操作指令如下:
cd /usr/local/hadoop
./sbin/start-dfs.sh
./bin/hdfs dfs -mkdir -p spark/mycode/rdd/TopN
./bin/hdfs dfs -put /usr/local/spark/mycode/TopN_file1.txt spark/mycode/rdd/TopN
./bin/hdfs dfs -put /usr/local/spark/mycode/TopN_file2.txt spark/mycode/rdd/TopN
./bin/hdfs dfs -ls ./spark/mycode/rdd/TopN
./bin/hdfs dfs -cat spark/mycode/rdd/TopN/TopN_file1.txt
./bin/hdfs dfs -cat spark/mycode/rdd/TopN/TopN_file2.txt
cd ~/sparkapp
/usr/local/sbt/sbt package
/usr/local/spark/bin/spark-submit --class "TopN" ~/sparkapp/target/scala-2.11/simple-project_2.11-1.0.jar
案例1:求TOP值1 案
//TopN.scala
import org.apache.spark.{SparkConf, SparkContext}
object TopN {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("TopN").setMaster("local")
val sc = new SparkContext(conf)
sc.setLogLevel("ERROR")
val lines = sc.textFile("hdfs://localhost:9000/user/hadoop/spark/mycode/rdd/examples",2)
var num = 0;
val result = lines.filter(line => (line.trim().length > 0) && (line.split(",").length == 4))
.map(_.split(",")(2))
.map(x => (x.toInt,""))
.sortByKey(false)
.map(x => x._1).take(5)
.foreach(x => {
num = num + 1
println(num + "\t" + x)
})
}
}
案例2:求最大最小值
例1:求TOP值5.4.15.4.1案例1OP值55.4.1 案例1:求TOP值5.4.1 案例1:求TOP值.4.1 案例1:求TOP值 案例1:求?/TOP值
案例3:文件排序
这是怎么了?
用了朋友的代码 又可以了……
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf
import org.apache.spark.HashPartitioner
object FileSort {
def main(args: Array[String]) {
val conf = new SparkConf().setAppName("FileSort")
val sc = new SparkContext(conf)
val dataFile = "file:///usr/local/spark/mycode/rdd/data"
val lines = sc.textFile(dataFile,3)
var index = 0
val result = lines.filter(_.trim().length>0).map(n=>(n.trim.toInt,"")).partitionBy(new HashPartitioner(1)).sortByKey().map(t => {
index += 1
(index,t._1)
})
result.saveAsTextFile("file:///usr/local/spark/mycode/rdd/examples/result")
}
}
案例4:二次排序
二次排序,具体的实现步骤:
* 第一步:按照Ordered和Serializable接口实现自定义排序的key
* 第二步:将要进行二次排序的文件加载进来生成<key,value>类型的RDD
* 第三步:使用sortByKey基于自定义的Key进行二次排序
* 第四步:去除掉排序的Key,只保留排序的结果
SecondarySortKey.scala代码如下:
class SecondarySortKey(val first:Int,val second:Int) extends Ordered [SecondarySortKey] with Serializable {
def compare(other:SecondarySortKey):Int = {
if (this.first - other.first !=0) {
this.first - other.first
} else {
this.second - other.second
}
}
}
SecondarySortApp.scala代码如下:
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
object SecondarySortApp {
def main(args:Array[String]){
val conf = new SparkConf().setAppName("SecondarySortApp").setMaster("local")
val sc = new SparkContext(conf)
val lines = sc.textFile("file:///usr/local/spark/mycode/rdd/examples/SecondarySortApp_file1.txt", 1)
val pairWithSortKey = lines.map(line=>(new SecondarySortKey(line.split(" ")(0).toInt, line.split(" ")(1).toInt),line))
val sorted = pairWithSortKey.sortByKey(false)
val sortedResult = sorted.map(sortedLine =>sortedLine._2)
sortedResult.collect().foreach (println)
}
}
案例5:连接操作
任务描述:在推荐领域有一个著名的开放测试集,下载链接是:http://grouplens.org/datasets/movielens/,该测试集包含三个文件,分别是ratings.dat、sers.dat、movies.dat,具体介绍可阅读:README.txt。请编程实现:通过连接ratings.dat和movies.dat两个文件得到平均得分超过4.0的电影列表,采用的数据集是:ml-1m
/*movies.dat
MovieID::Title::Genres
1::Toy Story (1995)::Animation|Children's|Comedy
2::Jumanji (1995)::Adventure|Children's|Fantasy
3::Grumpier Old Men (1995)::Comedy|Romance
4::Waiting to Exhale (1995)::Comedy|Drama
5::Father of the Bride Part II (1995)::Comedy
6::Heat (1995)::Action|Crime|Thriller
7::Sabrina (1995)::Comedy|Romance
8::Tom and Huck (1995)::Adventure|Children's
9::Sudden Death (1995)::Action
10::GoldenEye (1995)::Action|Adventure|Thriller*/
/*ratings.dat
UserID::MovieID::Rating::Timestamp
1::1193::5::978300760
1::661::3::978302109
1::914::3::978301968
1::3408::4::978300275
1::2355::5::978824291
1::1197::3::978302268
1::1287::5::978302039
1::2804::5::978300719
1::594::4::978302268
1::919::4::978301368
1::595::5::978824268
1::938::4::978301752
1::2398::4::978302281
1::2918::4::978302124
1::1035::5::978301753
1::2791::4::978302188
1::2687::3::978824268*/
import org.apache.spark._
import SparkContext._
object SparkJoin {
def main(args: Array[String]) {
if(args.length != 3 ){
println("usage is SparkJoin <rating> <movie> <output>")
return
}
val conf = new SparkConf().setAppName("SparkJoin").setMaster("local")
val sc = new SparkContext(conf)
// Read rating from HDFS file
val textFile = sc.textFile(args(0))
//extract (movieid, rating)
val rating = textFile.map(line => {
val fileds = line.split("::")
(fileds(1).toInt, fileds(2).toDouble)
})
//get (movieid,ave_rating)
val movieScores = rating
.groupByKey()
.map(data => {
val avg = data._2.sum / data._2.size
(data._1, avg)
})
// Read movie from HDFS file
val movies = sc.textFile(args(1))
val movieskey = movies.map(line => {
val fileds = line.split("::")
(fileds(0).toInt, fileds(1)) //(MovieID,MovieName)
}).keyBy(tup => tup._1)
// by join, we get <movie, averageRating, movieName>
val result = movieScores
.keyBy(tup => tup._1)
.join(movieskey)
.filter(f => f._2._1._2 > 4.0)
.map(f => (f._1, f._2._1._2, f._2._2._2))
result.saveAsTextFile(args(2))
}
}
//连接操作
使用网址http://files.grouplens.org/datasets/movielens/ml-1m.zip下载所需文件,解压后存在"~/下载/ml-1m"目录里