Example usage for org.apache.spark.sql RowFactory create

Introduction

In this page you can find the example usage for org.apache.spark.sql RowFactory create.

Prototype

public static Row create(Object... values)

Source Link

Document

Create a Row from the given arguments.

Usage

From source file:spark.JavaWord2VecExample.java

License:Apache License

public static void main(String[] args) {
    SparkConf conf = new SparkConf().setAppName("JavaWord2VecExample").setMaster("local");
    JavaSparkContext jsc = new JavaSparkContext(conf);
    SQLContext sqlContext = new SQLContext(jsc);

    // $example on$
    // Input data: Each row is a bag of words from a sentence or document.
    JavaRDD<Row> jrdd = jsc/*from ww w  .j  ava 2s  . com*/
            .parallelize(Arrays.asList(RowFactory.create(Arrays.asList("Hi I heard about Spark".split(" "))),
                    RowFactory.create(Arrays.asList("I wish Java could use case classes".split(" "))),
                    RowFactory.create(Arrays.asList("Logistic regression models are neat".split(" ")))));
    StructType schema = new StructType(new StructField[] {
            new StructField("text", new ArrayType(DataTypes.StringType, true), false, Metadata.empty()) });
    DataFrame documentDF = sqlContext.createDataFrame(jrdd, schema);

    // Learn a mapping from words to Vectors.
    Word2Vec word2Vec = new Word2Vec().setInputCol("text").setOutputCol("result").setVectorSize(3)
            .setMinCount(0);
    Word2VecModel model = word2Vec.fit(documentDF);
    DataFrame result = model.transform(documentDF);
    for (Row r : result.select("result").take(3)) {
        System.out.println(r);
    }
    // $example off$
}