Packages

class Word2VecApproach extends AnnotatorApproach[Word2VecModel] with HasStorageRef with HasEnableCachingProperties

Trains a Word2Vec model that creates vector representations of words in a text corpus.

The algorithm first constructs a vocabulary from the corpus and then learns vector representation of words in the vocabulary. The vector representation can be used as features in natural language processing and machine learning algorithms.

We use Word2Vec implemented in Spark ML. It uses skip-gram model in our implementation and a hierarchical softmax method to train the model. The variable names in the implementation match the original C implementation.

For instantiated/pretrained models, see Word2VecModel.

Sources :

For the original C implementation, see https://code.google.com/p/word2vec/

For the research paper, see Efficient Estimation of Word Representations in Vector Space and Distributed Representations of Words and Phrases and their Compositionality.

Example

import spark.implicits._
import com.johnsnowlabs.nlp.annotator.{Tokenizer, Word2VecApproach}
import com.johnsnowlabs.nlp.base.DocumentAssembler
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val tokenizer = new Tokenizer()
  .setInputCols(Array("document"))
  .setOutputCol("token")

val embeddings = new Word2VecApproach()
  .setInputCols("token")
  .setOutputCol("embeddings")

val pipeline = new Pipeline()
  .setStages(Array(
    documentAssembler,
    tokenizer,
    embeddings
  ))

val path = "src/test/resources/spell/sherlockholmes.txt"
val dataset = spark.sparkContext.textFile(path)
  .toDF("text")
val pipelineModel = pipeline.fit(dataset)
Linear Supertypes
HasEnableCachingProperties, HasStorageRef, ParamsAndFeaturesWritable, HasFeatures, AnnotatorApproach[Word2VecModel], CanBeLazy, DefaultParamsWritable, MLWritable, HasOutputAnnotatorType, HasOutputAnnotationCol, HasInputAnnotationCols, Estimator[Word2VecModel], PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. Word2VecApproach
  2. HasEnableCachingProperties
  3. HasStorageRef
  4. ParamsAndFeaturesWritable
  5. HasFeatures
  6. AnnotatorApproach
  7. CanBeLazy
  8. DefaultParamsWritable
  9. MLWritable
  10. HasOutputAnnotatorType
  11. HasOutputAnnotationCol
  12. HasInputAnnotationCols
  13. Estimator
  14. PipelineStage
  15. Logging
  16. Params
  17. Serializable
  18. Serializable
  19. Identifiable
  20. AnyRef
  21. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new Word2VecApproach()
  2. new Word2VecApproach(uid: String)

Type Members

  1. type AnnotatorType = String
    Definition Classes
    HasOutputAnnotatorType

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. def $$[T](feature: StructFeature[T]): T
    Attributes
    protected
    Definition Classes
    HasFeatures
  5. def $$[K, V](feature: MapFeature[K, V]): Map[K, V]
    Attributes
    protected
    Definition Classes
    HasFeatures
  6. def $$[T](feature: SetFeature[T]): Set[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  7. def $$[T](feature: ArrayFeature[T]): Array[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  8. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  9. def _fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): Word2VecModel
    Attributes
    protected
    Definition Classes
    AnnotatorApproach
  10. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  11. def beforeTraining(spark: SparkSession): Unit
    Definition Classes
    Word2VecApproachAnnotatorApproach
  12. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  13. final def clear(param: Param[_]): Word2VecApproach.this.type
    Definition Classes
    Params
  14. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  15. final def copy(extra: ParamMap): Estimator[Word2VecModel]
    Definition Classes
    AnnotatorApproach → Estimator → PipelineStage → Params
  16. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  17. def createDatabaseConnection(database: Name): RocksDBConnection
    Definition Classes
    HasStorageRef
  18. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  19. val description: String
    Definition Classes
    Word2VecApproachAnnotatorApproach
  20. val enableCaching: BooleanParam

    Whether to enable caching DataFrames or RDDs during the training

    Whether to enable caching DataFrames or RDDs during the training

    Definition Classes
    HasEnableCachingProperties
  21. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  22. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  23. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  24. def explainParams(): String
    Definition Classes
    Params
  25. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  26. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  27. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  28. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  29. final def fit(dataset: Dataset[_]): Word2VecModel
    Definition Classes
    AnnotatorApproach → Estimator
  30. def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[Word2VecModel]
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" )
  31. def fit(dataset: Dataset[_], paramMap: ParamMap): Word2VecModel
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" )
  32. def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): Word2VecModel
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" ) @varargs()
  33. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  34. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  35. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  36. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  37. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  38. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  39. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  40. def getEnableCaching: Boolean

    Definition Classes
    HasEnableCachingProperties
  41. def getInputCols: Array[String]

    returns

    input annotations columns currently used

    Definition Classes
    HasInputAnnotationCols
  42. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  43. def getMaxIter: Int

  44. def getMaxSentenceLength: Int

  45. def getMinCount: Int

  46. def getNumPartitions: Int

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

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  49. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  50. def getSeed: Int

  51. def getStepSize: Double

  52. def getStorageRef: String
    Definition Classes
    HasStorageRef
  53. def getVectorSize: Int

  54. def getWindowSize: Int

  55. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  56. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  57. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  58. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  59. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  60. val inputAnnotatorTypes: Array[AnnotatorType]

    Input Annotator Types: TOKEN

    Input Annotator Types: TOKEN

    Definition Classes
    Word2VecApproachHasInputAnnotationCols
  61. final val inputCols: StringArrayParam

    columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified

    columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified

    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  62. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  63. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  64. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  65. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  66. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  67. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  68. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  69. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  70. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  73. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  75. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  76. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  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. val maxIter: IntParam

    Param for maximum number of iterations (>= 0) (Default: 1)

  80. val maxSentenceLength: IntParam

    Sets the maximum length (in words) of each sentence in the input data (Default: 1000).

    Sets the maximum length (in words) of each sentence in the input data (Default: 1000). Any sentence longer than this threshold will be divided into chunks of up to maxSentenceLength size.

  81. val minCount: IntParam

    The minimum number of times a token must appear to be included in the word2vec model's vocabulary (Default: 5).

  82. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  83. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  84. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  85. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  86. val numPartitions: IntParam

    Number of partitions for sentences of words (Default: 1).

  87. def onTrained(model: Word2VecModel, spark: SparkSession): Unit
    Definition Classes
    AnnotatorApproach
  88. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  89. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  90. val outputAnnotatorType: String

    Output Annotator Types: WORD_EMBEDDINGS

    Output Annotator Types: WORD_EMBEDDINGS

    Definition Classes
    Word2VecApproachHasOutputAnnotatorType
  91. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  92. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  93. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  94. val seed: IntParam

    Random seed for shuffling the dataset (Default: 44)

  95. def set[T](feature: StructFeature[T], value: T): Word2VecApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  96. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): Word2VecApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  97. def set[T](feature: SetFeature[T], value: Set[T]): Word2VecApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  98. def set[T](feature: ArrayFeature[T], value: Array[T]): Word2VecApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  99. final def set(paramPair: ParamPair[_]): Word2VecApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  100. final def set(param: String, value: Any): Word2VecApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  101. final def set[T](param: Param[T], value: T): Word2VecApproach.this.type
    Definition Classes
    Params
  102. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): Word2VecApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  103. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): Word2VecApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  104. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): Word2VecApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  105. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): Word2VecApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  106. final def setDefault(paramPairs: ParamPair[_]*): Word2VecApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  107. final def setDefault[T](param: Param[T], value: T): Word2VecApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  108. def setEnableCaching(value: Boolean): Word2VecApproach.this.type

    Definition Classes
    HasEnableCachingProperties
  109. final def setInputCols(value: String*): Word2VecApproach.this.type
    Definition Classes
    HasInputAnnotationCols
  110. def setInputCols(value: Array[String]): Word2VecApproach.this.type

    Overrides required annotators column if different than default

    Overrides required annotators column if different than default

    Definition Classes
    HasInputAnnotationCols
  111. def setLazyAnnotator(value: Boolean): Word2VecApproach.this.type
    Definition Classes
    CanBeLazy
  112. def setMaxIter(value: Int): Word2VecApproach.this.type

  113. def setMaxSentenceLength(value: Int): Word2VecApproach.this.type

  114. def setMinCount(value: Int): Word2VecApproach.this.type

  115. def setNumPartitions(value: Int): Word2VecApproach.this.type

  116. final def setOutputCol(value: String): Word2VecApproach.this.type

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  117. def setSeed(value: Int): Word2VecApproach.this.type

  118. def setStepSize(value: Double): Word2VecApproach.this.type

  119. def setStorageRef(value: String): Word2VecApproach.this.type
    Definition Classes
    HasStorageRef
  120. def setVectorSize(value: Int): Word2VecApproach.this.type

  121. def setWindowSize(value: Int): Word2VecApproach.this.type

  122. val stepSize: DoubleParam

    Param for Step size to be used for each iteration of optimization (> 0) (Default: 0.025).

  123. val storageRef: Param[String]

    Unique identifier for storage (Default: this.uid)

    Unique identifier for storage (Default: this.uid)

    Definition Classes
    HasStorageRef
  124. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  125. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  126. def train(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): Word2VecModel
    Definition Classes
    Word2VecApproachAnnotatorApproach
  127. final def transformSchema(schema: StructType): StructType

    requirement for pipeline transformation validation.

    requirement for pipeline transformation validation. It is called on fit()

    Definition Classes
    AnnotatorApproach → PipelineStage
  128. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  129. val uid: String
    Definition Classes
    Word2VecApproach → Identifiable
  130. def validate(schema: StructType): Boolean

    takes a Dataset and checks to see if all the required annotation types are present.

    takes a Dataset and checks to see if all the required annotation types are present.

    schema

    to be validated

    returns

    True if all the required types are present, else false

    Attributes
    protected
    Definition Classes
    AnnotatorApproach
  131. def validateStorageRef(dataset: Dataset[_], inputCols: Array[String], annotatorType: String): Unit
    Definition Classes
    HasStorageRef
  132. val vectorSize: IntParam

    The dimension of the code that you want to transform from words (Default: 100).

  133. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  134. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  135. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  136. val windowSize: IntParam

    The window size (context words from [-window, window]) (Default: 5)

  137. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from HasStorageRef

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from CanBeLazy

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from HasOutputAnnotatorType

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from Estimator[Word2VecModel]

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

Parameters

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

Annotator types

Required input and expected output annotator types

Members

Parameter setters

Parameter getters