mk_sparse.py

import unittest

class TestExtract(unittest.TestCase): 
    def test_mk_sparse(self):
        # https://en.wikipedia.org/wiki/Sparse_matrix#Dictionary_of_keys_.28DOK.29
        raw = {'A': {'x', 'y', 'z'}, 'B': {'w', 'y'}}
        expected = {('A', 'x'): 1, ('B', 'y'): 1, ('A', 'z'): 1, ('A', 'y'): 1, ('B', 'w'): 1}
        tested = mk_sparse(raw)
        msg = '\nExpected:\n{}\nGot:\n{}'.format(expected, tested)
        self.assertEqual(expected, tested, msg=msg)

def mk_sparse(dic):
    '''
    Returns a DOK sparse matrix ( (k,v):1 ) from a k:set_of_v dict
    '''
    keys = chain(*( [(samp,f) for f in feats] for samp, feats in dic.iteritems() ))
    return {k:1 for k in keys}