groupBy Example in Pyspark

from pyspark.sql.functions import count

df = spark.read.format("csv").option("header",True).\

            option("inferSchema",True).\

            load("E:\\vow\\CancerData10.csv")

#df.printSchema()

#df.show(5)

df1 = df.select("ID","Age","State","Sex")

df2 = df1.groupBy("Sex").agg(count('Sex').alias("Count"))

df2.show()

+---+-----+

|Sex|Count|

+---+-----+

|  F|    4|

|  M|    5|

+---+-----+