Examples
Average
// given: have a CSV file with the schema: registration_dttm,id,first_name,last_name,email,gender,ip_address,cc,country,birthdate,salary,title,comments
// when: doing an average of salary per gender
// then: should return a map with (gender,salary)
val users = sc.textFile("file:///userdata.csv").split(",",-1)
// removing empty salaries and genders
val usersClean = users.filter(x => !x(5).isEmpty && !x(10).isEmpty)
val usersGend = usersClean.map(x => (x(5), x(10).toFloat))
// adding a counter for each item
val usersGendAvgSal = usersGend.mapValues((_,1)).reduceByKey((x,y) => )
usersGendAvgSal.collect
Last updated
Was this helpful?