def test_sanity(self):
v1 = compute_dtw_vector(self.ink1,
self.ink3,
alpha=0.5,
penup_z=10)
self.assertEqual(v1.shape, (140,))
v2 = compute_dtw_vector(self.ink2,
self.ink3,
alpha=0.5,
penup_z=10)
self.assertEqual(v2.shape, (150,))
def _find_centroid(obs, obs_weights, medoid_idx, distmat):
n_features = obs[0].shape[1]
medoid = obs[medoid_idx]
# Ignore outliers by setting their weights to 0
if ignore_outliers:
dist_mean = distmat[medoid_idx, :].mean()
dist_std = distmat[medoid_idx, :].std()
# only remove outliers when std is not too small
if dist_std > 1e-3:
for i in xrange(len(obs)):
if (distmat[medoid_idx, i] - dist_mean) / dist_std > 3.0:
obs_weights[i] = 0.0
# Ignore examples that doesn't have the same number of strokes
medoid_n_strokes = medoid[:, _PU_IDX].sum()
for i, o in enumerate(obs):
if o[:, _PU_IDX].sum() != medoid_n_strokes:
obs_weights[i] = 0.0
f = [compute_dtw_vector(medoid, ink) for ink in obs]
feature_mat = np.vstack(f)
feature_mat = np.nan_to_num(feature_mat)
weighted_feature_mat = feature_mat * np.tile(obs_weights, (feature_mat.shape[1], 1)).T
# reconstruct weighted-average ink
mean_ink = weighted_feature_mat.sum(axis=0) / obs_weights.sum()
mean_ink = mean_ink.reshape((-1, n_features), order="C")
mean_ink = mean_ink + medoid
# make sure pen-up is binary
mean_ink[:, _PU_IDX] = mean_ink[:, _PU_IDX].round()
# number of penups is off, fallback to medoid
if mean_ink[:, _PU_IDX].sum() != medoid_n_strokes:
return medoid
# It seems like not updating the direction yeilds
# a better result.
# return update_directions(mean_ink)
return mean_ink