Icon

AutoML - Preview (PMML)

--------------- !!! DISCLAIMER !!! ---------------

This Component is a not-verified Beta version shared in Fall 2019 on my personal space for demo purposes.

Official Components verified by the KNIME team are available via the Example Server at:

hub.knime.com/knime/spaces/Examples/latest/00_Components

--------------- !!! \\\ END /// !!! --------------

This Component can automatically train supervised machine learning models by performing some data preparation, parameter optimization, scoring, evaluation and selection.

Options

Target Column:
Select with this setting which column you want to predict.
Target Column:
Select with this setting which column you want to predict.
Models to Train:
Select with this setting which algorithm you want to use.
Metric for Auto Selection
Select here which performance metric should be used to automatically select the best model.

Input Ports

Icon
A KNIME Table with data rows with input features and ground truth.

Output Ports

Icon
The best trained model stored in a model port. Use the Component "Model Agnostic Predictor" to score new data using this port. This object also stores missing value imputation and normalization. Use the Component "Interpretability View" to create an interactive dashboard visualizing machine learning interpretability techniques.

Nodes

Extensions