ordinal Variables

An ordinal variable can be discrete or continuous order is important, e.g., rank Can be treated like interval-scaled r if {1,..., M f } replacing x by their rank
if

map the range of each variable onto [0, 1] by replacing i-th object in the f-th variable by r if 1 z if = M f 1 compute the dissimilarity using methods for intervalscaled variables
Data Mining: Concepts and Techniques 13

January 21, 2003

Ratio-Scaled Variables

Ratio-scaled variable: a positive measurement on a nonlinear scale, approximately at exponential scale, such as AeBt or Ae-Bt Methods:

treat them like interval-scaled variables not a good

choice! (why?)

apply logarithmic transformation

yif = log(xif)

treat them as continuous ordinal data treat their rank as interval-scaled.

Data Mining: Concepts and Techniques 14

January 21, 2003

Variables of Mixed Types

A database may contain all the six types of variables symmetric binary, asymmetric binary, nominal, ordinal, interval and ratio. One may use a weighted formula to combine their ( f ) ( f ) effects. p d f = 1 ij ij d (i, j ) = ( f ) p f = 1 ij f is binary or nominal: dij(f) = 0 if xif = xjf , or dij(f) = 1 o.w. f is interval-based: use the normalized distance f is ordinal or ratio-scaled z if = r 1 compute ranks rif and M 1 and treat zif as interval-scaled
if f

January 21, 2003

Data Mining: Concepts and Techniques

15

Major Clustering Approaches

Partitioning algorithms: Construct various partitions and then evaluate them by some criterion Hierarchy algorithms: Create a hierarchical decomposition of the set of data (or objects) using some criterion Density-based: based on connectivity and density functions Grid-based: based on a multiple-level granularity structure Model-based: A model is hypothesized for each of the clusters and the idea is to find the best fit of that model to each other

January 21, 2003

Data Mining: Concepts and Techniques

16

Partitioning Algorithms: Basic Concept

Partitioning method: Construct a partition of a database D of n objects into a set of k clusters Given a k, find a partition of k clusters that optimizes the chosen partitioning criterion

Global optimal: exhaustively enumerate all partitions Heuristic methods: k-means and k-medoids algorithms

k-means (MacQueen67): Each cluster is represented

by the center of the cluster

k-medoids or PAM (Partition around medoids)

(Kaufman & Rousseeuw87): Each cluster is represented by one of the objects in the cluster

January 21, 2003

Data Mining: Concepts and Techniques

17

The K-Means Clustering Method

Given k, the k-means algorithm is implemented in 4 steps: Partition objects into k nonempty subsets Compute seed points as the centroids of the clusters of the current partition. The centroid is the center (mean point) of the cluster. Assign each object to the cluster with the nearest seed point. Go back to Step 2, stop when no more new assignment.

January 21, 2003

Data Mining: Concepts and Techniques

18

The K-Means Clustering Method

Example
10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

January 21, 2003

Data Mining: Concepts and Techniques

19

Comments on the K-Means Method

Strength

Relatively efficient: O(tkn), where n is # objects, k is # clusters, and t is # iterations. Normally, k, t << n. Often terminates at a local optimum. The global optimum may be found using techniques such as: deterministic annealing and genetic algorithms

Weakness Applicable only when mean is defined, then what about categorical data? Need to specify k, the number of clusters, in advance Unable to handle noisy data and outliers Not suitable to discover clusters with non-convex shapes
Data Mining: Concepts and Techniques 20

January 21, 2003

Variations of the K-Means Method

A few variants of the k-means which differ in Selection of the initial k means Dissimilarity calculations Strategies to calculate cluster means Handling categorical data: k-modes (Huang98) Replacing means of clusters with modes Using new dissimilarity measures to deal with categorical objects Using a frequency-based method to update modes of clusters A mixture of categorical and numerical data: kprototype method
Data Mining: Concepts and Techniques 21

January 21, 2003

The K-Medoids Clustering Method

Find representative objects, called medoids, in clusters

PAM (Partitioning Around Medoids, 1987)

starts from an initial set of medoids and iteratively replaces one of the medoids by one of the nonmedoids if it improves the total distance of the resulting clustering

PAM works effectively for small data sets, but does not
scale well for large data sets

CLARA (Kaufmann & Rousseeuw, 1990) CLARANS (Ng & Han, 1994): Randomized sampling
Focusing + spatial data structure (Ester et al., 1995)
Data Mining: Concepts and Techniques 22

January 21, 2003

PAM (Partitioning Around Medoids) (1987)

PAM (Kaufman and Rousseeuw, 1987), built in Splus Use real object to represent the cluster

Select k representative objects arbitrarily For each pair of non-selected object h and selected object i, calculate the total swapping cost TCih For each pair of i and h,

If TCih < 0, i is replaced by h Then assign each non-selected object to the most similar representative object
Data Mining: Concepts and Techniques 23

repeat steps 2-3 until there is no change

January 21, 2003

PAM Clustering: Total swapping cost TCih=jCjih

10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10
10 9

t j i h

8 7 6 5 4 3 2 1 0 0 1 2

h i
3 4 5 6 7 8 9 10

Cjih = d(j, h) - d(j, i)

10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

Cjih = 0
10 9

h i

j t

7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

h t

January 21, 2003jih

Cjih = d(j, h) - d(j, t) = d(j, t) - d(j, i) Data Mining: Concepts and Techniques

24

CLARA (Clustering Large Applications) (1990)

CLARA (Kaufmann and Rousseeuw in 1990)

Built in statistical analysis packages, such as S+

It draws multiple samples of the data set, applies PAM on each sample, and gives the best clustering as the output Strength: deals with larger data sets than PAM Weakness:

Efficiency depends on the sample size A good clustering based on samples will not necessarily represent a good clustering of the whole data set if the sample is biased
Data Mining: Concepts and Techniques 25

January 21, 2003

CLARANS (Randomized CLARA) (1994)

CLARANS (A Clustering Algorithm based on Randomized

Search) (Ng and Han94) CLARANS draws sample of neighbors dynamically The clustering process can be presented as searching a graph where every node is a potential solution, that is, a set of k medoids If the local optimum is found, CLARANS starts with new randomly selected node in search for a new local optimum It is more efficient and scalable than both PAM and CLARA Focusing techniques and spatial access structures may further improve its performance (Ester et al.95)
Data Mining: Concepts and Techniques 26

January 21, 2003

Hierarchical Clustering

Use distance matrix as clustering criteria. This method does not require the number of clusters k as an input, but needs a termination condition
Step 0 Step 1 Step 2 Step 3 Step 4

a b c d e
Step 4
January 21, 2003

agglomerative (AGNES)

ab abcde cde de
Step 3 Step 2 Step 1 Step 0
Data Mining: Concepts and Techniques

divisive (DIANA)
27

AGNES (Agglomerative Nesting)

Introduced in Kaufmann and Rousseeuw (1990) Implemented in statistical analysis packages, e.g., Splus Use the Single-Link method and the dissimilarity matrix. Merge nodes that have the least dissimilarity Go on in a non-descending fashion Eventually all nodes belong to the same cluster
10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

January 21, 2003

Data Mining: Concepts and Techniques

28

A Dendrogram Shows How the Clusters are Merged Hierarchically

Decompose data objects into a several levels of nested partitioning (tree of clusters), called a dendrogram. A clustering of the data objects is obtained by cutting the dendrogram at the desired level, then each connected component forms a cluster.

January 21, 2003

Data Mining: Concepts and Techniques

29

DIANA (Divisive Analysis)

Introduced in Kaufmann and Rousseeuw (1990) Implemented in statistical analysis packages, e.g., Splus Inverse order of AGNES Eventually each node forms a cluster on its own

10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

January 21, 2003

Data Mining: Concepts and Techniques

30

More on Hierarchical Clustering Methods

Major weakness of agglomerative clustering methods 2 do not scale well: time complexity of at least O(n ), where n is the number of total objects can never undo what was done previously Integration of hierarchical with distance-based clustering BIRCH (1996): uses CF-tree and incrementally adjusts the quality of sub-clusters CURE (1998): selects well-scattered points from the cluster and then shrinks them towards the center of the cluster by a specified fraction CHAMELEON (1999): hierarchical clustering using dynamic modeling
Data Mining: Concepts and Techniques 31

January 21, 2003

BIRCH (1996)

Birch: Balanced Iterative Reducing and Clustering using Hierarchies, by Zhang, Ramakrishnan, Livny (SIGMOD96) Incrementally construct a CF (Clustering Feature) tree, a hierarchical data structure for multiphase clustering

Phase 1: scan DB to build an initial in-memory CF tree (a multi-level compression of the data that tries to preserve the inherent clustering structure of the data) Phase 2: use an arbitrary clustering algorithm to cluster the leaf nodes of the CF-tree

Scales linearly: finds a good clustering with a single scan

and improves the quality with a few additional scans order of the data record.

Weakness: handles only numeric data, and sensitive to the

Data Mining: Concepts and Techniques 32

January 21, 2003

Clustering Feature Vector

Clustering Feature: CF = (N, LS, SS) N: Number of data points LS: Ni=1=Xi SS: Ni=1=Xi2
10 9 8 7 6 5 4 3 2 1 0 0 1 2 3 4 5 6 7 8 9 10

CF = (5, (16,30),(54,190)) (3,4) (2,6) (4,5) (4,7) (3,8)

33

January 21, 2003

Data Mining: Concepts and Techniques

CF Tree
B=7 L=6 CF1
child1

Root CF2 CF3

child2 child3

CF6
child6

CF1
child1

Non-leaf node CF2 CF3

child2 child3

CF5
child5

Leaf node
prev

Leaf node
prev

CF1 CF2

CF6 next

CF1 CF2

CF4 next

January 21, 2003

Data Mining: Concepts and Techniques

34

CURE (Clustering Using

REpresentatives )

CURE: proposed by Guha, Rastogi & Shim, 1998

Stops the creation of a cluster hierarchy if a level consists of k clusters Uses multiple representative points to evaluate the distance between clusters, adjusts well to arbitrary shaped clusters and avoids single-link effect
Data Mining: Concepts and Techniques 35

January 21, 2003

Drawbacks of Distance-Based Method

Drawbacks of square-error based clustering method

Consider only one point as representative of a cluster Good only for convex shaped, similar size and density, and if k can be reasonably estimated
Data Mining: Concepts and Techniques 36

January 21, 2003

Cure: The Algorithm

Draw random sample s. Partition sample to p partitions with size s/p Partially cluster partitions into s/pq clusters Eliminate outliers

By random sampling If a cluster grows too slow, eliminate it.

January 21, 2003

Cluster partial clusters. Label data in disk

Data Mining: Concepts and Techniques 37

Data Partitioning and Clustering

s = 50 p=2 s/p = 25 y x

s/pq = 5

y y

y x x x
38

January 21, 2003

Data Mining: Concepts and Techniques

Cure: Shrinking Representative Points

y y

Shrink the multiple representative points towards the gravity center by a fraction of . Multiple representatives capture the shape of the cluster
Data Mining: Concepts and Techniques 39

January 21, 2003

Clustering Categorical Data: ROCK

ROCK: Robust Clustering using linKs, by S. Guha, R. Rastogi, K. Shim (ICDE99). Use links to measure similarity/proximity Not distance based 2 2 Computational complexity: O ( n + nmm ma + n log n ) Basic ideas: Similarity function and neighbors: S im ( T , T ) = T T T T Let T1 = {1,2,3}, T2={3,4,5}
1 1 2 2 1 2

S im ( T 1, T 2 ) =
January 21, 2003

{ 3} { 1 , 2 , 3 , 4 ,5 }

1 = 0 .2 5
40

Data Mining: Concepts and Techniques

Rock: Algorithm

Links: The number of common neighbours for the two points.

{1,2,3}, {1,2,4}, {1,2,5}, {1,3,4}, {1,3,5} {1,4,5}, {2,3,4}, {2,3,5}, {2,4,5}, {3,4,5} 3 {1,2,3} {1,2,4}

Algorithm Draw random sample Cluster with links Label data in disk
Data Mining: Concepts and Techniques 41

January 21, 2003

CHAMELEON

CHAMELEON: hierarchical clustering using dynamic modeling, by G. Karypis, E.H. Han and V. Kumar99 Measures the similarity based on a dynamic model Two clusters are merged only if the interconnectivity and closeness (proximity) between two clusters are high relative to the internal interconnectivity of the clusters and closeness of items within the clusters A two phase algorithm 1. Use a graph partitioning algorithm: cluster objects into a large number of relatively small sub-clusters 2. Use an agglomerative hierarchical clustering algorithm: find the genuine clusters by repeatedly combining these sub-clusters
Data Mining: Concepts and Techniques 42

January 21, 2003

Overall Framework of CHAMELEON

Construct Sparse Graph Partition the Graph

Data Set

Merge Partition Final Clusters

January 21, 2003

Data Mining: Concepts and Techniques

43

Density-Based Clustering Methods

Clustering based on density (local cluster criterion), such as density-connected points Major features: Discover clusters of arbitrary shape Handle noise One scan Need density parameters as termination condition Several interesting studies: DBSCAN: Ester, et al. (KDD96) OPTICS: Ankerst, et al (SIGMOD99). DENCLUE: Hinneburg & D. Keim (KDD98) CLIQUE: Agrawal, et al. (SIGMOD98)
Data Mining: Concepts and Techniques 44

January 21, 2003

Density-Based Clustering: Background

Two parameters:

Eps: Maximum radius of the neighbourhood MinPts: Minimum number of points in an Epsneighbourhood of that point

NEps(p): {q belongs to D | dist(p,q) <= Eps}

Directly density-reachable: A point p is directly densityreachable from a point q wrt. Eps, MinPts if

1) p belongs to NEps(q) 2) core point condition: |NEps (q)| >= MinPts q

MinPts = 5 Eps = 1 cm
45

January 21, 2003

Data Mining: Concepts and Techniques

Density-Based Clustering: Background (II)

Density-reachable:

A point p is density-reachable from a point q wrt. Eps, MinPts if there is a chain of points p1, , pn, p1 = q, pn = p such that pi+1 is directly density-reachable from pi A point p is density-connected to a point q wrt. Eps, MinPts if there is a point o such that both, p and q are density-reachable from o wrt. Eps and MinPts. p

p q p1

Density-connected

q o

January 21, 2003

Data Mining: Concepts and Techniques

46

DBSCAN: Density Based Spatial Clustering of Applications with Noise

Relies on a density-based notion of cluster: A cluster is defined as a maximal set of density-connected points Discovers clusters of arbitrary shape in spatial databases with noise Outlier Border Core Eps = 1cm MinPts = 5

January 21, 2003

Data Mining: Concepts and Techniques

47

DBSCAN: The Algorithm

Arbitrary select a point p Retrieve all points density-reachable from p wrt Eps and MinPts. If p is a core point, a cluster is formed. If p is a border point, no points are density-reachable from p and DBSCAN visits the next point of the database. Continue the process until all of the points have been processed.
Data Mining: Concepts and Techniques 48

January 21, 2003

OPTICS: A Cluster-Ordering Method (1999)

OPTICS: Ordering Points To Identify the Clustering Structure Ankerst, Breunig, Kriegel, and Sander (SIGMOD99) Produces a special order of the database wrt its density-based clustering structure This cluster-ordering contains info equiv to the density-based clusterings corresponding to a broad range of parameter settings Good for both automatic and interactive cluster analysis, including finding intrinsic clustering structure Can be represented graphically or using visualization techniques
Data Mining: Concepts and Techniques 49

January 21, 2003

OPTICS: Some Extension from DBSCAN

Index-based: k = number of dimensions N = 20 p = 75% M = N(1-p) = 5

Complexity: O(kN2)

Core Distance Reachability Distance p2

p1 o o MinPts = 5

Max (core-distance (o), d (o, p)) r(p1, o) = 2.8cm. r(p2,o) = 4cm

January 21, 2003

Data Mining: Concepts and Techniques

= 3 cm

50

Reachability -distance

undefined

January 21, 2003

Data Mining: Concepts and Techniques

Cluster-order of the objects

51

DENCLUE: using density functions

DENsity-based CLUstEring by Hinneburg & Keim (KDD98) Major features

Solid mathematical foundation Good for data sets with large amounts of noise Allows a compact mathematical description of arbitrarily shaped clusters in high-dimensional data sets Significant faster than existing algorithm (faster than DBSCAN by a factor of up to 45) But needs a large number of parameters

January 21, 2003

Data Mining: Concepts and Techniques

52

Denclue: Technical Essence

Uses grid cells but only keeps information about grid cells that do actually contain data points and manages these cells in a tree-based access structure. Influence function: describes the impact of a data point within its neighborhood. Overall density of the data space can be calculated as the sum of the influence function of all data points. Clusters can be determined mathematically by identifying density attractors. Density attractors are local maximal of the overall density function.
Data Mining: Concepts and Techniques 53

January 21, 2003

Gradient: The steepness of a slope

Example

f Gaussian ( x , y ) = e
f
D Gaussian

d ( x , y )2 2 2

( x ) = i =1 e
N

d ( x , xi ) 2 2 2

D Gaussian

( x, xi ) = i =1 ( xi x) e
N
Data Mining: Concepts and Techniques

d ( x , xi ) 2 2 2

January 21, 2003

54

Density Attractor

January 21, 2003

Data Mining: Concepts and Techniques

55

Center-Defined and Arbitrary

January 21, 2003

Data Mining: Concepts and Techniques

56

Grid-Based Clustering Method

Using multi-resolution grid data structure Several interesting methods

STING (a STatistical INformation Grid approach) by Wang, Yang and Muntz (1997) WaveCluster by Sheikholeslami, Chatterjee, and Zhang (VLDB98)

A multi-resolution clustering approach using wavelet method

CLIQUE: Agrawal, et al. (SIGMOD98)

Data Mining: Concepts and Techniques 57

January 21, 2003

STING: A Statistical Information Grid Approach

Wang, Yang and Muntz (VLDB97) The spatial area area is divided into rectangular cells There are several levels of cells corresponding to different levels of resolution

January 21, 2003

Data Mining: Concepts and Techniques

58

STING: A Statistical Information Grid Approach (2)

Each cell at a high level is partitioned into a number of smaller cells in the next lower level Statistical info of each cell is calculated and stored beforehand and is used to answer queries Parameters of higher level cells can be easily calculated from parameters of lower level cell count, mean, s, min, max type of distributionnormal, uniform, etc. Use a top-down approach to answer spatial data queries Start from a pre-selected layertypically with a small number of cells For each cell in the current level compute the confidence interval

STING: A Statistical Information Grid Approach (3)

Remove the irrelevant cells from further consideration When finish examining the current layer, proceed to the next lower level Repeat this process until the bottom layer is reached Advantages: Query-independent, easy to parallelize, incremental update O(K), where K is the number of grid cells at the lowest level Disadvantages: All the cluster boundaries are either horizontal or vertical, and no diagonal boundary is detected

WaveCluster (1998)

Sheikholeslami, Chatterjee, and Zhang (VLDB98) A multi-resolution clustering approach which applies wavelet transform to the feature space

A wavelet transform is a signal processing technique that decomposes a signal into different frequency sub-band.

Both grid-based and density-based Input parameters:

# of grid cells for each dimension the wavelet, and the # of applications of wavelet transform.
Data Mining: Concepts and Techniques 61

January 21, 2003

What is Wavelet (1)?

January 21, 2003

Data Mining: Concepts and Techniques

62

WaveCluster (1998)

How to apply wavelet transform to find clusters Summaries the data by imposing a multidimensional grid structure onto data space These multidimensional spatial data objects are represented in a n-dimensional feature space Apply wavelet transform on feature space to find the dense regions in the feature space Apply wavelet transform multiple times which result in clusters at different scales from fine to coarse

January 21, 2003

Data Mining: Concepts and Techniques

63

What Is Wavelet (2)?

January 21, 2003

Data Mining: Concepts and Techniques

64

Quantization

January 21, 2003

Data Mining: Concepts and Techniques

65

Transformation

January 21, 2003

Data Mining: Concepts and Techniques

66

WaveCluster (1998)

January 21, 2003

Why is wavelet transformation useful for clustering Unsupervised clustering It uses hat-shape filters to emphasize region where points cluster, but simultaneously to suppress weaker information in their boundary Effective removal of outliers Multi-resolution Cost efficiency Major features: Complexity O(N) Detect arbitrary shaped clusters at different scales Not sensitive to noise, not sensitive to input order Only applicable to low dimensional data
Data Mining: Concepts and Techniques

67

CLIQUE (Clustering In QUEst)

Agrawal, Gehrke, Gunopulos, Raghavan (SIGMOD98). Automatically identifying subspaces of a high dimensional data space that allow better clustering than original space CLIQUE can be considered as both density-based and gridbased

It partitions each dimension into the same number of equal length interval It partitions an m-dimensional data space into nonoverlapping rectangular units A unit is dense if the fraction of total data points contained in the unit exceeds the input model parameter A cluster is a maximal set of connected dense units within a subspace
Data Mining: Concepts and Techniques 68

January 21, 2003

CLIQUE: The Major Steps

Partition the data space and find the number of points that lie inside each cell of the partition. Identify the subspaces that contain clusters using the Apriori principle Identify clusters:

Determine dense units in all subspaces of interests Determine connected dense units in all subspaces of interests.

Generate minimal description for the clusters Determine maximal regions that cover a cluster of connected dense units for each cluster Determination of minimal cover for each cluster
Data Mining: Concepts and Techniques 69

January 21, 2003

Salary (10,000) 0 1 2 3 4 5 6 7

20

30

40

50 Vacation

age 60

Vacation (week) 0 1 2 3 4 5 6 7

20

30

40

50

age 60

=3

lar a S

30

50

age

January 21, 2003

Data Mining: Concepts and Techniques

70

Strength and Weakness of CLIQUE

Strength It automatically finds subspaces of the highest dimensionality such that high density clusters exist in those subspaces It is insensitive to the order of records in input and does not presume some canonical data distribution It scales linearly with the size of input and has good scalability as the number of dimensions in the data increases Weakness The accuracy of the clustering result may be degraded at the expense of simplicity of the method
Data Mining: Concepts and Techniques 71

January 21, 2003

Model-Based Clustering Methods

Attempt to optimize the fit between the data and some mathematical model Statistical and AI approach Conceptual clustering

A form of clustering in machine learning Produces a classification scheme for a set of unlabeled objects Finds characteristic description for each concept (class) A popular a simple method of incremental conceptual learning Creates a hierarchical clustering in the form of a classification tree Each node refers to a concept and contains a probabilistic description of that concept
Data Mining: Concepts and Techniques 72

COBWEB (Fisher87)

January 21, 2003

COBWEB Clustering Method

A classification tree

January 21, 2003

Data Mining: Concepts and Techniques

73

More on Statistical-Based Clustering

Limitations of COBWEB The assumption that the attributes are independent of each other is often too strong because correlation may exist Not suitable for clustering large database data skewed tree and expensive probability distributions CLASSIT an extension of COBWEB for incremental clustering of continuous data suffers similar problems as COBWEB AutoClass (Cheeseman and Stutz, 1996) Uses Bayesian statistical analysis to estimate the number of clusters Popular in industry
Data Mining: Concepts and Techniques 74

January 21, 2003

Other Model-Based Clustering Methods

Neural network approaches Represent each cluster as an exemplar, acting as a prototype of the cluster New objects are distributed to the cluster whose exemplar is the most similar according to some dostance measure Competitive learning Involves a hierarchical architecture of several units (neurons) Neurons compete in a winner-takes-all fashion for the object currently being presented
Data Mining: Concepts and Techniques 75

January 21, 2003

Model-Based Clustering Methods

January 21, 2003

Data Mining: Concepts and Techniques

76

Self-organizing feature maps (SOMs)

Clustering is also performed by having several units competing for the current object The unit whose weight vector is closest to the current object wins The winner and its neighbors learn by having their weights adjusted SOMs are believed to resemble processing that can occur in the brain Useful for visualizing high-dimensional data in 2- or 3-D space
Data Mining: Concepts and Techniques 77

January 21, 2003

What Is Outlier Discovery?

What are outliers? The set of objects are considerably dissimilar from the remainder of the data Example: Sports: Michael Jordon, Wayne Gretzky, ... Problem Find top n outlier points Applications: Credit card fraud detection Telecom fraud detection Customer segmentation Medical analysis
Data Mining: Concepts and Techniques 78

January 21, 2003

Outlier Discovery: Statistical Approaches

Assume a model underlying distribution that generates data set (e.g. normal distribution) Use discordancy tests depending on data distribution distribution parameter (e.g., mean, variance) number of expected outliers Drawbacks most tests are for single attribute In many cases, data distribution may not be known
Data Mining: Concepts and Techniques 79

January 21, 2003

Outlier Discovery: DistanceBased Approach

Introduced to counter the main limitations imposed by statistical methods We need multi-dimensional analysis without knowing data distribution. Distance-based outlier: A DB(p, D)-outlier is an object O in a dataset T such that at least a fraction p of the objects in T lies at a distance greater than D from O Algorithms for mining distance-based outliers Index-based algorithm Nested-loop algorithm Cell-based algorithm

Outlier Discovery: DeviationBased Approach

Identifies outliers by examining the main characteristics of objects in a group Objects that deviate from this description are considered outliers sequential exception technique

simulates the way in which humans can distinguish unusual objects from among a series of supposedly like objects uses data cubes to identify regions of anomalies in large multidimensional data
Data Mining: Concepts and Techniques 81

OLAP data cube technique

January 21, 2003

Problems and Challenges

Considerable progress has been made in scalable clustering methods

Partitioning: k-means, k-medoids, CLARANS Hierarchical: BIRCH, CURE Density-based: DBSCAN, CLIQUE, OPTICS Grid-based: STING, WaveCluster Model-based: Autoclass, Denclue, Cobweb

Current clustering techniques do not address all the requirements adequately Constraint-based clustering analysis: Constraints exist in data space (bridges and highways) or in user queries
Data Mining: Concepts and Techniques 82

January 21, 2003

Constraint-Based Clustering Analysis

Clustering analysis: less parameters but more user-desired constraints, e.g., an ATM allocation problem

January 21, 2003

Data Mining: Concepts and Techniques

83

Summary

Cluster analysis groups objects based on their similarity and has wide applications Measure of similarity can be computed for various types of data Clustering algorithms can be categorized into partitioning methods, hierarchical methods, density-based methods, grid-based methods, and model-based methods Outlier detection and analysis are very useful for fraud detection, etc. and can be performed by statistical, distance-based or deviation-based approaches There are still lots of research issues on cluster analysis, such as constraint-based clustering
Data Mining: Concepts and Techniques 84

January 21, 2003

References (1)

R. Agrawal, J. Gehrke, D. Gunopulos, and P. Raghavan. Automatic subspace clustering of high dimensional data for data mining applications. SIGMOD'98 M. R. Anderberg. Cluster Analysis for Applications. Academic Press, 1973. M. Ankerst, M. Breunig, H.-P. Kriegel, and J. Sander. Optics: Ordering points to identify the clustering structure, SIGMOD99. P. Arabie, L. J. Hubert, and G. De Soete. Clustering and Classification. World Scietific, 1996 M. Ester, H.-P. Kriegel, J. Sander, and X. Xu. A density-based algorithm for discovering clusters in large spatial databases. KDD'96. M. Ester, H.-P. Kriegel, and X. Xu. Knowledge discovery in large spatial databases: Focusing techniques for efficient class identification. SSD'95. D. Fisher. Knowledge acquisition via incremental conceptual clustering. Machine Learning, 2:139-172, 1987. D. Gibson, J. Kleinberg, and P. Raghavan. Clustering categorical data: An approach based on dynamic systems. In Proc. VLDB98. S. Guha, R. Rastogi, and K. Shim. Cure: An efficient clustering algorithm for large databases. SIGMOD'98. A. K. Jain and R. C. Dubes. Algorithms for Clustering Data. Printice Hall, 1988.
Data Mining: Concepts and Techniques 85

January 21, 2003

References (2)

L. Kaufman and P. J. Rousseeuw. Finding Groups in Data: an Introduction to Cluster Analysis. John Wiley & Sons, 1990. E. Knorr and R. Ng. Algorithms for mining distance-based outliers in large datasets. VLDB98. G. J. McLachlan and K.E. Bkasford. Mixture Models: Inference and Applications to Clustering. John Wiley and Sons, 1988. P. Michaud. Clustering techniques. Future Generation Computer systems, 13, 1997. R. Ng and J. Han. Efficient and effective clustering method for spatial data mining. VLDB'94. E. Schikuta. Grid clustering: An efficient hierarchical clustering method for very large data sets. Proc. 1996 Int. Conf. on Pattern Recognition, 101-105. G. Sheikholeslami, S. Chatterjee, and A. Zhang. WaveCluster: A multi-resolution clustering approach for very large spatial databases. VLDB98. W. Wang, Yang, R. Muntz, STING: A Statistical Information grid Approach to Spatial Data Mining, VLDB97. T. Zhang, R. Ramakrishnan, and M. Livny. BIRCH : an efficient data clustering method for very large databases. SIGMOD'96.
Data Mining: Concepts and Techniques 86

January 21, 2003