def simulate_tree(sample_size, sparse_factor, gen_exp, init_keep_rate):
wanted_number_of_ibds = (sample_size**2) * sparse_factor
# create an adjacency matrix representing
gens = get_generations(generation_size(sample_size, gen_exp))
edges = combine_ind_to_households(gens, init_keep_rate)
rel_matrix = csr_matrix(
(np.ones(edges.shape[0]), (edges[:, 0], edges[:, 1])),
shape=(sample_size, sample_size),
dtype=np.bool)
# check that every individual's parents are before him.
assert triu(rel_matrix).nnz == 0
# find the currect number of edges to remove till it matches
np.random.shuffle(edges)
res = find_number_of_edges_to_remove(rel_matrix, edges,
wanted_number_of_ibds)
if res == None:
raise Exception("Did not find a good enough tree")
else:
num_edges = int(edges.shape[0] * res)
rel_matrix[edges[:num_edges, 0], edges[:num_edges, 1]] = False
rel_matrix.eliminate_zeros()
# check that the resulting matrix is valid for our criteria
assert np.abs(count_IBD_nonzero(rel_matrix) -
wanted_number_of_ibds) < 0.1 * wanted_number_of_ibds
sex = np.zeros((sample_size))
gen_ind = np.zeros((sample_size))
for i, gen in enumerate(gens):
sex[gen[:int(gen.size / 2)]] = 1
gen_ind[gen] = i
return rel_matrix, sex, gen_ind
def count_with_removed_edges(edges_remove_part, rel_matrix, edges,
wanted_number_of_ibds):
num_edges = int(edges.shape[0] * edges_remove_part)
sub_rel = rel_matrix.copy()
sub_rel[edges[:num_edges, 0], edges[:num_edges, 1]] = False
diff = np.abs(count_IBD_nonzero(sub_rel) - wanted_number_of_ibds)
if diff < 0.1 * wanted_number_of_ibds:
raise Exception(edges_remove_part)
return diff
help='Gen size = gen_exp X prev gen size')
parser.add_argument(
'--init_keep_rate',
dest='init_keep_rate',
type=float,
default=0.8,
help='1 - number of edges to remove before iteration begins')
parser.add_argument('--save_folder',
dest='save_folder',
type=str,
default='.',
help='which folder it should save the output to.')
args = parser.parse_args()
if args.sample_size <= 0:
raise Exception("Sample size should be a positive number")
if (args.sparsity_factor <= 0) or (args.sparsity_factor >= 1):
raise Exception("Sparsity factor is within the range (0, 1)")
if args.gen_exp <= 0:
raise Exception("gen_exp is a positive number")
if (args.init_keep_rate <= 0) or (args.init_keep_rate > 1):
raise Exception("init_keep_rate is within the range (0, 1)")
rel = load_sparse_csr('rel.npz')
print(count_IBD_nonzero(rel))
# rel, sex, gen_ind = simulate_tree(args.sample_size, args.sparsity_factor, args.gen_exp, args.init_keep_rate)
# save_sparse_csr(os.path.join(args.save_folder, 'rel.npz'), rel)
# np.save(os.path.join(args.save_folder, 'sex.npy'), sex)
# np.save(os.path.join(args.save_folder, 'gen_ind.npy'), gen_ind)