“Pyspark Pivot Max Aggregation” Réponses codées

Pyspark Pivot Max Aggregation

from pyspark.sql.functions import *
from pyspark.sql import Window
var win = Window.partitionBy("date") 
data.withColumn("max_vol",max("volume").over(win)).groupBy("date","max_vol") .pivot("recipe") .agg(avg("percent")).show()