class TextPreprocessor extends Transformer with HasInputCol with HasOutputCol with Wrappable with ComplexParamsWritable with SynapseMLLogging

TextPreprocessor takes a dataframe and a dictionary that maps (text -> replacement text), scans each cell in the input col and replaces all substring matches with the corresponding value. Priority is given to longer keys and from left to right.

Linear Supertypes
SynapseMLLogging, ComplexParamsWritable, MLWritable, Wrappable, DotnetWrappable, RWrappable, PythonWrappable, BaseWrappable, HasOutputCol, HasInputCol, Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. TextPreprocessor
  2. SynapseMLLogging
  3. ComplexParamsWritable
  4. MLWritable
  5. Wrappable
  6. DotnetWrappable
  7. RWrappable
  8. PythonWrappable
  9. BaseWrappable
  10. HasOutputCol
  11. HasInputCol
  12. Transformer
  13. PipelineStage
  14. Logging
  15. Params
  16. Serializable
  17. Serializable
  18. Identifiable
  19. AnyRef
  20. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new TextPreprocessor()
  2. new TextPreprocessor(uid: String)

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def $[T](param: Param[T]): T
    Attributes
    protected
    Definition Classes
    Params
  4. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  5. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  6. lazy val classNameHelper: String
    Attributes
    protected
    Definition Classes
    BaseWrappable
  7. final def clear(param: Param[_]): TextPreprocessor.this.type
    Definition Classes
    Params
  8. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  9. def companionModelClassName: String
    Attributes
    protected
    Definition Classes
    BaseWrappable
  10. def copy(extra: ParamMap): TextPreprocessor
    Definition Classes
    TextPreprocessor → Transformer → PipelineStage → Params
  11. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  12. lazy val copyrightLines: String
    Attributes
    protected
    Definition Classes
    BaseWrappable
  13. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  14. def dotnetAdditionalMethods: String
    Definition Classes
    DotnetWrappable
  15. def dotnetClass(): String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  16. lazy val dotnetClassName: String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  17. lazy val dotnetClassNameString: String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  18. lazy val dotnetClassWrapperName: String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  19. lazy val dotnetCopyrightLines: String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  20. def dotnetExtraEstimatorImports: String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  21. def dotnetExtraMethods: String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  22. lazy val dotnetInternalWrapper: Boolean
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  23. def dotnetMLReadWriteMethods: String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  24. lazy val dotnetNamespace: String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  25. lazy val dotnetObjectBaseClass: String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  26. def dotnetParamGetter(p: Param[_]): String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  27. def dotnetParamGetters: String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  28. def dotnetParamSetter(p: Param[_]): String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  29. def dotnetParamSetters: String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  30. def dotnetWrapAsTypeMethod: String
    Attributes
    protected
    Definition Classes
    DotnetWrappable
  31. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  32. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  33. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  34. def explainParams(): String
    Definition Classes
    Params
  35. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  36. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  37. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  38. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  39. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  40. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  41. def getInputCol: String

    Definition Classes
    HasInputCol
  42. def getMap: Map[String, String]

  43. def getNormFunc: String

  44. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  45. def getOutputCol: String

    Definition Classes
    HasOutputCol
  46. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  47. def getParamInfo(p: Param[_]): ParamInfo[_]
    Definition Classes
    BaseWrappable
  48. def getPayload(methodName: String, numCols: Option[Int], executionSeconds: Option[Double], exception: Option[Exception]): Map[String, String]
    Attributes
    protected
    Definition Classes
    SynapseMLLogging
  49. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  50. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  51. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  52. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  53. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  54. val inputCol: Param[String]

    The name of the input column

    The name of the input column

    Definition Classes
    HasInputCol
  55. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  56. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  57. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  58. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  59. def isValidNormFunc(normFuncName: String): Boolean
  60. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  61. def logBase(info: Map[String, String], featureName: Option[String]): Unit
    Attributes
    protected
    Definition Classes
    SynapseMLLogging
  62. def logBase(methodName: String, numCols: Option[Int], executionSeconds: Option[Double], featureName: Option[String]): Unit
    Attributes
    protected
    Definition Classes
    SynapseMLLogging
  63. def logClass(featureName: String): Unit
    Definition Classes
    SynapseMLLogging
  64. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  65. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  66. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  67. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  68. def logErrorBase(methodName: String, e: Exception): Unit
    Attributes
    protected
    Definition Classes
    SynapseMLLogging
  69. def logFit[T](f: ⇒ T, columns: Int): T
    Definition Classes
    SynapseMLLogging
  70. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  73. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  75. def logTransform[T](f: ⇒ T, columns: Int): T
    Definition Classes
    SynapseMLLogging
  76. def logVerb[T](verb: String, f: ⇒ T, columns: Option[Int] = None): T
    Definition Classes
    SynapseMLLogging
  77. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  78. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  79. def makeDotnetFile(conf: CodegenConfig): Unit
    Definition Classes
    DotnetWrappable
  80. def makePyFile(conf: CodegenConfig): Unit
    Definition Classes
    PythonWrappable
  81. def makeRFile(conf: CodegenConfig): Unit
    Definition Classes
    RWrappable
  82. val map: StringStringMapParam
  83. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  84. val normFunc: Param[String]
  85. val normFuncs: Map[String, (Char) ⇒ Char]
  86. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  87. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  88. val outputCol: Param[String]

    The name of the output column

    The name of the output column

    Definition Classes
    HasOutputCol
  89. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  90. def pyAdditionalMethods: String
    Definition Classes
    PythonWrappable
  91. lazy val pyClassDoc: String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  92. lazy val pyClassName: String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  93. def pyExtraEstimatorImports: String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  94. def pyExtraEstimatorMethods: String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  95. lazy val pyInheritedClasses: Seq[String]
    Attributes
    protected
    Definition Classes
    PythonWrappable
  96. def pyInitFunc(): String
    Definition Classes
    PythonWrappable
  97. lazy val pyInternalWrapper: Boolean
    Attributes
    protected
    Definition Classes
    PythonWrappable
  98. lazy val pyObjectBaseClass: String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  99. def pyParamArg[T](p: Param[T]): String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  100. def pyParamDefault[T](p: Param[T]): Option[String]
    Attributes
    protected
    Definition Classes
    PythonWrappable
  101. def pyParamGetter(p: Param[_]): String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  102. def pyParamSetter(p: Param[_]): String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  103. def pyParamsArgs: String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  104. def pyParamsDefaults: String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  105. lazy val pyParamsDefinitions: String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  106. def pyParamsGetters: String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  107. def pyParamsSetters: String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  108. def pythonClass(): String
    Attributes
    protected
    Definition Classes
    PythonWrappable
  109. def rClass(): String
    Attributes
    protected
    Definition Classes
    RWrappable
  110. def rDocString: String
    Attributes
    protected
    Definition Classes
    RWrappable
  111. def rExtraBodyLines: String
    Attributes
    protected
    Definition Classes
    RWrappable
  112. def rExtraInitLines: String
    Attributes
    protected
    Definition Classes
    RWrappable
  113. lazy val rFuncName: String
    Attributes
    protected
    Definition Classes
    RWrappable
  114. lazy val rInternalWrapper: Boolean
    Attributes
    protected
    Definition Classes
    RWrappable
  115. def rParamArg[T](p: Param[T]): String
    Attributes
    protected
    Definition Classes
    RWrappable
  116. def rParamsArgs: String
    Attributes
    protected
    Definition Classes
    RWrappable
  117. def rSetterLines: String
    Attributes
    protected
    Definition Classes
    RWrappable
  118. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  119. final def set(paramPair: ParamPair[_]): TextPreprocessor.this.type
    Attributes
    protected
    Definition Classes
    Params
  120. final def set(param: String, value: Any): TextPreprocessor.this.type
    Attributes
    protected
    Definition Classes
    Params
  121. final def set[T](param: Param[T], value: T): TextPreprocessor.this.type
    Definition Classes
    Params
  122. final def setDefault(paramPairs: ParamPair[_]*): TextPreprocessor.this.type
    Attributes
    protected
    Definition Classes
    Params
  123. final def setDefault[T](param: Param[T], value: T): TextPreprocessor.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  124. def setInputCol(value: String): TextPreprocessor.this.type

    Definition Classes
    HasInputCol
  125. def setMap(value: Map[String, String]): TextPreprocessor.this.type

  126. def setNormFunc(value: String): TextPreprocessor.this.type

  127. def setOutputCol(value: String): TextPreprocessor.this.type

    Definition Classes
    HasOutputCol
  128. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  129. val thisStage: Params
    Attributes
    protected
    Definition Classes
    BaseWrappable
  130. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  131. def transform(dataset: Dataset[_]): DataFrame

    dataset

    - The input dataset, to be transformed

    returns

    The DataFrame that results from column selection

    Definition Classes
    TextPreprocessor → Transformer
  132. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  133. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  134. def transformSchema(schema: StructType): StructType
    Definition Classes
    TextPreprocessor → PipelineStage
  135. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  136. val uid: String
    Definition Classes
    TextPreprocessorSynapseMLLogging → Identifiable
  137. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  138. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  139. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  140. def write: MLWriter
    Definition Classes
    ComplexParamsWritable → MLWritable

Inherited from SynapseMLLogging

Inherited from ComplexParamsWritable

Inherited from MLWritable

Inherited from Wrappable

Inherited from DotnetWrappable

Inherited from RWrappable

Inherited from PythonWrappable

Inherited from BaseWrappable

Inherited from HasOutputCol

Inherited from HasInputCol

Inherited from Transformer

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

getParam

param

setParam

Ungrouped