SparkSQL 内置函数的使用（JAVA与Scala版本）

SparkSQL 内置函数的使用（JAVA与Scala版本）

agg的使用（根据时间，去重id相同，统计相同时间内的id个数）

Scala版本！

package com.bynear.Scala

import org.apache.spark.sql.functions._
import org.apache.spark.sql.types.{IntegerType, StringType, StructField, StructType}
import org.apache.spark.sql.{Row, SQLContext}
import org.apache.spark.{SparkConf, SparkContext}
object SparkSQLAgg {
  def main(args: Array[String]) {
    val conf = new SparkConf().setMaster("local").setAppName("SparkSQLAgg")
    val sc = new SparkContext(conf)
    val sqlContext = new SQLContext(sc) //构建SQL上下文

    //要使用Spark SQL的内置函授，就一定要导入SQLContext下的隐式转换
    import sqlContext.implicits._


    val userAccessLog = Array(
      "2016-3-27,1122",
      "2016-3-27,1122",
      "2016-3-27,1123",
      "2016-3-27,1124",
      "2016-3-27,1124",
      "2016-3-28,1122"
    )
    val userAccessRDDLog = sc.parallelize(userAccessLog, 5)
    val userAccessLogRowRDD = userAccessRDDLog.map { log => Row(log.split(",")(0), log.split(",")(1).toInt) }
    val structType = StructType(Array(
      StructField("date", StringType, true),
      StructField("userid", IntegerType, true)))

    val userAccessLogRowDF = sqlContext.createDataFrame(userAccessLogRowRDD, structType);


    userAccessLogRowDF.groupBy("date")
      .agg('date, countDistinct('userid))
      .map {
        row => Row(row(1), row(2))
      }.collect()
      .foreach(println)


  }
}

Java版本！

package com.bynear.spark_sql;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SQLContext;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;

import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;

import static org.apache.spark.sql.functions.*;
//一定要引入：
//
//import static org.apache.spark.sql.functions.*;
//否则无法直接使用countDistinct函数。本人在这里也是折腾了很久，最后查官网才发现这个坑的。
public class agg {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("agg").setMaster("local");
        JavaSparkContext sc = new JavaSparkContext(conf);
        SQLContext sqlContext = new SQLContext(sc);
        List<String> list = Arrays.asList(
                "2016-3-27,1122",
                "2016-3-27,1122",
                "2016-3-27,1123",
                "2016-3-27,1124",
                "2016-3-27,1124",
                "2016-3-28,1122"
        );
        JavaRDD<String> userAccessRDDLog = sc.parallelize(list, 5);
        JavaRDD<Row> mapROWRDD = userAccessRDDLog.map(new Function<String, Row>() {
            @Override
            public Row call(String line) throws Exception {
                String[] LineSplit = line.split(",");
                return RowFactory.create(LineSplit[0], Integer.valueOf(LineSplit[1]));
            }
        });
        ArrayList<StructField> fields = new ArrayList<StructField>();
        fields.add(DataTypes.createStructField("date", DataTypes.StringType, true));
        fields.add(DataTypes.createStructField("userid", DataTypes.IntegerType, true));
        StructType structType = DataTypes.createStructType(fields);
        DataFrame userAccessLogRowDF = sqlContext.createDataFrame(mapROWRDD, structType);
        userAccessLogRowDF.groupBy("date").agg(max("userid")).show();


        sc.close();
    }
}

注意点：：：

Scala版本中，如果需要使用内置函数，必须引用

import org.apache.spark.sql.functions._

Java版本，如果使用内置函数的话，必须引用

import static org.apache.spark.sql.functions.*;

必须为static 静态的  才可以使用其中的方法！