Last active
August 27, 2020 10:28
-
-
Save willprice76/a6c1ffa3dc9dedec4b8099a1bde50a26 to your computer and use it in GitHub Desktop.
method to build training pipeline for sentiment analysis with Spark NLP
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
private Pipeline getSentimentTrainingPipeline() { | |
DocumentAssembler document = new DocumentAssembler(); | |
document.setInputCol("text"); | |
document.setOutputCol("document"); | |
String[] tokenizerInputCols = {"document"}; | |
Tokenizer tokenizer = new Tokenizer(); | |
tokenizer.setInputCols(tokenizerInputCols); | |
tokenizer.setOutputCol("token"); | |
String[] sentimentInputCols = {"document", "token"}; | |
ViveknSentimentApproach sentimentApproach = new ViveknSentimentApproach(); | |
sentimentApproach.setInputCols(sentimentInputCols); | |
sentimentApproach.setOutputCol("sentiment"); | |
sentimentApproach.setSentimentCol("label"); | |
sentimentApproach.setCorpusPrune(0); | |
Pipeline pipeline = new Pipeline(); | |
pipeline.setStages(new PipelineStage[]{document, tokenizer, sentimentApproach}); | |
return pipeline; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment