Package com.cloudera.cdk.data

Examples of com.cloudera.cdk.data.DatasetRepository.create()


    // Create a dataset of events with the Avro schema in the repository
    DatasetDescriptor descriptor = new DatasetDescriptor.Builder()
        .schemaUri("resource:event.avsc")
        .build();
    repo.create("events", descriptor);

    return 0;
  }

  public static void main(String... args) throws Exception {
View Full Code Here


        .name("rating").type().intType().noDefault()
        .name("timeInSeconds").type().intType().noDefault()
        .endRecord();

    // create
    repo.create("ratings", new DatasetDescriptor.Builder()
//        .location("hdfs:u.data")
        .format(Formats.CSV)
        .property("cdk.csv.delimiter", "\t")
        .schema(ratingSchema)
        .build());
View Full Code Here

        .name("videoReleaseDate").type().stringType().noDefault()
        .name("imdbURL").type().stringType().noDefault()
        // ignore genre fields for now
        .endRecord();

    repo.create("movies", new DatasetDescriptor.Builder()
//        .location("hdfs:u.item")
        .format(Formats.CSV)
        .property("cdk.csv.delimiter", "|")
        .schema(movieSchema)
        .build());
View Full Code Here

TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.