TransformableRDD

final def !=(arg0: AnyRef): Boolean

final def !=(arg0: Any): Boolean

final def ##(): Int

def ++(other: RDD[String]): RDD[String]

final def ==(arg0: AnyRef): Boolean

final def ==(arg0: Any): Boolean

def addColumnsFrom(otherRDD: TransformableRDD): TransformableRDD

Zips the other TransformableRDD with this TransformableRDD and returns a new TransformableRDD with current file format.

def aggregate[U](zeroValue: U)(seqOp: (U, String) ⇒ U, combOp: (U, U) ⇒ U)(implicit arg0: ClassTag[U]): U

final def asInstanceOf[T0]: T0

def cache(): TransformableRDD.this.type

def cartesian[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[(String, U)]

def checkpoint(): Unit

def clearDependencies(): Unit

def clone(): AnyRef

def clusters(columnIndex: Int, clusteringAlgorithm: ClusteringAlgorithm): Clusters

Returns Clusters that has all cluster of text of @columnIndex according to @algorithm

def coalesce(numPartitions: Int, shuffle: Boolean)(implicit ord: Ordering[String]): RDD[String]

def collect[U](f: PartialFunction[String, U])(implicit arg0: ClassTag[U]): RDD[U]

def collect(): Array[String]

val columnLength: Int

def compute(split: Partition, context: TaskContext): Iterator[String]

def context: SparkContext

def count(): Long

def countApprox(timeout: Long, confidence: Double): PartialResult[BoundedDouble]

def countApproxDistinct(relativeSD: Double): Long

def countApproxDistinct(p: Int, sp: Int): Long

def countByValue()(implicit ord: Ordering[String]): Map[String, Long]

def countByValueApprox(timeout: Long, confidence: Double)(implicit ord: Ordering[String]): PartialResult[Map[String, BoundedDouble]]

def deduplicate(primaryKeyColumns: List[Int]): TransformableRDD

Returns a new TransformableRDD containing unique duplicate records of this TransformableRDD by considering the given columns as primary key.

def deduplicate(): TransformableRDD

Returns a new TransformableRDD containing unique duplicate records of this TransformableRDD by considering all the columns as primary key.

final def dependencies: Seq[Dependency[_]]

def distinct(): RDD[String]

def distinct(numPartitions: Int)(implicit ord: Ordering[String]): RDD[String]

def drop(columnIndex: Int, columnIndexes: Int*): TransformableRDD

Returns a new TransformableRDD by dropping the @columnIndex

def duplicates(primaryKeyColumns: List[Int]): TransformableRDD

Returns a new TransformableRDD containing unique duplicate records of this TransformableRDD by considering the given columns as primary key.

def duplicates(): TransformableRDD

Returns a new TransformableRDD containing duplicate records of this TransformableRDD by considering all the columns as primary key.

def duplicatesAt(columnIndex: Int): RDD[String]

Returns a new RDD containing the duplicate values at the specified column

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def filter(f: (String) ⇒ Boolean): RDD[String]

def finalize(): Unit

def first(): String

def firstParent[U](implicit arg0: ClassTag[U]): RDD[U]

def flag(symbol: String, markerPredicate: (RowRecord) ⇒ Boolean): TransformableRDD

Returns a new TransformableRDD that contains records flagged by @symbol based on the evaluation of @markerPredicate

def flatMap[U](f: (String) ⇒ TraversableOnce[U])(implicit arg0: ClassTag[U]): RDD[U]

def fold(zeroValue: String)(op: (String, String) ⇒ String): String

def foreach(f: (String) ⇒ Unit): Unit

def foreachPartition(f: (Iterator[String]) ⇒ Unit): Unit

def getCheckpointFile: Option[String]

final def getClass(): Class[_]

def getDependencies: Seq[Dependency[_]]

final def getNumPartitions: Int

def getPartitions: Array[Partition]

def getPreferredLocations(split: Partition): Seq[String]

def getStorageLevel: StorageLevel

def glom(): RDD[Array[String]]

def groupBy[K](f: (String) ⇒ K, p: Partitioner)(implicit kt: ClassTag[K], ord: Ordering[K]): RDD[(K, Iterable[String])]

def groupBy[K](f: (String) ⇒ K, numPartitions: Int)(implicit kt: ClassTag[K]): RDD[(K, Iterable[String])]

def groupBy[K](f: (String) ⇒ K)(implicit kt: ClassTag[K]): RDD[(K, Iterable[String])]

def hashCode(): Int

val id: Int

def impute(columnIndex: Int, strategy: ImputationStrategy, missingHints: List[String]): TransformableRDD

Returns a new TransformableRDD by imputing missing values and @missingHints of the @columnIndex using the @strategy

def impute(column: Int, strategy: ImputationStrategy): TransformableRDD

Returns a new TransformableRDD by imputing missing values of the @columnIndex using the @strategy

def inferType(columnIndex: Int): DataType

Returns inferred DataType of @columnIndex

def intersection(other: RDD[String], numPartitions: Int): RDD[String]

def intersection(other: RDD[String], partitioner: Partitioner)(implicit ord: Ordering[String]): RDD[String]

def intersection(other: RDD[String]): RDD[String]

def isCheckpointed: Boolean

def isEmpty(): Boolean

final def isInstanceOf[T0]: Boolean

def isTraceEnabled(): Boolean

final def iterator(split: Partition, context: TaskContext): Iterator[String]

def keyBy[K](f: (String) ⇒ K): RDD[(K, String)]

def listFacets(columnIndexes: List[Int]): TextFacets

Returns a new TextFacet containing the facets of @columnIndexes

def listFacets(columnIndex: Int): TextFacets

Returns a new TextFacet containing the cardinal values of @columnIndex

def localCheckpoint(): TransformableRDD.this.type

def log: Logger

def logDebug(msg: ⇒ String, throwable: Throwable): Unit

def logDebug(msg: ⇒ String): Unit

def logError(msg: ⇒ String, throwable: Throwable): Unit

def logError(msg: ⇒ String): Unit

def logInfo(msg: ⇒ String, throwable: Throwable): Unit

def logInfo(msg: ⇒ String): Unit

def logName: String

def logTrace(msg: ⇒ String, throwable: Throwable): Unit

def logTrace(msg: ⇒ String): Unit

def logWarning(msg: ⇒ String, throwable: Throwable): Unit

def logWarning(msg: ⇒ String): Unit

def map[U](f: (String) ⇒ U)(implicit arg0: ClassTag[U]): RDD[U]

def mapByFlag(symbol: String, symbolColumnIndex: Int, mapFunction: (String) ⇒ String): TransformableRDD

Returns a new TransformableRDD by applying the function on all rows marked as @flag

def mapPartitions[U](f: (Iterator[String]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

def mapPartitionsWithIndex[U](f: (Int, Iterator[String]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

def max()(implicit ord: Ordering[String]): String

def mergeColumns(columns: List[Int], separator: String = " ", retainColumns: Boolean = false): TransformableRDD

Returns a new TransformableRDD by merging 2 or more columns together

def min()(implicit ord: Ordering[String]): String

def multiplyColumns(firstColumn: Int, secondColumn: Int): RDD[Double]

Returns a RDD of double which is a product of the values in @firstColumn and @secondColumn

var name: String

final def ne(arg0: AnyRef): Boolean

def normalize(columnIndex: Int, normalizer: NormalizationStrategy): TransformableRDD

Returns a new TransformableRDD by normalizing values of the given column using different Normalizers

final def notify(): Unit

final def notifyAll(): Unit

def numberOfColumns(): Int

Returns number of column in this rdd

def parent[U](j: Int)(implicit arg0: ClassTag[U]): RDD[U]

val partitioner: Option[Partitioner]

final def partitions: Array[Partition]

def persist(): TransformableRDD.this.type

def persist(newLevel: StorageLevel): TransformableRDD.this.type

def pipe(command: Seq[String], env: Map[String, String], printPipeContext: ((String) ⇒ Unit) ⇒ Unit, printRDDElement: (String, (String) ⇒ Unit) ⇒ Unit, separateWorkingDir: Boolean): RDD[String]

def pipe(command: String, env: Map[String, String]): RDD[String]

def pipe(command: String): RDD[String]

def pivotByCount(pivotalColumn: Int, independentColumnIndexes: Seq[Int]): PivotTable[Integer]

Generates a PivotTable by pivoting data in the pivotalColumn

final def preferredLocations(split: Partition): Seq[String]

def randomSplit(weights: Array[Double], seed: Long): Array[RDD[String]]

def reduce(f: (String, String) ⇒ String): String

def removeRows(predicate: (RowRecord) ⇒ Boolean): TransformableRDD

Returns a new TransformableRDD containing only the elements that satisfy the matchInDictionary.

def repartition(numPartitions: Int)(implicit ord: Ordering[String]): RDD[String]

def replaceValues(cluster: Cluster, newValue: String, columnIndex: Int): TransformableRDD

Returns a new TransformableRDD by replacing the @cluster's text with specified @newValue

def sample(withReplacement: Boolean, fraction: Double, seed: Long): RDD[String]

def sampleColumnValues(columnIndex: Int): List[String]

Returns a List of some elements of @columnIndex

val sampleRecords: List[String]

def saveAsObjectFile(path: String): Unit

def saveAsTextFile(path: String, codec: Class[_ <: CompressionCodec]): Unit

def saveAsTextFile(path: String): Unit

def select(columnIndexes: List[Int]): TransformableRDD

Returns a new TransformableRDD containing values of @columnIndexes

def select(columnIndex: Int): RDD[String]

Returns a RDD of given column

def setName(_name: String): TransformableRDD.this.type

def smooth(columnIndex: Int, smoothingMethod: SmoothingMethod): RDD[Double]

Returns a new RDD containing smoothed values of @columnIndex using @smoothingMethod

def sortBy[K](f: (String) ⇒ K, ascending: Boolean, numPartitions: Int)(implicit ord: Ordering[K], ctag: ClassTag[K]): RDD[String]

def sparkContext: SparkContext

def splitByDelimiter(column: Int, delimiter: String, retainColumn: Boolean = false, maxSplit: Int = 1): TransformableRDD

Returns a new TransformableRDD by splitting the @column by the delimiter provided

def splitByFieldLength(column: Int, fieldLengths: List[Int], retainColumn: Boolean = false): TransformableRDD

Returns a TransformableRDD by splitting the @column according to the specified lengths

def subtract(other: RDD[String], p: Partitioner)(implicit ord: Ordering[String]): RDD[String]

def subtract(other: RDD[String], numPartitions: Int): RDD[String]

def subtract(other: RDD[String]): RDD[String]

final def synchronized[T0](arg0: ⇒ T0): T0

def take(num: Int): Array[String]

def takeOrdered(num: Int)(implicit ord: Ordering[String]): Array[String]

def takeSample(withReplacement: Boolean, num: Int, seed: Long): Array[String]

def toDebugString: String

def toDoubleRDD(columnIndex: Int): RDD[Double]

Returns a double RDD of given column index

def toJavaRDD(): JavaRDD[String]

def toLocalIterator: Iterator[String]

def toRDD: RDD[String]

Returns RDD

def toString(): String

def top(num: Int)(implicit ord: Ordering[String]): Array[String]

def treeAggregate[U](zeroValue: U)(seqOp: (U, String) ⇒ U, combOp: (U, U) ⇒ U, depth: Int)(implicit arg0: ClassTag[U]): U

def treeReduce(f: (String, String) ⇒ String, depth: Int): String

def union(other: RDD[String]): RDD[String]

def unique(columnIndex: Int): RDD[String]

Returns a new TransformableRDD containing the unique elements in the specified column

def unpersist(blocking: Boolean): TransformableRDD.this.type

def validateColumnIndex(columnIndexes: List[Int]): Unit

def validateColumnIndex(columnIndex: Int): Unit

def validateNumericColumn(columnIndex: Int): Unit

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

def zip[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[(String, U)]

def zipPartitions[B, C, D, V](rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D])(f: (Iterator[String], Iterator[B], Iterator[C], Iterator[D]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[D], arg3: ClassTag[V]): RDD[V]

def zipPartitions[B, C, D, V](rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D], preservesPartitioning: Boolean)(f: (Iterator[String], Iterator[B], Iterator[C], Iterator[D]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[D], arg3: ClassTag[V]): RDD[V]

def zipPartitions[B, C, V](rdd2: RDD[B], rdd3: RDD[C])(f: (Iterator[String], Iterator[B], Iterator[C]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[V]): RDD[V]

def zipPartitions[B, C, V](rdd2: RDD[B], rdd3: RDD[C], preservesPartitioning: Boolean)(f: (Iterator[String], Iterator[B], Iterator[C]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[V]): RDD[V]

def zipPartitions[B, V](rdd2: RDD[B])(f: (Iterator[String], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]

def zipPartitions[B, V](rdd2: RDD[B], preservesPartitioning: Boolean)(f: (Iterator[String], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]

def zipWithIndex(): RDD[(String, Long)]

def zipWithUniqueId(): RDD[(String, Long)]

def filterWith[A](constructA: (Int) ⇒ A)(p: (String, A) ⇒ Boolean): RDD[String]

def flatMapWith[A, U](constructA: (Int) ⇒ A, preservesPartitioning: Boolean)(f: (String, A) ⇒ Seq[U])(implicit arg0: ClassTag[U]): RDD[U]

def foreachWith[A](constructA: (Int) ⇒ A)(f: (String, A) ⇒ Unit): Unit

def mapPartitionsWithContext[U](f: (TaskContext, Iterator[String]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

def mapPartitionsWithSplit[U](f: (Int, Iterator[String]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

def mapWith[A, U](constructA: (Int) ⇒ A, preservesPartitioning: Boolean)(f: (String, A) ⇒ U)(implicit arg0: ClassTag[U]): RDD[U]

def toArray(): Array[String]