SPARK AvgById

spark.py

sc.textFile("/home/bibi/Desktop/distributed.csv") \
    .map(lambda line: line.split(",")) \
    .map(lambda line: (int(line[0]),float(line[2]))) \
    .combineByKey( lambda value: (value, 1),
                   lambda x, value: (x[0] + value, x[1] + 1),
                   lambda x, y: (x[0] + y[0], x[1] + y[1])) \
    .map(lambda (label, (value_sum, count)): (label, value_sum / count)) \
    .collectAsMap()