object PreprocessedDataFrameManager
Object to keep the preprocessed DataFrames by Pyspark.
- Alphabetic
- By Inheritance
- PreprocessedDataFrameManager
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
getPreprocessedDataframe(featureAnchors: Seq[FeatureAnchorWithSource]): Option[DataFrame]
* Get the preprocessed DataFrame for the anchor group.
-
def
getPreprocessingUniquenessForAnchor(featureAnchorWithSource: FeatureAnchorWithSource): String
* Get the uniqueness of the anchor if it has preprocessing UDFs.
* Get the uniqueness of the anchor if it has preprocessing UDFs. preprocessedDfMap is in the form of feature list of an anchor separated by comma to their preprocessed DataFrame. We use feature list to denote if the anchor has corresponding preprocessing UDF. For example, an anchor have f1, f2, f3, then corresponding preprocessedDfMap is Map("f1,f2,f3"-> df1) (Anchor name is not chosen since it may be duplicated and not unique and stable.) If this anchor has preprocessing UDF, then we need to make its FeatureGroupingCriteria unique so it won't be merged by different anchor of same source. Otherwise our preprocessing UDF may impact anchors that dont' need preprocessing.
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- var preprocessedDfMap: Map[String, DataFrame]
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()