Spark Gradient Boosted Trees Learner

Gradient Boosted Trees are ensembles of Decision Trees. Learning a Gradient Boosted Trees model means training a sequence of Decision Trees one-by-one, in order to minimize a loss function. This node uses the spark.ml Gradient Boosted Trees implementation to train a classification model in Spark, using a logistic loss function .

Note that only binary classification is supported. The target column must be nominal (with two distinct values), whereas the feature columns can be either nominal or numerical.

Use the Spark Predictor (Classification) node to apply the learned model to unseen data.

Please refer to the Spark documentation for a full description of the underlying algorithm.

This node requires at least Apache Spark 2.0.

Input ports

1. Type: Spark Data
   Input data
   Input Spark DataFrame with training data.

Output ports

1. Type: Table
   Feature importance measures
   Table with estimates of the importance of each feature. The features are listed in order of decreasing importance and are normalized to sum up to 1.
2. Type: Spark ML Model
   Spark ML Gradient Boosted Trees model (classification)
   Spark ML Gradient Boosted Trees model (classification)