def test_best_fit_line_multiple_coresets(self):
# generate points
N = 1200
# for example1 choose N that divides by 6
data = example1(N)
P = np.c_[np.mgrid[1:N + 1], data]
P1 = P[:1000]
P2 = P[1000:]
C = Coreset.OneSegmentCorset(P)
C1 = Coreset.OneSegmentCorset(P1)
C2 = Coreset.OneSegmentCorset(P2)
best_fit_line_P = utils.calc_best_fit_line(P)
best_fit_line_C = utils.calc_best_fit_line(C.repPoints)
best_fit_line_P1 = utils.calc_best_fit_line(P1)
best_fit_line_C1 = utils.calc_best_fit_line(C1.repPoints)
original_cost_not_best_fit_line = utils.sqrd_dist_sum(P, best_fit_line_P)
single_coreset_cost = utils.sqrd_dist_sum(C.repPoints, best_fit_line_P) * C.weight
C1_cost = int(utils.sqrd_dist_sum(C1.repPoints, best_fit_line_P) * C1.weight)
P1_cost = int(utils.sqrd_dist_sum(P1, utils.calc_best_fit_line(P1)))
C2_cost = int(utils.sqrd_dist_sum(C2.repPoints, best_fit_line_P) * C2.weight)
dual_coreset_cost = C1_cost + C2_cost
self.assertEqual(int(original_cost_not_best_fit_line), int(single_coreset_cost))
self.assertEqual(C1_cost, P1_cost)
self.assertEqual(int(original_cost_not_best_fit_line), int(dual_coreset_cost))
res2 = utils.calc_best_fit_line_coreset(C1, C2)
self.assertEqual(best_fit_line_P, res2)
def calc_prep_dist(P):
prep_dist = np.full((len(P), len(P)), float("inf"))
for index, value in np.ndenumerate(prep_dist):
if index[0] < index[1]:
segment = P[index[0] : index[1] + 1, :]
best_fit_line = utils.calc_best_fit_line_polyfit(segment)
prep_dist[index] = utils.sqrd_dist_sum(segment, best_fit_line)
return prep_dist
def test_OneSegmentCoreset_Cost(self):
# generate points
n = 1200
data = example1(n)
P = np.c_[np.mgrid[1:n + 1], data]
P1 = P[:1000]
C1 = Coreset.OneSegmentCorset(P1)
best_fit_line_P = utils.calc_best_fit_line(P)
best_fit_line_P1 = utils.calc_best_fit_line(P1)
best_fit_line_C1 = utils.calc_best_fit_line(C1.repPoints)
self.assertEqual(best_fit_line_P1.all(), best_fit_line_C1.all())
original_cost_not_best_fit_line = utils.sqrd_dist_sum(P1, best_fit_line_P)
original_cost_best_fit_line = utils.sqrd_dist_sum(P1, best_fit_line_P1)
single_coreset_cost_not_best_fit_line = utils.sqrd_dist_sum(C1.repPoints, best_fit_line_P) * C1.weight
single_coreset_cost_best_fit_line = utils.sqrd_dist_sum(C1.repPoints, best_fit_line_C1) * C1.weight
self.assertEqual(int(original_cost_best_fit_line), int(single_coreset_cost_best_fit_line))
self.assertEqual(int(original_cost_not_best_fit_line), int(single_coreset_cost_not_best_fit_line))
def calc_coreset_prep_dist(D):
prep_dist = np.full((len(D), len(D)), float("inf"))
for (first_coreset, second_coreset), value in np.ndenumerate(prep_dist):
# we only want to calculate for segments that start in
# starting coreset endpoints and end in ending coreset endpoints
if first_coreset <= second_coreset:
C = []
for coreset in D[first_coreset:second_coreset+1]:
C.append(coreset)
coreset_of_coresets = Coreset.OneSegmentCorset(C, True)
best_fit_line = utils.calc_best_fit_line_polyfit(coreset_of_coresets.repPoints, True)
fitting_cost = utils.sqrd_dist_sum(coreset_of_coresets.repPoints, best_fit_line)*coreset_of_coresets.weight
prep_dist[first_coreset, second_coreset] = fitting_cost
return prep_dist
def calc_coreset_prep_dist(D):
prep_dist = np.full((len(D), len(D)), float("inf"))
for (first_coreset, second_coreset), value in np.ndenumerate(prep_dist):
# we only want to calculate for segments that start in
# starting coreset endpoints and end in ending coreset endpoints
if first_coreset <= second_coreset:
C = []
W = []
for coreset in D[first_coreset:second_coreset+1]:
# segment = np.vstack([segment, coreset.C.repPoints]) if segment.size else coreset.C.repPoints
C.append(coreset)
W.append(coreset.C.weight)
coreset_of_coresets = Coreset.OneSegmentCorset(C, True)
best_fit_line = utils.calc_best_fit_line_polyfit(coreset_of_coresets.repPoints, True)
# best_fit_line = utils.calc_best_fit_line(segment)
# fitting_cost = 0
# for i in xrange(len(C)):
# fitting_cost += utils.sqrd_dist_sum(C[i], best_fit_line)*W[i]
fitting_cost = utils.sqrd_dist_sum(coreset_of_coresets.repPoints, best_fit_line)*coreset_of_coresets.weight
prep_dist[first_coreset, second_coreset] = fitting_cost
return prep_dist
