class ClassifierDatasetEncoder extends Serializable
- Alphabetic
- By Inheritance
- ClassifierDatasetEncoder
- Serializable
- Serializable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
- new ClassifierDatasetEncoder(params: ClassifierDatasetEncoderParams)
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
- def calculateEmbeddingsDim(dataset: DataFrame): Int
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
collectTrainingInstances(dataset: DataFrame, labelCol: String): Array[Array[(String, Array[Float])]]
Converts DataFrame to Array of Arrays of Labels (string)
Converts DataFrame to Array of Arrays of Labels (string)
- dataset
Input DataFrame with embeddings and labels
- returns
Array of Array of Map(String, Array(Float))
-
def
collectTrainingInstancesMultiLabel(dataset: DataFrame, labelCol: String): Array[Array[(Array[String], Array[Float])]]
Converts DataFrame to labels and embeddings
Converts DataFrame to labels and embeddings
- dataset
Input DataFrame with embeddings and labels
- returns
Array of Array of Map(Array(String), Array(Float))
-
def
decodeOutputData(tagIds: Array[Array[Float]]): Array[Array[(String, Float)]]
Converts Tag Identifiers to Tag Names
Converts Tag Identifiers to Tag Names
- tagIds
Tag Ids encoded for Tensorflow Model.
- returns
Tag names
- def encodeTags(labels: Array[String]): Array[Array[Int]]
- def encodeTagsMultiLabel(labels: Array[Array[String]]): Array[Array[Float]]
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
extractLabels(dataset: Array[Array[(String, Array[Float])]]): Array[String]
Converts DataFrame to Array of Arrays of Labels (string)
Converts DataFrame to Array of Arrays of Labels (string)
- dataset
Input DataFrame with labels
- returns
Array of Array of String
-
def
extractLabelsMultiLabel(dataset: Array[Array[(Array[String], Array[Float])]]): Array[Array[String]]
Converts DataFrame to Array of Arrays of Labels (string)
Converts DataFrame to Array of Arrays of Labels (string)
- dataset
Input DataFrame with labels
- returns
Array of Array of String
-
def
extractSentenceEmbeddings(docs: Seq[(Int, Seq[Annotation])]): Array[Array[Float]]
Converts DataFrame to Array of Arrays of Embeddings
Converts DataFrame to Array of Arrays of Embeddings
- docs
Input DataFrame with sentence_embeddings
- returns
Array of Array of Float
-
def
extractSentenceEmbeddings(dataset: Array[Array[(String, Array[Float])]]): Array[Array[Float]]
Converts DataFrame to Array of Arrays of Embeddings
Converts DataFrame to Array of Arrays of Embeddings
- dataset
Input DataFrame with sentence_embeddings
- returns
Array of Array of Float
-
def
extractSentenceEmbeddingsMultiLabel(docs: Seq[(Int, Seq[Annotation])]): Array[Array[Array[Float]]]
Converts DataFrame to Array of arrays of arrays of arrays of Embeddings The difference in this function is to create a sequence in case of multiple sentences in a document Used in MultiClassifierDL
Converts DataFrame to Array of arrays of arrays of arrays of Embeddings The difference in this function is to create a sequence in case of multiple sentences in a document Used in MultiClassifierDL
- docs
Input DataFrame with sentence_embeddings
- returns
Array of Arrays of Arrays of Floats
-
def
extractSentenceEmbeddingsMultiLabel(dataset: Array[Array[(Array[String], Array[Float])]]): Array[Array[Array[Float]]]
Converts DataFrame to Array of arrays of arrays of arrays of Embeddings The difference in this function is to create a sequence in case of multiple sentences in a document Used in MultiClassifierDL
Converts DataFrame to Array of arrays of arrays of arrays of Embeddings The difference in this function is to create a sequence in case of multiple sentences in a document Used in MultiClassifierDL
- dataset
Input DataFrame with sentence_embeddings
- returns
Array of Arrays of Arrays of Floats
- def extractSentenceEmbeddingsMultiLabelPredict(docs: Seq[(Int, Seq[Annotation])]): Array[Array[Array[Float]]]
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- val params: ClassifierDatasetEncoderParams
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
- val tags: Array[String]
- val tags2Id: Map[String, Int]
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
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( ... ) @native()