Visualisation-and-Outliers-Removal-via-Weka

Ref: https://www.cs.waikato.ac.nz/ml/weka/courses.html

Using the Visualize panel

• Open iris.arff
• Bring up Visualize panel
• Click one of the plots; examine some instances
• Set x axis to petalwidth and y axis to petallength
• Click on Class colour to change the colour
• Bars on the right change correspond to attributes: click for x axis; right‐click for y axis
• Jitter slider
• Show Select Instance: Rectangle option
• Submit, Reset, Clear and Save

Exercise -1

• Open diabetes data;
• Use the Visualize panel to select the outliers based on the feature "diabetes pedigree function".

Exercise -2

• Find the InterquartileRange in the Filter;
• Read the detailed information;
• Apply InterquartileRange and report the outliers;
• Apply InterquartileRange and report the outliers only based on the feature "diabetes pedigree function".

Exercise -3

• If we only need to output five outliers based on the feature "diabetes pedigree function", how?
• For this data, we identify the outliers with the values of the feature "diabetes pedigree function" >= 1.6. How to achieve this goal?