jianping fan department of computer science unc-charlotte density-based data clustering algorithms:...
TRANSCRIPT
![Page 1: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/1.jpg)
Jianping FanDepartment of Computer Science UNC-Charlotte
Density-Based Data Clustering Algorithms: K-Means & Others
![Page 2: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/2.jpg)
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
Inter-cluster distances are maximized
Intra-cluster distances are
minimized
What are key issues here?
![Page 3: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/3.jpg)
APPLICATIONS OF CLUSTER ANALYSIS Understanding
Group related documents for browsing, group genes and proteins that have similar functionality, or group stocks with similar price fluctuations
Summarization Reduce the size of large
data sets
Discovered Clusters Industry Group
1 Applied-Matl-DOWN,Bay-Network-Down,3-COM-DOWN,
Cabletron-Sys-DOWN,CISCO-DOWN,HP-DOWN, DSC-Comm-DOWN,INTEL-DOWN,LSI-Logic-DOWN,
Micron-Tech-DOWN,Texas-Inst-Down,Tellabs-Inc-Down, Natl-Semiconduct-DOWN,Oracl-DOWN,SGI-DOWN,
Sun-DOWN
Technology1-DOWN
2 Apple-Comp-DOWN,Autodesk-DOWN,DEC-DOWN,
ADV-Micro-Device-DOWN,Andrew-Corp-DOWN, Computer-Assoc-DOWN,Circuit-City-DOWN,
Compaq-DOWN, EMC-Corp-DOWN, Gen-Inst-DOWN, Motorola-DOWN,Microsoft-DOWN,Scientific-Atl-DOWN
Technology2-DOWN
3 Fannie-Mae-DOWN,Fed-Home-Loan-DOWN, MBNA-Corp-DOWN,Morgan-Stanley-DOWN
Financial-DOWN
4 Baker-Hughes-UP,Dresser-Inds-UP,Halliburton-HLD-UP,
Louisiana-Land-UP,Phillips-Petro-UP,Unocal-UP, Schlumberger-UP
Oil-UP
Clustering precipitation in Australia
Why?
![Page 4: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/4.jpg)
NOTION OF A CLUSTER CAN BE AMBIGUOUS
How many clusters?
Four Clusters Two Clusters
Six Clusters
Why it is ambiguous?
![Page 5: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/5.jpg)
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
a. K centroids b. Similarity functionc. Objective function for optimization
Key Issues for K-Means:
![Page 6: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/6.jpg)
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’ Complexity is O( n * K * I * d )
n = number of points, K = number of clusters, I = number of iterations, d = number of attributes
![Page 7: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/7.jpg)
EVALUATING K-MEANS CLUSTERS
K
i Cxi
i
xmdistSSE1
2 ),(
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
can show that mi corresponds 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
![Page 8: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/8.jpg)
K-MEANS Given a set of observations (x1, x2, …, xn), where
each observation is a d-dimensional real vector, k-means clustering aims to partition the n observations into k (≤ n) sets S = {S1, S2, …, Sk}
so as to minimize the within-cluster sum of squares (WCSS). In other words, its objective is to find:
where μi is the mean of points in Si.
![Page 9: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/9.jpg)
K-MEANS Given an initial set of k means m1
(1),…,mk(1) , the
algorithm proceeds by alternating between two steps:
Assignment step: Assign each observation to the cluster whose mean yields the least within-cluster sum of squares (WCSS). Since the sum of squares is the squared Euclidean distance, this is intuitively the "nearest" mean.
Update step: Calculate the new means to be the centroids of the observations in the new clusters.
![Page 10: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/10.jpg)
TWO DIFFERENT K-MEANS CLUSTERINGS
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Sub-optimal Clustering
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Optimal Clustering
Original Points
![Page 11: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/11.jpg)
IMPORTANCE OF CHOOSING INITIAL CENTROIDS
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
yIteration 1
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
yIteration 2
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
yIteration 3
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
yIteration 4
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
yIteration 5
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
yIteration 6
![Page 12: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/12.jpg)
IMPORTANCE OF CHOOSING INITIAL CENTROIDS
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Iteration 1
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Iteration 2
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Iteration 3
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Iteration 4
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Iteration 5
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Iteration 6
![Page 13: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/13.jpg)
IMPORTANCE OF CHOOSING INITIAL CENTROIDS …
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
yIteration 1
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
yIteration 2
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
yIteration 3
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
yIteration 4
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
yIteration 5
![Page 14: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/14.jpg)
IMPORTANCE OF CHOOSING INITIAL CENTROIDS …
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Iteration 1
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Iteration 2
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Iteration 3
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Iteration 4
-2 -1.5 -1 -0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
x
y
Iteration 5
![Page 15: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/15.jpg)
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
![Page 16: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/16.jpg)
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
Postprocessing Bisecting K-means
Not as susceptible to initialization issues
![Page 17: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/17.jpg)
BISECTING K-MEANS Bisecting K-means algorithm
Variant of K-means that can produce a partitional or a hierarchical clustering
![Page 18: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/18.jpg)
BISECTING K-MEANS EXAMPLE
![Page 19: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/19.jpg)
LIMITATIONS OF K-MEANS: DIFFERING SIZES
Original Points K-means (3 Clusters)
![Page 20: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/20.jpg)
LIMITATIONS OF K-MEANS: DIFFERING DENSITY
Original Points K-means (3 Clusters)
![Page 21: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/21.jpg)
LIMITATIONS OF K-MEANS: NON-GLOBULAR SHAPES
Original Points K-means (2 Clusters)
![Page 22: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/22.jpg)
OVERCOMING K-MEANS LIMITATIONS
Original Points K-means Clusters
One solution is to use many clusters.Find parts of clusters, but need to put together.
![Page 23: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/23.jpg)
OVERCOMING K-MEANS LIMITATIONS
Original Points K-means Clusters
![Page 24: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/24.jpg)
OVERCOMING K-MEANS LIMITATIONS
Original Points K-means Clusters
![Page 25: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/25.jpg)
ISSUES AND LIMITATIONS FOR K-MEANS
How to choose initial centers? How to choose K? How to handle Outliers? Clusters different in
Shape Density Size
![Page 26: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/26.jpg)
TYPES OF CLUSTERINGS
A clustering is a set of clusters
Important distinction between hierarchical and partitional sets of clusters
Partitional Clustering A division data objects into non-overlapping subsets
(clusters) such that each data object is in exactly one subset
Hierarchical Clustering A set of nested clusters organized as a hierarchical
tree
![Page 27: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/27.jpg)
PARTITIONAL CLUSTERING
Original PointsA Partitional Clustering
Three critical issues for clustering: a. Similarity functionb. Decision thresholdc. Objective function for optimization
![Page 28: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/28.jpg)
HIERARCHICAL CLUSTERING
p4p1
p3
p2
p4 p1
p3
p2
p4p1 p2 p3
p4p1 p2 p3
Traditional Hierarchical Clustering
Non-traditional Hierarchical Clustering Non-traditional Dendrogram
Traditional Dendrogram
![Page 29: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/29.jpg)
OTHER DISTINCTIONS BETWEEN SETS OF CLUSTERS
Exclusive versus non-exclusive In non-exclusive clustering, points may belong to
multiple clusters. Can represent multiple classes or ‘border’ points
Fuzzy versus non-fuzzy In fuzzy clustering, a point belongs to every cluster
with some weight between 0 and 1 Weights must sum to 1 Probabilistic clustering has similar characteristics
Partial versus complete In some cases, we only want to cluster some of the
data Heterogeneous versus homogeneous
Cluster of widely different sizes, shapes, and densities
![Page 30: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/30.jpg)
HIERARCHICAL CLUSTERING
Produces a set of nested clusters organized as a hierarchical tree
Can be visualized as a dendrogram A tree like diagram that records the sequences of
merges or splits
1 3 2 5 4 60
0.05
0.1
0.15
0.2
1
2
3
4
5
6
1
23 4
5
![Page 31: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/31.jpg)
STRENGTHS OF HIERARCHICAL CLUSTERING Do not have to assume any particular
number of clusters Any desired number of clusters can be obtained
by ‘cutting’ the dendogram at the proper level
They may correspond to meaningful taxonomies Example in biological sciences (e.g., animal
kingdom, phylogeny reconstruction, …)
It has to pre-define branches (number of child nodes)!
![Page 32: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/32.jpg)
HIERARCHICAL CLUSTERING
Two main types of hierarchical clustering Agglomerative:
Start with the points as individual clusters At each step, merge the closest pair of clusters until
only one cluster (or k clusters) left
Divisive: Start with one, all-inclusive cluster At each step, split a cluster until each cluster contains
a point (or there are k clusters)
Traditional hierarchical algorithms use a similarity or distance matrix Merge or split one cluster at a time
![Page 33: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/33.jpg)
AGGLOMERATIVE CLUSTERING ALGORITHM
More popular hierarchical clustering technique
Basic algorithm is straightforward1. Compute the proximity matrix2. Let each data point be a cluster3. Repeat4. Merge the two closest clusters5. Update the proximity matrix6. Until only a single cluster remains
Key operation is the computation of the proximity of two clusters
Different approaches to defining the distance between clusters distinguish the different algorithms
![Page 34: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/34.jpg)
STARTING SITUATION
...p1 p2 p3 p4 p9 p10 p11 p12
Start with clusters of individual points and a proximity matrix
p1
p3
p5
p4
p2
p1 p2 p3 p4 p5 . . .
.
.
. Proximity Matrix
![Page 35: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/35.jpg)
INTERMEDIATE SITUATION
...p1 p2 p3 p4 p9 p10 p11 p12
After some merging steps, we have some clusters
C1
C4
C2 C5
C3
C2C1
C1
C3
C5
C4
C2
C3 C4 C5
Proximity Matrix
![Page 36: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/36.jpg)
INTERMEDIATE SITUATION
...p1 p2 p3 p4 p9 p10 p11 p12
We want to merge the two closest clusters (C2 and C5) and update the proximity matrix.
C1
C4
C2 C5
C3
C2C1
C1
C3
C5
C4
C2
C3 C4 C5
Proximity Matrix
![Page 37: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/37.jpg)
AFTER MERGING
...p1 p2 p3 p4 p9 p10 p11 p12
The question is “How do we update the proximity matrix?”
C1
C4
C2 U C5
C3? ? ? ?
?
?
?
C2 U C5C1
C1
C3
C4
C2 U C5
C3 C4
Proximity Matrix
![Page 38: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/38.jpg)
HOW TO DEFINE INTER-CLUSTER SIMILARITY
p1
p3
p5
p4
p2
p1 p2 p3 p4 p5 . . .
.
.
.
Similarity?
MIN MAX Group Average Distance Between Centroids Other methods driven by an objective
function Ward’s Method uses squared error
Proximity Matrix
![Page 39: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/39.jpg)
HOW TO DEFINE INTER-CLUSTER SIMILARITY
p1
p3
p5
p4
p2
p1 p2 p3 p4 p5 . . .
.
.
.Proximity Matrix
MIN MAX Group Average Distance Between Centroids Other methods driven by an
objective function Ward’s Method uses squared error
![Page 40: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/40.jpg)
HOW TO DEFINE INTER-CLUSTER SIMILARITY
p1
p3
p5
p4
p2
p1 p2 p3 p4 p5 . . .
.
.
.Proximity Matrix
MIN MAX Group Average Distance Between Centroids Other methods driven by an
objective function Ward’s Method uses squared error
![Page 41: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/41.jpg)
HOW TO DEFINE INTER-CLUSTER SIMILARITY
p1
p3
p5
p4
p2
p1 p2 p3 p4 p5 . . .
.
.
.Proximity Matrix
MIN MAX Group Average Distance Between Centroids Other methods driven by an
objective function Ward’s Method uses squared error
![Page 42: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/42.jpg)
HOW TO DEFINE INTER-CLUSTER SIMILARITY
p1
p3
p5
p4
p2
p1 p2 p3 p4 p5 . . .
.
.
.Proximity Matrix
MIN MAX Group Average Distance Between Centroids Other methods driven by an
objective function Ward’s Method uses squared error
![Page 43: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/43.jpg)
CLUSTER SIMILARITY: MIN OR SINGLE LINK
Similarity of two clusters is based on the two most similar (closest) points in the different clusters Determined by one pair of points, i.e., by one
link in the proximity graph.
I1 I2 I3 I4 I5I1 1.00 0.90 0.10 0.65 0.20I2 0.90 1.00 0.70 0.60 0.50I3 0.10 0.70 1.00 0.40 0.30I4 0.65 0.60 0.40 1.00 0.80I5 0.20 0.50 0.30 0.80 1.00 1 2 3 4 5
![Page 44: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/44.jpg)
HIERARCHICAL CLUSTERING: MIN
Nested Clusters Dendrogram
1
2
3
4
5
6
1
2
3
4
5
3 6 2 5 4 10
0.05
0.1
0.15
0.2
![Page 45: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/45.jpg)
STRENGTH OF MIN
Original Points Two Clusters
• Can handle non-elliptical shapes
![Page 46: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/46.jpg)
LIMITATIONS OF MIN
Original Points Two Clusters
• Sensitive to noise and outliers
![Page 47: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/47.jpg)
CLUSTER SIMILARITY: MAX OR COMPLETE LINKAGE Similarity of two clusters is based on the two least
similar (most distant) points in the different clusters Determined by all pairs of points in the two clusters
I1 I2 I3 I4 I5I1 1.00 0.90 0.10 0.65 0.20I2 0.90 1.00 0.70 0.60 0.50I3 0.10 0.70 1.00 0.40 0.30I4 0.65 0.60 0.40 1.00 0.80I5 0.20 0.50 0.30 0.80 1.00 1 2 3 4 5
![Page 48: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/48.jpg)
HIERARCHICAL CLUSTERING: MAX
Nested Clusters Dendrogram
3 6 4 1 2 50
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0.4
1
2
3
4
5
6
1
2 5
3
4
![Page 49: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/49.jpg)
STRENGTH OF MAX
Original Points Two Clusters
• Less susceptible to noise and outliers
![Page 50: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/50.jpg)
LIMITATIONS OF MAX
Original Points Two Clusters
•Tends to break large clusters
•Biased towards globular clusters
![Page 51: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/51.jpg)
CLUSTER SIMILARITY: GROUP AVERAGE Proximity of two clusters is the average of pairwise
proximity between points in the two clusters.
Need to use average connectivity for scalability since total proximity favors large clusters
||Cluster||Cluster
)p,pproximity(
)Cluster,Clusterproximity(ji
ClusterpClusterp
ji
jijjii
I1 I2 I3 I4 I5I1 1.00 0.90 0.10 0.65 0.20I2 0.90 1.00 0.70 0.60 0.50I3 0.10 0.70 1.00 0.40 0.30I4 0.65 0.60 0.40 1.00 0.80I5 0.20 0.50 0.30 0.80 1.00 1 2 3 4 5
![Page 52: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/52.jpg)
HIERARCHICAL CLUSTERING: GROUP AVERAGE
Nested Clusters Dendrogram
3 6 4 1 2 50
0.05
0.1
0.15
0.2
0.25
1
2
3
4
5
6
1
2
5
3
4
![Page 53: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/53.jpg)
HIERARCHICAL CLUSTERING: GROUP AVERAGE
Compromise between Single and Complete Link
Strengths Less susceptible to noise and
outliers
Limitations Biased towards globular clusters
![Page 54: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/54.jpg)
CLUSTER SIMILARITY: WARD’S METHOD
Similarity of two clusters is based on the increase in squared error when two clusters are merged Similar to group average if distance between
points is distance squared
Less susceptible to noise and outliers
Biased towards globular clusters
Hierarchical analogue of K-means Can be used to initialize K-means
![Page 55: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/55.jpg)
HIERARCHICAL CLUSTERING: COMPARISON
Group Average
Ward’s Method
1
2
3
4
5
61
2
5
3
4
MIN MAX
1
2
3
4
5
61
2
5
34
1
2
3
4
5
61
2 5
3
41
2
3
4
5
6
12
3
4
5
![Page 56: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/56.jpg)
HIERARCHICAL CLUSTERING: TIME AND SPACE REQUIREMENTS O(N2) space since it uses the proximity
matrix. N is the number of points.
O(N3) time in many cases There are N steps and at each step the size, N2,
proximity matrix must be updated and searched Complexity can be reduced to O(N2 log(N) ) time
for some approaches
![Page 57: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/57.jpg)
HIERARCHICAL CLUSTERING: PROBLEMS AND LIMITATIONS Once a decision is made to combine two
clusters, it cannot be undone
No objective function is directly minimized
Different schemes have problems with one or more of the following: Sensitivity to noise and outliers Difficulty handling different sized clusters and
convex shapes Breaking large clusters
When we can stop?
![Page 58: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/58.jpg)
MST: DIVISIVE HIERARCHICAL CLUSTERING
Build MST (Minimum Spanning Tree) Start with a tree that consists of any point In successive steps, look for the closest pair of points (p,
q) such that one point (p) is in the current tree but the other (q) is not
Add q to the tree and put an edge between p and q
![Page 59: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/59.jpg)
MST: DIVISIVE HIERARCHICAL CLUSTERING
Use MST for constructing hierarchy of clusters
![Page 60: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/60.jpg)
DBSCAN DBSCAN is a density-based algorithm.
Density = number of points within a specified radius (Eps)
A point is a core point if it has more than a specified number of points (MinPts) within Eps
These are points that are at the interior of a cluster
A border point has fewer than MinPts within Eps, but is in the neighborhood of a core point
A noise point is any point that is not a core point or a border point.
Where are the centroids for K-Means?
![Page 61: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/61.jpg)
DBSCAN: CORE, BORDER, AND NOISE POINTS
![Page 62: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/62.jpg)
DBSCAN ALGORITHM
Eliminate noise points Perform clustering on the remaining points
![Page 63: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/63.jpg)
![Page 64: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/64.jpg)
![Page 65: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/65.jpg)
![Page 66: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/66.jpg)
![Page 67: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/67.jpg)
DBSCAN: CORE, BORDER AND NOISE POINTS
Original Points Point types: core, border and noise
Eps = 10, MinPts = 4
![Page 68: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/68.jpg)
WHEN DBSCAN WORKS WELL
Original Points Clusters
• Resistant to Noise
• Can handle clusters of different shapes and sizes
![Page 69: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/69.jpg)
WHEN DBSCAN DOES NOT WORK WELL
Original Points
(MinPts=4, Eps=9.75).
(MinPts=4, Eps=9.92)
• Varying densities
• High-dimensional data
![Page 70: Jianping Fan Department of Computer Science UNC-Charlotte Density-Based Data Clustering Algorithms: K-Means & Others](https://reader035.vdocuments.site/reader035/viewer/2022062805/5697bfe81a28abf838cb6580/html5/thumbnails/70.jpg)
DBSCAN: DETERMINING EPS AND MINPTS Idea is that for points in a cluster, their kth
nearest neighbors are at roughly the same distance
Noise points have the kth nearest neighbor at farther distance
So, plot sorted distance of every point to its kth nearest neighbor