Spark Streaming最強(qiáng)大的地方在于尘颓，可以與Spark Core佃声、Spark SQL整合使用菲嘴，之前已經(jīng)通過(guò)transform虏辫、foreachRDD等算子看到蚌吸，如何將DStream中的RDD使用Spark Core執(zhí)行批處理操作。現(xiàn)在就來(lái)看看乒裆，如何將DStream中的RDD與Spark SQL結(jié)合起來(lái)使用套利。
Demo：每隔10秒推励，統(tǒng)計(jì)最近60秒的鹤耍，每個(gè)種類的每個(gè)商品的點(diǎn)擊次數(shù)，然后統(tǒng)計(jì)出每個(gè)種類top3熱門的商品验辞。
package cn.spark.study.streaming;
import java.util.ArrayList;
import java.util.List;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.hive.HiveContext;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
import org.apache.spark.streaming.Durations;
import org.apache.spark.streaming.api.java.JavaPairDStream;
import org.apache.spark.streaming.api.java.JavaReceiverInputDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
import scala.Tuple2;
/**
* 與Spark SQL整合使用稿黄，top3熱門商品實(shí)時(shí)統(tǒng)計(jì)
*/
public class Top3HotProduct {
public static void main(String[] args) {
SparkConf conf = new SparkConf()
.setMaster("local[2]")
.setAppName("Top3HotProduct");
JavaStreamingContext jssc = new JavaStreamingContext(conf, Durations.seconds(1));
// 輸入日志的格式
// leo iphone mobile_phone
// 首先，獲取輸入數(shù)據(jù)流
JavaReceiverInputDStream<String> productClickLogsDStream = jssc.socketTextStream("hadoop1", 9999);
// 然后跌造，應(yīng)該是做一個(gè)映射杆怕，將每個(gè)種類的每個(gè)商品，映射為(category_product, 1)的這種格式
// 從而在后面可以使用window操作壳贪，對(duì)窗口中的這種格式的數(shù)據(jù)陵珍，進(jìn)行reduceByKey操作
// 從而統(tǒng)計(jì)出來(lái)，一個(gè)窗口中的每個(gè)種類的每個(gè)商品的违施，點(diǎn)擊次數(shù)
JavaPairDStream<String, Integer> categoryProductPairsDStream = productClickLogsDStream
.mapToPair(new PairFunction<String, String, Integer>() {
private static final long serialVersionUID = 1L;
@Override
public Tuple2<String, Integer> call(String productClickLog)
throws Exception {
String[] productClickLogSplited = productClickLog.split(" ");
return new Tuple2<String, Integer>(productClickLogSplited[2] + "_" +
productClickLogSplited[1], 1);
}
});
// 然后執(zhí)行window操作
// 到這里互纯，就可以做到，每隔10秒鐘磕蒲，對(duì)最近60秒的數(shù)據(jù)留潦，執(zhí)行reduceByKey操作
// 計(jì)算出來(lái)這60秒內(nèi)，每個(gè)種類的每個(gè)商品的點(diǎn)擊次數(shù)
JavaPairDStream<String, Integer> categoryProductCountsDStream =
categoryProductPairsDStream.reduceByKeyAndWindow(
new Function2<Integer, Integer, Integer>() {
private static final long serialVersionUID = 1L;
@Override
public Integer call(Integer v1, Integer v2) throws Exception {
return v1 + v2;
}
}, Durations.seconds(60), Durations.seconds(10));
// 然后針對(duì)60秒內(nèi)的每個(gè)種類的每個(gè)商品的點(diǎn)擊次數(shù)
// foreachRDD辣往，在內(nèi)部兔院，使用Spark SQL執(zhí)行top3熱門商品的統(tǒng)計(jì)
categoryProductCountsDStream.foreachRDD(new Function<JavaPairRDD<String,Integer>, Void>() {
private static final long serialVersionUID = 1L;
@Override
public Void call(JavaPairRDD<String, Integer> categoryProductCountsRDD) throws Exception {
// 將該RDD，轉(zhuǎn)換為JavaRDD<Row>的格式
JavaRDD<Row> categoryProductCountRowRDD = categoryProductCountsRDD.map(
new Function<Tuple2<String,Integer>, Row>() {
private static final long serialVersionUID = 1L;
@Override
public Row call(Tuple2<String, Integer> categoryProductCount)
throws Exception {
String category = categoryProductCount._1.split("_")[0];
String product = categoryProductCount._1.split("_")[1];
Integer count = categoryProductCount._2;
return RowFactory.create(category, product, count);
}
});
// 然后站削，執(zhí)行DataFrame轉(zhuǎn)換
List<StructField> structFields = new ArrayList<StructField>();
structFields.add(DataTypes.createStructField("category", DataTypes.StringType, true));
structFields.add(DataTypes.createStructField("product", DataTypes.StringType, true));
structFields.add(DataTypes.createStructField("click_count", DataTypes.IntegerType, true));
StructType structType = DataTypes.createStructType(structFields);
HiveContext hiveContext = new HiveContext(categoryProductCountsRDD.context());
DataFrame categoryProductCountDF = hiveContext.createDataFrame(
categoryProductCountRowRDD, structType);
// 將60秒內(nèi)的每個(gè)種類的每個(gè)商品的點(diǎn)擊次數(shù)的數(shù)據(jù)坊萝，注冊(cè)為一個(gè)臨時(shí)表
categoryProductCountDF.registerTempTable("product_click_log");
// 執(zhí)行SQL語(yǔ)句，針對(duì)臨時(shí)表，統(tǒng)計(jì)出來(lái)每個(gè)種類下屹堰，點(diǎn)擊次數(shù)排名前3的熱門商品
DataFrame top3ProductDF = hiveContext.sql(
"SELECT category,product,click_count "
+ "FROM ("
+ "SELECT "
+ "category,"
+ "product,"
+ "click_count,"
+ "row_number() OVER (PARTITION BY category ORDER BY click_count DESC) rank "
+ "FROM product_click_log"
+ ") tmp "
+ "WHERE rank<=3");
// 接下來(lái)應(yīng)該將數(shù)據(jù)保存到redis緩存肛冶、或者是mysql db中
// 然后，配合一個(gè)J2EE系統(tǒng)扯键，進(jìn)行數(shù)據(jù)的展示和查詢睦袖、圖形報(bào)表
top3ProductDF.show();
return null;
}
});
jssc.start();
jssc.awaitTermination();
jssc.close();
}
}
package cn.spark.study.streaming
import org.apache.spark.SparkConf
import org.apache.spark.streaming.StreamingContext
import org.apache.spark.streaming.Seconds
import org.apache.spark.sql.Row
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.types.StructField
import org.apache.spark.sql.types.StringType
import org.apache.spark.sql.types.IntegerType
import org.apache.spark.sql.hive.HiveContext
object Top3HotProduct {
def main(args: Array[String]): Unit = {
val conf = new SparkConf()
.setMaster("local[2]")
.setAppName("Top3HotProduct")
val ssc = new StreamingContext(conf, Seconds(1))
val productClickLogsDStream = ssc.socketTextStream("spark1", 9999)
val categoryProductPairsDStream = productClickLogsDStream
.map { productClickLog => (productClickLog.split(" ")(2) + "_" + productClickLog.split(" ")(1), 1)}
val categoryProductCountsDStream = categoryProductPairsDStream.reduceByKeyAndWindow(
(v1: Int, v2: Int) => v1 + v2,
Seconds(60),
Seconds(10))
categoryProductCountsDStream.foreachRDD(categoryProductCountsRDD => {
val categoryProductCountRowRDD = categoryProductCountsRDD.map(tuple => {
val category = tuple._1.split("_")(0)
val product = tuple._1.split("_")(1)
val count = tuple._2
Row(category, product, count)
})
val structType = StructType(Array(
StructField("category", StringType, true),
StructField("product", StringType, true),
StructField("click_count", IntegerType, true)))
val hiveContext = new HiveContext(categoryProductCountsRDD.context)
val categoryProductCountDF = hiveContext.createDataFrame(categoryProductCountRowRDD, structType)
categoryProductCountDF.registerTempTable("product_click_log")
val top3ProductDF = hiveContext.sql(
"SELECT category,product,click_count "
+ "FROM ("
+ "SELECT "
+ "category,"
+ "product,"
+ "click_count,"
+ "row_number() OVER (PARTITION BY category ORDER BY click_count DESC) rank "
+ "FROM product_click_log"
+ ") tmp "
+ "WHERE rank<=3")
top3ProductDF.show()
})
ssc.start()
ssc.awaitTermination()
}
}
