R: Data Analysis and Visualization

Classification using frequent patterns

There are two types of classification using frequent patterns:

• Associative classification model as well as association rules, which are generated from frequent patterns and used for classifications
• Discriminative frequent pattern-based classification

The associative classification

The generic association classification algorithm is defined here. The input parameters for the kNN algorithm are as follows:

• D, which is a set of training objects
• F, which is the itemset
• MIN_SUP, which is the minimal support
• MIN_CONF, which is the minimal confidence

The output of the algorithm is a rule-based classifier and is shown as follows:

Two popular algorithms are illustrated in the successive sections, one is Classification Based ...