Multiclass Classification Evaluator

Creates a multiclass classification evaluator. Multiclass classification evaluator does not assume any label class is special, thus it cannot be used for calculation of metrics specific for binary classification (where this assumption is taken into account).

This operation is ported from Spark ML.

For a comprehensive introduction, see Spark documentation.

For scala docs details, see documentation.

Since: Seahorse 1.0.0


This operation does not take any input.


Port Type Qualifier Description
0EvaluatorAn Evaluator that can be used in an Evaluate operation.


Name Type Description
multiclass metric SingleChoice The metric used in evaluation. Possible values: ["f1", "precision", "recall", "weightedPrecision", "weightedRecall"]
prediction column SingleColumnSelector The prediction column.
label column SingleColumnSelector The label column for model fitting.