def tcf_cut(orig_datapoints, boundary_width=0.1, n=2):
"""
input: datapoints, table, type of method
output: two list of data in each cluster
"""
datapoints = deepcopy(orig_datapoints)
datapoints = utl.centralize_data(datapoints)
datapoints = utl.normalize_data(datapoints)
coeff, oa, ob = _tcf(datapoints)
c_left = []
c_right = []
r_bp = []
l_bp = []
r_nbp = []
l_nbp = []
for orig_point, copy_point in zip(orig_datapoints, datapoints):
# calc distance from point to boundary
unit_len = sum(coeff[:-1] ** 2) ** 0.5
p2b_dist = (sum(copy_point * coeff[:-1]) + coeff[-1]) / unit_len
if abs(p2b_dist) <= boundary_width * n:
if p2b_dist >= 0:
r_nbp.append(orig_point)
else:
l_nbp.append(orig_point)
if abs(p2b_dist) <= boundary_width:
if p2b_dist >= 0:
r_bp.append(orig_point)
else:
l_bp.append(orig_point)
if p2b_dist >= 0:
c_right.append(orig_point)
else:
c_left.append(orig_point)
c_left = np.array(c_left, np.float)
c_right = np.array(c_right, np.float)
r_bp = np.array(r_bp, np.float)
l_bp = np.array(l_bp, np.float)
r_nbp = np.array(r_nbp, np.float)
l_nbp = np.array(l_nbp, np.float)
# left, right, in boundary point, coeff
return c_left, c_right, (r_bp, l_bp), (r_nbp, l_nbp), coeff
def tcf_cut(orig_datapoints, boundary_width=0.1, n=2):
"""
input: datapoints, table, type of method
output: two list of data in each cluster
"""
datapoints = deepcopy(orig_datapoints)
datapoints = utl.centralize_data(datapoints)
datapoints = utl.normalize_data(datapoints)
coeff, oa, ob = _tcf(datapoints)
c_left = []
c_right = []
r_bp = []
l_bp = []
r_nbp = []
l_nbp = []
for orig_point, copy_point in zip(orig_datapoints, datapoints):
# calc distance from point to boundary
unit_len = sum(coeff[:-1]**2)**0.5
p2b_dist = (sum(copy_point * coeff[:-1]) + coeff[-1]) / unit_len
if abs(p2b_dist) <= boundary_width * n:
if p2b_dist >= 0:
r_nbp.append(orig_point)
else:
l_nbp.append(orig_point)
if abs(p2b_dist) <= boundary_width:
if p2b_dist >= 0:
r_bp.append(orig_point)
else:
l_bp.append(orig_point)
if p2b_dist >= 0:
c_right.append(orig_point)
else:
c_left.append(orig_point)
c_left = np.array(c_left, np.float)
c_right = np.array(c_right, np.float)
r_bp = np.array(r_bp, np.float)
l_bp = np.array(l_bp, np.float)
r_nbp = np.array(r_nbp, np.float)
l_nbp = np.array(l_nbp, np.float)
# left, right, in boundary point, coeff
return c_left, c_right, (r_bp, l_bp), (r_nbp, l_nbp), coeff
def rwm_cut(orig_datapoints, boundary_width=0.1, n=2):
datapoints = deepcopy(orig_datapoints)
datapoints = utl.centralize_data(datapoints)
datapoints = utl.normalize_data(datapoints)
in_boundary = 0
size, dim = datapoints.shape
c_left = []
c_right = []
coeff = _rwm(datapoints)
r_bp = []
l_bp = []
r_nbp = []
l_nbp = []
for orig_point, copy_point in zip(orig_datapoints, datapoints):
# calc distance from point to boundary
unit_len = sum(coeff[:-1] ** 2) ** 0.5
p2b_dist = (sum(copy_point * coeff[:-1]) + coeff[-1]) / unit_len
if abs(p2b_dist) <= boundary_width * n:
if p2b_dist >= 0:
r_nbp.append(orig_point)
else:
l_nbp.append(orig_point)
if abs(p2b_dist) <= boundary_width:
if p2b_dist >= 0:
r_bp.append(orig_point)
else:
l_bp.append(orig_point)
if p2b_dist >= 0:
c_right.append(orig_point)
else:
c_left.append(orig_point)
c_left = np.array(c_left, np.float)
c_right = np.array(c_right, np.float)
r_bp = np.array(r_bp, np.float)
l_bp = np.array(l_bp, np.float)
r_nbp = np.array(r_nbp, np.float)
l_nbp = np.array(l_nbp, np.float)
# left, right, in boundary point, coeff
return c_left, c_right, (r_bp, l_bp), (r_nbp, l_nbp), coeff
def cut_by_coeff(orig_datapoints, coeff):
datapoints = deepcopy(orig_datapoints)
datapoints = utl.centralize_data(datapoints)
datapoints = utl.normalize_data(datapoints)
c_left = []
c_right = []
unit_len = sum(coeff[:-1] ** 2) ** 0.5
for orig_point, copy_point in zip(orig_datapoints, datapoints):
p2b_dist = (sum(copy_point * coeff[:-1]) + coeff[-1]) / unit_len
if p2b_dist >= 0:
c_right.append(orig_point)
else:
c_left.append(orig_point)
c_left = np.array(c_left, np.float)
c_right = np.array(c_right, np.float)
return (c_left, c_right)
def cut_by_coeff(orig_datapoints, coeff):
datapoints = deepcopy(orig_datapoints)
datapoints = utl.centralize_data(datapoints)
datapoints = utl.normalize_data(datapoints)
c_left = []
c_right = []
unit_len = sum(coeff[:-1]**2)**0.5
for orig_point, copy_point in zip(orig_datapoints, datapoints):
p2b_dist = (sum(copy_point * coeff[:-1]) + coeff[-1]) / unit_len
if p2b_dist >= 0:
c_right.append(orig_point)
else:
c_left.append(orig_point)
c_left = np.array(c_left, np.float)
c_right = np.array(c_right, np.float)
return (c_left, c_right)
for cls in tmp_clusters:
res_cls.append(cls)
print("#cls {} -> {}".format(len(clusters), len(res_cls)))
print(calc_num_point(res_cls))
return res_cls
if __name__ == '__main__':
doctest.testmod()
points, label = utl.read_from_text('2d5c_noncycle')
points = utl.centralize_data(points)
points = utl.normalize_data(points)
# points, label = utl.read_from_text('2d5c_cov')
# points, label = utl.read_from_text('hand_write_digit_2d')
# seleted = datasets.load_digits()
# points = seleted.data
# label = seleted.target
#
ms_tree = ms2c(points)
# paint_tree(ms_tree, ms_tree)
final_nodes = ms_tree.merge()
grounded_nodes = ms_tree.grounded_nodes
grounded_cls = [x.datapoints for x in grounded_nodes]
final_cls = [x.datapoints for x in final_nodes]
