StopWordsRemover

Instance Constructors

new StopWordsRemover()

Annotations
@Since( "1.5.0" )
new StopWordsRemover(uid: String)

Annotations
@Since( "1.5.0" )

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def $[T](param: Param[T]): T

An alias for getOrDefault().
An alias for getOrDefault().

Attributes
protected
Definition Classes
Params
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def asInstanceOf[T0]: T0

Definition Classes
Any
val caseSensitive: BooleanParam

Whether to do a case sensitive comparison over the stop words.
Whether to do a case sensitive comparison over the stop words. Default: false

Annotations
@Since( "1.5.0" )
final def clear(param: Param[_]): StopWordsRemover.this.type

Clears the user-supplied value for the input param.
Clears the user-supplied value for the input param.

Definition Classes
Params
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def copy(extra: ParamMap): StopWordsRemover

Creates a copy of this instance with the same UID and some extra params.
Creates a copy of this instance with the same UID and some extra params. Subclasses should implement this method and set the return type properly. See defaultCopy().

Definition Classes
StopWordsRemover → Transformer → PipelineStage → Params
Annotations
@Since( "1.5.0" )
def copyValues[T <: Params](to: T, extra: ParamMap = ParamMap.empty): T

Copies param values from this instance to another instance for params shared by them.
Copies param values from this instance to another instance for params shared by them.
This handles default Params and explicitly set Params separately. Default Params are copied from and to defaultParamMap, and explicitly set Params are copied from and to paramMap. Warning: This implicitly assumes that this Params instance and the target instance share the same set of default Params.
to
the target instance, which should work with the same set of default Params as this source instance
extra
extra params to be copied to the target's paramMap
returns
the target instance with param values copied

Attributes
protected
Definition Classes
Params
final def defaultCopy[T <: Params](extra: ParamMap): T

Default implementation of copy with extra params.
Default implementation of copy with extra params. It tries to create a new instance with the same UID. Then it copies the embedded and extra parameters over and returns the new instance.

Attributes
protected
Definition Classes
Params
final def eq(arg0: AnyRef): Boolean

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

Definition Classes
AnyRef → Any
def explainParam(param: Param[_]): String

Explains a param.
Explains a param.
param
input param, must belong to this instance.
returns
a string that contains the input param name, doc, and optionally its default value and the user-supplied value

Definition Classes
Params
def explainParams(): String

Explains all params of this instance.
Explains all params of this instance. See explainParam().

Definition Classes
Params
final def extractParamMap(): ParamMap

extractParamMap with no extra values.
extractParamMap with no extra values.

Definition Classes
Params
final def extractParamMap(extra: ParamMap): ParamMap

Extracts the embedded default param values and user-supplied values, and then merges them with extra values from input into a flat param map, where the latter value is used if there exist conflicts, i.e., with ordering: default param values less than user-supplied values less than extra.
Extracts the embedded default param values and user-supplied values, and then merges them with extra values from input into a flat param map, where the latter value is used if there exist conflicts, i.e., with ordering: default param values less than user-supplied values less than extra.

Definition Classes
Params
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def get[T](param: Param[T]): Option[T]

Optionally returns the user-supplied value of a param.
Optionally returns the user-supplied value of a param.

Definition Classes
Params
def getCaseSensitive: Boolean

Annotations
@Since( "1.5.0" )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
final def getDefault[T](param: Param[T]): Option[T]

Gets the default value of a parameter.
Gets the default value of a parameter.

Definition Classes
Params
final def getInputCol: String

Definition Classes
HasInputCol
def getLocale: String

Annotations
@Since( "2.4.0" )
final def getOrDefault[T](param: Param[T]): T

Gets the value of a param in the embedded param map or its default value.
Gets the value of a param in the embedded param map or its default value. Throws an exception if neither is set.

Definition Classes
Params
final def getOutputCol: String

Definition Classes
HasOutputCol
def getParam(paramName: String): Param[Any]

Gets a param by its name.
Gets a param by its name.

Definition Classes
Params
def getStopWords: Array[String]

Annotations
@Since( "1.5.0" )
final def hasDefault[T](param: Param[T]): Boolean

Tests whether the input param has a default value set.
Tests whether the input param has a default value set.

Definition Classes
Params
def hasParam(paramName: String): Boolean

Tests whether this instance contains a param with a given name.
Tests whether this instance contains a param with a given name.

Definition Classes
Params
def hashCode(): Int

Definition Classes
AnyRef → Any
def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean = false): Boolean

Attributes
protected
Definition Classes
Logging
def initializeLogIfNecessary(isInterpreter: Boolean): Unit

Attributes
protected
Definition Classes
Logging
final val inputCol: Param[String]

Param for input column name.
Param for input column name.

Definition Classes
HasInputCol
final def isDefined(param: Param[_]): Boolean

Checks whether a param is explicitly set or has a default value.
Checks whether a param is explicitly set or has a default value.

Definition Classes
Params
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
final 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
val locale: Param[String]

Locale of the input for case insensitive matching.
Locale of the input for case insensitive matching. Ignored when caseSensitive is true. Default: Locale.getDefault.toString

Annotations
@Since( "2.4.0" )
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
final val outputCol: Param[String]

Param for output column name.
Param for output column name.

Definition Classes
HasOutputCol
lazy val params: Array[Param[_]]

Returns all params sorted by their names.
Returns all params sorted by their names. The default implementation uses Java reflection to list all public methods that have no arguments and return Param.

Definition Classes
Params
Note
Developer should not use this method in constructor because we cannot guarantee that this variable gets initialized before other params.
def save(path: String): Unit

Saves this ML instance to the input path, a shortcut of write.save(path).
Saves this ML instance to the input path, a shortcut of write.save(path).

Definition Classes
MLWritable
Annotations
@Since( "1.6.0" ) @throws( ... )
final def set(paramPair: ParamPair[_]): StopWordsRemover.this.type

Sets a parameter in the embedded param map.
Sets a parameter in the embedded param map.

Attributes
protected
Definition Classes
Params
final def set(param: String, value: Any): StopWordsRemover.this.type

Sets a parameter (by name) in the embedded param map.
Sets a parameter (by name) in the embedded param map.

Attributes
protected
Definition Classes
Params
final def set[T](param: Param[T], value: T): StopWordsRemover.this.type

Sets a parameter in the embedded param map.
Sets a parameter in the embedded param map.

Definition Classes
Params
def setCaseSensitive(value: Boolean): StopWordsRemover.this.type

Annotations
@Since( "1.5.0" )
final def setDefault(paramPairs: ParamPair[_]*): StopWordsRemover.this.type

Sets default values for a list of params.
Sets default values for a list of params.
Note: Java developers should use the single-parameter setDefault. Annotating this with varargs can cause compilation failures due to a Scala compiler bug. See SPARK-9268.
paramPairs
a list of param pairs that specify params and their default values to set respectively. Make sure that the params are initialized before this method gets called.

Attributes
protected
Definition Classes
Params
final def setDefault[T](param: Param[T], value: T): StopWordsRemover.this.type

Sets a default value for a param.
Sets a default value for a param.
param
param to set the default value. Make sure that this param is initialized before this method gets called.
value
the default value

Attributes
protected
Definition Classes
Params
def setInputCol(value: String): StopWordsRemover.this.type

Annotations
@Since( "1.5.0" )
def setLocale(value: String): StopWordsRemover.this.type

Annotations
@Since( "2.4.0" )
def setOutputCol(value: String): StopWordsRemover.this.type

Annotations
@Since( "1.5.0" )
def setStopWords(value: Array[String]): StopWordsRemover.this.type

Annotations
@Since( "1.5.0" )
val stopWords: StringArrayParam

The words to be filtered out.
The words to be filtered out. Default: English stop words

Annotations
@Since( "1.5.0" )
See also
StopWordsRemover.loadDefaultStopWords()
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
def transform(dataset: Dataset[_]): DataFrame

Transforms the input dataset.
Transforms the input dataset.

Definition Classes
StopWordsRemover → Transformer
Annotations
@Since( "2.0.0" )
def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame

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
Annotations
@Since( "2.0.0" )
def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame

Transforms the dataset with optional parameters
Transforms the dataset with optional parameters
dataset
input dataset
firstParamPair
the first param pair, overwrite embedded params
otherParamPairs
other param pairs, overwrite embedded params
returns
transformed dataset

Definition Classes
Transformer
Annotations
@Since( "2.0.0" ) @varargs()
def transformSchema(schema: StructType): StructType

:: DeveloperApi ::
:: DeveloperApi ::
Check transform validity and derive the output schema from the input schema.
We check validity for interactions between parameters during transformSchema and raise an exception if any parameter value is invalid. Parameter value checks which do not depend on other parameters are handled by Param.validate().
Typical implementation should first conduct verification on schema change and parameter validity, including complex parameter interaction checks.

Definition Classes
StopWordsRemover → PipelineStage
Annotations
@Since( "1.5.0" )
def transformSchema(schema: StructType, logging: Boolean): StructType

:: DeveloperApi ::
:: DeveloperApi ::
Derives the output schema from the input schema and parameters, optionally with logging.
This should be optimistic. If it is unclear whether the schema will be valid, then it should be assumed valid until proven otherwise.

Attributes
protected
Definition Classes
PipelineStage
Annotations
@DeveloperApi()
val uid: String

An immutable unique ID for the object and its derivatives.
An immutable unique ID for the object and its derivatives.

Definition Classes
StopWordsRemover → Identifiable
Annotations
@Since( "1.5.0" )
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( ... )
def write: MLWriter

Returns an MLWriter instance for this ML instance.
Returns an MLWriter instance for this ML instance.

Definition Classes
DefaultParamsWritable → MLWritable

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from HasOutputCol

Inherited from HasInputCol

Inherited from Transformer

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

Parameters

A list of (hyper-)parameter keys this algorithm can take. Users can set and get the parameter values through setters and getters, respectively.

Members

Parameter setters

Parameter getters

Related Docs: object StopWordsRemover | package feature

class StopWordsRemover extends Transformer with HasInputCol with HasOutputCol with DefaultParamsWritable

Instance Constructors

new StopWordsRemover()

new StopWordsRemover(uid: String)

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def $[T](param: Param[T]): T

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

val caseSensitive: BooleanParam

final def clear(param: Param[_]): StopWordsRemover.this.type

def clone(): AnyRef

def copy(extra: ParamMap): StopWordsRemover

def copyValues[T <: Params](to: T, extra: ParamMap = ParamMap.empty): T

final def defaultCopy[T <: Params](extra: ParamMap): T

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def explainParam(param: Param[_]): String

def explainParams(): String

final def extractParamMap(): ParamMap

final def extractParamMap(extra: ParamMap): ParamMap

def finalize(): Unit

final def get[T](param: Param[T]): Option[T]

def getCaseSensitive: Boolean

final def getClass(): Class[_]

final def getDefault[T](param: Param[T]): Option[T]

final def getInputCol: String

def getLocale: String

final def getOrDefault[T](param: Param[T]): T

final def getOutputCol: String

def getParam(paramName: String): Param[Any]

def getStopWords: Array[String]

final def hasDefault[T](param: Param[T]): Boolean

def hasParam(paramName: String): Boolean

def hashCode(): Int

def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean = false): Boolean

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

final val inputCol: Param[String]

final def isDefined(param: Param[_]): Boolean

final def isInstanceOf[T0]: Boolean

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

def isTraceEnabled(): Boolean

val locale: Param[String]

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

final val outputCol: Param[String]

lazy val params: Array[Param[_]]

def save(path: String): Unit

final def set(paramPair: ParamPair[_]): StopWordsRemover.this.type

final def set(param: String, value: Any): StopWordsRemover.this.type

final def set[T](param: Param[T], value: T): StopWordsRemover.this.type

def setCaseSensitive(value: Boolean): StopWordsRemover.this.type

final def setDefault(paramPairs: ParamPair[_]*): StopWordsRemover.this.type

final def setDefault[T](param: Param[T], value: T): StopWordsRemover.this.type

def setInputCol(value: String): StopWordsRemover.this.type

def setLocale(value: String): StopWordsRemover.this.type

def setOutputCol(value: String): StopWordsRemover.this.type

def setStopWords(value: Array[String]): StopWordsRemover.this.type

val stopWords: StringArrayParam

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

def toString(): String

def transform(dataset: Dataset[_]): DataFrame

def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame

def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame