SimpleTokenizer

Value Members

1. final def !=(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

2. final def ##(): Int

   

   Definition Classes

   AnyRef → Any

3. final def ==(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

4. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

5. def clone(): AnyRef

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

6. final def eq(arg0: AnyRef): Boolean

   

   Definition Classes

   AnyRef

7. def equals(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

8. def finalize(): Unit

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( classOf[java.lang.Throwable] )

9. final def getClass(): Class[_]

   

   Definition Classes

   AnyRef → Any

10. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

11. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

12. final def ne(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

13. final def notify(): Unit

    

    Definition Classes

    AnyRef

14. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

15. def shaping(tokens: Array[Float], sequenceLen: Int, trunc: String = "pre"): Array[Float]

    

    Shape the token sequence to the specified length.

    Shape the token sequence to the specified length. The sequence would be either padded or truncated.

    sequenceLen

    the desired seq length

    trunc

    truncated from pre or post.

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

    

    Definition Classes

    AnyRef

17. def toString(): String

    

    Definition Classes

    AnyRef → Any

18. def toTokens(text: String, word2Meta: Map[String, WordMeta]): Array[Float]

    

    Transform sample text into tokens and ignore those unknown tokens.

    Transform sample text into tokens and ignore those unknown tokens.

    word2Meta

    Indicate the included words.

19. def toTokens(text: String, lower: Boolean = true): Array[String]

    

    Simple tokenizer to split text into separated tokens.

    Simple tokenizer to split text into separated tokens.

    text

    text to be split.

    lower

    convert to lower case or not.

    returns

    An array of separated tokens.

20. def vectorization(tokens: Array[Float], embeddingSize: Int, word2Vec: Map[Float, Array[Float]]): Array[Array[Float]]

    

    Transform word to pre-trained vector.

    Transform word to pre-trained vector.

    embeddingSize

    size of the pre-trained vector

    word2Vec

    pre-trained word2Vec

21. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

23. final def wait(arg0: Long): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )