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)
def extract_rows_cols(K, subset_rows, subset_cols):
" returns K[numpy.ix_(subset_rows, subset_cols)] (also slow in pure numpy)"
_check_row_float32(K)
_check_row_int32(subset_rows)
_check_row_int32(subset_cols)
nr = subset_rows.size
nc = subset_cols.size
assert subset_rows.min() >= 0 and subset_rows.max() < K.shape[0]
assert subset_cols.min() >= 0 and subset_cols.max() < K.shape[1]
Ksub = numpy.empty((nr, nc), dtype=numpy.float32)
yael.fmat_get_rows_cols(yael.numpy_to_fvec_ref(K), K.shape[0], nc,
yael.numpy_to_ivec_ref(subset_cols), nr,
yael.numpy_to_ivec_ref(subset_rows),
yael.numpy_to_fvec_ref(Ksub))
return Ksub
def extract_rows_cols(K, subset_rows, subset_cols):
" returns K[numpy.ix_(subset_rows, subset_cols)] (also slow in pure numpy)"
_check_row_float32(K)
_check_row_int32(subset_rows)
_check_row_int32(subset_cols)
nr = subset_rows.size
nc = subset_cols.size
assert subset_rows.min() >= 0 and subset_rows.max() < K.shape[0]
assert subset_cols.min() >= 0 and subset_cols.max() < K.shape[1]
Ksub = numpy.empty((nr, nc), dtype = numpy.float32)
yael.fmat_get_rows_cols(yael.numpy_to_fvec_ref(K),
K.shape[0],
nc, yael.numpy_to_ivec_ref(subset_cols),
nr, yael.numpy_to_ivec_ref(subset_rows),
yael.numpy_to_fvec_ref(Ksub))
return Ksub
def extract_lines(a, indices):
" returns a[indices, :] from a matrix a (this operation is slow in numpy) "
_check_row_float32(a)
_check_row_int32(indices)
n, d = a.shape
assert indices.size == 0 or indices.min() >= 0 and indices.max() < n
out = numpy.empty((indices.size, d), dtype=numpy.float32)
yael.fmat_get_columns(yael.numpy_to_fvec_ref(a), d, indices.size,
yael.numpy_to_ivec_ref(indices),
yael.numpy_to_fvec_ref(out))
return out
def extract_lines(a, indices):
" returns a[indices, :] from a matrix a (this operation is slow in numpy) "
_check_row_float32(a)
_check_row_int32(indices)
n, d = a.shape
assert indices.size == 0 or indices.min() >= 0 and indices.max() < n
out = numpy.empty((indices.size, d), dtype=numpy.float32)
yael.fmat_get_columns(
yael.numpy_to_fvec_ref(a), d, indices.size, yael.numpy_to_ivec_ref(indices), yael.numpy_to_fvec_ref(out)
)
return out
def knn(queries, base, nnn=1, distance_type=2, nt=1):
_check_row_float32(base)
_check_row_float32(queries)
n, d = base.shape
nq, d2 = queries.shape
assert d == d2, "base and queries must have same nb of rows (got %d != %d) " % (
d, d2)
idx = numpy.empty((nq, nnn), dtype=numpy.int32)
dis = numpy.empty((nq, nnn), dtype=numpy.float32)
yael.knn_full_thread(distance_type, nq, n, d, nnn,
yael.numpy_to_fvec_ref(base),
yael.numpy_to_fvec_ref(queries), None,
yael.numpy_to_ivec_ref(idx),
yael.numpy_to_fvec_ref(dis), nt)
return idx, dis
def knn(queries, base,
nnn = 1,
distance_type = 2,
nt = 1):
_check_row_float32(base)
_check_row_float32(queries)
n, d = base.shape
nq, d2 = queries.shape
assert d == d2, "base and queries must have same nb of rows (got %d != %d) " % (d, d2)
idx = numpy.empty((nq, nnn), dtype = numpy.int32)
dis = numpy.empty((nq, nnn), dtype = numpy.float32)
yael.knn_full_thread(distance_type,
nq, n, d, nnn,
yael.numpy_to_fvec_ref(base),
yael.numpy_to_fvec_ref(queries),
None,
yael.numpy_to_ivec_ref(idx),
yael.numpy_to_fvec_ref(dis),
nt)
return idx, dis
