def get_subprobs(size, max_size):
'''
Compute probabilities of shapes of partial assignment vectors.
Inputs:
size = sample_size
max_size = dataset_size
Returns:
dict : shape -> prob
'''
assert 0 <= size
assert size <= max_size
cache_file = '{}/subprobs.{}.{}.json.bz2'.format(TEMP, size, max_size)
if cache_file not in CACHE:
if os.path.exists(cache_file):
flat = json_stream_load(cache_file)
small_probs = {tuple(key): val for key, val in flat}
else:
if size == max_size:
small_probs = get_probs(size)
else:
small_counts = get_counts(size)
large_counts = get_counts(size + 1)
large_probs = get_subprobs(size + 1, max_size)
small_probs = get_smaller_probs(
small_counts,
large_counts,
large_probs)
print 'caching', cache_file
json_stream_dump(small_probs.iteritems(), cache_file)
CACHE[cache_file] = small_probs
return CACHE[cache_file]
def get_counts(size):
'''
Count partition shapes of a given sample size.
Inputs:
size = sample_size
Returns:
dict : shape -> count
'''
assert 0 <= size
cache_file = '{}/counts.{}.json.bz2'.format(TEMP, size)
if cache_file not in CACHE:
if os.path.exists(cache_file):
flat = json_stream_load(cache_file)
large = {tuple(key): val for key, val in flat}
else:
if size == 0:
large = {(): 1.0}
else:
small = get_counts(size - 1)
large = get_larger_counts(small)
print 'caching', cache_file
json_stream_dump(large.iteritems(), cache_file)
CACHE[cache_file] = large
return CACHE[cache_file]
def create_dataset(sample_count=SAMPLE_COUNT):
'''
Extract dataset from image.
'''
scipy.misc.imsave(os.path.join(RESULTS, 'original.png'), IMAGE)
print 'sampling {} points from image'.format(sample_count)
samples = sample_from_image(IMAGE, sample_count)
json_stream_dump(samples, SAMPLES)
image = visualize_dataset(json_stream_load(SAMPLES))
scipy.misc.imsave(os.path.join(RESULTS, 'samples.png'), image)
def create_dataset(sample_count=SAMPLE_COUNT):
'''
Extract dataset from image.
'''
scipy.misc.imsave(os.path.join(RESULTS, 'original.png'), IMAGE)
print 'sampling {} points from image'.format(sample_count)
samples = sample_from_image(IMAGE, sample_count)
json_stream_dump(samples, SAMPLES)
image = visualize_dataset(json_stream_load(SAMPLES))
scipy.misc.imsave(os.path.join(RESULTS, 'samples.png'), image)