M10LA2A
docx
keyboard_arrow_up
School
Algonquin College *
*We aren’t endorsed by this school
Course
8390
Subject
Industrial Engineering
Date
Dec 6, 2023
Type
docx
Pages
4
Uploaded by GrandMouse3342
CST8390 Business Intelligence and Data Analytics
Module 10: Activity 2 - Simulation: Weka – Discretization
There are two types of discretization techniques: unsupervised ones, which are “class blind,” and
supervised ones, which take the class value of the instances into account when creating intervals. Weka’s
main unsupervised method for discretizing numeric attributes is weka > filters > unsupervised > attribute
> Discretize. It implements these two methods: equal-width (the default) and equal-frequency
discretization.
Instructions
Exercise 1: Unsupervised Discretization
1.
Launch Weka and in the
GUI
choose
Explorer
, load
glass.arf
and take a
screenshot
of the
histogram
.
2.
Select the unsupervised Discretize filter (
Choose
>
weka
>
filters
>
unsupervised
>
attribute
>
Discretize
).
3.
Apply the unsupervised discretization filter,
Discretize,
in the
equal-width
(default) mode and
take a
screenshot
of the
histogram
.
Module 10: Activity 2 - Instructions
Page 1
4.
Click
Undo
.
5.
Apply the unsupervised discretization filter,
Discretize,
in the
equal-frequency
mode and take a
screenshot
of the
histogram
.
6.
Click
Undo
7.
Apply the unsupervised discretization filter,
PKIDiscretize
(
Choose
>
weka
>
filters
>
unsupervised
>
attribute
>
PKIDiscretize
) and take a
screenshot
of the
histogram
.
Module 10: Activity 2 - Instructions
Page 2
Question
1.
What do you observe when you compare the histograms obtained?
Answer
The histogram for equalfrequency discretization is skewed for some attributes.
Module 10: Activity 2 - Instructions
Page 3
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
- Access to all documents
- Unlimited textbook solutions
- 24/7 expert homework help
Exercise 2: Supervised Discretization
1.
Launch Weka and in the
GUI
choose
Explorer
, load
iris.arf
and take a
screenshot
of the
histogram
.
2.
Select the supervised
Discretize
filter (
Choose
>
weka
>
filters
>
supervised
>
attribute
>
Discretize
), click
Apply
, and take a
screenshot
of the
histogram
.
Question
1.
What do you observe about the histogram?
Answer
Supervised discretization strives to create intervals within which the class distribution is
consistent, although the distributions vary from one interval to the next.
Module 10: Activity 2 - Instructions
Page 4