def seed(self):
k = self.k - 1
centers = []
prob = self.w / np.sum(self.w)
center = utils.sample(self.p, 1, prob)
centers.append(center[0])
min_dist = None
while k > 0:
np_centers = np.array(centers)
if min_dist is None:
d = utils.get_sq_distances(x=self.p, y=np_centers).ravel()
min_dist = d
else:
d = utils.get_sq_distances(x=self.p, y=np.array([np_centers[-1]])).ravel()
min_dist = np.minimum(min_dist, d)
dist = np.array(min_dist)
dist *= self.w
prob = dist / np.sum(dist)
center = utils.sample(self.p, 1, prob)
centers.append(center[0])
k -= 1
return np.array(centers, dtype=np.float64)
def points_cost(self, points, centers):
"""
this function will return the minimal distance of each point from its closest center
:param points: a list of points with dimension d
:param centers: a list of centers from which we'll take the miniaml distance
:return: the minimal distance of each point from its closest center
"""
minDist = float("inf")
for center in centers:
center = [np.array(center)]
tmpDistances = utils.get_sq_distances(x=points, y=center)
minDist = np.minimum(minDist, np.amin(tmpDistances))
return minDist
def compute(self, size, grnds=10, ginit=1):
q = w_KMeans.KMeans(self.p, np.expand_dims(self.w , axis=0), self.k, grnds, ginit).compute() # this is my kmeans for the coreset.
sq_d = utils.get_sq_distances(self.p, q) # Squared distances from each point to each center
dist = utils.get_dist_to_centers(d=sq_d) # I get the sq dist from each point its center.
dist /= np.sum(dist) # Norm
dist *= 2 # according to the paper
c = utils.get_centers(d=sq_d) # I get the index of the center
c = self._find_cluster_size(c) # Find the size of the cluster for each point.
s = dist + 4.0/c # I add it, the 4 is according to the paper.
t = np.sum(s*self.w) # This is the t from the paper.
u = t/(s*size) # the new weights for coreset.
prob = s*self.w/t # the probability for sampling
p, w = utils.sample(self.p, size, prob=prob, weights=u) # sample coreset: points + weights.
return p, w
def sample_independently_bahman(self, points, centers, overSamplingFactor):
"""
will return a set of center candidates using formulat described in calling function
:param points:
:param centers:
:param overSamplingFactor: how many new centers will we sample
:return: center candidates
"""
C_prime = []
sq_min_dist_array = utils.get_sq_distances(x=points, y=centers).ravel()
phy_x_c = sum(sq_min_dist_array)
if phy_x_c is 0:
phy_x_c = 0.0000001 #used to handle a singular case where all points are the same point
for i in range(0, len(points) - 1):
tmp = sq_min_dist_array[i]
p_x = overSamplingFactor*sq_min_dist_array[i]/phy_x_c
rand_x=random()
if rand_x <= p_x:
C_prime.append(points[i])
return list(set(C_prime)) #set removes duplicates
