python clump

clump.py

from random import shuffle

to_clump = [0, 0.2, 5, 9, 9.1, 100, 100.2]
shuffle(to_clump)

def clump_same(comparables, distance_threshold):
    def do_clump(so_far, current):
        last_clump = so_far[-1]
        lowest_in_last_clump = last_clump[0]
        if (current - lowest_in_last_clump) < distance_threshold:
            last_clump.append(current)
        else:
            so_far.append([current])
        return so_far

    sorted_list = sorted(to_clump)
    return reduce(do_clump, sorted_list[1:], [[sorted_list[0]]])

def skim_clumps(to_clump, threshold):
    return [clump[-1] for clump in clump_same(to_clump, threshold)]


print clump_same(to_clump, 0.5)
print skim_clumps(to_clump, 0.5)

#[[0, 0.2], [5], [9, 9.1], [100, 100.2]]
#[0.2, 5, 9.1, 100.2]