Showing content from https://api-docs.databricks.com/scala/spark/latest/org/apache/spark/sql/Dataset.html below:
Databricks Scala Spark API - org.apache.spark.sql.Dataset
class Dataset[T] extends Serializable
î· î
Ordering
- Grouped
- Alphabetic
- By Inheritance
Inherited
- Dataset
- Serializable
- Serializable
- AnyRef
- Any
Value Members
- î
final def !=(arg0: Any): Boolean
- î
final def ##(): Int
- î
final def ==(arg0: Any): Boolean
- î
def agg(expr: Column, exprs: Column*): DataFrame
- î
def agg(exprs: Map[String, String]): DataFrame
- î
def agg(exprs: Map[String, String]): DataFrame
- î
def agg(aggExpr: (String, String), aggExprs: (String, String)*): DataFrame
- î
def alias(alias: Symbol): Dataset[T]
- î
def alias(alias: String): Dataset[T]
- î
def apply(colName: String): Column
- î
def as(alias: Symbol): Dataset[T]
- î
def as(alias: String): Dataset[T]
- î
def as(schema: StructType): DataFrame
- î
def as[U](implicit arg0: Encoder[U]): Dataset[U]
- î
final def asInstanceOf[T0]: T0
- î
def cache(): Dataset.this.type
- î
def checkpoint(eager: Boolean): Dataset[T]
- î
def checkpoint(): Dataset[T]
- î
def clone(): AnyRef
- î
def coalesce(numPartitions: Int): Dataset[T]
- î
def col(colName: String): Column
- î
def colRegex(colName: String): Column
- î
def collect(): Array[T]
- î
def collectAsList(): List[T]
- î
def columns: Array[String]
- î
def count(): Long
- î
def createGlobalTempView(viewName: String): Unit
- î
def createOrReplaceGlobalTempView(viewName: String): Unit
- î
def createOrReplaceTempView(viewName: String): Unit
- î
def createTempView(viewName: String): Unit
- î
def crossJoin(right: Dataset[_]): DataFrame
- î
def cube(col1: String, cols: String*): RelationalGroupedDataset
- î
def cube(cols: Column*): RelationalGroupedDataset
- î
def describe(cols: String*): DataFrame
- î
def distinct(): Dataset[T]
- î
def drop(col: Column): DataFrame
- î
def drop(colNames: String*): DataFrame
- î
def drop(colName: String): DataFrame
- î
def dropDuplicates(col1: String, cols: String*): Dataset[T]
- î
def dropDuplicates(colNames: Array[String]): Dataset[T]
- î
def dropDuplicates(colNames: Seq[String]): Dataset[T]
- î
def dropDuplicates(): Dataset[T]
- î
def dtypes: Array[(String, String)]
- î
val encoder: Encoder[T]
- î
final def eq(arg0: AnyRef): Boolean
- î
def equals(arg0: Any): Boolean
- î
def except(other: Dataset[T]): Dataset[T]
- î
def exceptAll(other: Dataset[T]): Dataset[T]
- î
def explain(): Unit
- î
def explain(extended: Boolean): Unit
- î
def explain(mode: String): Unit
- î
def filter(func: FilterFunction[T]): Dataset[T]
- î
def filter(func: (T) â Boolean): Dataset[T]
- î
def filter(conditionExpr: String): Dataset[T]
- î
def filter(condition: Column): Dataset[T]
- î
def finalize(): Unit
- î
def first(): T
- î
def flatMap[U](f: FlatMapFunction[T, U], encoder: Encoder[U]): Dataset[U]
- î
def flatMap[U](func: (T) â TraversableOnce[U])(implicit arg0: Encoder[U]): Dataset[U]
- î
def foreach(func: ForeachFunction[T]): Unit
- î
def foreach(f: (T) â Unit): Unit
- î
def foreachPartition(func: ForeachPartitionFunction[T]): Unit
- î
def foreachPartition(f: (Iterator[T]) â Unit): Unit
- î
final def getClass(): Class[_]
- î
def groupBy(col1: String, cols: String*): RelationalGroupedDataset
- î
def groupBy(cols: Column*): RelationalGroupedDataset
- î
def groupByKey[K](func: MapFunction[T, K], encoder: Encoder[K]): KeyValueGroupedDataset[K, T]
- î
def groupByKey[K](func: (T) â K)(implicit arg0: Encoder[K]): KeyValueGroupedDataset[K, T]
- î
def hashCode(): Int
- î
def head(): T
- î
def head(n: Int): Array[T]
- î
def hint(name: String, parameters: Any*): Dataset[T]
- î
def inputFiles: Array[String]
- î
def intersect(other: Dataset[T]): Dataset[T]
- î
def intersectAll(other: Dataset[T]): Dataset[T]
- î
def isEmpty: Boolean
- î
final def isInstanceOf[T0]: Boolean
- î
def isLocal: Boolean
- î
def isStreaming: Boolean
- î
def javaRDD: JavaRDD[T]
- î
def join(right: Dataset[_], joinExprs: Column, joinType: String): DataFrame
- î
def join(right: Dataset[_], joinExprs: Column): DataFrame
- î
def join(right: Dataset[_], usingColumns: Seq[String], joinType: String): DataFrame
- î
def join(right: Dataset[_], usingColumns: Array[String], joinType: String): DataFrame
- î
def join(right: Dataset[_], usingColumn: String, joinType: String): DataFrame
- î
def join(right: Dataset[_], usingColumns: Seq[String]): DataFrame
- î
def join(right: Dataset[_], usingColumns: Array[String]): DataFrame
- î
def join(right: Dataset[_], usingColumn: String): DataFrame
- î
def join(right: Dataset[_]): DataFrame
- î
def joinWith[U](other: Dataset[U], condition: Column): Dataset[(T, U)]
- î
def joinWith[U](other: Dataset[U], condition: Column, joinType: String): Dataset[(T, U)]
- î
def limit(n: Int): Dataset[T]
- î
def localCheckpoint(eager: Boolean): Dataset[T]
- î
def localCheckpoint(): Dataset[T]
- î
def map[U](func: MapFunction[T, U], encoder: Encoder[U]): Dataset[U]
- î
def map[U](func: (T) â U)(implicit arg0: Encoder[U]): Dataset[U]
- î
def mapPartitions[U](f: MapPartitionsFunction[T, U], encoder: Encoder[U]): Dataset[U]
- î
def mapPartitions[U](func: (Iterator[T]) â Iterator[U])(implicit arg0: Encoder[U]): Dataset[U]
- î
def na: DataFrameNaFunctions
- î
final def ne(arg0: AnyRef): Boolean
- î
final def notify(): Unit
- î
final def notifyAll(): Unit
- î
def observe(observation: Observation, expr: Column, exprs: Column*): Dataset[T]
- î
def observe(name: String, expr: Column, exprs: Column*): Dataset[T]
- î
def offset(n: Int): Dataset[T]
- î
def orderBy(sortExprs: Column*): Dataset[T]
- î
def orderBy(sortCol: String, sortCols: String*): Dataset[T]
- î
def persist(newLevel: StorageLevel): Dataset.this.type
- î
def persist(): Dataset.this.type
- î
def printSchema(level: Int): Unit
- î
def printSchema(): Unit
- î
val queryExecution: QueryExecution
- î
def randomSplit(weights: Array[Double]): Array[Dataset[T]]
- î
def randomSplit(weights: Array[Double], seed: Long): Array[Dataset[T]]
- î
def randomSplitAsList(weights: Array[Double], seed: Long): List[Dataset[T]]
- î
lazy val rdd: RDD[T]
- î
def reduce(func: ReduceFunction[T]): T
- î
def reduce(func: (T, T) â T): T
- î
def repartition(partitionExprs: Column*): Dataset[T]
- î
def repartition(numPartitions: Int, partitionExprs: Column*): Dataset[T]
- î
def repartition(numPartitions: Int): Dataset[T]
- î
def repartitionByRange(partitionExprs: Column*): Dataset[T]
- î
def repartitionByRange(numPartitions: Int, partitionExprs: Column*): Dataset[T]
- î
def rollup(col1: String, cols: String*): RelationalGroupedDataset
- î
def rollup(cols: Column*): RelationalGroupedDataset
- î
def sameSemantics(other: Dataset[T]): Boolean
- î
def sample(withReplacement: Boolean, fraction: Double): Dataset[T]
- î
def sample(withReplacement: Boolean, fraction: Double, seed: Long): Dataset[T]
- î
def sample(fraction: Double): Dataset[T]
- î
def sample(fraction: Double, seed: Long): Dataset[T]
- î
def schema: StructType
- î
def select[U1, U2, U3, U4, U5](c1: TypedColumn[T, U1], c2: TypedColumn[T, U2], c3: TypedColumn[T, U3], c4: TypedColumn[T, U4], c5: TypedColumn[T, U5]): Dataset[(U1, U2, U3, U4, U5)]
- î
def select[U1, U2, U3, U4](c1: TypedColumn[T, U1], c2: TypedColumn[T, U2], c3: TypedColumn[T, U3], c4: TypedColumn[T, U4]): Dataset[(U1, U2, U3, U4)]
- î
def select[U1, U2, U3](c1: TypedColumn[T, U1], c2: TypedColumn[T, U2], c3: TypedColumn[T, U3]): Dataset[(U1, U2, U3)]
- î
def select[U1, U2](c1: TypedColumn[T, U1], c2: TypedColumn[T, U2]): Dataset[(U1, U2)]
- î
def select[U1](c1: TypedColumn[T, U1]): Dataset[U1]
- î
def select(col: String, cols: String*): DataFrame
- î
def select(cols: Column*): DataFrame
- î
def selectExpr(exprs: String*): DataFrame
- î
def selectUntyped(columns: TypedColumn[_, _]*): Dataset[_]
- î
def semanticHash(): Int
- î
def show(numRows: Int, truncate: Int, vertical: Boolean): Unit
- î
def show(numRows: Int, truncate: Int): Unit
- î
def show(numRows: Int, truncate: Boolean): Unit
- î
def show(truncate: Boolean): Unit
- î
def show(): Unit
- î
def show(numRows: Int): Unit
- î
def sort(sortExprs: Column*): Dataset[T]
- î
def sort(sortCol: String, sortCols: String*): Dataset[T]
- î
def sortWithinPartitions(sortExprs: Column*): Dataset[T]
- î
def sortWithinPartitions(sortCol: String, sortCols: String*): Dataset[T]
- î
lazy val sparkSession: SparkSession
- î
lazy val sqlContext: SQLContext
- î
def stat: DataFrameStatFunctions
- î
def storageLevel: StorageLevel
- î
def summary(statistics: String*): DataFrame
- î
final def synchronized[T0](arg0: â T0): T0
- î
def tail(n: Int): Array[T]
- î
def take(n: Int): Array[T]
- î
def takeAsList(n: Int): List[T]
- î
def toDF(colNames: String*): DataFrame
- î
def toDF(): DataFrame
- î
def toJSON: Dataset[String]
- î
def toJavaRDD: JavaRDD[T]
- î
def toLocalIterator(): Iterator[T]
- î
def toString(): String
- î
def transform[U](t: (Dataset[T]) â Dataset[U]): Dataset[U]
- î
def union(other: Dataset[T]): Dataset[T]
- î
def unionAll(other: Dataset[T]): Dataset[T]
- î
def unionByName(other: Dataset[T], allowMissingColumns: Boolean): Dataset[T]
- î
def unionByName(other: Dataset[T]): Dataset[T]
- î
def unpersist(): Dataset.this.type
- î
def unpersist(blocking: Boolean): Dataset.this.type
- î
final def wait(): Unit
- î
final def wait(arg0: Long, arg1: Int): Unit
- î
final def wait(arg0: Long): Unit
- î
def where(conditionExpr: String): Dataset[T]
- î
def where(condition: Column): Dataset[T]
- î
def withColumn(colName: String, col: Column): DataFrame
- î
def withColumnRenamed(existingName: String, newName: String): DataFrame
- î
def withColumns(colsMap: Map[String, Column]): DataFrame
- î
def withColumns(colsMap: Map[String, Column]): DataFrame
- î
def withMetadata(columnName: String, metadata: Metadata): DataFrame
- î
def withWatermark(eventTime: String, delayThreshold: String): Dataset[T]
- î
def write: DataFrameWriter[T]
- î
def writeStream: DataStreamWriter[T]
- î
def writeTo(table: String): DataFrameWriterV2[T]
Deprecated Value Members
- î
def explode[A, B](inputColumn: String, outputColumn: String)(f: (A) â TraversableOnce[B])(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[B]): DataFrame
- î
def explode[A <: Product](input: Column*)(f: (Row) â TraversableOnce[A])(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[A]): DataFrame
- î
def registerTempTable(tableName: String): Unit
Inherited from Serializable
Inherited from Serializable
Inherited from Any
Actions
Basic Dataset functions
streaming
Typed transformations
Untyped transformations
Ungrouped
RetroSearch is an open source project built by @garambo
| Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4