case class ColumnStat(distinctCount: Option[BigInt] = None, min: Option[Any] = None, max: Option[Any] = None, nullCount: Option[BigInt] = None, avgLen: Option[Long] = None, maxLen: Option[Long] = None, histogram: Option[Histogram] = None, version: Int = CatalogColumnStat.VERSION) extends Product with Serializable
Statistics collected for a column.
1. The JVM data type stored in min/max is the internal data type for the corresponding Catalyst data type. For example, the internal type of DateType is Int, and that the internal type of TimestampType is Long. 2. There is no guarantee that the statistics collected are accurate. Approximation algorithms (sketches) might have been used, and the data collected can also be stale.
- distinctCount
number of distinct values
- min
minimum value
- max
maximum value
- nullCount
number of nulls
- avgLen
average length of the values. For fixed-length types, this should be a constant.
- maxLen
maximum length of the values. For fixed-length types, this should be a constant.
- histogram
histogram of the values
- version
version of statistics saved to or retrieved from the catalog
- Alphabetic
- By Inheritance
- ColumnStat
- Serializable
- Product
- Equals
- AnyRef
- Any
- Hide All
- Show All
- Public
- Protected
Instance Constructors
- new ColumnStat(distinctCount: Option[BigInt] = None, min: Option[Any] = None, max: Option[Any] = None, nullCount: Option[BigInt] = None, avgLen: Option[Long] = None, maxLen: Option[Long] = None, histogram: Option[Histogram] = None, version: Int = CatalogColumnStat.VERSION)
- distinctCount
number of distinct values
- min
minimum value
- max
maximum value
- nullCount
number of nulls
- avgLen
average length of the values. For fixed-length types, this should be a constant.
- maxLen
maximum length of the values. For fixed-length types, this should be a constant.
- histogram
histogram of the values
- version
version of statistics saved to or retrieved from the catalog
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
- val avgLen: Option[Long]
- def clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.CloneNotSupportedException]) @native()
- val distinctCount: Option[BigInt]
- final def eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- def finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.Throwable])
- final def getClass(): Class[_ <: AnyRef]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- val hasCountStats: Boolean
- val hasLenStats: Boolean
- val hasMinMaxStats: Boolean
- val histogram: Option[Histogram]
- final def isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- val max: Option[Any]
- val maxLen: Option[Long]
- val min: Option[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()
- val nullCount: Option[BigInt]
- def productElementNames: Iterator[String]
- Definition Classes
- Product
- final def synchronized[T0](arg0: => T0): T0
- Definition Classes
- AnyRef
- def toCatalogColumnStat(colName: String, dataType: DataType): CatalogColumnStat
- def updateCountStats(oldNumRows: BigInt, newNumRows: BigInt, updatedColumnStatOpt: Option[ColumnStat] = None): ColumnStat
- val version: Int
- final def wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException]) @native()