def quiet_runs(nPts_list, nDim_list, nClusters_list, nRep_list):
# quiet_runs(nTest_list, nPts_list, nDim_list, nClusters_list [, print_it]):
# when number of tests is -1, it will be calculated based on the size of the problem
print "mpi_kmeans timing runs"
for pts in nPts_list:
for dim in nDim_list:
if dim >= pts:
continue
for clst in nClusters_list:
if clst >= pts:
continue
for rep in nRep_list:
data = N.random.rand(pts, dim)
t1 = time.time()
py_kmeans.kmeans(data, clst, rep, 0)
t2 = time.time()
print "[MPIKMEANS]({0:8},{1:5},{2:5},{3:5})...".format(pts, dim, clst, rep),
print 1000.*(t2-t1)
def run_labels(data, nClusters, nReps, seed=SEED):
random.seed(seed)
# run py_kmeans.kmeans once to get a starting label assignment,
# which will be used by the scipy routine and others
clusters, dist, labels = py_kmeans.kmeans(data, nClusters, 1, 0)
if VERBOSE:
print "data"
print data
print "initial clusters:"
print clusters
(nPts, nDim) = data.shape
nClusters = clusters.shape[0]
print "[nPts:{0:6}][nDim:{1:4}][nClusters:{2:4}][nReps:{3:3}]...".format(nPts, nDim,
nClusters, nReps),
data2 = np.swapaxes(data, 0, 1).astype(np.float32).copy('C')
clusters2 = np.swapaxes(clusters, 0, 1).astype(np.float32).copy('C')
if VERBOSE:
print "data2"
print data2
print "clusters2"
print clusters2
"""
t1 = time.time()
(cuda_clusters, cuda_labels) = cuda_kmeans.kmeans_gpu(data2, clusters2, nReps+1)
if VERBOSE:
print "cuda_kmeans labels:"
print cuda_labels
t2 = time.time()
if PRINT_TIMES:
print "\ncuda ", t2-t1
"""
t1 = time.time()
(tri_clusters, tri_labels) = cuda_kmeans_tri.trikmeans_gpu(data2, clusters2, nReps+1)
if VERBOSE:
print "cuda_kmeans_tri labels:"
print tri_labels
t2 = time.time()
if PRINT_TIMES:
print "tri ", t2-t1
t1 = time.time()
labels_mpi = mpi_labels(data, nClusters, nReps+1, seed)
if VERBOSE:
print "mpi labels:"
print labels_mpi[0]
t2 = time.time()
if PRINT_TIMES:
print "mpi ", t2-t1
if scipyFlag:
t1 = time.time()
labels_scipy = scipy_labels(data, clusters, nReps)
if VERBOSE:
print "scipy labels:"
print labels_scipy[0]
t2 = time.time()
if PRINT_TIMES:
print "scipy", t2-t1
t1 = time.time()
(cpu_clusters, cpu_labels) = cpu_kmeans.kmeans_cpu(data2, clusters2, nReps+1)
if VERBOSE:
print "cpu_kmeans labels:"
print cpu_labels
t2 = time.time()
if PRINT_TIMES:
print "cpu ", t2-t1
error = 0
if scipyFlag:
try:
np.testing.assert_array_equal(labels_mpi[0], labels_scipy[0])
except AssertionError:
print "mpi<>scipy",
error = 1
try:
np.testing.assert_array_equal(labels_mpi[0], cpu_labels)
except AssertionError:
print "mpi<>cpu",
error = 1
"""
try:
np.testing.assert_array_equal(cuda_labels, tri_labels)
except AssertionError:
print "cuda<>tri",
error = 1
"""
try:
np.testing.assert_array_equal(tri_labels, cpu_labels)
except AssertionError:
print "tri<>cpu",
error = 1
try:
np.testing.assert_array_equal(labels_mpi[0], tri_labels)
except AssertionError:
print "tri<>mpi",
error = 1
if error == 0:
print "Labels OK ..."
else:
print ""
def mpi_labels(data, num_clusters, nReps, seed = SEED):
# reset the random seed so the first cluster assignments will be the same
# as calculated at the beginning of run_labels()
random.seed(seed)
clusters, dist, labels = py_kmeans.kmeans(data, num_clusters, nReps, 0)
return labels-1, clusters
def run_labels(data, nClusters, nReps, skip_cpu = SKIP_CPU, seed=SEED):
random.seed(seed)
# run py_kmeans.kmeans once to get a starting label assignment,
# which will be used by the scipy routine and others
clusters, dist, labels = py_kmeans.kmeans(data, nClusters, 1, 0)
if VERBOSE:
print "data"
print data
print "initial clusters:"
print clusters
(nPts, nDim) = data.shape
nClusters = clusters.shape[0]
print "[nPts:{0:6}][nDim:{1:4}][nClusters:{2:4}][nReps:{3:3}]...".format(nPts, nDim,
nClusters, nReps),
data2 = np.swapaxes(data, 0, 1).astype(np.float32).copy('C')
clusters2 = np.swapaxes(clusters, 0, 1).astype(np.float32).copy('C')
if VERBOSE:
print "data2"
print data2
print "clusters2"
print clusters2
"""
t1 = time.time()
(cuda_clusters, cuda_labels) = cuda_kmeans.kmeans_gpu(data2, clusters2, nReps+1)
if VERBOSE:
print "cuda_kmeans labels:"
print cuda_labels
t2 = time.time()
if PRINT_TIMES:
print "\ncuda ", t2-t1
"""
t1 = time.time()
(tri_clusters, tri_labels) = cuda_kmeans_tri.trikmeans_gpu(data2, clusters2, nReps+1)
if VERBOSE:
print "\ncuda_kmeans_tri labels:"
print tri_labels
t2 = time.time()
if PRINT_TIMES:
print "\ntri ", t2-t1
t1 = time.time()
labels_mpi = mpi_labels(data, nClusters, nReps+1, seed)
if VERBOSE:
print "mpi labels:"
print labels_mpi[0]
t2 = time.time()
if PRINT_TIMES:
print "mpi ", t2-t1
if scipyFlag:
t1 = time.time()
labels_scipy = scipy_labels(data, clusters, nReps)
if VERBOSE:
print "scipy labels:"
print labels_scipy[0]
t2 = time.time()
if PRINT_TIMES:
print "scipy", t2-t1
t1 = time.time()
if not skip_cpu:
(cpu_clusters, cpu_labels) = cpu_kmeans.kmeans_cpu(data2, clusters2, nReps+1)
if VERBOSE:
print "cpu_kmeans labels:"
print cpu_labels
t2 = time.time()
if PRINT_TIMES:
print "cpu ", t2-t1
error = 0
if scipyFlag:
try:
np.testing.assert_array_equal(labels_mpi[0], labels_scipy[0])
except AssertionError:
print "mpi<>scipy",
error = 1
if not skip_cpu:
try:
np.testing.assert_array_equal(labels_mpi[0], cpu_labels)
except AssertionError:
print "mpi<>cpu",
error = 1
try:
np.testing.assert_array_equal(tri_labels, cpu_labels)
except AssertionError:
print "tri<>cpu",
error = 1
"""
try:
np.testing.assert_array_equal(cuda_labels, tri_labels)
except AssertionError:
print "cuda<>tri",
error = 1
"""
try:
np.testing.assert_array_equal(labels_mpi[0], tri_labels)
except AssertionError:
print "tri<>mpi",
error = 1
if error == 0:
print "Labels OK ..."
else:
print ""
def mpi_labels(data, num_clusters, nReps, seed = SEED):
# reset the random seed so the first cluster assignments will be the same
# as calculated at the beginning of run_labels()
random.seed(seed)
clusters, dist, labels = py_kmeans.kmeans(data, num_clusters, nReps, 0)
return labels-1, clusters