Unit3

Clustering
 Unit – 3 Syllabus
• Clustering: Introduction
• Hierarchical Clustering:
– Agglomerative Clustering Algorithm
– The single Linkage Algorithm
– The Complete Linkage Algorithm
– The Average – Linkage Algorithm

• Partitional Clustering:
– Forgy’s Algorithm
– The K-Means Algorithm
 Introduction
• In the earlier chapters, we saw that how samples may be classified if
a training set is available to use in the design of a classifier.
• However in many situations classes are themselves are initially
undefined.
• Given a set of feature vectors sampled from some population, we
would like to know if the data set consists of a number of relatively
distinct subsets, then we can define them to be classes.
• This is sometimes called as class discovery or unsupervised
classification
 When the goal is to group similar data points in a dataset, then we use cluster
analysis.
Clustering refers to the process of grouping samples so that the samples are
similar within each group. The groups are called clusters.

This method is defined under the branch of Unsupervised Learning, which aims at
gaining insights from unlabelled data points, that is, unlike supervised learning we
don’t have a target variable.

It evaluates the similarity based on a metric like Euclidean distance, Cosine

similarity, Manhattan distance, etc. and then group the points with highest
similarity score together.
 What is Clustering?
• Clustering is the task of dividing the population or data points
into a number of groups such that data points in the same
groups are more similar to other data points in the same
group than those in other groups.

• In simple words, the aim is to segregate groups with similar

traits and assign them into clusters.

• A good clustering will have high intra-class similarity and low inter-
class similarity
 Applications of Clustering
• Recommendation
engines
• Market segmentation
• Social network analysis
• Search result grouping
• Medical imaging
• Image segmentation
• Anomaly detection
 Types of clustering:
• Hierarchical Clustering:
– Agglomerative Clustering Algorithm
• The single Linkage Algorithm
• The Complete Linkage Algorithm
• The Average – Linkage Algorithm
– Divisive approach
• Polythetic The division is based on more than one feature.
• Monothetic Only one feature is considered at a time.

• Partitional Clustering:
– Forgy’s Algorithm
– The K-Means Algorithm
– The Isodata Algorithm.
 Hierarchical clustering
• Hierarchical clustering refers to a clustering process that
organizes the data into large groups, which contain smaller
groups and so on.
• A hierarchical clustering may be drawn as a tree or
dendrogram.
• The finest grouping is at the bottom of the dendrogram, each
sample by itself forms a cluster.
• At the top of the dendrogram, where all samples are grouped
into one cluster.
 Hierarchical clustering
• Figure shown in figure illustrates hierarchical clustering.
• At the top level we have Animals…
followed by sub groups…
• Do not have to assume any particular
number of clusters.
• The representation is called dendrogram.
• Any desired number of clusters can be
obtained by ‘cutting’ the dendrogram at the
proper level.
we develop the hierarchy of clusters in the form of a tree, and this tree-shaped
structure is known as the dendrogram.
 Example: Agglomerative
• 100 students from India join MS program in some particular
university in USA.
• Initially each one of them looks like single cluster.
• After some times, 2 students from SJCE, Mysuru makes a
cluster.
• Similarly another cluster of 3 students(patterns / Samples) from RVCE
meets SJCE students.
• Now these two clusters makes another bigger cluster of Karnataka
students.
• Later … south Indian student cluster and so on…
Agglomerative Clustering: It uses a bottom-up approach. It starts with
each object forming its own cluster and then iteratively merges the
clusters according to their similarity to form large clusters.

When certain clustering condition imposed by user is achieved or

All clusters merge into a single cluster
 Example : Divisive approach
• In a large gathering of engineering students..
– Separate JSS S&TU students
• Further computer science students
– Again ..7th sem students
» In sub group and divisive cluster is B section students.
>> Further gangs will be segregated.
Divisive Clustering: It uses the top-down strategy, the starting point is
the largest cluster with all objects in it and then split recursively to form
smaller and smaller clusters.
It terminates when the user-defined condition is achieved or final
clusters contain only one object.
 Two types of Hierarchical Clustering
– Agglomerative:
•It is the most popular algorithm, It is popular than divisive algorithm.
• Start with the points as individual clusters
•It follows bottom up approach
•At each step, merge the closest pair of clusters until only one cluster (or k clusters)
left

•Ex: single-linkage, complete-linkage, Average linking algorithm etc.

– 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
Agglomerative Clustering Algorithm
1. Compute the proximity matrix
2. Let each data point be a cluster
3. Repeat
4. Merge the two closest clusters
5. Update the proximity matrix
6. 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
 Some commonly used criteria in Agglomerative clustering Algorithms
(The most popular distance measure used is Euclidean distance)

Single Linkage:
Distance between two clusters is the smallest pairwise distance between

two observations/nodes, each belonging to different clusters.

Complete Linkage:
Distance between two clusters is the largest pairwise distance between two
observations/nodes, each belonging to different clusters.
Mean or average linkage clustering:
Distance between two clusters is the average of all the pairwise distances,
each node/observation belonging to different clusters.
Centroid linkage clustering:
Distance between two clusters is the distance between their centroids.
 Single linkage algorithm
• Consider the following scatter plot points.
• In single link hierarchical clustering, we merge in each step the
two clusters, whose two closest members have the smallest
distance
 Single linkage… Continued
• The single linkage algorithm is also known as the minimum
method and the nearest neighbor method.
• Consider Ci and Cj are two clusters.
• ‘a’ and ‘b’ are samples from cluster Ci and Cj respectively.

• Where d(a,b) represents the distance between ‘a’ and ‘b’.

First level of distance computation D1
(Euclidean distance used)
• Use Euclidean distance for distance between samples.
• The table shown in the previous slide gives feature values for
each sample and the distance d between each pair of samples.
• The algorithm begins with five clusters, each consisting of one
sample.
• The two nearest clusters are then merged.
• The smallest number is 4 which is the distance between (1 and
2), so they are merged. Merged matrix is as shown in next slide.
D2 matrix
• In the next level, the smallest number in the matrix is 8
• It is between 4 and 5.
• Now the cluster 4 and 5 are merged.
• With this we will have 3 clusters: {1,2}, {3},{4,5}
• The matrix is as shown in the next slide.
D3 distance
• In the next step {1,2} will be merged with {3}.
• Now we will have two cluster {1,2,3} and {4,5}

• In the next step.. these two are merged to have single cluster.
• Dendrogram is as shown here.
• Height of the dendrogram is decided
based on the merger distance.
For example: 1 and 2 are merged at
the least distance 4. hence the height
is 4.
 The complete linkage Algorithm
• It is also called the maximum method or the farthest neighbor
method.
• It is obtained by defining the distance between two clusters to be
largest distance between a sample in one cluster and a sample in
the other cluster.
• If Ci and Cj are clusters, we define:
 Example : Complete linkage algorithm
• Consider the same samples used in single linkage:
• Apply Euclidean distance and compute the distance.
• Algorithm starts with 5 clusters.
• As earlier samples 1 and 2 are the closest, they are merged first.
• While merging the maximum distance will be used to replace the
distance/ cost value.
• For example, the distance between 1&3 = 11.7 and 2&3=8.1.
This algorithm selects 11.7 as the distance.
• In complete linkage hierarchical clustering, the distance
between two clusters is defined as the longest distance
between two points in each cluster.
• In the next level, the smallest distance in the matrix is 8.0
between 4 and 5. Now merge 4 and 5.
• In the next step, the smallest distance is 9.8 between 3 and {4,5},
they are merged.
• At this stage we will have two clusters {1,2} and {3,4,5}.
• Notice that these clusters are different from those obtained from
single linkage algorithm.
• At the next step, the two remaining clusters will be merged.
• The hierarchical clustering will be complete.
• The dendrogram is as shown in the figure.
 The Average Linkage Algorithm
• The average linkage algorithm, is an attempt to compromise
between the extremes of the single and complete linkage
algorithm.
• It is also known as the unweighted pair group method using
arithmetic averages.
 Example: Average linkage clustering algorithm
• Consider the same samples: compute the Euclidian distance
between the samples
• In the next step, cluster 1 and 2 are merged, as the distance
between them is the least.
• The distance values are computed based on the average
values.
• For example distance between 1 & 3 =11.7 and 2&3=8.1 and the
average is 9.9. This value is replaced in the matrix between {1,2}
and 3.
• In the next stage 4 and 5 are merged:
Example 2: Single Linkage
Then, the updated distance matrix becomes
Then the updated distance matrix is
Example 3: Single linkage
As we are using single linkage, we choose the minimum distance, therefore, we choose 4.97
and consider it as the distance between the D1 and D4, D5. If we were using complete linkage
then the maximum value would have been selected as the distance between D1 and D4, D5
which would have been 6.09. If we were to use Average Linkage then the average of these two
distances would have been taken. Thus, here the distance between D1 and D4, D5 would have
come out to be 5.53 (4.97 + 6.09 / 2).
From now on we will simply repeat Step 2 and Step 3 until we are left with one
cluster. We again look for the minimum value which comes out to be 1.78 indicating
that the new cluster which can be formed is by merging the data points D1 and D2.
Similar to what we did in Step
3, we again recalculate the
distance this time for cluster
D1, D2 and come up with the
following updated distance
matrix.

We repeat what we did in step 2

and find the minimum value
available in our distance matrix.
The minimum value comes out
to be 1.78 which indicates that
we have to merge D3 to the
cluster D1, D2.
Update the distance matrix using
Single Link method.

Find the minimum distance in the matrix.

 Merge the data points accordingly and form another cluster.

Update the distance matrix using Single Link method.

 Ward’s Algorithm
This is also called minimum variance method. Begins with one cluster for each individual sample
point.
• At each iteration, among all pairs of clusters, it merges pairs with least
squared error
• The squared error for each cluster is defined as follows
• If a cluster contains m samples
x1,x2,x3……..xm where xi is the feature
vector(xi1,xi2,….xid),

• the squared error for sample xi, which is the squared Euclidean
distance from the mean: σ 𝑑 (𝑥𝑖𝑗 − μ𝑗)2 (Variance)
• Where μ𝑗 is the mean of the feature j for the values in the cluster
given by : μ𝑗 = 1 σ 𝑚𝑖 = (𝑥𝑖𝑗)
𝑚
1
 Ward’s Algorithm… Continued
• The squared error E for the entire cluster is the sum of the
squared errors for the samples
(𝑥𝑖𝑗 − μ𝑗) 2 = m σ2
• E= 𝑖 =1 σ 𝑑
σ𝑚
𝑗 =1
• The vector composed of the means of each feature,
(μ1, … … . . μ𝑑) =
μ, 𝑖𝑠 𝑐𝑎𝑙𝑙𝑒𝑑 𝑡ℎ𝑒 𝑚𝑒𝑎𝑛 𝑜𝑓 𝑡ℎ𝑒 𝑣𝑒𝑐𝑡𝑜𝑟 𝑜𝑟
𝑐𝑒𝑛𝑡𝑟𝑜𝑖𝑑 𝑜𝑓 𝑡ℎ𝑒 𝑐𝑙𝑢𝑠𝑡𝑒𝑟
• The squared error is thus the total variance of the
cluster σ2 𝑡𝑖𝑚𝑒𝑠 the number of samples m.
 One Hot Encoding
• Popularly used in classification problem.
• One hot encoding creates new (binary) columns, indicating the
presence of each possible value from the original data.
• It is good only when less number of classes.
• A typical dataset in any Data Science project consists of
numerical and categorical features. While numerical features
can contain only numbers, i.e., integers or decimals,
categorical features can be referred to as a variable
A colour variable with values red, blue, and green
A country variable with values India, USA, and Germany
One Hot Encoding can be defined as a process of transforming
categorical variables into numerical format before fitting and training a
Machine Learning algorithm.
For each categorical variable, One Hot Encoding produces a numeric
vector with a length equal to the number of categories present in the
feature.
One Hot Encoding is a technique that is used to convert categorical
variables into numerical format. It maps a categorical variable to a
binary vector with a length equal to the number of categories present
in the variable.

Ex: ?
Divisive Clustering Algorithm

In this process, we assume all the data points to be in a single

cluster, and in each iteration, we separate the data points from
the cluster which are not similar.
This method follows a top-down approach, and in the end, we
are left with n clusters.
Divisive approach
 How to divide
• Fix some condition.
• Example: In this example, after computing the distance/ cost
matrix, the least two will be put into one group (D,E), and others
into another group.
Hierarchical clustering: cluster is usually placed inside
another cluster…follows tree structure
 Partitional clustering: A sample belongs to exactly one
cluster : No tree structure, no dendrogram representation
 Partitional Clustering:
Agglomerative clustering creates a series of Nested clusters.

In partitional clustering the goal is to usually create one set of clusters

that partitions the data into similar groups.

Samples close to one another are assumed to be in one cluster. This is

the goal of partitional clustering.

Partitional clustering creates ‘k’ clusters for the given ‘n’

samples. The number of clusters ‘k’ is also to be given in
 Forgy’s Algorithm
One of the simplest partitional algorithm is the Forgy’s algorithm.

Apart from the data, the input to the algorithm is ‘k’ , the number
of clusters to be constructed

‘k’ samples are called seed points.

The seed points could be chosen randomly, or some knowledge of the

desired could be used to guide their selection.
 Forgy’s Algorithm

1. Initialize the cluster centroid to the seed points.

2. For each sample, find the cluster centroid nearest to it. Put
the sample in the nearest cluster identified with the
cluster centroid.
3. If no samples changed the clusters in step 2
4. Compute the centroids of the resulting clusters and go to
step 2.
Consider the Data points listed in the table and set k = 2 to produce two clusters
Use the first two samples (4,4) and (8,4) as the seed points.
Now applying the algorithm by computing the distance from each
cluster centroid and assigning them to the clusters:

Data X Y
Point
s
1 4 4
2 8 4
3 15 8
4 24 4
5 24 12
Sample Nearest Cluster
Centroid
(4,4) (4,4)
(8,4) (8,4)

(15,8) (8,4)

(24,4) (8,4)

(24,12) (8,4)
The clusters {(4,4)} and {(8,4),(15,8),(24,4),(24,12)} are formed.
Now re-compute the cluster centroids
New centroids are:
The first cluster (4,4) and
The second cluster centroid is x = (8+15+24+24)/4 = 17.75
y = (4+8+4+12)/4 =7

Sample Nearest Cluster

Centroid
(4,4) (4,4)

(8,4) (4,4)

(15,8) (17.75,7)

(24,4) (17.75,7)

(24,12) (17.75,7)
The clusters {(4,4),(8,4)} and {(15,8),(24,4),(24,12)} are formed.
Now re-compute the cluster centroids
The first cluster centroid x = (4+8)/2 = 6 and y = (4+4)/2 = 4
The second cluster centroid is x = (15+24+24)/3 = 21
y = (8+4+12)/4 = 8
Sample Nearest Cluster
Centroid
In the next step notice that the cluster centroid does not change (4,4) (6,4)

And samples also do not change the clusters. (8,4) (6,4)

Algorithm terminates.
(15,8) (21,12)

(24,4) (21,12)

(24,12) (21,12)
 Example-2 Illustration Forgy’s clustering algorithms
A1 A2
6.8 12.6 Plotting data of Table
0.8 9.8 25

1.2 11.6
2.8 9.6 20

3.8 9.9
15
4.4 6.5

A2
4.8 1.1 10
6.0 19.9
6.2 18.5 5

7.6 17.4
0
7.8 12.2 0 2 4 6 8 10 12

6.6 7.7 A1

8.2 4.5
8.4 6.9
9.0 3.4
62
9.6 11.1
 Example 2: Forgy’s clustering algorithms
• Suppose, k=3. Three objects are chosen at random shown as circled. These three
centroids are shown below.
Initial Centroids chosen randomly

Centroid Objects
A1 A2
c1 3.8 9.9
c2 7.8 12.2
c3 6.2 18.5

• Let us consider the Euclidean distance measure (L2 Norm) as the

distance measurement in our illustration.
• Let d1, d2 and d3 denote the distance from an object to c1, c2 and
c3 respectively. The distance calculations are shown in Table
• Assignment of each object to the respective centroid is shown in the right-most
column and the clustering so obtained is shown in Figure.
63
 Example 2: Forgy’s clustering algorithms
A1 A2 d1 d2 d3 cluster
6.8 12.6 4.0 1.1 5.9 2
0.8 9.8 3.0 7.4 10.2 1
1.2 11.6 3.1 6.6 8.5 1
2.8 9.6 1.0 5.6 9.5 1
3.8 9.9 0.0 4.6 8.9 1
4.4 6.5 3.5 6.6 12.1 1
4.8 1.1 8.9 11.5 17.5 1
6.0 19.9 10.2 7.9 1.4 3
6.2 18.5 8.9 6.5 0.0 3
7.6 17.4 8.4 5.2 1.8 3
7.8 12.2 4.6 0.0 6.5 2
6.6 7.7 3.6 4.7 10.8 1
8.2 4.5 7.0 7.7 14.1 1
8.4 6.9 5.5 5.3 11.8 2
9.0 3.4 8.3 8.9 15.4 1
9.6 11.1 5.9 2.1 8.1 2
64
 Example 2: Forgy’s clustering algorithms

The calculation new centroids of the three cluster using the mean of attribute values of A1
and A2 is shown in the Table below. The cluster with new centroids are shown in Figure.

Calculation of new centroids

New Objects
Centro
i d A1 A2

c1 4.6 7.1

c2 8.2 10.7

c3 6.6 18.6
Next cluster with new centroids 65
 Example 2: of Forgy’s clustering algorithms

We next reassign the 16 objects to three clusters by determining which centroid is

closest to each one. This gives the revised set of clusters shown in.

Note that point p moves from cluster C2 to cluster C1.

Cluster after first iteration

66
 Example 2: of Forgy’s clustering algorithms

• The newly obtained centroids after second iteration are given in the table below. Note that
the centroid c3 remains unchanged, where c2 and c1 changed a little.

• With respect to newly obtained cluster centres, 16 points are reassigned again. These are
the same clusters as before. Hence, their centroids also remain unchanged.
• Considering this as the termination criteria, the algorithm stops here.

Centroid Revised
Centroids
A1 A2
c1 5.0 7.1
c2 8.1 12.0
c3 6.6 18.6
67
Apply Forgy’s algorithm for the following dataset with K = 2

Sample X Y
1 0.0 0.5
2 0.5 0.0
3 1.0 0.5
4 2.0 2.0
5 3.5 8.0
6 5.0 3.0
7 7.0 3.0
 K-Means Algorithm
It is similar to Forgy’s algorithm.

The k-means algorithm differs from Forgy’s algorithm in that the centroids of the
clusters are recomputed as soon as sample joins a cluster.

Also unlike Forgy’s algorithm which is iterative in nature, the k-means only two
passes through the data set.
 The K-Means Algorithm
1. Input for this algorithm is K (the number of clusters) and ‘n’ samples, x1,x2,
…xn.

1. Identify the centroids c1 to ck from the random locations. That is randomly

select ‘k’ samples as centroids. (note: n should be greater than k)

2. For each remaining (n-k) samples, find the centroid nearest it. Put the
sample in the cluster identified with this nearest centroid. After each
sample is assigned, re-compute the centroid of the altered cluster.

3. Go through the data a second time. For each sample, find the centroid
nearest it. Put the sample in the cluster identified with the nearest cluster.
(During this step do not recompute the centroid)
Apply k-means Algorithm on the following sample points
Begin with two clusters {(8,4)} and {(24,4)} with the centroids
(8,4) and (24,4)

For each remaining samples, find the nearest centroid and put it in that
cluster.
Then re-compute the centroid of the cluster.

The next sample (15,8) is closer to (8,4) so it joins the cluster {(8,4)}.
The centroid of the first cluster is updated to (11.5,6).
(8+15)/2 = 11.5 and (4+8)/2 = 6.

The next sample is (4,4) is nearest to the centroid (11.5,6) so it joins the
cluster {(8,4),(15,8),(4,4)}.
Now the new centroid of the cluster is (9,5.3)

The next sample (24,12) is closer to centroid (24,4) and joins the cluster {(24,4),(24,12)}.
Now the new centroid of the second cluster is updated to (24,8).
At this point step1 is completed.
For step2 examine the samples one by one and put each sample in the identified with
the nearest cluster centroid.

Sample Distance to Distance to

centroid (9,5.3) centroid
(24,8)
(8,4) 1.6 16.5
(24,4) 15.1 4.0
(15,8) 6.6 9.0
(4,4) 5.16 40.0
(24,12) 16.4 4.0
Example: Sqrt ( square of (9-8) + square of (4-5.3) = 1.6
 Final clusters of K-Means algorithms
• So the new clusters are :
• C1 = { (8,4), (15,8), (4,4) }
• C2 = { (24,4), (24,12) }

• K-Means algorithms ends.

AI-ML-DL and Data Science
Summary of Machine Learning Algorithms learnt so far…
End of Unit 3
Other Clustering Types