def print_evaluation(X, distance, Y, subsample_size=500):
idx = np.random.permutation(len(X))[:subsample_size]
D_sub = distance(X[idx], X[idx])
DY_sub = distance_matrix(Y[idx], Y[idx])
print(" Stress = %s" % stress(D_sub.flatten(), DY_sub.flatten()))
print(" Correlation = %s" % correlation(D_sub.flatten(), DY_sub.flatten()))
print(" Distortion = %s" % distortion(D_sub.flatten(), DY_sub.flatten()))
def lipschitz_eval(s, original_dist_matrixes, idxs, exec_number, track):
"""
function evaluates stress, correlation distance, distortion and embedding computation time
given array of lipschitz embedding of streamlines s
:param s: input data
:param original_dist_matrixes: array of matrixes of stress_samples dimensions
:param idx: array of indexes of data used for calculation of original_dist_matrixes
:param eval_seeds: list of seeds used for data sampling
:return:
"""
from lipschitz import compute_lipschitz
results_dir = "../eval_results/lipschitz/"
if not os.path.exists(results_dir):
os.makedirs(results_dir)
distance = partial(parallel_distance_computation,
distance=bundles_distances_mam)
k = [2, 4, 8, 10, 12, 20, 30, 40]
for n in k:
resFileName = "n_reference_objects_{0}__exec_num_{1}__n_streamlines_{2}__track_{3}".format(
n, exec_number, len(idxs[0]), track)
if os.path.isfile(results_dir + resFileName):
continue
start_time = time.time()
embeddings, _ = compute_lipschitz(s, distance, linial1994=False, k=n)
comp_time = time.time() - start_time
for (idx, original_dist) in zip(idxs, original_dist_matrixes):
embedded_dist = pdist(embeddings[idx], 'euclidean')
emb_stress_norm = stress_normalized(dist_embedd=embedded_dist,
dist_original=original_dist)
emb_stress = stress(dist_embedd=embedded_dist,
dist_original=original_dist)
emb_correlation = correlation(embedded_dist.flatten(),
original_dist.flatten())
emb_distortion = distortion(dist_embedd=embedded_dist,
dist_original=original_dist)
emb_rel_dist = relative_distance_error(dist_embedd=embedded_dist,
dist_original=original_dist)
with open(results_dir + resFileName, 'w') as f:
f.write('rel_dist\t' + str(emb_rel_dist) + '\n')
f.write('stress\t' + str(emb_stress) + '\n')
f.write('stress_norm\t' + str(emb_stress_norm) + '\n')
f.write('correlation\t' + str(emb_correlation) + '\n')
f.write('distortion\t' + str(emb_distortion) + '\n')
f.write('n_streamlines\t' + str(len(s)) + '\n')
f.write('eval_streamlines\t' + str(len(idx)) + '\n')
f.write('exec_time\t' + str(comp_time) + '\n')
f.write('n_reference_objects\t' + str(n) + '\n')
def resampling_eval(s, original_dist_matrixes, idxs, exec_number, track):
"""
function evaluates stress, correlation distance, distortion and embedding computation time
given array of resampling embedding of streamlines s
:param s: input data
:param original_dist_matrixes: array of matrixes of stress_samples dimensions
:param idx: array of indexes of data used for calculation of original_dist_matrixes
:return:
"""
results_dir = "../eval_results/resampling/"
if not os.path.exists(results_dir):
os.makedirs(results_dir)
sampling_n = [2, 4, 8, 10, 12, 20, 30, 40]
for n in sampling_n:
resFileName = "resampling_pts_{0}__exec_num_{1}__eval_streamlines_{2}__emb_streamlines{3}__track_{4}".format(
n, exec_number, len(idxs[0]), len(s), track)
if os.path.isfile(results_dir + resFileName):
continue
start_time = time.time()
embeddings = set_number_of_points(s, nb_points=n)
comp_time = time.time() - start_time
for (idx, original_dist) in zip(idxs, original_dist_matrixes):
embedded_dist = pdist(
(np.asarray(embeddings[idx], dtype=object).reshape(
len(idx), -1)), 'euclidean')
emb_stress = stress(dist_embedd=embedded_dist,
dist_original=original_dist)
emb_stress_norm = stress_normalized(dist_embedd=embedded_dist,
dist_original=original_dist)
emb_correlation = correlation(embedded_dist.flatten(),
original_dist.flatten())
emb_distortion = distortion(dist_embedd=embedded_dist,
dist_original=original_dist)
emb_rel_dist = relative_distance_error(dist_embedd=embedded_dist,
dist_original=original_dist)
#write results to file
with open(results_dir + resFileName, 'w') as f:
f.write('stress\t' + str(emb_stress) + '\n')
f.write('stress_norm\t' + str(emb_stress_norm) + '\n')
f.write('correlation\t' + str(emb_correlation) + '\n')
f.write('distortion\t' + str(emb_distortion) + '\n')
f.write('n_streamlines\t' + str(len(s)) + '\n')
f.write('eval_streamlines\t' + str(len(idx)) + '\n')
f.write('exec_time\t' + str(comp_time) + '\n')
f.write('resampling_points\t' + str(n) + '\n')