def kmeans(v,
k,
distance_type=2,
nt=1,
niter=30,
seed=0,
redo=1,
verbose=True,
normalize=False,
init='random',
output='centroids'):
_check_row_float32(v)
n, d = v.shape
centroids = numpy.zeros((k, d), dtype=numpy.float32)
dis = numpy.empty(n, dtype=numpy.float32)
assign = numpy.empty(n, dtype=numpy.int32)
nassign = numpy.empty(k, dtype=numpy.int32)
flags = nt
if not verbose:
flags |= yael.KMEANS_QUIET
if distance_type == 2:
pass # default
elif distance_type == 1:
flags |= yael.KMEANS_L1
elif distance_type == 3:
flags |= yael.KMEANS_CHI2
if init == 'random':
flags |= yael.KMEANS_INIT_RANDOM # also default
elif init == 'kmeans++':
flags |= yael.KMEANS_INIT_BERKELEY
if normalize:
flags |= yael.KMEANS_NORMALIZE_CENTS
qerr = yael.kmeans(d, n, k, niter, yael.numpy_to_fvec_ref(v), flags, seed,
redo, yael.numpy_to_fvec_ref(centroids),
yael.numpy_to_fvec_ref(dis),
yael.numpy_to_ivec_ref(assign),
yael.numpy_to_ivec_ref(nassign))
if qerr < 0:
raise RuntimeError(
"kmeans: clustering failed. Is dataset diverse enough?")
if output == 'centroids':
return centroids
else:
return (centroids, qerr, dis, assign, nassign)
def kmeans(v, k,
distance_type=2,
nt=1,
niter=30,
seed=0,
redo=1,
verbose=True,
normalize=False,
init='random',
output='centroids'):
_check_row_float32(v)
n, d = v.shape
centroids = numpy.zeros((k, d), dtype=numpy.float32)
dis = numpy.empty(n, dtype=numpy.float32)
assign = numpy.empty(n, dtype=numpy.int32)
nassign = numpy.empty(k, dtype=numpy.int32)
flags = nt
if not verbose:
flags |= yael.KMEANS_QUIET
if distance_type == 2:
pass # default
elif distance_type == 1:
flags |= yael.KMEANS_L1
elif distance_type == 3:
flags |= yael.KMEANS_CHI2
if init == 'random':
flags |= yael.KMEANS_INIT_RANDOM # also default
elif init == 'kmeans++':
flags |= yael.KMEANS_INIT_BERKELEY
if normalize:
flags |= yael.KMEANS_NORMALIZE_CENTS
qerr = yael.kmeans(d, n, k, niter,
yael.numpy_to_fvec_ref(v), flags, seed, redo,
yael.numpy_to_fvec_ref(centroids),
yael.numpy_to_fvec_ref(dis),
yael.numpy_to_ivec_ref(assign),
yael.numpy_to_ivec_ref(nassign))
if qerr < 0:
raise RuntimeError(
"kmeans: clustering failed. Is dataset diverse enough?")
if output == 'centroids':
return centroids
else:
return (centroids, qerr, dis, assign, nassign)