Spark Gradient-Boosted Trees Learner


This node applies the Apache Spark Gradient-Boosted Trees (GBTs) algorithm.

Note: GBTs do not yet support multiclass classification. The class column needs to contain 0 and 1 as class labels. For multiclass problems, please use decision trees or Random Forests.

Please note that all data must be numeric, including the label column which needs to contain 0 and 1. Use the Spark Category To Number nodes to convert nominal values to numeric columns. The mapping dictionary of the converter node is the input of the second in port of this node.

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

Input Ports

  1. Type: Spark Data Input Spark DataFrame/RDD
  2. Type: PMML PMML with the nominal values mapping dictionary (optional)

Output Ports

  1. Type: Spark Model Spark MLlib Gradient-Boosted Trees Model

Find here

Tools & Services > Apache Spark > Mining > Prediction

Make sure to have this extension installed:

KNIME Extension for Apache Spark

Update site for KNIME Analytics Platform 3.7:
KNIME Analytics Platform 3.7 Update Site

How to install extensions