Python function to calculate cumulative relative frequency distribution (for contexts where numpy/scipy/etc not available, e.g. in Pig pre-v.0.12). Originally designed to work as a User Defined Function for Pig on Hadoop.

cumRelFreqDistn.py

def cumRelFreqDistn(tups):
    
    # create bins of increment 0.01
    a = [i*-0.01 for i in range(100)]
    a = a[1:len(a)]
    b = [i*0.01 for i in range(101)]
    a.extend(b)
    a.sort()
    bins = a
    
    # build cumulative relative frequency distribution
    cumfreq = [0]*200
    for tup in tups:
        tup = list(tup)
        tup = tup[0]
        for bin in range(len(bins)):
            if tup <= bins[bin]:
                cumfreq[bin] = cumfreq[bin]+1
    
    cumrelfreq = [float(cumfreq[i]) / max(cumfreq) for i in range(len(cumfreq))]
    
    crfd = zip(bins, cumrelfreq)
    
    return crfd