bayes_kotlin_2.kt

companion object {
    val CLASS_POSITIVE = 0 // Spam
    val CLASS_NEGATIVE = 1 // Ham
    private val englishStopWords = arrayOf(
        "i", "me", "my", "myself", "we", "our", "ours", "ourselves", "you", "your", "yours", "yourself", "yourselves",
        "he", "him", "his", "himself", "she", "her", "hers", "herself", "it", "its", "itself", "they", "them", "their",
        "theirs", "themselves", "what", "which", "who", "whom", "this", "that", "these", "those", "am", "is", "are", "was",
        "were", "be", "been", "being", "have", "has", "had", "having", "do", "does", "did", "doing", "a", "an", "the",
        "and", "but", "if", "or", "because", "as", "until", "while", "of", "at", "by", "for", "with", "about", "against",
        "between", "into", "through", "during", "before", "after", "above", "below", "to", "from", "up", "down", "in",
        "out", "on", "off", "over", "under", "again", "further", "then", "once", "here", "there", "when", "where", "why",
        "how", "all", "any", "both", "each", "few", "more", "most", "other", "some", "such", "no",
        "nor", "not", "only", "own", "same", "so", "than", "too", "very", "s", "t", "can", "will", "just", "don", "should",
        "now" , "hello" , "hi" , "dear" , "respected" , "thank"
    )
    fun getTokens( text : String ) : Array<String> {
        val tokens = text.toLowerCase().split( " " )
        val filteredTokens = ArrayList<String>()
        for ( i in 0 until tokens.count() ) {
            if ( !tokens[i].trim().isBlank() ) {
                filteredTokens.add( tokens[ i ] )
            }
        }
        val stopWordRemovedTokens = tokens.map { Regex("[^a-zA-Z]").replace( it , "") }
                as ArrayList<String>
        stopWordRemovedTokens.removeAll {
            englishStopWords.contains( it ) or it.trim().isBlank()
        }
        return stopWordRemovedTokens.distinct().toTypedArray()
    }
}