The positive class is "1" and negative is "0" by convention; I don't think you can change that (though you can translate your data if needed). F1 is defined only in a one-vs-rest sense in multi-class evaluation. You can set 'metricLabel' to define which class is 'positive' in multiclass - everything else is 'negative'.
On Wed, Jul 7, 2021 at 7:19 PM Reed Villanueva <villanuevar...@gmail.com> wrote: > How to specify the "positive class" in sparkml binary classification? (Or > perhaps: How does a MulticlassClassificationEvaluator > <https://spark.apache.org/docs/latest/api/python/reference/api/pyspark.ml.evaluation.MulticlassClassificationEvaluator.html?highlight=multiclassclassificationevaluator> > determine > which class is the "positive" one when evaluating for, say, F1 or even just > Recall?) > I have a Pipeline like... > > pipeline = Pipeline(stages=[label_idxer, feature_idxer, onehotencoder, > assembler, my_ml_algo, label_converter]) > > crossval = CrossValidator(estimator=pipeline, > evaluator=MulticlassClassificationEvaluator( > labelCol=my_ml_algo.getLabelCol(), > predictionCol=my_ml_algo.getPredictionCol(), > metricName="f1"), > numFolds=3) > > Is there a way to specify which label or index is the positive/negative > class? >
