大数据毕业设计hadoop+spark+hive知识图谱租房数据分析可视化大屏 租房推荐系统 58同城租房爬虫 房源推荐系统 房价预测系统 计算机毕业设计 机器学习 深度学习 人工智能_基于spark的租房数据可视化

核心算法代码分享如下：

package com.sql
 
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.types._
import org.junit.Test
 
import java.util.Properties
 
class Spark58_FixBug2024 {
  val spark = SparkSession.builder()
    .master("local[6]")
    .appName("租房数据实时计算V1.0")
    .getOrCreate()
  //课程数仓CSV 模式
  val ods_house_Schema = StructType(
    List(
      StructField("house_title", StringType),
      StructField("house_pay", StringType),
      StructField("house_pay_way", StringType),
      StructField("rent_way",StringType),
      StructField("house_type", StringType),
      StructField("house_area", StringType),
      StructField("house_decora",StringType),
      StructField("toward", StringType),
      StructField("floor", StringType),
      StructField("floor_height", StringType),
      StructField("house_estate", StringType),
      StructField("area", StringType),
      StructField("address", StringType),
      StructField("pic", StringType),
      StructField("time", StringType),
      StructField("agent_name", StringType),
      StructField("house_disposal", StringType),
      StructField("house_spot", StringType),
      StructField("house_desc", StringType),
      StructField("url", StringType),
      StructField("sentiments", FloatType)
 
    )
  )
 
  val ods_house_Df = spark.read.option("header", "false").schema(ods_house_Schema).csv("hdfs://bigdata:9000/beike/house/beike.csv")
 
 
 
 
 
  @Test
  def init(): Unit = {
    //school_province_score_Df.show()
    //ods_courses_Df.show()
    ods_house_Df.show()
    //school_special_score_Df.show()
    //school_Df.show()
    //ruanke_rank_Df.show()
    //qs_world_Df.show()
  }
 
 
 
//  ----剩余使用spark_sql完成
//    ---指标8：租金支付方式占比
  @Test
  def tables08(): Unit = {
  ods_house_Df.createOrReplaceTempView("ods_house")
    val df2 = spark.sql(
      """
      select house_pay_way,count(1) num
      from ods_house
      group by house_pay_way
      order by num desc
      limit 10
    """)
    df2
//      .show(50)
     .coalesce(1)
      .write
      .mode("overwrite")
      .option("driver", "com.mysql.cj.jdbc.Driver")
      .option("user", "root")
      .option("password", "123456")
      .jdbc(
        "jdbc:mysql://bigdata:3306/beike_hive?useSSL=false",
        "table08",
        new Properties()
      )
  }
 
 // ---指标9：地址词云
  @Test
  def tables09(): Unit = {
    ods_house_Df.createOrReplaceTempView("ods_house")
    val df2 = spark.sql(
      """
      select address,count(1) num
      from ods_house
      group by address
      order by num desc
      limit 10
    """)
    df2
      //      .show(50)
      .coalesce(1)
      .write
      .mode("overwrite")
      .option("driver", "com.mysql.cj.jdbc.Driver")
      .option("user", "root")
      .option("password", "123456")
      .jdbc(
        "jdbc:mysql://bigdata:3306/beike_hive?useSSL=false",
        "table09",
        new Properties()
      )
  }
 
 
 
 
}