练习
package scala_01.practice
import org.junit.{Before, Test}
import scala.collection.immutable
import scala.collection.immutable.StringOps
import scala.collection.mutable.ListBuffer
import scala.io.Source
/**
* 1、统计班级人数
* 2、统计学生的总分
*/
class Practice1 {
var students: List[Student] = _
var score: List[Score] = _
var cource: List[Cource] = _
@Before
def read_file(): Unit = {
// 读取students.txt数据
// 这里路径不能是 scala/data/students.txt
students = Source.fromFile("data/students.txt")
.getLines()
.toList
.map(s => {
val spilts: Array[String] = s.split(",")
val id: String = spilts(0)
val name: String = spilts(1)
val age: Int = spilts(2).toInt
val gender: String = spilts(3)
val clazz: String = spilts(4)
Student(id, name, age, gender, clazz)
})
// 读取Score.txt数据
score = Source.fromFile("data/score.txt")
.getLines()
.toList
.map(s => {
val splits: Array[String] = s.split(",")
val id: String = splits(0)
val sub_id: String = splits(1)
val score_sc: Int = splits(2).toInt
Score(id, sub_id, score_sc)
})
// 读取Cource.txt数据
cource = Source.fromFile("data/cource.txt")
.getLines()
.toList
.map(s => {
val splits: Array[String] = s.split(",")
val sub_id: String = splits(0)
val sub_name: String = splits(1)
val score_max: Int = splits(2).toInt
Cource(sub_id, sub_name, score_max)
})
}
@Test
def printAll: Unit = {
students.take(10).foreach(println)
score.take(10).foreach(println)
cource.take(10).foreach(println)
}
// 1、统计班级人数
@Test
def count_students: Unit = {
val count_stu: Map[String, Int] = students
.groupBy(s => s.clazz)
.map(kv => (kv._1, kv._2.size))
count_stu.foreach(println)
}
// 2、统计学生的总分
@Test
def sum_score: Unit = {
val sum_sc: Map[String, Int] = score.groupBy(s => s.id)
.map(kv => {
val id: String = kv._1
val score_sc: List[Score] = kv._2
val sum_s = score_sc.map(s => s.score_sc).sum
(id, sum_s)
})
sum_sc.foreach(println)
}
@Test
// 1、统计年级排名前十学生各科的分数 [学号,学生姓名，学生班级，科目名，分数]
def um_score_top10_stu: Unit = {
//先拿到排名前十的学生id
val top10ids: List[String] = score.groupBy(s => s.id)
.map(kv => {
val id: String = kv._1
val score_sc: List[Score] = kv._2
val sum_s = score_sc.map(s => s.score_sc).sum
(id, sum_s)
}).toList
.sortBy(s => (-s._2)) // 按照总分倒序排列
.take(10)
.map(s => s._1) // 直接取出id
// 将score转成kv格式的Map集合
// 将id作为key Score对象作为value
val scomap: Map[String, List[(String, Score)]] = score.map(kv => {
val id: String = kv.id
val values: Score = kv
(id, values)
}).groupBy(kv => kv._1)
// 将cource_id作为key cource_name作为value 构建subMap
val submap: Map[String, String] = cource.map(s => (s.sub_id, s.sub_name)).toMap
val result: List[(String, String, String, String, Int)] = students.filter(s => {
top10ids.contains(s.id)
}).flatMap(s => {
// 初始化一个ListBuffer用于保留最后的结果
// ListBuffer中每个元素的类型是一个5元组（同题目需要的5列结果类型一一对应）
val tuples: ListBuffer[(String, String, String, String, Int)] = ListBuffer[(String, String, String, String, Int)]()
val id: String = s.id
val name: String = s.name
val clazz: String = s.clazz
// 根据学生id从scoMap中将该学生的6门科目的分数取出来 得到一个Score对象构成的List
val scores: List[Score] = scomap(s.id).map(_._2)
// 遍历每个学生的6门科目成绩
scores.map(sco => {
val sub_id: String = sco.sub_id
val score_sc: Int = sco.score_sc
// 根据科目id从subMap中取出科目名称
val sub_name: String = submap(sub_id)
tuples.append((id, name, clazz, sub_name, score_sc))
})
tuples
})
result.foreach(println)
}
// 2、统计总分大于年级平均分的学生 [学号，姓名，班级，总分]
@Test
def sum_score_beyond_avg: Unit = {
// 年级的总分拿过来
val sum_sc: Map[String, Int] = score.groupBy(s => s.id)
.map(kv => {
val id: String = kv._1
val score_sc: List[Score] = kv._2
val sum_s = score_sc.map(s => s.score_sc).sum
(id, sum_s)
})
// 计算年级平均分
val bigsum: Int = sum_sc.map(_._2).sum
val avg: Double = bigsum / (sum_sc.size.toDouble)
println(avg)
// 以学生id作为key Students对象最为value 构建stuMap
val stumap: Map[String, Student] = students.map(s => (s.id, s)).toMap
sum_sc.filter(kv => kv._2 > avg) // 过滤出成绩大于年级平均分的学生
.map(kv => {
val id: String = kv._1
val sum_ss: Int = kv._2
// 根据学生id从stuMap中提取出学生信息
val stu: Student = stumap(id)
val name: String = stu.name
val clazz: String = stu.clazz
(id, name, clazz, sum_ss)
}).foreach(println)
}
// 3、统计每科都及格的学生 [学号，姓名，班级，科目，分数]
@Test
def every_subject_pass: Unit = {
// 每门科目的及格分数Map
// k：科目id v：二元组(科目名称，科目及格分数)
val sub_pass_map: Map[String, (String, Double)] = cource.map(s => {
val id: String = s.sub_id
val sub_name: String = s.sub_name
val pass_score: Double = (s.score_max) * 0.6
(id, (sub_name, pass_score))
}).toMap
// 所有6门科目都及格的学生id
val pass_id: List[String] = score
.filter(s => s.score_sc > sub_pass_map(s.sub_id)._2)
.groupBy(kv => kv.id)
.map(kv => (kv._1, kv._2.size))
.filter(s => s._2 == 6)
.map(s => s._1)
.toList
val groupsc: Map[String, List[(String, Score)]] = score.map(s => (s.id, s)).groupBy(_._1)
students.filter(s => pass_id.contains(s.id))
.map(s => {
val lb: ListBuffer[(String, String, String, String, Int)] = ListBuffer[(String, String, String, String, Int)]()
val id: String = s.id
val name = s.name
val clazz = s.clazz
// 根据学生id从scoMap中将该学生的6门科目的分数取出来 得到一个Score对象构成的List
val scores: List[Score] = groupsc(id).map(_._2)
// 遍历每个学生的6门科目成绩
scores.map(s => {
val score_sc: Int = s.score_sc
val sub_id: String = s.sub_id
val sub_name: String = sub_pass_map(sub_id)._1
lb.append((id, name, clazz, sub_name, score_sc))
})
lb
}).foreach(println)
}
@Test
// 4、统计每个班级的前三名 [学号，姓名，班级，分数]
def clazz_sum_score_top3: Unit = {
// 学生总分
val id_sum_core: Map[String, Int] = score.groupBy(s => s.id)
.map(kv => {
val id: String = kv._1
val sum_sc: Int = kv._2.map(s => s.score_sc).sum
(id, sum_sc)
})
// 根据学生id 从id_sum_score中获取学生总分
students.map(s => (s.id, s.name, s.clazz, id_sum_core(s.id)))
.groupBy(s => s._3)
.flatMap(kv => {
val clazz: String = kv._1
val stuList: List[(String, String, String, Int)] = kv._2
val top3: List[(String, String, String, Int)] = stuList.sortBy(s => s._4)
.take(3)
top3
}).foreach(println)
}
// 5、统计偏科最严重的前100名学生 [学号，姓名，班级，科目，分数]
@Test
def unbalanceTop100: Unit ={
val cour_map: Map[String, Int] = cource.map(s => {
val sub_id: String = s.sub_id
val score_max: Int = s.score_max
(sub_id, score_max)
}).toMap
//每个学生的百分制分数
val per_score: List[(String, Double)] = score.map(s => {
val id: String = s.id
val score_sc: Int = s.score_sc
val sub_id: String = s.sub_id
val score_max: Int = cour_map(sub_id)
val per_sco: Double = (score_sc / score_max.toDouble) * 100
(id, per_sco)
})
//学生平均分
val stu_avg: Map[String, Double] = per_score.groupBy(s => s._1)
.map(kv => {
val id: String = kv._1
val values: List[(String, Double)] = kv._2
val sum: Double = values.map(s => s._2).sum
val avg: Double = sum / values.size.toDouble
(id, avg)
})
// 求100位方差
val top100: List[String] = per_score.map(kv => {
val id: String = kv._1
val per_sco: Double = kv._2
val avg: Double = stu_avg(id)
val fenzi: Double = math.pow((avg - per_sco), 2)
(id, fenzi)
}).groupBy(_._1)
.map(kv => {
val id: String = kv._1
val size: Int = kv._2.size
val fancha: Double = kv._2.map(_._2).sum / size
(id, fancha)
}).toList
.sortBy(-_._2)
.map(_._1)
.take(100)
val cou_map: Map[String, String] = cource.map(s=>(s.sub_id,s.sub_name)).toMap
val sco_map: Map[String, List[Score]] = score.groupBy(_.id)
students.filter(s=>top100.contains(s.id))
.flatMap(s=>{
val tuples: ListBuffer[(String, String, String, String, Int)] = ListBuffer[(String,String,String,String,Int)]()
val id: String = s.id
val name: String = s.name
val clazz: String = s.clazz
sco_map(id).foreach(s=>{
val sub_id: String = s.sub_id
val score_sc: Int = s.score_sc
val sub_name: String = cou_map(sub_id)
tuples.append((id,name,clazz,sub_name,score_sc))
})
tuples
}).foreach(println)
}
case class Student(id: String, name: String, age: Int, gender: String, clazz: String)
case class Score(id: String, sub_id: String, score_sc: Int)
case class Cource(sub_id: String, sub_name: String, score_max: Int)
}
