本文整理汇总了Scala中org.apache.spark.sql.expressions.Window类的典型用法代码示例。如果您正苦于以下问题：Scala Window类的具体用法？Scala Window怎么用？Scala Window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Window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: SparkSQLSearch
//设置package包名称以及导入依赖的类
package com.jjzhk.sparkexamples.sql.search
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.expressions.Window
import org.apache.spark.sql.functions._
object SparkSQLSearch {
def main(args: Array[String]): Unit = {
val spark = SparkSession.builder().appName("SparkSQLSearch").master("spark://Master:7077").enableHiveSupport().getOrCreate()
import spark.implicits._
spark.sql("use hive")
var dfuv = spark.sql("select date, item, count(*) as uv from searchinfo group by date, item order by date")
.withColumn("number", row_number().over(Window.partitionBy($"date").orderBy($"date", $"uv".desc)))
.filter($"number".leq(5))
var dfitems = spark.sql("select * from items")
dfuv.join(dfitems, Seq("item")).select("date", "itemname", "uv").show(200)
}
}