This is a training on Machine Learning with R for the Big Data and Analytics course, the S P Jain School of Global Management, Mumbai, India, 30 May - 5 June 2016.

Contents of Training

Unsupervised Learning – I : Cluster Analysis
​1. ​Basic Concepts
​2. ​Partitioning Methods
     2.1. K-means
     2.2. K-medoids
3. Hierarchical Methods
     3.1. Diana
4. Density based Methods
     4.1. DBSCAN
5. Evaluation of Clustering
6. Applications with real world problems
 
Unsupervised Learning- II :  Associations & Correlations
1. Basic Concepts
2. Frequent Itemset Mining Methods
     2.1. Apriori
     2.2. Improving the Efficiency of Apriori
     2.3. FPGrowth
     2.4. ECLAT: Frequent Pattern Mining with  Vertical Data Format
3. Pattern Evaluation Methods
4. Applications with real world problems

Slides

• Introduction

• Cluster Analysis

• Cluster Analysis with R

• Association Rule Mining

• Association Rule Mining with R
  

• R Reference Card for Data Mining

Software and Datasets

Some software/tools and datasets needed for the training as below.

• R


• RStudio


• R packages: arules, arulesViz, cluster, fpc
  


• Datasets: 
  


• titanic.raw.rdata
  


• mushroom