from pyspark import SparkContext
from pyspark.sql import SparkSession

sc = SparkContext.getOrCreate()
spark = SparkSession(sc)

spark.read.load( "users.csv", format="csv", sep="|" ) \
      .toDF( "id","age","gender","occupation","zip" ) \
      .createOrReplaceTempView( "users" )

spark.sql( "select gender, count(*) from users group by gender" ).show()