Packages

t

com.microsoft.azure.synapse.ml.featurize.text

TextFeaturizerParams

trait TextFeaturizerParams extends Wrappable with DefaultParamsWritable

Linear Supertypes
DefaultParamsWritable, MLWritable, Wrappable, RWrappable, PythonWrappable, BaseWrappable, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Known Subclasses
TextFeaturizer
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. TextFeaturizerParams
  2. DefaultParamsWritable
  3. MLWritable
  4. Wrappable
  5. RWrappable
  6. PythonWrappable
  7. BaseWrappable
  8. Params
  9. Serializable
  10. Serializable
  11. Identifiable
  12. AnyRef
  13. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Abstract Value Members

  1. abstract def copy(extra: ParamMap): Params
    Definition Classes
    Params
  2. abstract val uid: String
    Definition Classes
    Identifiable

Concrete Value Members

  1. val binary: BooleanParam

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

  2. val caseSensitiveStopWords: BooleanParam

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

  3. final def clear(param: Param[_]): TextFeaturizerParams.this.type
    Definition Classes
    Params
  4. val defaultStopWordLanguage: Param[String]

    Specify the language to use for stop word removal.

    Specify the language to use for stop word removal. The Use the custom setting when using the stopWords input

  5. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  6. def explainParams(): String
    Definition Classes
    Params
  7. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  8. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  9. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  10. final def getBinary: Boolean

  11. final def getCaseSensitiveStopWords: Boolean

  12. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  13. final def getDefaultStopWordLanguage: String

  14. final def getMinDocFreq: Int

  15. final def getMinTokenLength: Int

  16. final def getNGramLength: Int

  17. final def getNumFeatures: Int

  18. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  19. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  20. def getParamInfo(p: Param[_]): ParamInfo[_]
    Definition Classes
    BaseWrappable
  21. final def getStopWords: String

  22. final def getToLowercase: Boolean

  23. final def getTokenizerGaps: Boolean

  24. final def getTokenizerPattern: String

  25. final def getUseIDF: Boolean

  26. final def getUseNGram: Boolean

  27. final def getUseStopWordsRemover: Boolean

  28. final def getUseTokenizer: Boolean

  29. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  30. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  31. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  32. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  33. def makePyFile(conf: CodegenConfig): Unit
    Definition Classes
    PythonWrappable
  34. def makeRFile(conf: CodegenConfig): Unit
    Definition Classes
    RWrappable
  35. val minDocFreq: IntParam

    Minimum number of documents in which a term should appear.

  36. val minTokenLength: IntParam

    Minumum token length; must be 0 or greater.

  37. val nGramLength: IntParam

    The size of the Ngrams

  38. val numFeatures: IntParam

    Set the number of features to hash each document to

  39. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  40. def pyAdditionalMethods: String
    Definition Classes
    PythonWrappable
  41. def pyInitFunc(): String
    Definition Classes
    PythonWrappable
  42. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  43. final def set[T](param: Param[T], value: T): TextFeaturizerParams.this.type
    Definition Classes
    Params
  44. val stopWords: Param[String]

    The words to be filtered out.

    The words to be filtered out. This is a comma separated list of words, encoded as a single string. For example, "a, the, and"

  45. val toLowercase: BooleanParam

    Indicates whether to convert all characters to lowercase before tokenizing.

  46. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  47. val tokenizerGaps: BooleanParam

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

  48. val tokenizerPattern: Param[String]

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

  49. val useIDF: BooleanParam

    Scale the Term Frequencies by IDF when set to true

  50. val useNGram: BooleanParam

    Enumerate N grams when set

  51. val useStopWordsRemover: BooleanParam

    Indicates whether to remove stop words from tokenized data.

  52. val useTokenizer: BooleanParam

    Tokenize the input when set to true

  53. def write: MLWriter
    Definition Classes
    DefaultParamsWritable → MLWritable