def spam_maker(args):
if args.json:
spam = shuffle_from_file(args.json)
elif args.text:
spam = utils.read_from_text(args.text)
else:
spam = [
" ".join(get_random_word() for _ in range(400))
for _ in range(2000)
]
return spam
def data_seletor(dataset_name):
if dataset_name == 'hand_write_digits':
'''
Classes 10
Samples per class ~180
Samples total 1797
Dimensionality 64
Features integers 0-16
'''
seleted = datasets.load_digits(n_class=5)
points = seleted.data
label = seleted.target
elif dataset_name == '5d5c':
'''
Classes 5
Samples per class ?
Samples total ?
Dimensionality 25
'''
points, label = utl.read_from_text('5d5c_std')
elif dataset_name == "letter-recognition":
points, label = utl.read_from_text('letter-recognition')
elif dataset_name == "lung-cancer":
points, label = utl.read_from_text('lung-cancer')
elif dataset_name == "image_seg":
points, label = utl.read_from_text('imgseg')
elif dataset_name == '20d6c':
points, label = utl.read_from_text('20d6c_std')
elif dataset_name == '50d6c':
points, label = utl.read_from_text('50d6c_std')
else:
assert("not found")
return points, label
res_cls.append(cur_cls)
for cls in tmp_clusters:
res_cls.append(cls)
print("#cls {} -> {}".format(len(clusters), len(res_cls)))
print(calc_num_point(res_cls))
return res_cls
if __name__ == '__main__':
doctest.testmod()
points, label = utl.read_from_text('2d5c_noncycle')
points = utl.centralize_data(points)
points = utl.normalize_data(points)
# points, label = utl.read_from_text('2d5c_cov')
# points, label = utl.read_from_text('hand_write_digit_2d')
# seleted = datasets.load_digits()
# points = seleted.data
# label = seleted.target
#
ms_tree = ms2c(points)
# paint_tree(ms_tree, ms_tree)
final_nodes = ms_tree.merge()
grounded_nodes = ms_tree.grounded_nodes