def dbscan_tests(features, ftype='mean', eps=0.7, min_samples=2):
if ftype == 'min':
D = facedist.min_dist(features)
elif ftype == 'max':
D = facedist.max_dist(features)
elif ftype == 'meanmin':
D = facedist.meanmin_dist(features)
else:
D = facedist.mean_dist(features)
print D.shape
nrow = len(features)
dense_distances = np.zeros((nrow, nrow), dtype=np.double)
for ii in range(nrow):
for jj in range(ii + 1, nrow):
nn = ii + jj * (jj - 1) / 2
rd = D[nn]
dense_distances[ii, jj] = rd
dense_distances[jj, ii] = rd
del D
db = DBSCAN(eps=eps, min_samples=min_samples,
metric='precomputed').fit(dense_distances)
labels = db.labels_
unique, counts = np.unique(labels, return_counts=True)
return np.asarray((unique, counts)).T, labels, None
def hdbscan_tests(features, ftype='mean', min_cluster_size=2):
if ftype == 'min':
D = facedist.min_dist(features)
elif ftype == 'max':
D = facedist.max_dist(features)
elif ftype == 'meanmin':
D = facedist.meanmin_dist(features)
else:
D = facedist.mean_dist(features)
print D.shape
nrow = len(features)
dense_distances = np.zeros((nrow, nrow), dtype=np.double)
for ii in range(nrow):
for jj in range(ii + 1, nrow):
nn = ii + jj * (jj - 1) / 2
rd = D[nn]
dense_distances[ii, jj] = rd
dense_distances[jj, ii] = rd
del D
db = hdbscan.HDBSCAN(min_cluster_size=min_cluster_size,
metric='precomputed').fit(dense_distances)
labels = db.labels_
probabilities = db.probabilities_
pers = db.cluster_persistence_
unique, counts = np.unique(labels, return_counts=True)
return np.asarray((unique, counts)).T, labels, probabilities, pers
def dbscan_tests(features, ftype='mean', eps=0.7, min_samples=2):
if ftype=='min':
D = facedist.min_dist(features)
elif ftype=='max':
D = facedist.max_dist(features)
elif ftype=='meanmin':
D = facedist.meanmin_dist(features)
else:
D = facedist.mean_dist(features)
#print D.shape
db = DBSCAN(eps=eps, min_samples=min_samples, metric='precomputed').fit(D)
labels = db.labels_
unique, counts = np.unique(labels, return_counts=True)
return np.asarray((unique, counts)).T, labels, None
def agglo_tests(features, ftype='mean', num_cluster=8, metric='precomputed'):
if ftype=='min':
D = facedist.min_dist(features)
elif ftype=='max':
D = facedist.max_dist(features)
elif ftype=='meanmin':
D = facedist.meanmin_dist(features)
else:
D = facedist.mean_dist(features)
#print D.shape
Hclustering = AgglomerativeClustering(n_clusters=num_cluster, affinity=metric, linkage='average')
Hclustering.fit(D)
labels = Hclustering.labels_
unique, counts = np.unique(labels, return_counts=True)
return np.asarray((unique, counts)).T, labels, None
def hdbscan_tests(features, ftype='mean', min_cluster_size=2):
if ftype=='min':
D = facedist.min_dist(features)
elif ftype=='max':
D = facedist.max_dist(features)
elif ftype=='meanmin':
D = facedist.meanmin_dist(features)
else:
D = facedist.mean_dist(features)
#print D.shape
db = hdbscan.HDBSCAN(min_cluster_size=min_cluster_size, metric='precomputed').fit(D)
labels = db.labels_
probabilities = db.probabilities_
pers = db.cluster_persistence_
unique, counts = np.unique(labels, return_counts=True)
return np.asarray((unique, counts)).T, labels, probabilities, pers