def test_iris(self):
num_constraints = 200
C = LSML.prepare_constraints(self.iris_labels, num_constraints)
lsml = LSML().fit(self.iris_points, C, verbose=False)
csep = class_separation(lsml.transform(), self.iris_labels)
self.assertLess(csep, 0.8) # it's pretty terrible
def test_iris(self):
num_constraints = 200
C = LSML.prepare_constraints(self.iris_labels, num_constraints)
lsml = LSML().fit(self.iris_points, C, verbose=False)
csep = class_separation(lsml.transform(), self.iris_labels)
self.assertLess(csep, 0.8) # it's pretty terrible
def sandwich_demo():
x, y = sandwich_data()
knn = nearest_neighbors(x, k=2)
ax = pyplot.subplot(3, 1, 1) # take the whole top row
plot_sandwich_data(x, y, ax)
plot_neighborhood_graph(x, knn, y, ax)
ax.set_title('input space')
ax.set_aspect('equal')
ax.set_xticks([])
ax.set_yticks([])
num_constraints = 60
mls = [
(LMNN(), (x, y)),
(ITML(), (x, ITML.prepare_constraints(y, len(x), num_constraints))),
(SDML(), (x, SDML.prepare_constraints(y, len(x), num_constraints))),
(LSML(), (x, LSML.prepare_constraints(y, num_constraints)))
]
for ax_num, (ml,args) in zip(xrange(3,7), mls):
ml.fit(*args)
tx = ml.transform()
ml_knn = nearest_neighbors(tx, k=2)
ax = pyplot.subplot(3,2,ax_num)
plot_sandwich_data(tx, y, ax)
plot_neighborhood_graph(tx, ml_knn, y, ax)
ax.set_title('%s space' % ml.__class__.__name__)
ax.set_xticks([])
ax.set_yticks([])
pyplot.show()
def build_quadruplets(with_preprocessor=False):
# builds a toy quadruplets problem
X, indices = build_data()
c = np.column_stack(indices)
target = np.ones(c.shape[0]) # quadruplets targets are not used
# anyways
c, target = shuffle(c, target, random_state=SEED)
if with_preprocessor:
# if preprocessor, we build a 2D array of quadruplets of indices
return Dataset(c, target, X, c[:, 0])
else:
# if not, we build a 3D array of quadruplets of samples
return Dataset(X[c], target, None, X[c[:, 0]])
quadruplets_learners = [(LSML(), build_quadruplets)]
ids_quadruplets_learners = list(
map(lambda x: x.__class__.__name__,
[learner for (learner, _) in quadruplets_learners]))
pairs_learners = [
(ITML(), build_pairs),
(MMC(max_iter=2), build_pairs), # max_iter=2 for faster
(SDML(), build_pairs),
]
ids_pairs_learners = list(
map(lambda x: x.__class__.__name__,
[learner for (learner, _) in pairs_learners]))
classifiers = [(Covariance(), build_classification),
(LFDA(), build_classification), (LMNN(), build_classification),
def build_quadruplets(with_preprocessor=False):
# builds a toy quadruplets problem
X, indices = build_data()
c = np.column_stack(indices)
target = np.ones(c.shape[0]) # quadruplets targets are not used
# anyways
c, target = shuffle(c, target, random_state=SEED)
if with_preprocessor:
# if preprocessor, we build a 2D array of quadruplets of indices
return Dataset(c, target, X, c[:, 0])
else:
# if not, we build a 3D array of quadruplets of samples
return Dataset(X[c], target, None, X[c[:, 0]])
quadruplets_learners = [(LSML(), build_quadruplets)]
ids_quadruplets_learners = list(
map(lambda x: x.__class__.__name__,
[learner for (learner, _) in quadruplets_learners]))
pairs_learners = [
(ITML(max_iter=2), build_pairs), # max_iter=2 to be faster
(MMC(max_iter=2), build_pairs), # max_iter=2 to be faster
(SDML(prior='identity', balance_param=1e-5), build_pairs)
]
ids_pairs_learners = list(
map(lambda x: x.__class__.__name__,
[learner for (learner, _) in pairs_learners]))
classifiers = [(Covariance(), build_classification),
(LFDA(), build_classification), (LMNN(), build_classification),
def fit(self, X, y):
num_constraints = NUM_CONSTRAINTS
constraints = LSML.prepare_constraints(y, num_constraints)
return super(LSML_sk, self).fit(X, constraints)