Scribd
Upload
28 views11 pages

Chinninti Venkata Assessment Machine Learning

The document discusses implementing hierarchical clustering on the Iris dataset to classify the data into clusters based on similarities. It provides the steps which include exploratory analysis of the dataset, describing the hierarchical clustering algorithm and providing a flowchart, and writing a program to generate results. Hierarchical clustering is chosen over k-means clustering as it is well-suited for this small dataset that is known to have 3 classes.

Uploaded by

sriharsha jinni
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
28 views11 pages

Chinninti Venkata Assessment Machine Learning

The document discusses implementing hierarchical clustering on the Iris dataset to classify the data into clusters based on similarities. It provides the steps which include exploratory analysis of the dataset, describing the hierarchical clustering algorithm and providing a flowchart, and writing a program to generate results. Hierarchical clustering is chosen over k-means clustering as it is well-suited for this small dataset that is known to have 3 classes.

Uploaded by

sriharsha jinni
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 11

MACHINE LEARNING

ASSIGNMENT ON DESIGN

KORITALA JINNI SRIHARSHA.


S20002717
TASKS TO IMPLEMENT THE PROBLEM: Iris Dataset

Step 1. Exploratory analysis of given iris dataset.

Step 2. Algorithm

Step 3. Flowchart of clustering algorithm.

Step 4. Program and results.

Step 1.

Analysis of given Iris Dataset.

The Iris Dataset depends on many factors which need to be clustered precisely
using different available machine learning algorithms.

Here, I have solved the problem using Hierarchical Clustering Algorithm as we


have a small dataset.

As we know that Hierarchical Clustering is a method of clustering analysis which


tries to build a hierarchy of clusters without having fixed number of clusters.

In hierarchical clustering nodes relate to the similarities in the data. Hierarchical


methods are especially useful when the target is to arrange the clusters into a
natural hierarchy [1].

On the other hand, we have k-means Clustering as well to divide the data into
clusters using centroids, but I choose hierarchical clustering as of the we know
that it has 3 types of classes in the given data.

For this data hierarchical clustering, be well suited and can classify the data into
the respected clusters by the similarities in between the dataset.

In hierarchical clustering the distance between each point is calculated to form a


big cluster which is then decomposed to get N clusters.
There are two types in hierarchical clustering Agglomerative and Divisive
Clustering. The results of Hierarchical clustering can be shown by dendrogram.

The decision of merging the clusters can be calculated by the closeness of the
clusters. We use the Euclidean distance matric.

Euclidean distance: ||a-b||2 = √(Σ(ai-bi))

Next, we select the linkage for computing the distance matric. There are many
linkages single, complete, ward, centroid etc.
Flowchart of Hierarchical Clustering Algorithm [2]

Here, we have seted each data point as a Cluster from the Computation Matrix
for the considered Inputs.

If we get the no.of Cluster equals to one then we end that.

Hence ,not equals to one ,we need to merge the closet cluster hence after need
to update the Matrix.
Algorithm:

Step1: Start.
Step2: Enter the data input features.
Step3: Compute the distance matrix.
Step4: Set each point as a cluster.
Step5: iterate foe n=1 cluster if data is clustered end otherwise next step

Step6: Merge closest clusters


Step7: Update distance matic then iterate.
Step8: End
REFERENCES:

[1] https://www.geeksforgeeks.org/difference-between-k-means-and-
hierarchical-clustering/

[2] https://www.researchgate.net/figure/Flowchart-of-the-Hierarchical-
Clustering_fig7_232402905

You might also like