Created
June 13, 2019 05:36
-
-
Save shubham0204/906c02ed1cc62984bffa8e46ef76b268 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
fun tokenize ( message : String ): Array<DoubleArray> { | |
val tokens : List<String> = Tokenizer.getTokens( message ).toList() | |
val tokenizedMessage = ArrayList<DoubleArray>() | |
for ( part in tokens ) { | |
var vector : DoubleArray? = null | |
if ( embeddingData!![part] == null ) { | |
vector = DoubleArray( embeddingDim!! ){ 0.0 } | |
} | |
else{ | |
vector = embeddingData!![part] | |
} | |
tokenizedMessage.add( vector!! ) | |
} | |
return tokenizedMessage.toTypedArray() | |
} | |
fun padSequence ( sequence : Array<DoubleArray> ) : Array<DoubleArray> { | |
val maxlen = this.maxlen | |
if ( sequence.size > maxlen!!) { | |
return sequence.sliceArray( 0..maxlen ) | |
} | |
else if ( sequence.size < maxlen ) { | |
val array = ArrayList<DoubleArray>() | |
array.addAll( sequence.asList() ) | |
for ( i in array.size until maxlen ){ | |
array.add( DoubleArray( embeddingDim!! ){ 0.0 }) | |
} | |
return array.toTypedArray() | |
} | |
else{ | |
return sequence | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment