本文整理汇总了Scala中org.apache.spark.sql.functions.max类的典型用法代码示例。如果您正苦于以下问题：Scala max类的具体用法？Scala max怎么用？Scala max使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
在下文中一共展示了max类的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Scala代码示例。
示例1: DrawdownCalculator
//设置package包名称以及导入依赖的类
import org.apache.spark.sql.expressions.Window
import org.apache.spark.sql.{DataFrame, SparkSession}
import org.apache.spark.sql.functions.max
object DrawdownCalculator {
def calculate(sparkSession: SparkSession, df: DataFrame): Double = {
val windowUptoCurrentRow = Window.orderBy("date").rowsBetween(Long.MinValue, 0)
val dfWithRollingMaxPrice = df.withColumn("rolling_max_price",
max(df("price")).over(windowUptoCurrentRow))
val dfWithRollingDrawdowns = dfWithRollingMaxPrice.withColumn("rolling_dd",
max(dfWithRollingMaxPrice("rolling_max_price") - dfWithRollingMaxPrice("price")).over(windowUptoCurrentRow))
dfWithRollingDrawdowns.createOrReplaceTempView("DrawdownCalculation")
val dfWithOrderedDrawndowns = sparkSession.sql("SELECT date, price, rolling_dd, rolling_max_price, " +
"(rolling_dd / rolling_max_price) as drawdown_pct " +
"FROM DrawdownCalculation ORDER BY drawdown_pct ASC")
dfWithOrderedDrawndowns.show()
val rollingDrawdown = dfWithOrderedDrawndowns.first().getDouble(2)
val rollingMaxPrice = dfWithOrderedDrawndowns.first().getDouble(3)
val maxDrawdownPct = dfWithOrderedDrawndowns.first().getDouble(4)
maxDrawdownPct
}
} 示例2: naturalKeyColumns
//设置package包名称以及导入依赖的类
package org.alghimo.spark.dimensionalModelling
import org.apache.spark.sql._
import org.apache.spark.sql.expressions.Window
import org.apache.spark.sql.functions.{lit, max, row_number}
def naturalKeyColumns: Seq[String]
def enrichedDimensionsToDimensions(enrichedDims: EnrichedDimensions, refreshDimensionTable: Boolean = false): Dimensions = {
val dimensions = dimensionTable(refreshDimensionTable)
val maxSk = dimensions.select(max(surrogateKeyColumn)).as[Long].collect().head
val rankWindow = Window.partitionBy().orderBy(naturalKeyColumns.head, naturalKeyColumns.tail:_*)
enrichedDims
.withColumn(surrogateKeyColumnName, lit(maxSk) + (row_number() over rankWindow))
.withColumn(startTimestampColumnName, timestampColumn)
.withColumn(endTimestampColumnName, lit(null).cast("timestamp"))
.withColumn(isCurrentColumnName, lit(true))
.selectExpr(dimensions.columns:_*)
.as[DIM]
}
def keepOnlyMostRecentEvents(enrichedDimensions: EnrichedDimensions): EnrichedDimensions = {
val naturalKeyWindow = Window.partitionBy(naturalKeyColumns.map(new Column(_)):_*).orderBy(timestampColumn.desc)
enrichedDimensions
.withColumn("row_num", row_number() over naturalKeyWindow)
.filter("row_num = 1")
.drop("row_num")
.as[ENRICHED_DIM]
}
} 示例3: TrackApp
//设置package包名称以及导入依赖的类
package com.esri
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.functions.{max, min}
object TrackApp extends App {
val spark = SparkSession
.builder()
.appName("Path SOM")
.master("local[*]")
.config("spark.ui.enabled", "false")
.getOrCreate()
import spark.implicits._
try {
val df = spark
.read
.json("Paths")
.as[TrackCells]
.cache()
val qrAgg = df
.flatMap(_.cells)
.distinct()
.agg(min("q").as("qmin"), max("q").alias("qmax"), min("r").alias("rmin"), max("r").alias("rmax"))
.as[QRMinMax]
.head
val qrMin = Cell(qrAgg.qmin, qrAgg.rmin)
val qrMax = Cell(qrAgg.qmax, qrAgg.rmax)
val qrDel = (qrMax - qrMin) + 1
val qrSize = qrDel size
val trainingArr = df
.rdd
.map(trackCells => trackCells.toBreeze(qrMin, qrDel, qrSize))
.collect()
val rnd = new java.security.SecureRandom()
val somSize = 3
val nodes = for {
q <- 0 until somSize
r <- 0 until somSize
} yield Node(q, r, trainingArr(rnd.nextInt(trainingArr.length)))
val som = SOM(nodes)
val epochMax = trainingArr.length * 400
implicit val progressBar = TerminalProgressBar(epochMax)
som.train(trainingArr, epochMax, 2.5, initialAlpha = 0.4)
som.saveAsFig("/tmp/fig.png", qrDel)
} finally {
spark.stop()
}
}