gistfile1.txt

#to find the max of one row in the file
from pyspark import SparkContext
def mapMax(line):
    line = line.split(',')
    return line[0], max((float(x) for x in line[1:]))
textfile = sc.textFile("wasb://wgkspark@teststoragespark.blob.core.windows.net/dataA.csv").cache()
lines = textfile.takeSample(False, 50)
print mapMax(lines[-1])
#print lines[0] was just for debugging

#second program to find the max of every row in a csv file
from pyspark import SparkContext
def mapMax(line):
    line = line.split(',')
    return line[0], max((float(x) for x in line[1:]))
textfile = sc.textFile("wasb://wgkspark@teststoragespark.blob.core.windows.net/dataA.csv").cache()
somethingRDD = textfile.filter(lambda line: line.split(',')[0][0] != 'T').map(mapMax)
print somethingRDD.collect()

(B1-1 EW DI [mm])