0 ×

PMML Ensemble Predictor

KNIME Ensemble Learning version 4.0.0.v201906060925 by KNIME AG, Zurich, Switzerland

The PMML Ensemble Predictor node takes a pmml document containing an ensemble of other models and executes all of them on the given data. The results from all models are then aggregated using a method specified in the ensemble model. The output contains a column for each prediction of the single models (if set in the settings) and one column with the combined result. Note that ensembles of ensembles are not supported with the exception of Gradient Boosted Trees which are treated base model. It's on the other hand not possible to predict Gradient Boosted Trees models with this predictor, please use the PMML Predictor node or the Gradient Boosted Trees Predictor (PMML) nodes for this task.

Options

Return individual predictions
Determines whether the output contains one column for each model's prediction
Multiple model method as column name
Determines whether the column with the combined predictions should be named after the combination method
Tie break
Determines what is output when there is a tie between two classes in the combination methods majority vote and weighted majority vote

Input Ports

A PMML Model containing an ensemble mining model
Data to be predicted

Output Ports

Prediction of every single model and the aggregated ensemble prediction

Best Friends (Incoming)

Best Friends (Outgoing)

Installation

To use this node in KNIME, install KNIME Ensemble Learning Wrappers from the following update site:

KNIME 4.0
Wait a sec! You want to explore and install nodes even faster? We highly recommend our NodePit for KNIME extension for your KNIME Analytics Platform.

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.