val sc: SparkContext // An existing SparkContext.
val sqlContext = new org.apache.spark.sql.SQLContext(sc)

JavaSparkContext sc = ...; // An existing JavaSparkContext.
SQLContext sqlContext = new org.apache.spark.sql.SQLContext(sc);

val sc: SparkContext // An existing SparkContext.
val sqlContext = new org.apache.spark.sql.SQLContext(sc)
val df = sqlContext.read.json("examples/src/main/resources/people.json")
// Displays the content of the DataFrame to stdout
df.show()

JavaSparkContext sc = ...; // An existing JavaSparkContext.
SQLContext sqlContext = new org.apache.spark.sql.SQLContext(sc);
DataFrame df = sqlContext.read().json("examples/src/main/resources/people.json");
// Displays the content of the DataFrame to stdout
df.show();

val sc: SparkContext // An existing SparkContext.
val sqlContext = new org.apache.spark.sql.SQLContext(sc)
// Create the DataFrame
val df = sqlContext.read.json("examples/src/main/resources/people.json")
// Show the content of the DataFrame
df.show()
// age  name
// null Michael
// 30   Andy
// 19   Justin
// Print the schema in a tree format
df.printSchema()
// root
// |-- age: long (nullable = true)
// |-- name: string (nullable = true)
// Select only the "name" column
df.select("name").show()
// name
// Michael
// Andy
// Justin
// Select everybody, but increment the age by 1
df.select(df("name"), df("age") + 1).show()
// name    (age + 1)
// Michael null
// Andy    31
// Justin  20
// Select people older than 21
df.filter(df("age") > 21).show()
// age name
// 30  Andy
// Count people by age
df.groupBy("age").count().show()
// age  count
// null 1
// 19   1
// 30   1

JavaSparkContext sc // An existing SparkContext.
SQLContext sqlContext = new org.apache.spark.sql.SQLContext(sc)
// Create the DataFrame
DataFrame df = sqlContext.read().json("examples/src/main/resources/people.json");
// Show the content of the DataFrame
df.show();
// age  name
// null Michael
// 30   Andy
// 19   Justin
// Print the schema in a tree format
df.printSchema();
// root
// |-- age: long (nullable = true)
// |-- name: string (nullable = true)
// Select only the "name" column
df.select("name").show();
// name
// Michael
// Andy
// Justin
// Select everybody, but increment the age by 1
df.select(df.col("name"), df.col("age").plus(1)).show();
// name    (age + 1)
// Michael null
// Andy    31
// Justin  20
// Select people older than 21
df.filter(df.col("age").gt(21)).show();
// age name
// 30  Andy
// Count people by age
df.groupBy("age").count().show();
// age  count
// null 1
// 19   1
// 30   1

val sqlContext = ...  // An existing SQLContext
val df = sqlContext.sql("SELECT * FROM table")

SQLContext sqlContext = ...  // An existing SQLContext
DataFrame df = sqlContext.sql("SELECT * FROM table")

public static class Person implements Serializable {
  private String name;
  private int age;
  public String getName() {
    return name;
  }
  public void setName(String name) {
    this.name = name;
  }
  public int getAge() {
    return age;
  }
  public void setAge(int age) {
    this.age = age;
  }
}

// sc is an existing JavaSparkContext.
SQLContext sqlContext = new org.apache.spark.sql.SQLContext(sc);
// Load a text file and convert each line to a JavaBean.
JavaRDD<Person> people = sc.textFile("examples/src/main/resources/people.txt").map(
  new Function<String, Person>() {
    public Person call(String line) throws Exception {
      String[] parts = line.split(",");
      Person person = new Person();
      person.setName(parts[0]);
      person.setAge(Integer.parseInt(parts[1].trim()));
      return person;
    }
  });
// Apply a schema to an RDD of JavaBeans and register it as a table.
DataFrame schemaPeople = sqlContext.createDataFrame(people, Person.class);
schemaPeople.registerTempTable("people");
// SQL can be run over RDDs that have been registered as tables.
DataFrame teenagers = sqlContext.sql("SELECT name FROM people WHERE age >= 13 AND age <= 19")
// The results of SQL queries are DataFrames and support all the normal RDD operations.
// The columns of a row in the result can be accessed by ordinal.
List<String> teenagerNames = teenagers.javaRDD().map(new Function<Row, String>() {
  public String call(Row row) {
    return "Name: " + row.getString(0);
  }
}).collect();