We will explore three common classification models available in Spark: linear models, decision trees, and naïve Bayes models. Linear models, while less complex, are relatively easier to scale to very large datasets. Decision tree is a powerful nonlinear technique that can be a little more difficult to scale up (fortunately, MLlib takes care of this for us!) and more computationally intensive to train, but delivers leading performance in many situations. Naïve Bayes models are more simple but are easy to train efficiently and parallelize (in fact, they require only one pass over the dataset). They can also give reasonable performance in many cases when appropriate feature engineering is used. A naïve Bayes model also provides a good baseline model against which we can measure the performance of other models.

Currently, Spark's MLlib library supports binary classification for linear models, decision trees, and naïve Bayes models and multiclass classification for...