You are on page 1of 6

Session Topic/Title Session No.

Session
Duration
(Minutes)
Clustering algorithms 11-12 100

• Understanding of Clustering Algorithms


• Implementation of Clustering Algorithms (K-mean and Hierarchical) in WEKA
for the given dataset
• Exercise

1. Session Outcomes

Students should be able to apply K-mean and Hierarchical clustering Algorithm in


WEKA for the given dataset.

2. Tool(s)/Software

WEKA

3. Procedural steps (Tasks)

Submission instructions:
• Use this template.
• Name the file: group#_studentId_firstName_surname
• Save your file as PDF.

[Clustering algorithms: K-mean and Hierarchical]


Task 1:
• Load dataset iris arff dataset:
• Implement Hierarchical clustering using Complete link, average link
Complete Link :
With class attribute

Without class attribute


Average Link:
with class attribute

• Report the results.


Task 2:
• Apply K means (k= 3 and Hierarchical clustering (Complete link) using
diabetes dataset.
• Contrast the results.
With class attribute

Without class attribute


Task 2:
• Apply K means(k= 3 and Hierarchical clustering (average link) using
bmw training dataset
• Contrast the results.
With class attribute

Without class attribute


Apply K means (k= 3)
With class attribute

Without class attribute

4. Assessment

• Students will be asked to apply the K-mean and Hierarchical clustering


algorithm on the given dataset.
• Students will submit their exercise answers in PDF file.

5. Resources Suggest further resources for the students to manage their learning
after the class. Make sure that the resources are specific and
different to suit all students, e. g. Figures, Tables, Links, etc.

▪ Lab Handout

You might also like