val sqlContext = new org.apache.spark.sql.SQLContext(sc)// this is used to implicitly convert an RDD to a DataFrame.
    import sqlContext.implicits._// Define the schema using a case class.case class Person(name: String, age: Int)// Create an RDD of Person objects and register it as a table.val people = sc.textFile("examples/src/main/resources/people.txt").map(_.split(",")).map(p => Person(p(0), p(1).trim.toInt)).toDF()

   val people = sc.textFile("examples/src/main/resources/people.txt").map(_.split(",")).map(p => Person(p(0), p(1).trim.toInt)) sqlContext.createDataFrame(people)

  val sqlContext = new org.apache.spark.sql.SQLContext(sc)// this is used to implicitly convert an RDD to a DataFrame.
        import sqlContext.implicits._// Define the schema using a case class.case class Person(name: String, age: Int)// Create an RDD of Person objects and register it as a table.val people = sc.textFile("examples/src/main/resources/people.txt").map(_.split(",")).map(p => Person(p(0), p(1).trim.toInt)).toDF()people.write.parquet("xxxx")val parquetFile = sqlContext.read.parquet("people.parquet")//Parquet files can also be registered as tables and then used in SQL statements.parquetFile.registerTempTable("parquetFile")val teenagers = sqlContext.sql("SELECT name FROM parquetFile WHERE age >= 13 AND age <= 19")teenagers.map(t => "Name: " + t(0)).collect().foreach(println)

// 可以是目录或者文件夹val path = "examples/src/main/resources/people.json"val people = sqlContext.read.json(path)// The inferred schema can be visualized using the printSchema() method.
            people.printSchema()// Register this DataFrame as a table.people.registerTempTable("people")// SQL statements can be run by using the sql methods provided by sqlContext.val teenagers = sqlContext.sql("SELECT name FROM people WHERE age >= 13 AND age <= 19")// Alternatively, a DataFrame can be created for a JSON dataset represented by// an RDD[String] storing one JSON object per string.val anotherPeopleRDD = sc.parallelize("""{"name":"Yin","address":{"city":"Columbus","state":"Ohio"}}""" :: Nil)val anotherPeople = sqlContext.read.json(anotherPeopleRDD)

val jdbcDF = sqlContext.read.format("jdbc").options(Map("url" -> "jdbc:postgresql:dbserver","dbtable" -> "schema.tablename")).load()