Get prediction column when running binary classification AutoML in a Spark pipeline

Description

In the sparkling water pipeline examples, when there is a prediction for binary classification there is a column named "prediction" with the predicted label. Example:


def isSpam(smsText, model):
smsTextDF = spark.createDataFrame([(smsText,)], ["text"]) # create one element tuple
prediction = model.transform(smsTextDF)
return prediction.select("prediction").first() == "spam"

However, I'm running an AutoML estimator on a spark pipeline and the output column is named "prediction_output" that is a struct with the probability of p0 and p1. There is not a "prediction" column with the predicted label.

Sparkling Water Version: 2.4.13
H2O cluster version: 3.24.0.5

Assignee

Unassigned

Reporter

Alfredo Lopes da Silva

CustomerVisible

No

testcase 1

None

testcase 2

None

testcase 3

None

h2ostream link

None

Affected Spark version

None

AffectedContact

None

AffectedCustomers

None

AffectedPilots

None

AffectedOpenSource

None

Support Assessment

None

Customer Request Type

None

Support ticket URL

None

End date

None

Baseline start date

None

Baseline end date

None

Task progress

None

Task mode

None

Priority

Major
Configure