创建DataFrame

Java版本：

JavaSparkContext sc = ...;

SQLContext sqlContext = new SQLContext(sc);

DataFrame df = sqlContext.read().json("hdfs://spark1:9000/students.json");

df.show();

Scala版本：

val sc: SparkContext = ...

val sqlContext = new SQLContext(sc)

val df = sqlContext.read.json("hdfs://spark1:9000/students.json")

df.show()

案例 json数据源

{"id":1, "name":"leo", "age":18}

{"id":2, "name":"jack", "age":19}

{"id":3, "name":"marry", "age":17}

Java版本

public class DataFrameCreate {
​public static void main(String[] args) {
​​SparkConf conf = newSparkConf().setAppName("DataFrameCreate").setMaster("local");
​​JavaSparkContext sc = new JavaSparkContext(conf);
​​SQLContext sqlContext = new SQLContext(sc);
​​DataFrame df = sqlContext.read().json("C:\\Users\\zhang\\Desktop\\students.json")      
​​df.show();
​}
}

运行到linux集群上面

1. 打包 文件路径改成hdfs://spark1:9000/students.json

Sh文件

spark-submit \

--class sql.DataFrameCreate \

--num-executors 3 \

--driver-memory 100m \

--executor-memory 100m \

--executor-cores 3 \

--files /usr/local/hive/conf/hive-site.xml \

--driver-class-path /usr/local/hive/lib/mysql-connector-java-5.1.17.jar \

/sql/worldcount.jar \

Scala版本

object DataFrameCreate {

def main(args: Array[String]){

val conf = new SparkConf().setAppName("DataFrameCreate")

val sc = new SparkContext(conf)

val sqlContext = new SQLContext(sc)

val df = sqlContext.read.json("hdfs://spark1:9000/students.json")

df.show()

}
}