from pyspark import SparkContext

sc = SparkContext.getOrCreate()

result = sc.textFile( "users.csv" ) \
    .map(lambda x: (x.split('|')[3],1) ) \
    .filter( lambda x: x[0] != 'other' ) \
    .reduceByKey( lambda x,y:x+y ) \
    .sortBy( lambda x: -x[1] ).collect()

for line in result:
    print line