ex1.py

covid060320 = spark\
    .read\
    .option("inferSchema", "true")\
    .option("header", "true")\
    .csv("03-06-2020.csv")
    
covid060320.take(10)

covid060320.sort("Deaths").explain()

spark.conf.set("spark.sql.shuffle.partitions", "5")

covid060320.sort("Deaths").explain()

ex1.scala

val covid060320 = spark
    .read
    .option("inferSchema", "true")
    .option("header", "true")
    .csv("03-06-2020.csv")

covid060320.take(10)

covid060320.sort("Deaths").explain()

spark.conf.set("spark.sql.shuffle.partitions", "5")

covid060320.sort("Deaths").explain()