def test_dbscan_spmd(self):
epsilon = 0.04
minObservations = 45
data = np_read_csv(
os.path.join(".", 'data', 'batch', 'dbscan_dense.csv'))
batch_algo = d4p.dbscan(minObservations=minObservations,
epsilon=epsilon,
resultsToCompute='computeCoreIndices')
batch_result = batch_algo.compute(data)
rpp = int(data.shape[0] / d4p.num_procs())
node_stride = rpp * d4p.my_procid()
node_range = range(node_stride, node_stride + rpp)
node_data = data[node_range, :]
spmd_algo = d4p.dbscan(minObservations=minObservations,
epsilon=epsilon,
distributed=True)
spmd_result = spmd_algo.compute(node_data)
# clusters can get different indexes in batch and spmd algos,
# to compare them we should take care about it
cluster_index_dict = {}
for i in node_range:
# border points assignments can be different
# with different amount of nodes but cores are the same
if i in batch_result.coreIndices:
right = spmd_result.assignments[i - node_stride][0]
if not batch_result.assignments[i][0] in cluster_index_dict:
cluster_index_dict[batch_result.assignments[i]
[0]] = right
left = cluster_index_dict[batch_result.assignments[i][0]]
self.assertTrue(left == right)
def verify_on_dbscan(self, X):
alg1 = d4p.dbscan(epsilon=2.0, minObservations=5, fptype='double')
res1 = alg1.compute(X)
Xc = np.ascontiguousarray(X)
alg2 = d4p.dbscan(epsilon=2.0, minObservations=5, fptype='double')
res2 = alg2.compute(Xc)
self.assertTrue(np.array_equal(res1.assignments, res2.assignments))
self.assertTrue(len(np.unique(res1.assignments)) > 2)
def _daal_dbscan(X, eps=0.5, min_samples=5, sample_weight=None):
if eps <= 0.0:
raise ValueError("eps must be positive.")
X = check_array(X, dtype=[np.float64, np.float32])
if sample_weight is not None:
sample_weight = _check_sample_weight(sample_weight, X)
ww = make2d(sample_weight)
else:
ww = None
XX = make2d(X)
fpt = getFPType(XX)
alg = daal4py.dbscan(method='defaultDense',
fptype=fpt,
epsilon=float(eps),
minObservations=int(min_samples),
memorySavingMode=False,
resultsToCompute="computeCoreIndices")
daal_res = alg.compute(XX, ww)
n_clusters = daal_res.nClusters[0, 0]
assignments = daal_res.assignments.ravel()
if daal_res.coreIndices is not None:
core_ind = daal_res.coreIndices.ravel()
else:
core_ind = np.array([], dtype=np.intc)
return (core_ind, assignments)
def main(readcsv=read_csv, method='defaultDense'):
infile = "./data/batch/dbscan_dense.csv"
epsilon = 0.02
minObservations = 180
# Load the data
data = readcsv(infile, range(2))
# configure dbscan main object: we also request the indices and observations of cluster cores
algo = d4p.dbscan(
minObservations=minObservations,
epsilon=epsilon,
resultsToCompute='computeCoreIndices|computeCoreObservations')
# and compute
result = algo.compute(data)
# Note: we could have done this in just one line:
# assignments = d4p.dbscan(minObservations=minObservations, epsilon=epsilon, resultsToCompute='computeCoreIndices|computeCoreObservations').compute(data).assignments
# DBSCAN result objects provide assignments, nClusters and coreIndices/coreObservations (if requested)
assert result.assignments.shape == (data.shape[0], 1)
assert result.coreObservations.shape == (result.coreIndices.shape[0],
data.shape[1])
return result
def compute(data, minObservations, epsilon):
# configure dbscan main object: we also request the indices and observations of cluster cores
algo = d4p.dbscan(minObservations=minObservations,
epsilon=epsilon,
resultsToCompute='computeCoreIndices|computeCoreObservations',
memorySavingMode=True)
# and compute
return algo.compute(data)
def main(method='defaultDense'):
infile = "./data/batch/dbscan_dense.csv"
epsilon = 0.04
minObservations = 45
# Load the data
data = np.loadtxt(infile, delimiter=',')
rpp = int(data.shape[0] / d4p.num_procs())
data = data[rpp * d4p.my_procid(): rpp * d4p.my_procid() + rpp, :]
# configure dbscan main object
algo = d4p.dbscan(minObservations=minObservations, epsilon=epsilon, distributed=True)
# and compute
result = algo.compute(data)
return result
def _daal_dbscan(X, eps=0.5, min_samples=5, sample_weight=None):
ww = make2d(sample_weight) if sample_weight is not None else None
XX = make2d(X)
fpt = getFPType(XX)
alg = daal4py.dbscan(method='defaultDense',
fptype=fpt,
epsilon=float(eps),
minObservations=int(min_samples),
memorySavingMode=False,
resultsToCompute="computeCoreIndices")
daal_res = alg.compute(XX, ww)
assignments = daal_res.assignments.ravel()
if daal_res.coreIndices is not None:
core_ind = daal_res.coreIndices.ravel()
else:
core_ind = np.array([], dtype=np.intc)
return (core_ind, assignments)
def test_dbscan(X):
algorithm = dbscan(fptype=getFPType(X),
epsilon=params.eps,
minObservations=params.min_samples,
resultsToCompute='computeCoreIndices')
return algorithm.compute(X)
