…to mt/spark-2.4

… made to decision tree pruning in Spark 2.4. If nodes are split, but both child nodes lead to the same prediction then the split is pruned away. This updates the test so this doesn't happen for feature 'b'

…to mt/spark-2.4

…to mt/spark-2.4

…spark-2.4

…la212

…la212

…scala212

…scala212

# Conflicts:
#	build.gradle

# Conflicts:
#	core/src/test/scala/com/salesforce/op/stages/impl/insights/RecordInsightsLOCOTest.scala
#	core/src/test/scala/com/salesforce/op/stages/impl/regression/OpRandomForestRegressorTest.scala
#	readers/src/main/scala/com/salesforce/op/readers/DataReader.scala

…enerate UDFs in FeatureSparkTypes.scala

… collections as empty behavior

…ashCode

…ts class

…to ndv/scala212

…eration in scala 2.12

…tMapVectorizerTest

… rely on spark.ml)

…instead

… in OpWorkflowModelLocal

…1404)

…ution

…ata actually works well enough when all input data schema metadata is set properly