Lecture 12: Learning Classification and Association Rules. Clustering

For this lecture we will use the material from 
More Data Mining with WEKA by Ian Witten [W2] chapter 3 Classification rules, association rules, and clustering. The slides are here: [W2ch3] 


Sections:

3.1. Decision Trees and Rules (slides 1-11)
3.2. Generating Decision Rules (12-18)
3.3 Association Rules (19-24)
3.4 Learning Association Rules (25-32)
3.5. Representing Clusters (33-43)
3.6. Evaluating Clusters (44-50)

Algorithms described in the various sections:

1: PRISM Algorithm (slides 10)
2: PART Algorithm (14)
2: Ripper Algorithm (15)
2: Comparison between PART, JRipp and J48 (16-17)
3,4: Apriori Algorithm (21-24, different parameters for it: 25-32)
5: K-Means Clustering Algorithm (38, example 39)
5: X-Means Clustering Algorithm (Expectation-Maximization (EM)) (40-41)
5: CobWeb Clustering (42)
6: Clustering Evaluation (46-49)

[W1]  Ian Witten - More Data Mining with WEKA (online version, last visited december 2018) https://www.cs.waikato.ac.nz/ml/weka/mooc/moredataminingwithweka/
[W2ch3] Chapter 3 of [W1]: Classification rules, association rules, and clustering (online version, last visited december 2018) http://www.myreadershttps://drive.google.com/file/d/0B-f7ZbfsS9-xYzlkWXYwQWFMX28/edit?usp=sharing