Tokenizer

Instance Constructors

new Tokenizer()

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[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def createTransformFunc(paramMap: ParamMap): (String) ⇒ Seq[String]

Creates the transform function using the given param map.
Creates the transform function using the given param map. The input param map already takes account of the embedded param map. So the param values should be determined solely by the input param map.

Attributes
protected
Definition Classes
Tokenizer → UnaryTransformer
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def explainParams(): String

Returns the documentation of all params.
Returns the documentation of all params.

Definition Classes
Params
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def getInputCol: String

Definition Classes
HasInputCol
def getOutputCol: String

Definition Classes
HasOutputCol
def hashCode(): Int

Definition Classes
AnyRef → Any
val inputCol: Param[String]

param for input column name
param for input column name

Definition Classes
HasInputCol
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
def isSet(param: Param[_]): Boolean

Checks whether a param is explicitly set.
Checks whether a param is explicitly set.

Definition Classes
Params
def isTraceEnabled(): Boolean

Attributes
protected
Definition Classes
Logging
def log: Logger

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logName: String

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
val outputCol: Param[String]

param for output column name
param for output column name

Definition Classes
HasOutputCol
def outputDataType: DataType

Returns the data type of the output column.
Returns the data type of the output column.

Attributes
protected
Definition Classes
Tokenizer → UnaryTransformer
val paramMap: ParamMap

Internal param map.
Internal param map.

Attributes
protected
Definition Classes
Params
def params: Array[Param[_]]

Returns all params.
Returns all params.

Definition Classes
Params
def setInputCol(value: String): Tokenizer

Definition Classes
UnaryTransformer
def setOutputCol(value: String): Tokenizer

Definition Classes
UnaryTransformer
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
AnyRef → Any
def transform(dataset: SchemaRDD, paramMap: ParamMap): SchemaRDD

Transforms the dataset with provided parameter map as additional parameters.
Transforms the dataset with provided parameter map as additional parameters.
dataset
input dataset
paramMap
additional parameters, overwrite embedded params
returns
transformed dataset

Definition Classes
UnaryTransformer → Transformer
def transform(dataset: JavaSchemaRDD, paramMap: ParamMap): JavaSchemaRDD

Transforms the dataset with provided parameter map as additional parameters.
Transforms the dataset with provided parameter map as additional parameters.
dataset
input dataset
paramMap
additional parameters, overwrite embedded params
returns
transformed dataset

Definition Classes
Transformer
def transform(dataset: JavaSchemaRDD, paramPairs: ParamPair[_]*): JavaSchemaRDD

Transforms the dataset with optional parameters.
Transforms the dataset with optional parameters.
dataset
input datset
paramPairs
optional list of param pairs, overwrite embedded params
returns
transformed dataset

Definition Classes
Transformer
Annotations
@varargs()
def transform(dataset: SchemaRDD, paramPairs: ParamPair[_]*): SchemaRDD

Transforms the dataset with optional parameters
Transforms the dataset with optional parameters
dataset
input dataset
paramPairs
optional list of param pairs, overwrite embedded params
returns
transformed dataset

Definition Classes
Transformer
Annotations
@varargs()
def transformSchema(schema: StructType, paramMap: ParamMap): StructType

Derives the output schema from the input schema and parameters.
Derives the output schema from the input schema and parameters.

Definition Classes
UnaryTransformer → PipelineStage
def transformSchema(schema: StructType, paramMap: ParamMap, logging: Boolean): StructType

Derives the output schema from the input schema and parameters, optionally with logging.
Derives the output schema from the input schema and parameters, optionally with logging.

Attributes
protected
Definition Classes
PipelineStage
def validate(): Unit

Validates parameter values stored internally.
Validates parameter values stored internally. Raise an exception if any parameter value is invalid.

Definition Classes
Params
def validate(paramMap: ParamMap): Unit

Validates parameter values stored internally plus the input parameter map.
Validates parameter values stored internally plus the input parameter map. Raises an exception if any parameter is invalid.

Definition Classes
Params
def validateInputType(inputType: DataType): Unit

Validates the input type.
Validates the input type. Throw an exception if it is invalid.

Attributes
protected
Definition Classes
Tokenizer → UnaryTransformer
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( ... )

class Tokenizer extends UnaryTransformer[String, Seq[String], Tokenizer]

Instance Constructors

new Tokenizer()

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def clone(): AnyRef

def createTransformFunc(paramMap: ParamMap): (String) ⇒ Seq[String]

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def explainParams(): String

def finalize(): Unit

final def getClass(): Class[_]

def getInputCol: String

def getOutputCol: String

def hashCode(): Int

val inputCol: Param[String]

final def isInstanceOf[T0]: Boolean

def isSet(param: Param[_]): Boolean

def isTraceEnabled(): Boolean

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

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

val outputCol: Param[String]

def outputDataType: DataType

val paramMap: ParamMap

def params: Array[Param[_]]

def setInputCol(value: String): Tokenizer

def setOutputCol(value: String): Tokenizer

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

def toString(): String

def transform(dataset: SchemaRDD, paramMap: ParamMap): SchemaRDD

def transform(dataset: JavaSchemaRDD, paramMap: ParamMap): JavaSchemaRDD

def transform(dataset: JavaSchemaRDD, paramPairs: ParamPair[_]*): JavaSchemaRDD

def transform(dataset: SchemaRDD, paramPairs: ParamPair[_]*): SchemaRDD

def transformSchema(schema: StructType, paramMap: ParamMap): StructType

def transformSchema(schema: StructType, paramMap: ParamMap, logging: Boolean): StructType

def validate(): Unit

def validate(paramMap: ParamMap): Unit

def validateInputType(inputType: DataType): Unit

final def wait(): Unit

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

final def wait(arg0: Long): Unit

Inherited from UnaryTransformer[String, Seq[String], Tokenizer]

Inherited from HasOutputCol

Inherited from HasInputCol

Inherited from Transformer

Inherited from Params

Inherited from Identifiable

Inherited from PipelineStage

Inherited from Logging

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped