org.apache.spark.ml.feature.NGram Java Examples

/**
 * Creates a n-gram data frame from text lines.
 * @param lines
 * @return a n-gram data frame.
 */
DataFrame createNGramDataFrame(JavaRDD<String> lines) {
	JavaRDD<Row> rows = lines.map(new Function<String, Row>(){
		private static final long serialVersionUID = -4332903997027358601L;
		
		@Override
		public Row call(String line) throws Exception {
			return RowFactory.create(Arrays.asList(line.split("\\s+")));
		}
	});
	StructType schema = new StructType(new StructField[] {
			new StructField("words",
					DataTypes.createArrayType(DataTypes.StringType), false,
					Metadata.empty()) });
	DataFrame wordDF = new SQLContext(jsc).createDataFrame(rows, schema);
	// build a bigram language model
	NGram transformer = new NGram().setInputCol("words")
			.setOutputCol("ngrams").setN(2);
	DataFrame ngramDF = transformer.transform(wordDF);
	ngramDF.show(10, false);
	return ngramDF;
}
 

public static void main(String[] args) {
  SparkSession spark = SparkSession
    .builder()
    .appName("JavaNGramExample")
    .getOrCreate();

  // $example on$
  List<Row> data = Arrays.asList(
    RowFactory.create(0, Arrays.asList("Hi", "I", "heard", "about", "Spark")),
    RowFactory.create(1, Arrays.asList("I", "wish", "Java", "could", "use", "case", "classes")),
    RowFactory.create(2, Arrays.asList("Logistic", "regression", "models", "are", "neat"))
  );

  StructType schema = new StructType(new StructField[]{
    new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
    new StructField(
      "words", DataTypes.createArrayType(DataTypes.StringType), false, Metadata.empty())
  });

  Dataset<Row> wordDataFrame = spark.createDataFrame(data, schema);

  NGram ngramTransformer = new NGram().setN(2).setInputCol("words").setOutputCol("ngrams");

  Dataset<Row> ngramDataFrame = ngramTransformer.transform(wordDataFrame);
  ngramDataFrame.select("ngrams").show(false);
  // $example off$

  spark.stop();
}
 

@Override
public List<Feature> encodeFeatures(SparkMLEncoder encoder){
	NGram transformer = getTransformer();

	DocumentFeature documentFeature = (DocumentFeature)encoder.getOnlyFeature(transformer.getInputCol());

	return Collections.singletonList(documentFeature);
}
 

public NGramConverter(NGram transformer){
	super(transformer);
}