Data Mining:

Concepts and Techniques

(3rd ed.)

Basic Cluster

Dosen: Dr. Vitri Tundjungsari

1
Chapter 10. Cluster Analysis: Basic Concepts and
Methods

 Cluster Analysis: Basic Concepts

 Partitioning Methods
 Hierarchical Methods
 Density-Based Methods
 Grid-Based Methods
 Evaluation of Clustering
 Summary
2
 What is Cluster Analysis?
 Cluster: A collection of data objects
 similar (or related) to one another within the same group

 dissimilar (or unrelated) to the objects in other groups

 Cluster analysis (or clustering, data segmentation, …)

 Finding similarities between data according to the

characteristics found in the data and grouping similar

data objects into clusters
 Unsupervised learning: no predefined classes (i.e., learning
by observations vs. learning by examples: supervised)
 Typical applications
 As a stand-alone tool to get insight into data distribution

 As a preprocessing step for other algorithms

3
 Clustering for Data Understanding and
Applications
 Biology: taxonomy of living things: kingdom, phylum, class, order,
family, genus and species
 Information retrieval: document clustering
 Land use: Identification of areas of similar land use in an earth
observation database
 Marketing: Help marketers discover distinct groups in their customer
bases, and then use this knowledge to develop targeted marketing
programs
 City-planning: Identifying groups of houses according to their house
type, value, and geographical location
 Earth-quake studies: Observed earth quake epicenters should be
clustered along continent faults
 Climate: understanding earth climate, find patterns of atmospheric
and ocean
 Economic Science: market resarch
4
 Clustering as a Preprocessing Tool (Utility)

 Summarization:
 Preprocessing for regression, PCA, classification, and
association analysis
 Compression:
 Image processing: vector quantization
 Finding K-nearest Neighbors
 Localizing search to one or a small number of clusters
 Outlier detection
 Outliers are often viewed as those “far away” from any
cluster

5
 Quality: What Is Good Clustering?

 A good clustering method will produce high quality

clusters
 high intra-class similarity: cohesive within clusters
 low inter-class similarity: distinctive between clusters
 The quality of a clustering method depends on
 the similarity measure used by the method
 its implementation, and
 Its ability to discover some or all of the hidden patterns

6
 Measure the Quality of Clustering
 Dissimilarity/Similarity metric
 Similarity is expressed in terms of a distance function,
typically metric: d(i, j)
 The definitions of distance functions are usually rather
different for interval-scaled, boolean, categorical, ordinal
ratio, and vector variables
 Weights should be associated with different variables
based on applications and data semantics
 Quality of clustering:
 There is usually a separate “quality” function that
measures the “goodness” of a cluster.
 It is hard to define “similar enough” or “good enough”
 The answer is typically highly subjective
7
 Considerations for Cluster Analysis
 Partitioning criteria
 Single level vs. hierarchical partitioning (often, multi-level
hierarchical partitioning is desirable)
 Separation of clusters
 Exclusive (e.g., one customer belongs to only one region) vs.
non-exclusive (e.g., one document may belong to more than one
class)
 Similarity measure
 Distance-based (e.g., Euclidian, road network, vector) vs.
connectivity-based (e.g., density or contiguity)
 Clustering space
 Full space (often when low dimensional) vs. subspaces (often in
high-dimensional clustering)
8
 Requirements and Challenges
 Scalability
 Clustering all the data instead of only on samples

 Ability to deal with different types of attributes

 Numerical, binary, categorical, ordinal, linked, and mixture of these

 Constraint-based clustering
 User may give inputs on constraints
 Use domain knowledge to determine input parameters
 Interpretability and usability
 Others
 Discovery of clusters with arbitrary shape

 Ability to deal with noisy data

 Incremental clustering and insensitivity to input order

 High dimensionality

9
 Major Clustering Approaches (I)

 Partitioning approach:
 Construct various partitions and then evaluate them by some

criterion, e.g., minimizing the sum of square errors

 Typical methods: k-means, k-medoids, CLARANS

 Hierarchical approach:
 Create a hierarchical decomposition of the set of data (or objects)

using some criterion

 Typical methods: Diana, Agnes, BIRCH, CAMELEON

 Density-based approach:
 Based on connectivity and density functions

 Typical methods: DBSACN, OPTICS, DenClue

 Grid-based approach:
 based on a multiple-level granularity structure

 Typical methods: STING, WaveCluster, CLIQUE

10
 Major Clustering Approaches (II)
 Model-based:
 A model is hypothesized for each of the clusters and tries to find

the best fit of that model to each other

 Typical methods: EM, SOM, COBWEB

 Frequent pattern-based:
 Based on the analysis of frequent patterns

 Typical methods: p-Cluster

 User-guided or constraint-based:
 Clustering by considering user-specified or application-specific

constraints
 Typical methods: COD (obstacles), constrained clustering

 Link-based clustering:
 Objects are often linked together in various ways

 Massive links can be used to cluster objects: SimRank, LinkClus

11
Chapter 10. Cluster Analysis: Basic Concepts and
Methods

 Cluster Analysis: Basic Concepts

 Partitioning Methods
 Hierarchical Methods
 Density-Based Methods
 Grid-Based Methods
 Evaluation of Clustering
 Summary
12
 Partitioning Algorithms: Basic Concept
 Partitioning method: Partitioning a database D of n objects into a set of k
clusters, such that the sum of squared distances is minimized (where c i is
the centroid or medoid of cluster Ci)

E   ik1 pCi ( p  ci ) 2
 Given 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 (MacQueen’67, Lloyd’57/’82): Each cluster is represented by
the center of the cluster
 k-medoids or PAM (Partition around medoids) (Kaufman &
Rousseeuw’87): Each cluster is represented by one of the objects in
the cluster
13
 The K-Means Clustering Method

 Given k, the k-means algorithm is implemented in four

steps:
 Partition objects into k nonempty subsets
 Compute seed points as the centroids of the
clusters of the current partitioning (the centroid is
the center, i.e., mean point, of the cluster)
 Assign each object to the cluster with the nearest
seed point
 Go back to Step 2, stop when the assignment does
not change

14
 An Example of K-Means Clustering

K=2

Arbitrarily Update the

partition cluster
objects into centroids
k groups

The initial data set Loop if Reassign objects

needed
 Partition objects into k nonempty
subsets
 Repeat
 Compute centroid (i.e., mean Update the
cluster
point) for each partition centroids
 Assign each object to the
cluster of its nearest centroid
 Until no change
15
 Comments on the K-Means Method

 Strength: Efficient: O(tkn), where n is # objects, k is # clusters, and t is #

iterations. Normally, k, t << n.
 Comparing: PAM: O(k(n-k)2 ), CLARA: O(ks2 + k(n-k))
 Comment: Often terminates at a local optimal.
 Weakness
 Applicable only to objects in a continuous n-dimensional space
 Using the k-modes method for categorical data
 In comparison, k-medoids can be applied to a wide range of data
 Need to specify k, the number of clusters, in advance (there are
ways to automatically determine the best k (see Hastie et al., 2009)
 Sensitive to noisy data and outliers
 Not suitable to discover clusters with non-convex shapes

16
 Variations of the K-Means Method

 Most of the 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
 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: k-prototype method

17
 What Is the Problem of the K-Means Method?

 The k-means algorithm is sensitive to outliers !

 Since an object with an extremely large value may substantially
distort the distribution of the data
 K-Medoids: Instead of taking the mean value of the object in a cluster
as a reference point, medoids can be used, which is the most
centrally located object in a cluster

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

18
 PAM: A Typical K-Medoids Algorithm
Total Cost = 20
10 10 10

9 9 9

8 8 8

7 7 7

6
Arbitrary 6
Assign 6

5
choose k 5 each 5

4 object as 4 remainin 4

3
initial 3
g object 3

2
medoids 2
to 2

1 1
nearest
1

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

K=2 Randomly select a

Total Cost = 26 nonmedoid object,Oramdom
10 10

Do loop 9

8 Compute
9

8
Swapping O 7 total cost of 7

Until no and Oramdom 6

swapping 6

change
5 5

If quality is 4 4

improved. 3

2
3

1 1

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

19
 The K-Medoid Clustering Method

 K-Medoids Clustering: Find representative objects (medoids) in clusters

 PAM (Partitioning Around Medoids, Kaufmann & Rousseeuw 1987)
 Starts from an initial set of medoids and iteratively replaces one
of the medoids by one of the non-medoids 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 (due to the computational complexity)
 Efficiency improvement on PAM
 CLARA (Kaufmann & Rousseeuw, 1990): PAM on samples
 CLARANS (Ng & Han, 1994): Randomized re-sampling

20
Chapter 10. Cluster Analysis: Basic Concepts and
Methods
 Cluster Analysis: Basic Concepts
 Partitioning Methods
 Hierarchical Methods
 Density-Based Methods
 Grid-Based Methods
 Evaluation of Clustering
 Summary

21
 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
agglomerative
(AGNES)
a
ab
b abcde
c
cde
d
de
e
divisive
Step 4 Step 3 Step 2 Step 1 Step 0 (DIANA)
22
 AGNES (Agglomerative Nesting)
 Introduced in Kaufmann and Rousseeuw (1990)
 Implemented in statistical 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 10 10

9 9 9

8 8 8

7 7 7

6 6 6

5 5 5

4 4 4

3 3 3

2 2 2

1 1 1

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

23
Dendrogram: Shows How Clusters are Merged

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

24
 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 10
10

9 9
9
8 8
8

7 7
7

6 6
6

5 5
5
4 4
4

3 3
3

2 2
2

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

25
 Distance between Clusters X X

 Single link: smallest distance between an element in one cluster and an

element in the other, i.e., dist(Ki, Kj) = min(tip, tjq)

 Complete link: largest distance between an element in one cluster and

an element in the other, i.e., dist(Ki, Kj) = max(tip, tjq)

 Average: avg distance between an element in one cluster and an

element in the other, i.e., dist(Ki, Kj) = avg(tip, tjq)

 Centroid: distance between the centroids of two clusters, i.e., dist(Ki, Kj)
= dist(Ci, Cj)

 Medoid: distance between the medoids of two clusters, i.e., dist(Ki, Kj) =
dist(Mi, Mj)
 Medoid: a chosen, centrally located object in the cluster
26
 Centroid, Radius and Diameter of a Cluster
(for numerical data sets)
 Centroid: the “middle” of a cluster iN 1(t )
Cm  N
ip

 Radius: square root of average distance from any point

of the cluster to its centroid  N (t  cm ) 2
Rm  i 1 ip
N
 Diameter: square root of average mean squared
distance between all pairs of points in the cluster
 N  N (t  t ) 2
Dm  i 1 i 1 ip iq
N ( N 1)

27
 Extensions to Hierarchical Clustering
 Major weakness of agglomerative clustering methods
 Can never undo what was done previously
 Do not scale well: time complexity of at least O(n2), where n
is the number of total objects
 Integration of hierarchical & distance-based clustering
 BIRCH (1996): uses CF-tree and incrementally adjusts the
quality of sub-clusters
 CHAMELEON (1999): hierarchical clustering using
dynamic modeling
28
 BIRCH (Balanced Iterative Reducing and
Clustering Using Hierarchies)
 Zhang, Ramakrishnan & Livny, SIGMOD’96
 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
 Weakness: handles only numeric data, and sensitive to the order of the
data record

29
 Clustering Feature Vector in BIRCH

Clustering Feature (CF): CF = (N, LS, SS)

N: Number of data points
N
LS: linear sum of N points:  X i
i 1

CF = (5, (16,30),(54,190))
SS: square sum of N points
N 2 10
(3,4)
 Xi
9

(2,6)
8

i 1
7

(4,5)
5

1
(4,7)
(3,8)
0
0 1 2 3 4 5 6 7 8 9 10

30
 CF-Tree in BIRCH
 Clustering feature:
 Summary of the statistics for a given subcluster: the 0-th, 1st,

and 2nd moments of the subcluster from the statistical point of

view
 Registers crucial measurements for computing cluster and

utilizes storage efficiently

A CF tree is a height-balanced tree that stores the clustering
features for a hierarchical clustering
 A nonleaf node in a tree has descendants or “children”

 The nonleaf nodes store sums of the CFs of their children

 A CF tree has two parameters

 Branching factor: max # of children

 Threshold: max diameter of sub-clusters stored at the leaf

nodes
31
 The CF Tree Structure
Root

B=7 CF1 CF2 CF3 CF6

L=6 child1 child2 child3 child6

Non-leaf node
CF1 CF2 CF3 CF5
child1 child2 child3 child5

Leaf node Leaf node

prev CF1 CF2 CF6 next prev CF1 CF2 CF4 next

32
 The Birch Algorithm
 Cluster Diameter 1 2
 (x  x )
n( n  1) i j

 For each point in the input

 Find closest leaf entry

 Add point to leaf entry and update CF

 If entry diameter > max_diameter, then split leaf, and possibly parents

 Algorithm is O(n)
 Concerns
 Sensitive to insertion order of data points

 Since we fix the size of leaf nodes, so clusters may not be so natural

 Clusters tend to be spherical given the radius and diameter measures

33
 CHAMELEON: Hierarchical Clustering Using
Dynamic Modeling (1999)
 CHAMELEON: G. Karypis, E. H. Han, and V. Kumar, 1999
 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
 Graph-based, and 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
34
 Overall Framework of CHAMELEON

Construct (K-NN)
Sparse Graph Partition the Graph

Data Set

K-NN Graph
P and q are connected if Merge Partition
q is among the top k
closest neighbors of p
Relative interconnectivity:
connectivity of c1 and c2
over internal connectivity
Final Clusters
Relative closeness:
closeness of c1 and c2 over
internal closeness 35
CHAMELEON (Clustering Complex Objects)

36
 Probabilistic Hierarchical Clustering
 Algorithmic hierarchical clustering
 Nontrivial to choose a good distance measure
 Hard to handle missing attribute values
 Optimization goal not clear: heuristic, local search
 Probabilistic hierarchical clustering
 Use probabilistic models to measure distances between clusters
 Generative model: Regard the set of data objects to be clustered as
a sample of the underlying data generation mechanism to be
analyzed
 Easy to understand, same efficiency as algorithmic agglomerative
clustering method, can handle partially observed data
 In practice, assume the generative models adopt common distributions
functions, e.g., Gaussian distribution or Bernoulli distribution, governed
by parameters
37
 Generative Model
 Given a set of 1-D points X = {x1, …, xn} for clustering
analysis & assuming they are generated by a
Gaussian distribution:

 The probability that a point xi ∈ X is generated by the

model

 The likelihood that X is generated by the model:

 The task of learning the generative model: find the

the maximum likelihood
parameters μ and σ such that
2

38
 A Probabilistic Hierarchical Clustering Algorithm

 For a set of objects partitioned into m clusters C1, . . . ,Cm, the quality can
be measured by,

where P() is the maximum likelihood

 Distance between clusters C1 and C2:
 Algorithm: Progressively merge points and clusters
Input: D = {o1, ..., on}: a data set containing n objects
Output: A hierarchy of clusters
Method
Create a cluster for each object Ci = {oi}, 1 ≤ i ≤ n;
For i = 1 to n {
Find pair of clusters Ci and Cj such that
Ci,Cj = argmaxi ≠ j {log (P(Ci∪Cj )/(P(Ci)P(Cj ))};
If log (P(Ci∪Cj )/(P(Ci)P(Cj )) > 0 then merge Ci and Cj }
39
Chapter 10. Cluster Analysis: Basic Concepts and
Methods
 Cluster Analysis: Basic Concepts
 Partitioning Methods
 Hierarchical Methods
 Density-Based Methods
 Grid-Based Methods
 Evaluation of Clustering
 Summary

40
 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. (KDD’96)

 OPTICS: Ankerst, et al (SIGMOD’99).

 DENCLUE: Hinneburg & D. Keim (KDD’98)

 CLIQUE: Agrawal, et al. (SIGMOD’98) (more grid-based)

41
 Density-Based Clustering: Basic Concepts
 Two parameters:
 Eps: Maximum radius of the neighbourhood
 MinPts: Minimum number of points in an Eps-
neighbourhood of that point
 NEps(p): {q belongs to D | dist(p,q) ≤ Eps}
 Directly density-reachable: A point p is directly density-
reachable from a point q w.r.t. Eps, MinPts if
 p belongs to NEps(q)
p MinPts = 5
 core point condition:
Eps = 1 cm
|NEps (q)| ≥ MinPts q

42
 Density-Reachable and Density-Connected
 Density-reachable:
 A point p is density-reachable from a p
point q w.r.t. Eps, MinPts if there is a
p1
chain of points p1, …, pn, p1 = q, pn = q
p such that pi+1 is directly density-
reachable from pi
 Density-connected
 A point p is density-connected to a p q
point q w.r.t. Eps, MinPts if there is a
point o such that both, p and q are o
density-reachable from o w.r.t. Eps
and MinPts
43
 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
Eps = 1cm
Core MinPts = 5

44
 DBSCAN: The Algorithm
 Arbitrary select a point p
 Retrieve all points density-reachable from p w.r.t. 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

45
DBSCAN: Sensitive to Parameters

46
 OPTICS: A Cluster-Ordering Method (1999)

 OPTICS: Ordering Points To Identify the Clustering

Structure
 Ankerst, Breunig, Kriegel, and Sander (SIGMOD’99)

 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
47
 OPTICS: Some Extension from DBSCAN
 Index-based:
 k = number of dimensions
 N = 20
 p = 75% D
M = N(1-p) = 5
 Complexity: O(NlogN)

 Core Distance: p1
 min eps s.t. point is core

 Reachability Distance o
p2
o
Max (core-distance (o), d (o, p)) MinPts = 5
r(p1, o) = 2.8cm. r(p2,o) = 4cm  = 3 cm 48
 Reachability
-distance

undefined


 ‘

Cluster-order
of the objects 49
Density-Based Clustering: OPTICS & Its Applications

50
 DENCLUE: Using Statistical Density Functions

 DENsity-based CLUstEring by Hinneburg & Keim (KDD’98)

total influence
 Using statistical density functions: on x
d ( x , xi ) 2
d ( x,y) 2 
( x )  i 1 e
D N 2

f Gaussian ( x , y )  e

2 2 f Gaussian
2

d ( x , xi ) 2
influence of y 
( x, xi )  i 1 ( xi  x)  e
D N
2 2
on x f Gaussian
 Major features
gradient of x in
 Solid mathematical foundation the direction of
xi
 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 (e.g., DBSCAN)
 But needs a large number of parameters
51
 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
 Center defined clusters: assign to each density attractor the points
density attracted to it
 Arbitrary shaped cluster: merge density attractors that are connected
through paths of high density (> threshold)

52
Density Attractor

53
Center-Defined and Arbitrary

54
Chapter 10. Cluster Analysis: Basic Concepts and
Methods
 Cluster Analysis: Basic Concepts
 Partitioning Methods
 Hierarchical Methods
 Density-Based Methods
 Grid-Based Methods
 Evaluation of Clustering
 Summary

55
 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 (VLDB’98)
 A multi-resolution clustering approach using
wavelet method
 CLIQUE: Agrawal, et al. (SIGMOD’98)
 Both grid-based and subspace clustering

56
 STING: A Statistical Information Grid Approach
 Wang, Yang and Muntz (VLDB’97)
 The spatial area is divided into rectangular cells
 There are several levels of cells corresponding to different
levels of resolution

1st layer

(i-1)st layer

i-th layer

57
 The STING Clustering Method
 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 distribution—normal, uniform, etc.

 Use a top-down approach to answer spatial data queries

 Start from a pre-selected layer—typically with a small
number of cells
 For each cell in the current level compute the confidence
interval
58
 STING Algorithm and Its Analysis
 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

59
 CLIQUE (Clustering In QUEst)

 Agrawal, Gehrke, Gunopulos, Raghavan (SIGMOD’98)

 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 grid-based
 It partitions each dimension into the same number of equal length
interval
 It partitions an m-dimensional data space into non-overlapping
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
60
 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

61
 Salary
(10,000)

=3
0 1 2 3 4 5 6 7

20
30
40
50

Sa
l ar
y
Vacation
60
age

30
Vacation
50
(week)
0 1 2 3 4 5 6 7
20
30
40

age
50
60
age

62
 Strength and Weakness of CLIQUE

 Strength
 automatically finds subspaces of the highest

dimensionality such that high density clusters exist in

those subspaces
 insensitive to the order of records in input and does not

presume some canonical data distribution

 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

63
Chapter 10. Cluster Analysis: Basic Concepts and
Methods

 Cluster Analysis: Basic Concepts

 Partitioning Methods
 Hierarchical Methods
 Density-Based Methods
 Grid-Based Methods
 Evaluation of Clustering
 Summary
64
 Assessing Clustering Tendency
 Assess if non-random structure exists in the data by measuring the
probability that the data is generated by a uniform data distribution
 Test spatial randomness by statistic test: Hopkins Static
 Given a dataset D regarded as a sample of a random variable o,

determine how far away o is from being uniformly distributed in the

data space
 Sample n points, p , …, p , uniformly from D. For each p , find its
1 n i
nearest neighbor in D: xi = min{dist (pi, v)} where v in D
 Sample n points, q1, …, qn, uniformly from D. For each qi, find its
nearest neighbor in D – {qi}: yi = min{dist (qi, v)} where v in D and v ≠
qi
 Calculate the Hopkins Statistic:

 If D is uniformly distributed, ∑ xi and ∑ yi will be close to each other

and H is close to 0.5. If D is highly skewed, H is close to 0
65
 Determine the Number of Clusters
 Empirical method
 # of clusters ≈√n/2 for a dataset of n points

 Elbow method
 Use the turning point in the curve of sum of within cluster variance

w.r.t the # of clusters

 Cross validation method
 Divide a given data set into m parts

 Use m – 1 parts to obtain a clustering model

 Use the remaining part to test the quality of the clustering

 E.g., For each point in the test set, find the closest centroid, and

use the sum of squared distance between all points in the test
set and the closest centroids to measure how well the model fits
the test set
 For any k > 0, repeat it m times, compare the overall quality measure

w.r.t. different k’s, and find # of clusters that fits the data the best
66
 Measuring Clustering Quality

 Two methods: extrinsic vs. intrinsic

 Extrinsic: supervised, i.e., the ground truth is available
 Compare a clustering against the ground truth using
certain clustering quality measure
 Ex. BCubed precision and recall metrics
 Intrinsic: unsupervised, i.e., the ground truth is unavailable
 Evaluate the goodness of a clustering by considering
how well the clusters are separated, and how compact
the clusters are
 Ex. Silhouette coefficient
67
Measuring Clustering Quality: Extrinsic Methods

 Clustering quality measure: Q(C, Cg), for a clustering C

given the ground truth Cg.
 Q is good if it satisfies the following 4 essential criteria
 Cluster homogeneity: the purer, the better

 Cluster completeness: should assign objects belong to

the same category in the ground truth to the same cluster

 Rag bag: putting a heterogeneous object into a pure

cluster should be penalized more than putting it into a rag

bag (i.e., “miscellaneous” or “other” category)
 Small cluster preservation: splitting a small category into

pieces is more harmful than splitting a large category into

pieces

68
Chapter 10. Cluster Analysis: Basic Concepts and
Methods

 Cluster Analysis: Basic Concepts

 Partitioning Methods
 Hierarchical Methods
 Density-Based Methods
 Grid-Based Methods
 Evaluation of Clustering
 Summary
69
 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
 K-means and K-medoids algorithms are popular partitioning-based
clustering algorithms
 Birch and Chameleon are interesting hierarchical clustering
algorithms, and there are also probabilistic hierarchical clustering
algorithms
 DBSCAN, OPTICS, and DENCLU are interesting density-based
algorithms
 STING and CLIQUE are grid-based methods, where CLIQUE is also a
subspace clustering algorithm
 Quality of clustering results can be evaluated in various ways
70
 CS512-Spring 2011: An Introduction
 Coverage
 Cluster Analysis: Chapter 11
 Outlier Detection: Chapter 12
 Mining Sequence Data: BK2: Chapter 8
 Mining Graphs Data: BK2: Chapter 9
 Social and Information Network Analysis
 BK2: Chapter 9
 Partial coverage: Mark Newman: “Networks: An Introduction”, Oxford U., 2010
 Scattered coverage: Easley and Kleinberg, “Networks, Crowds, and Markets:
Reasoning About a Highly Connected World”, Cambridge U., 2010
 Recent research papers
 Mining Data Streams: BK2: Chapter 8
 Requirements
 One research project
 One class presentation (15 minutes)
 Two homeworks (no programming assignment)
 Two midterm exams (no final exam)
71
 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, SIGMOD’99.
 Beil F., Ester M., Xu X.: "Frequent Term-Based Text Clustering", KDD'02
 M. M. Breunig, H.-P. Kriegel, R. Ng, J. Sander. LOF: Identifying Density-Based
Local Outliers. SIGMOD 2000.
 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. VLDB’98.
 V. Ganti, J. Gehrke, R. Ramakrishan. CACTUS Clustering Categorical Data
Using Summaries. KDD'99.
72
 References (2)
 D. Gibson, J. Kleinberg, and P. Raghavan. Clustering categorical data: An
approach based on dynamic systems. In Proc. VLDB’98.
 S. Guha, R. Rastogi, and K. Shim. Cure: An efficient clustering algorithm for
large databases. SIGMOD'98.
 S. Guha, R. Rastogi, and K. Shim. ROCK: A robust clustering algorithm for
categorical attributes. In ICDE'99, pp. 512-521, Sydney, Australia, March
1999.
 A. Hinneburg, D.l A. Keim: An Efficient Approach to Clustering in Large
Multimedia Databases with Noise. KDD’98.
 A. K. Jain and R. C. Dubes. Algorithms for Clustering Data. Printice Hall, 1988.
 G. Karypis, E.-H. Han, and V. Kumar. CHAMELEON: A Hierarchical Clustering
Algorithm Using Dynamic Modeling. COMPUTER, 32(8): 68-75, 1999.
 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. VLDB’98.

73
 References (3)
 G. J. McLachlan and K.E. Bkasford. Mixture Models: Inference and Applications to
Clustering. John Wiley and Sons, 1988.
 R. Ng and J. Han. Efficient and effective clustering method for spatial data mining.
VLDB'94.
 L. Parsons, E. Haque and H. Liu, Subspace Clustering for High Dimensional Data: A
Review, SIGKDD Explorations, 6(1), June 2004
 E. Schikuta. Grid clustering: An efficient hierarchical clustering method for very large
data sets. Proc. 1996 Int. Conf. on Pattern Recognition
 G. Sheikholeslami, S. Chatterjee, and A. Zhang. WaveCluster: A multi-resolution
clustering approach for very large spatial databases. VLDB’98.
 A. K. H. Tung, J. Han, L. V. S. Lakshmanan, and R. T. Ng. Constraint-Based Clustering
in Large Databases, ICDT'01.
 A. K. H. Tung, J. Hou, and J. Han. Spatial Clustering in the Presence of Obstacles,
ICDE'01
 H. Wang, W. Wang, J. Yang, and P.S. Yu. Clustering by pattern similarity in large data
sets,  SIGMOD’02
 W. Wang, Yang, R. Muntz, STING: A Statistical Information grid Approach to Spatial
Data Mining, VLDB’97
 T. Zhang, R. Ramakrishnan, and M. Livny. BIRCH : An efficient data clustering method
for very large databases. SIGMOD'96
 X. Yin, J. Han, and P. S. Yu, “LinkClus: Efficient Clustering via Heterogeneous Semantic
Links”, VLDB'06

74
Slides unused in class

75
 A Typical K-Medoids Algorithm (PAM)
Total Cost = 20
10 10 10

9 9 9

8 8 8

7 7 7

6
Arbitrary 6
Assign 6

5
choose k 5 each 5

4 object as 4 remainin 4

3
initial 3
g object 3

2
medoids 2
to 2

1 1
nearest
1

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

K=2 Randomly select a

Total Cost = 26 nonmedoid object,Oramdom
10 10

Do loop 9

8 Compute
9

8
Swapping O 7 total cost of 7

Until no and Oramdom 6

swapping 6

change
5 5

If quality is 4 4

improved. 3

2
3

1 1

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

76
 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
 repeat steps 2-3 until there is no change
77
 PAM Clustering: Finding the Best Cluster Center

 Case 1: p currently belongs to oj. If oj is replaced by orandom as a

representative object and p is the closest to one of the other
representative object oi, then p is reassigned to oi

78
 What Is the Problem with PAM?

 Pam is more robust than k-means in the presence of

noise and outliers because a medoid is less influenced by
outliers or other extreme values than a mean
 Pam works efficiently for small data sets but does not
scale well for large data sets.
 O(k(n-k)2 ) for each iteration
where n is # of data,k is # of clusters
 Sampling-based method
CLARA(Clustering LARge Applications)

79
 CLARA (Clustering Large Applications) (1990)

 CLARA (Kaufmann and Rousseeuw in 1990)

 Built in statistical analysis packages, such as SPlus
 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
80
 CLARANS (“Randomized” CLARA) (1994)
 CLARANS (A Clustering Algorithm based on Randomized
Search) (Ng and Han’94)
 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, it starts with new randomly

selected node in search for a new local optimum

 Advantages: More efficient and scalable than both PAM
and CLARA
 Further improvement: Focusing techniques and spatial
access structures (Ester et al.’95)

81
 ROCK: Clustering Categorical Data

 ROCK: RObust Clustering using linKs

 S. Guha, R. Rastogi & K. Shim, ICDE’99

 Major ideas
 Use links to measure similarity/proximity

 Not distance-based

 Algorithm: sampling-based clustering

 Draw random sample

 Cluster with links

 Label data in disk

 Experiments
 Congressional voting, mushroom data

82
 Similarity Measure in ROCK
 Traditional measures for categorical data may not work well, e.g.,
Jaccard coefficient
 Example: Two groups (clusters) of transactions
 C1. <a, b, c, d, e>: {a, b, c}, {a, b, d}, {a, b, e}, {a, c, d}, {a, c, e},
{a, d, e}, {b, c, d}, {b, c, e}, {b, d, e}, {c, d, e}
 C2. <a, b, f, g>: {a, b, f}, {a, b, g}, {a, f, g}, {b, f, g}
 Jaccard co-efficient may lead to wrong clustering result
 C1: 0.2 ({a, b, c}, {b, d, e}} to 0.5 ({a, b, c}, {a, b, d})
 C1 & C2: could be as high as 0.5 ({a, b, c}, {a, b, f})
 Jaccard co-efficient-based similarity function: Sim( T1 , T2 )  T1  T2
T1  T2
 Ex. Let T1 = {a, b, c}, T2 = {c, d, e}
{c} 1
Sim(T 1, T 2)    0.2
{a, b, c, d , e} 5

83
 Link Measure in ROCK
 Clusters

C1:<a, b, c, d, e>: {a, b, c}, {a, b, d}, {a, b, e}, {a, c, d}, {a, c, e}, {a, d, e}, {b,
c, d}, {b, c, e}, {b, d, e}, {c, d, e}

C2: <a, b, f, g>: {a, b, f}, {a, b, g}, {a, f, g}, {b, f, g}
 Neighbors

Two transactions are neighbors if sim(T 1,T2) > threshold
 Let T1 = {a, b, c}, T2 = {c, d, e}, T3 = {a, b, f}

T1 connected to: {a,b,d}, {a,b,e}, {a,c,d}, {a,c,e}, {b,c,d}, {b,c,e}, {a,b,f},
{a,b,g}

T2 connected to: {a,c,d}, {a,c,e}, {a,d,e}, {b,c,e}, {b,d,e}, {b,c,d}

T3 connected to: {a,b,c}, {a,b,d}, {a,b,e}, {a,b,g}, {a,f,g}, {b,f,g}
 Link Similarity
 Link similarity between two transactions is the # of common neighbors
 link(T1, T2) = 4, since they have 4 common neighbors
 {a, c, d}, {a, c, e}, {b, c, d}, {b, c, e}
 link(T1, T3) = 3, since they have 3 common neighbors
 {a, b, d}, {a, b, e}, {a, b, g}
84
 Aggregation-Based Similarity Computation
0.2
4 5 ST2
0.9 1.0 0.8 0.9 1.0
10 11 12 13 14

a b ST1
For each node nk ∈ {n10, n11, n12} and nl ∈ {n13, n14}, their path-
based similarity simp(nk, nl) = s(nk, n4)·s(n4, n5)·s(n5, nl).

k 10 snk , n4   s nl , n5 

12 14

simna , nb    sn , n 
4 5
l 13
 0.171
3 2

takes O(3+2) time

After aggregation, we reduce quadratic time computation to linear
time computation.

86
 Computing Similarity with Aggregation
Average similarity a: b:(0.95,2)
and total weight (0.9,3) 0.2
4 5

sim(na, nb) can be computed 10 11 12 13 14

from aggregated similarities
a b

sim(na, nb) = avg_sim(na,n4) x s(n4, n5) x avg_sim(nb,n5)

= 0.9 x 0.2 x 0.95 = 0.171
To compute sim(na,nb):
 Find all pairs of sibling nodes ni and nj, so that na linked with ni and nb with
nj.
 Calculate similarity (and weight) between na and nb w.r.t. ni and nj.
 Calculate weighted average similarity between na and nb w.r.t. all such pairs.

87
Chapter 10. Cluster Analysis: Basic Concepts and
Methods

 Cluster Analysis: Basic Concepts

 Overview of Clustering Methods
 Partitioning Methods
 Hierarchical Methods
 Density-Based Methods
 Grid-Based Methods
 Summary
88
 Link-Based Clustering: Calculate Similarities Based
On Links
Authors Proceedings Conferences
 The similarity between two
Tom sigmod03
objects x and y is defined as
sigmod04 sigmod the average similarity between
Mike sigmod05 objects linked with x and those
vldb03 with y:
Cathy
vldb04 vldb C
I a  I b 

John vldb05 sima, b  

I a  I b 
  simI a , I b 
i 1 j 1
i j

aaai04
aaai
Mary aaai05  Issue: Expensive to compute:
 For a dataset of N objects
Jeh & Widom, KDD’2002: SimRank
Two objects are similar if they are and M links, it takes O(N2)
linked with the same or similar space and O(M2) time to
objects compute all similarities.

89
 Observation 1: Hierarchical Structures

 Hierarchical structures often exist naturally among objects

(e.g., taxonomy of animals)
Relationships between articles and
A hierarchical structure of words (Chakrabarti, Papadimitriou,
products in Walmart Modha, Faloutsos, 2004)

All

Articles
grocery electronics apparel

TV DVD camera

Words
90
 Observation 2: Distribution of Similarity
0.4

Distribution of SimRank similarities

portion of entries

0.3
among DBLP authors
0.2

0.1

0
0.02

0.04

0.06

0.08

0.12

0.14

0.16

0.18

0.22

0.24
0.1

0.2
0

similarity value

 Power law distribution exists in similarities

 56% of similarity entries are in [0.005, 0.015]

 1.4% of similarity entries are larger than 0.1

 Can we design a data structure that stores the significant

similarities and compresses insignificant ones?

91
 A Novel Data Structure: SimTree
Each leaf node Each non-leaf node
represents an object represents a group
of similar lower-level
nodes
Similarities between
siblings are stored

Canon A40
digital camera
Digital
Sony V3 digital Cameras
Consumer Apparels
camera
electronics
TVs

92
 Similarity Defined by SimTree
Similarity between two
sibling nodes n1 and n2

n1 0.2 n2 n3

0.8 0.9 0.9

Adjustment ratio
for node n7 n4 0.3 n5 n6
0.9 0.8 1.0

n7 n8 n9
 Path-based node similarity
 simp(n7,n8) = s(n7, n4) x s(n4, n5) x s(n5, n8)
 Similarity between two nodes is the average similarity
between objects linked with them in other SimTrees
Average similarity between x and all other nodes
 Adjust/ ratio for x = Average similarity between x’s parent and all other nodes

93
LinkClus: Efficient Clustering via Heterogeneous
Semantic Links
Method
 Initialize a SimTree for objects of each type

 Repeat until stable

 For each SimTree, update the similarities between its

nodes using similarities in other SimTrees

 Similarity between two nodes x and y is the average

similarity between objects linked with them

 Adjust the structure of each SimTree

 Assign each node to the parent node that it is most

similar to
For details: X. Yin, J. Han, and P. S. Yu, “LinkClus: Efficient
Clustering via Heterogeneous Semantic Links”, VLDB'06
94
 Initialization of SimTrees
 Initializing a SimTree
 Repeatedly find groups of tightly related nodes, which

are merged into a higher-level node

 Tightness of a group of nodes
 For a group of nodes {n , …, n }, its tightness is
1 k
defined as the number of leaf nodes in other SimTrees
that are connected to all of {n1, …, nk}
Nodes Leaf nodes in
another
n1 1
SimTree
2
3 The tightness of {n1, n2} is 3
n2 4
5

95
 Finding Tight Groups by Freq. Pattern Mining
 Finding tight groups Frequent pattern mining
Reduced to
Transactions
n1 1 {n1}
The tightness of a g1 2 {n1, n2}
group of nodes is the n2 3 {n2}
4 {n1, n2}
support of a frequent 5 {n1, n2}
pattern n3 6 {n2, n3,
g2 7 n4}
{n4}
n4 8 {n3, n4}
9 {n3, n4}
 Procedure of initializing a tree
 Start from leaf nodes (level-0)

 At each level l, find non-overlapping groups of similar

nodes with frequent pattern mining

96
 Adjusting SimTree Structures

n1 n2 n3

0.9
n4 n5 n6
0.8

n7 n7 n8 n9

 After similarity changes, the tree structure also needs to be

changed
 If a node is more similar to its parent’s sibling, then move

it to be a child of that sibling

 Try to move each node to its parent’s sibling that it is most

similar to, under the constraint that each parent node can
have at most c children
97
 Complexity

For two types of objects, N in each, and M linkages between them.

Time Space
Updating similarities O(M(logN)2) O(M+N)
Adjusting tree structures O(N) O(N)

LinkClus O(M(logN)2) O(M+N)

SimRank O(M2) O(N2)

98
 Experiment: Email Dataset
 F. Nielsen. Email dataset. Approach Accuracy time (s)
www.imm.dtu.dk/~rem/data/Email-1431.zip
 370 emails on conferences, 272 on jobs,
LinkClus 0.8026 1579.6
and 789 spam emails SimRank 0.7965 39160
 Accuracy: measured by manually labeled ReCom 0.5711 74.6
data
F-SimRank 0.3688 479.7
 Accuracy of clustering: % of pairs of objects
in the same cluster that share common label CLARANS 0.4768 8.55
 Approaches compared:
 SimRank (Jeh & Widom, KDD 2002): Computing pair-wise similarities
 SimRank with FingerPrints (F-SimRank): Fogaras & R´acz, WWW 2005
 pre-computes a large sample of random paths from each object and uses
samples of two objects to estimate SimRank similarity
 ReCom (Wang et al. SIGIR 2003)
 Iteratively clustering objects using cluster labels of linked objects

99
 WaveCluster: Clustering by Wavelet Analysis (1998)

 Sheikholeslami, Chatterjee, and Zhang (VLDB’98)

 A multi-resolution clustering approach which applies wavelet transform to
the feature space; both grid-based and density-based
 Wavelet transform: A signal processing technique that decomposes a signal
into different frequency sub-band
 Data are transformed to preserve relative distance between objects at

different levels of resolution

 Allows natural clusters to become more distinguishable

100
 The WaveCluster Algorithm
 How to apply wavelet transform to find clusters
 Summarizes 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

 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

101
 Quantization
& Transformation
 Quantize data into m-D grid structure,
then wavelet transform
a) scale 1: high resolution
b) scale 2: medium resolution
c) scale 3: low resolution

102