Weak Label Model Predictor

Applies a weak label model learned with the Weak Label Model Learner to data. For each row, it appends the probability distribution over the class values as predicted by the weak label model. This node is a key component for the realization of weak supervision approaches as popularized by Snorkel . For more information, please see the Weak Label Model Learner.

Options

Class column name
The name of the label (or class) column that the labels provided by the label sources belong to. This value is used to create the column names for the probability columns in the output.
Append individual class probabilities
Select this option if you want to append the class probabilities as individual columns in addition to the class probability distribution column.
Remove source columns
Select if you want to remove the label source columns from the output table.

Input Ports

Icon
A weak label model trained with the Weak Label Model Learner.
Icon
The data on which to apply the weak label model.

Output Ports

Icon
The input table with a probability distribution over the possible classes appended.

Views

This node has no views

Workflows

Links

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.