class StatsCompute extends Serializable
Linear Supertypes
Ordering
- Alphabetic
- By Inheritance
Inherited
- StatsCompute
- Serializable
- Serializable
- AnyRef
- Any
- Hide All
- Show All
Visibility
- Public
- All
Instance Constructors
- new StatsCompute(inputDf: DataFrame, keys: Seq[String], name: String)
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
-
def
addDerivedMetrics(df: DataFrame, aggregator: RowAggregator): DataFrame
Given a summary Dataframe that computed the stats.
Given a summary Dataframe that computed the stats. Add derived data (example: null rate, median, etc)
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
dailySummary(aggregator: RowAggregator, sample: Double = 1.0, timeBucketMinutes: Long = 60): TimedKvRdd
Navigate the dataframe and compute statistics partitioned by date stamp
Navigate the dataframe and compute statistics partitioned by date stamp
Partitioned by day version of the normalized summary. Useful for scheduling a job that computes daily stats. Returns a KvRdd to be able to be pushed into a KvStore for fetching and merging. As well as a dataframe for storing in hive.
For entity on the left we use daily partition as the key. For events we bucket by timeBucketMinutes (def. 1 hr) Since the stats are mergeable coarser granularities can be obtained through fetcher merging.
-
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
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- val metrics: Seq[MetricTransform]
-
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()
- lazy val selectedDf: DataFrame
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
- implicit val tableUtils: TableUtils
- val timeColumns: Seq[String]
-
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()