TextFeaturizerParams

abstract def copy(extra: ParamMap): Params

abstract val uid: String

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 binary: BooleanParam

All nonnegative word counts are set to 1 when set to true

val caseSensitiveStopWords: BooleanParam

Indicates whether a case sensitive comparison is performed on stop words.

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

def clone(): AnyRef

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

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

val defaultStopWordLanguage: Param[String]

Specify the language to use for stop word removal.

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]

final def getBinary: Boolean

final def getCaseSensitiveStopWords: Boolean

final def getClass(): Class[_]

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

final def getDefaultStopWordLanguage: String

final def getMinDocFreq: Int

final def getMinTokenLength: Int

final def getNGramLength: Int

final def getNumFeatures: Int

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

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

final def getStopWords: String

final def getToLowercase: Boolean

final def getTokenizerGaps: Boolean

final def getTokenizerPattern: String

final def getUseIDF: Boolean

final def getUseNGram: Boolean

final def getUseStopWordsRemover: Boolean

final def getUseTokenizer: Boolean

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

def hasParam(paramName: String): Boolean

def hashCode(): Int

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

final def isInstanceOf[T0]: Boolean

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

val minDocFreq: IntParam

Minimum number of documents in which a term should appear.

val minTokenLength: IntParam

Minumum token length; must be 0 or greater.

val nGramLength: IntParam

The size of the Ngrams

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

val numFeatures: IntParam

Set the number of features to hash each document to

lazy val params: Array[Param[_]]

def save(path: String): Unit

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

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

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

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

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

val stopWords: Param[String]

The words to be filtered out.

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

val toLowercase: BooleanParam

Indicates whether to convert all characters to lowercase before tokenizing.

def toString(): String

val tokenizerGaps: BooleanParam

Indicates whether the regex splits on gaps (true) or matches tokens (false)

val tokenizerPattern: Param[String]

Regex pattern used to match delimiters if gaps (true) or tokens (false)

val useIDF: BooleanParam

Scale the Term Frequencies by IDF when set to true

val useNGram: BooleanParam

Enumerate N grams when set

val useStopWordsRemover: BooleanParam

Indicates whether to remove stop words from tokenized data.

val useTokenizer: BooleanParam

Tokenize the input when set to true

final def wait(): Unit

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

final def wait(arg0: Long): Unit

def write: MLWriter