Created
April 30, 2016 11:07
-
-
Save sadv1r/9db9b4e31f388a7cf925eaeb03aa4dc1 to your computer and use it in GitHub Desktop.
This file contains 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
#!/usr/bin/env kscript | |
//DEPS org.apache.opennlp:opennlp-tools:1.5.3,org.slf4j:slf4j-simple:1.7.7 | |
import opennlp.tools.doccat.DoccatModel | |
import opennlp.tools.doccat.DocumentCategorizerME | |
import opennlp.tools.doccat.DocumentSampleStream | |
import opennlp.tools.util.PlainTextByLineStream | |
import java.io.FileInputStream | |
/** | |
* Created on 4/30/16. | |
* | |
* @author sadv1r | |
* @version 0.1 | |
*/ | |
println("Hello Kotlin script") | |
val dataIn = FileInputStream("tweets.txt") | |
val lineStream = PlainTextByLineStream(dataIn, "UTF-8") | |
val sampleStream = DocumentSampleStream(lineStream) | |
val cutoff = 2 | |
val trainingIterations = 30 | |
val model = DocumentCategorizerME.train("en", sampleStream, cutoff, | |
trainingIterations) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment