spark计算两个DataFrame的差集、交集、合集

迷南。 2023-01-10 14:37 198阅读 0赞

# spark计算两个DataFrame的差集、交集、合集 #

闲话不说，直接上代码和结果

import org.apache.log4j.{Level, Logger}
    import org.apache.spark.{SparkConf, SparkContext}
    import org.apache.spark.sql.{SQLContext, SparkSession}
    
    /**
     * @class DataFrameFun
     * @author yyz
     * @date 2021/01/24 20:59
     *       spark计算两个DataFrame的差集、交集、合集
     *       spark 计算两个dataframe 的差集、交集、合集，只选择某一列来对比比较好。新建两个 dataframe ：
     *       https://www.cnblogs.com/TTyb/p/7991952.html
     * */
    object DataFrameFun {
      def main(args: Array[String]): Unit = {
        Logger.getLogger("org").setLevel(Level.OFF)
    
    
        //创建SparkSession 环境方法一
    //    val conf = new SparkConf().setAppName("TTyb").setMaster("local")
    //    val sc = new SparkContext(conf)
    //    val spark = new SQLContext(sc)
    
        //创建SparkSession 环境方法二 ，和方法一等价
        val spark = SparkSession.builder().master("local").appName("AppName").getOrCreate()
    
        val sentenceDataFrame1 = spark.createDataFrame(Seq(
          (1, "asf"),
          (2, "2143"),
          (4, "f8934y")
        )).toDF("label", "sentence")
        sentenceDataFrame1.show()
    
        val sentenceDataFrame = spark.createDataFrame(Seq(
          (1, "asf"),
          (2, "2143"),
          (3, "rfds")
        )).toDF("label", "sentence")
        sentenceDataFrame.show()
    
    
    
        println("1、差集 except")
        val newDF1 = sentenceDataFrame1.select("sentence").except(sentenceDataFrame.select("sentence"))
        newDF1.show()
    
        println("2、交集 intersect")
        val newDF2 = sentenceDataFrame1.select("sentence").intersect(sentenceDataFrame.select("sentence"))
        newDF2.show()
    
        println("3、合集 union")
        val newDF3 = sentenceDataFrame1.select("sentence").union(sentenceDataFrame.select("sentence"))
        newDF3.show()
    
        println("4、合集最好去一下重 distinct ：")
        val newDF4 = sentenceDataFrame1.select("sentence").union(sentenceDataFrame.select("sentence")).distinct()
        newDF4.show()
      }
    
    }
    /***
     +-----+--------+
    |label|sentence|
    +-----+--------+
    |    1|     asf|
    |    2|    2143|
    |    4|  f8934y|
    +-----+--------+
    
    +-----+--------+
    |label|sentence|
    +-----+--------+
    |    1|     asf|
    |    2|    2143|
    |    3|    rfds|
    +-----+--------+
    
    1、差集 except
    +--------+
    |sentence|
    +--------+
    |  f8934y|
    +--------+
    
    2、交集 intersect
    +--------+
    |sentence|
    +--------+
    |     asf|
    |    2143|
    +--------+
    
    3、合集 union
    +--------+
    |sentence|
    +--------+
    |     asf|
    |    2143|
    |  f8934y|
    |     asf|
    |    2143|
    |    rfds|
    +--------+
    
    4、合集最好去一下重 distinct ：
    +--------+
    |sentence|
    +--------+
    |    rfds|
    |     asf|
    |    2143|
    |  f8934y|
    +--------+
     * */