def setUp(self):
self.distance, self.label, self.vector = load_dexter()
self.n = self.distance.shape[0]
def setUp(self):
self.distance, self.target, self.vectors = load_dexter()
self.d_self = -np.inf
self.sort_order = -1 # descending, interested in highest similarity
else:
self.d_self = np.inf
self.sort_order = 1 # ascending, interested in smallest distance
np.random.seed()
def calculate_hubness(self, debug=False, n_jobs=-1):
"""Calculate hubness.
.. note:: Deprecated in hub-toolbox 2.3
Class will be removed in hub-toolbox 3.0.
Please use static functions instead.
"""
print("DEPRECATED: Please use Hubness_parallel.hubness().",
file=sys.stderr)
if self.sort_order == 1:
metric = 'distance'
elif self.sort_order == -1:
metric = 'similarity'
else:
raise ValueError("sort_order must be -1 or 1.")
return hubness(self.D, self.k, metric, debug, n_jobs)
if __name__ == '__main__':
"""Simple test case"""
from hub_toolbox.HubnessAnalysis import load_dexter
D, l, v = load_dexter()
Sn, Dk, Nk = hubness(D)
print("Hubness =", Sn)
from scipy.sparse import rand, triu
from hub_toolbox.Hubness import hubness
from hub_toolbox.HubnessAnalysis import load_dexter
from hub_toolbox.KnnClassification import score
#do = 'random'
do = 'dexter'
if do == 'random':
print("RANDOM DATA:")
print("------------")
S = triu(rand(1000, 1000, 0.05, 'csr', np.float32, 43), 1)
S += S.T
D = 1. - S.toarray()
elif do == 'dexter':
print("DEXTER:")
print("-------")
D, c, v = load_dexter()
acc_d, _, _ = score(D, c, [5], 'distance')
S = csr_matrix(1 - D)
acc_s, _, _ = score(S, c, [5], 'similarity')
Sn_d, _, _ = hubness(D, 5, 'distance')
Sn_s, _, _ = hubness(S, 5, 'similarity')
print("Orig. dist. hubness:", Sn_d)
print("Orig. sim. hubness:", Sn_s)
if do == 'dexter':
print("Orig. dist. k-NN accuracy:", acc_d)
print('Orig. sim. k-NN accuracy:', acc_s)
D_mp_emp_d = mutual_proximity_empiric(D)
D_mp_emp_s = mutual_proximity_empiric(S, 'similarity')
Sn_mp_emp_d, _, _ = hubness(D_mp_emp_d, 5)
if isSimilarityMatrix:
self.d_self = -np.inf
self.sort_order = -1 # descending, interested in highest similarity
else:
self.d_self = np.inf
self.sort_order = 1 # ascending, interested in smallest distance
np.random.seed()
def calculate_hubness(self, debug=False):
"""Calculate hubness.
.. note:: Deprecated in hub-toolbox 2.3
Class will be removed in hub-toolbox 3.0.
Please use static functions instead.
"""
print("DEPRECATED: Please use Hubness.hubness().", file=sys.stderr)
if self.sort_order == 1:
metric = 'distance'
elif self.sort_order == -1:
metric = 'similarity'
else:
raise ValueError("sort_order must be -1 or 1.")
return hubness(self.D, self.k, metric, debug)
if __name__ == '__main__':
# Simple test case
from hub_toolbox.HubnessAnalysis import load_dexter
dexter_distance, l, v = load_dexter()
Sn, Dk, Nk = hubness(dexter_distance)
print("Hubness =", Sn)
def setUp(self):
self.distance, self.label, self.vector = load_dexter()
