Age Grouping with spark

age_grouping.py

from pyspark import SparkContext, SparkConf

conf = SparkConf().setAppName('MyFirstStandaloneApp')
sc = SparkContext(conf=conf)

fle = sc.textFile("file:///home/nithya/girls.txt")

def age_calc(data):
        sno,fname,lname,age,desig,mob,location = data.split(",")
        return fname,lname,age_group(int(age)),desig,location,int(age)

def  age_group(age):
        if age < 30 :
           return '0-30'
        elif age < 40:
           return '30-40'
        elif age < 50:
           return '40-50'
        elif age < 60:
           return '50-60'
        else :
           return '60+'

age_map = fle.map(age_calc)
freq = age_map.map(lambda line : line[3]).countByValue()

print "Total no.of ladies",fle.count()
print "Total no.of ladies on each designation",dict(freq)

Under_age = sc.accumulator(0)
Over_age = sc.accumulator(0)

def promotion_check(data):
    global Over_age, Under_age
    age_grp = data[2]
    if(age_grp == "50-60"):
        Over_age +=1
    if(age_grp == "0-30"):
        Under_age +=1
    return data

df = age_map.map(promotion_check).collect()

print "Not qualified for promotions due to under age",Under_age
print "Not qualified for promotions due to over age",Over_age