Scala 練習題 學生分數案例
一、相關信息
題目:
1、統計班級人數
2、統計學生的總分
3、統計總分年級排名前十學生各科的分數
4、統計總分大於年級平均分的學生
5、統計每科都及格的學生
6、統計偏科最嚴重的前100名學生
數據樣例(部分數據):
1.學生信息數據:students.txt
1500100001,施笑槐,22,女,文科六班 1500100002,呂金鵬,24,男,文科七班 1500100003,單樂蕊,22,女,理科六班 1500100004,葛德曜,24,男,理科三班 1500100005,宣谷芹,22,女,理科五班 1500100006,邊昂雄,21,男,理科二班 1500100007,尚孤風,23,女,文科六班 1500100008,符半雙,22,女,理科六班 1500100009,沈德昌,21,男,理科一班 1500100010,羿彥昌,23,男,理科六班 1500100011,宰運華,21,男,理科三班 1500100012,梁易槐,21,女,理科一班 1500100013,逯君昊,24,男,文科二班 1500100014,羿旭炎,23,男,理科五班 1500100015,宦懷綠,21,女,理科一班 1500100016,潘訪煙,23,女,文科一班
2.學生分數信息(部分):
500100001,1000001,98 1500100001,1000002,5 1500100001,1000003,0 1500100001,1000004,29 1500100001,1000005,85 1500100001,1000006,52 1500100002,1000001,139 1500100002,1000002,102 1500100002,1000003,44 1500100002,1000004,18 1500100002,1000005,46 1500100002,1000006,91 1500100003,1000001,48
3.學生科目信息(部分):
1000001,語文,150 1000002,數學,150 1000003,英語,150 1000004,政治,100 1000005,歷史,100 1000006,物理,100 1000007,化學,100 1000008,地理,100 1000009,生物,100
二、題目代碼編寫
1、統計班級人數
package shujia import scala.io.Source //1、統計班級人數 /** * 以下所有的方法都是返回新的集合,不會修改原始的集合 * 同時以下這些方法在set集合中也有,除了sort * foreach:遍曆數據 * map:一條一條處理數據 * filter:過濾數據 * flatMap:將一行轉換成多行 * sortBy:排序 * groupBy:分組 */ object Test2 { def main(args: Array[String]): Unit = { //讀取文件 val students: List[String] = Source.fromFile("data/score.txt").getLines().toList //按照逗號分割 val stringses: List[Array[String]] = students.map(line => line.split(",")) //3.過濾臟數據 val listFilter: List[Array[String]] = stringses.filter(line => line.length == 3) //4.取數據 val scores: List[(String, Int)] = listFilter.map { case Array(id: String, _: String, sco: String) => (id, sco.toInt) } //分組group val group: Map[String, List[(String, Int)]] = scores.groupBy(word => word._1) //統計數量 val sumScoList: Map[String, Int] = group.map { case (id: String, list: List[(String, Int)]) => val sco: List[Int] = list.map { case (_, sco: Int) => sco } val sumSco: Int = sco.sum (id, sumSco) } sumScoList.foreach(println) } }
2、統計學生的總分
package com.shujia.scala import scala.io.Source object Demo22SumScore { def main(args: Array[String]): Unit = { /** * 2、統計學生的總分 */ //1、讀取分數表 val scoresList: List[String] = Source.fromFile("data/score.txt").getLines().toList //2、過濾臟數據 val filterList: List[String] = scoresList.filter((line: String) => { val length: Int = line.split(",").length length == 3 }) //3、取出學號和分數 val idAndScore: List[(String, Int)] = filterList.map((line => { val split: Array[String] = line.split(",") //學號 val id: String = split.head //分數 val score: Int = split.last.toInt (id, score) })) //4、按照學號分組 val groupByList: Map[String, List[(String, Int)]] = idAndScore.groupBy(kv => kv._1) //5、統計學生的總分 val sumScoMap: Map[String, Int] = groupByList.map((kv: (String, List[(String, Int)])) => { val id: String = kv._1 val scores: List[(String, Int)] = kv._2 //取出每個學生所有的分數 val scos: List[Int] = scores.map(sco => sco._2) //計算總分 val sumSco: Int = scos.sum (id, sumSco) }) sumScoMap.foreach(println) } }
/*
* 第二種方法,case
*/
object Demo22SumScore {
def main(args: Array[String]): Unit = {
/**
* 2、統計學生的總分
*/
//1、讀取分數表
val scoresList: List[String] = Source.fromFile("data/score.txt").getLines().toList
//2、過濾臟數據
val filterList: List[String] = scoresList.filter((line: String) => {
val length: Int = line.split(",").length
length == 3
})
//3、取出學號和分數
val idAndScore: List[(String, Int)] = filterList.map((line => {
val split: Array[String] = line.split(",")
//學號
val id: String = split.head
//分數
val score: Int = split.last.toInt
(id, score)
}))
//4、按照學號分組
val groupByList: Map[String, List[(String, Int)]] = idAndScore.groupBy(kv => kv._1)
//5、統計學生的總分
val sumScoMap: Map[String, Int] = groupByList.map((kv: (String, List[(String, Int)])) => {
val id: String = kv._1
val scores: List[(String, Int)] = kv._2
//取出每個學生所有的分數
val scos: List[Int] = scores.map(sco => sco._2)
//計算總分
val sumSco: Int = scos.sum
(id, sumSco)
})
sumScoMap.foreach(println)
}
}
3、統計總分年級排名前十學生各科的分數
package shujia import scala.io.Source //1、統計總分年級排名前十學生各科的分數 object Test3Top10 { def main(args: Array[String]): Unit = { //1、讀取分數 val lines: List[String] = Source.fromFile("data/score.txt").getLines().toList //2、切分數據 val scoreArr: List[Array[String]] = lines.map(line => line.split(",")) //3、過濾臟數據 val scoreFilter: List[Array[String]] = scoreArr.filter(arr => arr.length == 3) //scoreFilter.foreach(println) //4、取出學號和分數 val scoFilter: List[(String, String, Int)] = scoreFilter.map { case Array(id: String, subject: String, sco: String) => (id, subject, sco.toInt) } //5.學號分組 val scoGroupBy: Map[String, List[(String, String, Int)]] = scoFilter.groupBy(kv => kv._1) //6.計算學生總分 val sSos: List[(String, Int, List[(String, String, Int)])] = scoGroupBy.map { case (id: String, list: List[(String, String, Int)]) => val scores: List[Int] = list.map { case (_, _, sco: Int) => sco } val scoSum: Int = scores.sum (id, scoSum, list) }.toList val lists: List[(String, Int, List[(String, String, Int)])] = sSos.sortBy(kv => -kv._2) val top10: List[(String, Int, List[(String, String, Int)])] = lists.take(10) top10.foreach(println) } }
4、統計總分大於年級平均分的學生
import com.shujia.spark.util.HdfsUtil import org.apache.spark.rdd.RDD import org.apache.spark.{SparkConf, SparkContext} //統計總分大於年級平均分的學生 //平均總分=學生總分/學生人數 object Test2ScoreAvg { def main(args: Array[String]): Unit = { val conf = new SparkConf() conf.setAppName("AVG") // conf.setMaster("local") val sc = new SparkContext(conf) //讀取文件切分過濾臟數據 val scoFilter: RDD[Array[String]] = sc.textFile("/data/student/score.txt").map(_.split(",")).filter(_.length == 3) //提取分數出來 val scoRDD: RDD[(String, Int)] = scoFilter.map { case Array(id: String, _, sco: String) => (id, sco.toInt) } //按照學生學號進行分組 val scoGroRDD: RDD[(String, Iterable[(String, Int)])] = scoRDD.groupBy(_._1) //暫存緩存中,提高速率 scoRDD.cache() //計算學生的總分 val sumStusRDD: RDD[(String, Int)] = scoRDD.reduceByKey(_ + _) //計算年級的總分 val sumNJ: Double = sumStusRDD.map(_._2).sum //計算年級的平均總分 val avgSum: Double = sumNJ / scoGroRDD.count //過濾總分大於平均分的數據 val avgtoSum: RDD[(String, Int)] = sumStusRDD.filter { case (_, sco: Int) => sco >= avgSum } val l1: Long = avgtoSum.count() println(s"大於平均分有$l1+人,平均分是:$avgSum") // avgtoSum.foreach(println) HdfsUtil.delete("/data/sum_avgToSum") avgtoSum.saveAsTextFile("/data/sum_avgToSum") } }
5、統計每科都及格的學生
package shujia import scala.collection.immutable import scala.io.Source //3、統計每科都及格的學生 object Test5_60fen { def main(args: Array[String]): Unit = { //讀取文件 val list: List[String] = Source.fromFile("data/score.txt").getLines().toList // list.foreach(println) //按照逗號分割 val listSplit: List[Array[String]] = list.map(line => line.split(",")) // listSplit.foreach(println) //過濾數據 val listFilter: List[Array[String]] = listSplit.filter(line => line.length == 3) //提取數據,過濾分數大於60的人 // listFilter.foreach(println) val listFilter2: List[Array[String]] = listFilter.filter(sco => sco.last.toInt - (60) >= 0) //listFilter2.foreach(println) val lists: List[(String, String, Int)] = listFilter2.map { case Array(id: String, sub: String, sco: String) => (id, sub, sco.toInt) } //按照學號分組 val listGroup: Map[String, List[(String, String, Int)]] = lists.groupBy(line => line._1) val list1: List[(String, List[(String, String, Int)])] = listGroup.map((kv: (String, List[(String, String, Int)])) => { val id: String = kv._1 val count: List[(String, String, Int)] = kv._2 (id, count) }).toList list1.foreach(println) } }
6、統計偏科最嚴重的前100名學生
package com.shujia.scala import scala.collection.immutable import scala.io.Source object Demo31Student { def main(args: Array[String]): Unit = { /** * 4、統計偏科最嚴重的前100名學生 * * 偏科評估的標準: 方差 */ //1、讀取分數 val lines: List[String] = Source.fromFile("data/score.txt").getLines().toList //2、切分數據 val scoreArr: List[Array[String]] = lines.map(line => line.split(",")) //3、過濾臟數據 val scoreFilter: List[Array[String]] = scoreArr.filter(arr => arr.length == 3) //4、取出學號和分數 val idAndScore: List[(String, Int)] = scoreFilter.map { case Array(id: String, _, sco: String) => (id, sco.toInt) } //5、按照學號分組 val groupBy: Map[String, List[(String, Int)]] = idAndScore.groupBy(kv => kv._1) //計算方差 val std: List[(String, Double, List[(String, Int)])] = groupBy.map { case (id: String, list: List[(String, Int)]) => //一個學生所有的分數 val scores: List[Int] = list.map { case (_, sco: Int) => sco } /** * 計算方差 * 1、計算總數 * 2、計算平均值 * 3、計算方差 * */ //科目數 val N: Double = scores.length.toDouble //平均數 val avg: Double = scores.sum / N //計算方差 val std: Double = scores.map((sco: Int) => (sco - avg) * (sco - avg)).sum / N (id, std, list) }.toList //按照方差排序,取前100 val sortByStd: List[(String, Double, List[(String, Int)])] = std.sortBy(kv => -kv._2) //取前100 val top10: List[(String, Double, List[(String, Int)])] = sortByStd.take(100) top10.foreach(println) } }