def _daal_dbscan(X, eps=0.5, min_samples=5, sample_weight=None):
if not 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 = np.asarray(sample_weight)
check_consistent_length(X, sample_weight)
ww = make2d(sample_weight)
else:
ww = None
XX = make2d(X)
fpt = getFPType(XX)
alg = daal4py.dbscan(method='defaultDense',
epsilon=float(eps),
minObservations=int(min_samples),
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 __init__(self, X, y, beta, hess=False, fit_intercept=True):
self.compute_hess = hess
self.n = X.shape[0]
self.fptype = getFPType(X)
self.fit_intercept = fit_intercept
self.X = make2d(X)
self.y = make2d(y)
def __init__(self, X, y, beta, hess=False, fit_intercept=True):
self.compute_hess = hess
self.n = X.shape[0]
self.fptype = getFPType(X)
self.fit_intercept = fit_intercept
self.X = make2d(X)
self.y = make2d(y)
self.last_beta = beta.copy()
self.func = None
self.grad = None
self.hess = None
def compute(self, beta):
# Don't compute if we have already cached func, grad, hess
if self.func is not None and np.array_equal(beta, self.last_beta):
return
result = self.algo.compute(self.X, self.y, make2d(beta))
np.copyto(self.last_beta, beta)
self.func = result.valueIdx[0, 0] * self.n
self.grad = result.gradientIdx.ravel() * self.n
if self.compute_hess:
self.hess = result.hessianIdx * self.n
def compute(self, beta):
result = self.algo.compute(self.X, self.y, make2d(beta))
self.func = result.valueIdx[0, 0] * self.n
self.grad = result.gradientIdx.ravel() * self.n
if self.compute_hess:
self.hess = result.hessianIdx * self.n