Spark Scala Cassandra CSV插入cassandra

Question

下面是代码: Scala版本: 2.11。Spark版本: 2.0.2.6 Cassandra版本: cqlsh 5.0.1 | Cassandra 3.11.0.1855 | DSE 5.1.3 | CQL spec 3.4.4 |本地协议v4

我正在尝试从CSV读取并写入Cassandra Table。我是Scala和Spark的新手。请纠正我哪里做错了

import org.apache.spark.sql.SparkSession
import org.apache.log4j.{Level, Logger}
import com.datastax

import org.apache.spark.SparkContext
import org.apache.spark.SparkConf
import com.datastax.spark.connector._
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.{Row, SparkSession}
import org.apache.spark.sql.types.{DoubleType, StringType, StructField, StructType}
import org.apache.spark.sql._
import com.datastax.spark.connector.UDTValue
import com.datastax.spark.connector.mapper.DefaultColumnMapper


object dataframeset {

  def main(args: Array[String]): Unit = {

    // Cassandra Part

    val conf = new SparkConf().setAppName("Sample1").setMaster("local[*]")
    val sc = new SparkContext(conf)
    sc.setLogLevel("ERROR")
    val rdd1 = sc.cassandraTable("tdata", "map")

    rdd1.collect().foreach(println)

    // Scala Read CSV Part
    Logger.getLogger("org").setLevel(Level.ERROR)
    Logger.getLogger("akka").setLevel(Level.ERROR)
    val spark1 = org.apache.spark.sql.SparkSession
      .builder()
      .master("local")
      .appName("Spark SQL basic example")
      .getOrCreate()

    val df = spark1.read.format("csv")
      .option("header","true")
      .option("inferschema", "true")
      .load("/Users/tom/Desktop/del2.csv")
    import spark1.implicits._
      df.printSchema()
      val dfprev = df.select(col = "Year","Measure").filter("Category = 'Prevention'" )

//      dfprev.collect().foreach(println)
      val a = dfprev.select("YEAR")
      val b = dfprev.select("Measure")

      val collection = sc.parallelize(Seq(a,b))
    collection.saveToCassandra("tdata", "map", SomeColumns("sno", "name"))

    spark1.stop()

  }

}

错误：

Exception in thread "main" java.lang.IllegalArgumentException: Multiple constructors with the same number of parameters not allowed.

Cassandra表

cqlsh:tdata>描述图

创建表tdata.map ( sno int主键，名称文本；

我知道我错过了一些东西，尤其是试图一次将整个数据帧写入Cassandra。不，我也不知道该怎么做。

谢谢汤姆

Answer 1

您可以直接向cassandra写入数据帧(Spark2.x中的datasetRow)。

如果在spark conf中启用了身份验证，则必须定义cassandra主机、用户名和密码，才能使用以下内容连接到cassandra

val conf = new SparkConf(true)
    .set("spark.cassandra.connection.host", "CASSANDRA_HOST")
    .set("spark.cassandra.auth.username", "CASSANDRA_USERNAME")            
    .set("spark.cassandra.auth.password", "CASSANDRA_PASSWORD")

或

val spark1 = org.apache.spark.sql.SparkSession
      .builder()
      .master("local")
      .config("spark.cassandra.connection.host", "CASSANDRA_HOST")
      .config("spark.cassandra.auth.username", "CASSANDRA_USERNAME")            
      .config("spark.cassandra.auth.password", "CASSANDRA_PASSWORD")
      .appName("Spark SQL basic example")
      .getOrCreate()

val dfprev = df.filter("Category = 'Prevention'" ).select(col("Year").as("yearAdded"),col("Measure").as("Recording"))

dfprev .write
  .format("org.apache.spark.sql.cassandra")
  .options(Map("table" -> "map", "keyspace" -> "tdata"))
  .save()

Dataframe in spark-cassandra-connector