Data Mining Techniques Clustering

1
Data Mining Techniques Clustering
2
Purpose

• In clustering analysis, there is no
  pre-classified data
• Instead, clustering analysis is a process where a
  set of objects is partitioned into several
  clusters
• All members in one cluster are similar to each
  other and different from the members of other
  clusters, according to some similarity metric
  (e.g., the opposite of distance between objects)

3
Cluster Analysis
Cluster
Y (Age)
Customer (Object)
X (Income)
Variables
4
Cluster Analysis
n objetcs p variables
Data Matrix
Dissimilarity Matrix (n?n)
5
Attribute Types Involved in Cluster Analysis

• Interval Variables
• An interval variable contains continuous
  measurements (e.g., height, weight, temperature,
  cost, etc.) which follow a linear scale
• It is essential that intervals keep the same
  importance throughout the scale
• Nominal Variables
• A nominal variable takes on more than two states.
  For example, the eye color of a person can be
  blue, brown, green or grey eyes
• These states may be coded as 1, 2, ..., M,
  however their order and the interval between any
  two states do not have any meaning

6
Attribute Types Involved in Cluster Analysis

• Ordinal Variables
• An ordinal variable takes on more than two
  states. For example, you may ask someone to
  convey his/her appreciation of some paintings in
  terms of the following categories 1detest,
  2dislike, 3indifferent, 4like and 5admire
• In an ordinal variable, their states are ordered
  in a meaningful sequence. However, the interval
  between any two consecutive states are not
  equally distanced
• Binary Variables
• Binary variables have only two possible states.
  For example, the gender of a person is either
  female or male

7
Dissimilarity (Distance) Measure
8
Dissimilarity (Distance) Measure
9
Dissimilarity (Distance) Measure
10
Dissimilarity (Distance) Measure
11
Dissimilarity (Distance) Measure
12
Dissimilarity (Distance) Measure
13
Dissimilarity (Distance) Measure
14
Dissimilarity (Distance) Measure
15
Dissimilarity (Distance) Measure
16
Categorization of Clustering Methods

• Exclusive vs. Non-Exclusive (Overlapping)
• Hierarchical Methods vs. Partitioning Methods
• Hierarchical Methods
• Single Link Method
• Complete Link Method
• Partitioning Methods
• Kohonen Self-Organizing Feature Maps
• K-Means Methods
• K-Medoids Methods (PAM, CLARA, CLARANS)
• Density-Based Methods

17
Hierarchical Methods
Dissimilarity Matrix (5?5)
18
K-Means Methods
19
K-Means Methods
20
K-Means Methods
21
K-Means Methods
Sensitive to Outlier!
22
Exercise 7
Number
of clusters 2 Using Single Link, Complete Link
and K-Means to cluster the following data
Object X Y
1 22 60
2 40 25
3 60 30
4 64 66
5 80 30
6 82 55