я использую искры со scala и имею проблему с типом TimestampType
object regressionLinear {
case class X(
time:String,nodeID: Int, posX: Double,posY: Double,
speed: Double,period: Int)
def main (args: Array[String]) {
Logger.getLogger("org").setLevel(Level.OFF)
Logger.getLogger("akka").setLevel(Level.OFF)
/**
* Read the input data
*/
var dataset = "C:\\spark\\A6-d07-h08.csv"
if (args.length > 0) {
dataset = args(0)
}
val spark = SparkSession
.builder
.appName("regressionsol")
.master("local[4]")
.getOrCreate()
import spark.implicits._
val data = spark.sparkContext.textFile(dataset)
.map(line=>line.split(","))
.map(userRecord => (userRecord(0).trim.toString,
userRecord(1).trim.toInt, userRecord(2).trim.toDouble,userRecord(3).trim.toDouble,userRecord(4).trim.toDouble,userRecord(5).trim.toInt))
.toDF("time","nodeID","posX", "posY","speed","period").withColumn("time", $"time".cast("timestamp"))
val assembler = new VectorAssembler()
.setInputCols( Array(
"time","nodeID","posX", "posY","speed","period"))
.setOutputCol("features")
val lr = new LinearRegression()
.setLabelCol("period")
.setFeaturesCol("features")
.setRegParam(0.1)
.setMaxIter(100)
.setSolver("l-bfgs")
val steps =
Array(assembler, lr)
val pipeline = new Pipeline()
.setStages(steps)
val Array(training, test) = data.randomSplit(Array(0.75, 0.25), seed = 12345)
val model = pipeline.fit {
training
}
val holdout = model.transform(test)
holdout.show(20)
val prediction = holdout.select("prediction", "period","nodeID").orderBy(abs(col("prediction")-col("period")))
prediction.show(20)
val rm = new RegressionMetrics(prediction.rdd.map{
x => (x(0).asInstanceOf[Double], x(1).asInstanceOf[Double])
})
println(s"RMSE = ${rm.rootMeanSquaredError}")
println(s"R-squared = ${rm.r2}")
spark.stop()
}
}
это ошибка
Исключение в потоке "main" java.lang.IllegalArgumentException:Тип данных TimestampType времени столбца не поддерживается.в org.apache.spark.ml.feature.VectorAssembler.transformSchema (VectorAssembler.scala: 124) в org.apache.spark.ml.Pipeline $$ anonfun $ transformSchema $ 4.apply (Pipeline.scala: 184) в org.apache.spark..scala: 66) в scala.collection.mutable.ArrayOps $ ofRef.foldLeft (ArrayOps.scala: 186) в org.apache.spark.ml.Pipeline.transformSchema (Pipeline.scala: 184) в org.apache.spark.ml.PipelineStage.transformSchema (Pipeline.scala: 74) в org.apache.spark.ml.Pipeline.fit (Pipeline.scala: 136) в regressionLinear $ .main (regressionLinear.scala: 100) в regressionLinear.main (regressionLinear.scala)