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 sdml_fit(samples, similarity_set, prior='covariance', balance_param=0.15):
"""Prior can be 'covariance', 'identity' or 'random'.
balance_param was used 0.5 in the first version of the paper, but it does not work here with such a large value. """
n_samples = len(similarity_set)
sdml = SDML(prior=prior,
preprocessor=samples,
verbose=True,
balance_param=balance_param)
pairs, Y = [], []
for ind1 in range(n_samples):
for ind2 in range(n_samples):
pairs.append([ind1, ind2])
if similarity_set[ind1, ind2]:
Y.append(1)
else:
Y.append(-1)
start = time()
sdml.fit(pairs, Y)
print("Fitting took {:.2f} seconds.".format(time() - start))
return sdml
def test_sdml_converges_if_psd(self):
"""Tests that sdml converges on a simple problem where we know the
pseudo-covariance matrix is PSD"""
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., -55.], [0., -60]]])
y = [1, -1]
sdml = SDML(use_cov=True, sparsity_param=0.01, balance_param=0.5)
sdml.fit(pairs, y)
assert np.isfinite(sdml.get_mahalanobis_matrix()).all()
def test_sdml_converges_if_psd(self): """Tests that sdml converges on a simple problem where we know the pseudo-covariance matrix is PSD""" pairs = np.array([[[-10., 0.], [10., 0.]], [[0., -55.], [0., -60]]]) y = [1, -1] sdml = SDML(use_cov=True, sparsity_param=0.01, balance_param=0.5) sdml.fit(pairs, y) assert np.isfinite(sdml.get_mahalanobis_matrix()).all()
def update(request):
df_label = pd.read_csv(
os.path.join(settings.BASE_DIR, 'data/outcome_labels.csv'))
print("df_label", '\n', df_label)
df_data = pd.read_csv(
os.path.join(settings.BASE_DIR, 'data/features_rep.csv'))
#print("df_data", df_data)
#get unique row ids
rowIDLIst = pd.concat([df_label.id1, df_label.id2],
axis=0).unique().tolist()
#rowIDLIst2 = pd.concat([df_label.id1,df_label.id2],axis = 1).unique().tolist()
print("rowIDLIst", '\n', rowIDLIst)
#print("rowIDLIst2",'\n', rowIDLIst2)
#connectivity graph
cmatrix = np.zeros([len(rowIDLIst), len(rowIDLIst)])
print("as_Matrix", '\n', df_label.as_matrix)
for lbl in df_label.as_matrix():
print("lbl", lbl)
print("lbl[0]", lbl[0])
print("lbl[1]", lbl[1])
print("lbl[2]", lbl[2])
print("rowIDLIst.index(lbl[0])", rowIDLIst.index(lbl[0]),
"rowIDLIst.index(lbl[1])", rowIDLIst.index(lbl[1]))
cmatrix[rowIDLIst.index(lbl[0])][rowIDLIst.index(lbl[1])] = int(lbl[2])
cmatrix[rowIDLIst.index(lbl[1])][rowIDLIst.index(lbl[0])] = int(lbl[2])
print("cmatrix", '\n', cmatrix)
trainedData = []
for rid in rowIDLIst:
row = df_data.iloc[[rid]]
trainedData.append(row)
print("trainedData1", '\n', trainedData)
trainedData = pd.concat(trainedData, axis=0).as_matrix()
print("trainedData2" "\n", trainedData)
metric = SDML().fit(trainedData, cmatrix)
newData = metric.transform(df_data)
al_selection = request.session['clustering']
num_clustering = request.session['num_cluster']
clusteringAndTSNE(newData, al_selection, num_clustering)
# context is a dict of html code, containing three types of features representation
content = {'Title': "Step 7: Clustering Visualization", "listId": "li7"}
return render(request, 'clustering/stp7-clu-visualisation.html', content)
def test_verbose_has_not_installed_skggm_sdml(capsys): # Test that if users have installed skggm, a message is printed telling them # skggm's solver is used (when they use SDML) # TODO: remove if we don't need skggm anymore pairs = np.array([[[-10., 0.], [10., 0.]], [[0., -55.], [0., -60]]]) y_pairs = [1, -1] sdml = SDML(verbose=True) sdml.fit(pairs, y_pairs) out, _ = capsys.readouterr() assert "SDML will use scikit-learn's graphical lasso solver." in out
def test_verbose_has_not_installed_skggm_sdml(capsys):
# Test that if users have installed skggm, a message is printed telling them
# skggm's solver is used (when they use SDML)
# TODO: remove if we don't need skggm anymore
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., -55.], [0., -60]]])
y_pairs = [1, -1]
sdml = SDML(verbose=True)
sdml.fit(pairs, y_pairs)
out, _ = capsys.readouterr()
assert "SDML will use scikit-learn's graphical lasso solver." in out
def test_iris(self):
num_constraints = 1500
n = self.iris_points.shape[0]
np.random.seed(1234)
W = SDML.prepare_constraints(self.iris_labels, n, num_constraints)
# Test sparse graph inputs.
for graph in ((W, scipy.sparse.csr_matrix(W))):
sdml = SDML().fit(self.iris_points, graph)
csep = class_separation(sdml.transform(), self.iris_labels)
self.assertLess(csep, 0.25)
def update():
df_label = pd.read_csv('data/outcome_labels.csv')
print "df_label", '\n', df_label
df_data = pd.read_csv('data/features_rep.csv')
#df_data = pd.read_csv('data/alvin_rep.csv')
print "df_data", '\n', df_data
#print("df_data", df_data)
#get unique row ids
rowIDLIst = pd.concat([df_label.id1, df_label.id2],
axis=0).unique().tolist()
#rowIDLIst2 = pd.concat([df_label.id1,df_label.id2],axis = 1)
print "rowIDLIst", '\n', rowIDLIst
#print("rowIDLIst2",'\n', rowIDLIst2)
#connectivity graph
cmatrix = np.zeros([len(rowIDLIst), len(rowIDLIst)])
#print("as_Matrix", '\n', df_label.as_matrix)
for lbl in df_label.as_matrix():
#print ("lbl",lbl)
#print ("lbl[0]",lbl[0])
#print ("lbl[1]",lbl[1])
#print ("lbl[2]",lbl[2])
#print ("rowIDLIst.index(lbl[0])", rowIDLIst.index(lbl[0]),"rowIDLIst.index(lbl[1])",rowIDLIst.index(lbl[1]))
cmatrix[rowIDLIst.index(lbl[0])][rowIDLIst.index(lbl[1])] = int(lbl[2])
cmatrix[rowIDLIst.index(lbl[1])][rowIDLIst.index(lbl[0])] = int(lbl[2])
print "cmatrixShape", '\n', cmatrix.shape
trainedData = []
for rid in rowIDLIst:
row = df_data.iloc[[rid]]
#print "row","\n",row
#print "rowType","\n",type(row)
trainedData.append(row)
#print "trainedData","\n", trainedData
#print "typetrainedData1", '\n', len(trainedData)
trainedData = pd.concat(trainedData, axis=0).as_matrix()
#print "trainedData2", "\n", trainedData
print "trainedData.shape", '\n', trainedData.shape
metric = SDML().fit(trainedData, cmatrix)
newData = metric.transform(df_data)
clusteringAndTSNE(newData)
def test_iris(self):
num_constraints = 1500
n = self.iris_points.shape[0]
np.random.seed(1234)
W = SDML.prepare_constraints(self.iris_labels, n, num_constraints)
# Test sparse graph inputs.
for graph in ((W, scipy.sparse.csr_matrix(W))):
sdml = SDML().fit(self.iris_points, graph)
csep = class_separation(sdml.transform(), self.iris_labels)
self.assertLess(csep, 0.25)
def test_iris(self):
num_constraints = 1500
n = self.iris_points.shape[0]
# Note: this is a flaky test, which fails for certain seeds.
# TODO: un-flake it!
np.random.seed(5555)
W = SDML.prepare_constraints(self.iris_labels, n, num_constraints)
# Test sparse graph inputs.
for graph in ((W, scipy.sparse.csr_matrix(W))):
sdml = SDML().fit(self.iris_points, graph)
csep = class_separation(sdml.transform(), self.iris_labels)
self.assertLess(csep, 0.25)
def test_iris(self):
num_constraints = 1500
n = self.iris_points.shape[0]
# Note: this is a flaky test, which fails for certain seeds.
# TODO: un-flake it!
np.random.seed(5555)
W = SDML.prepare_constraints(self.iris_labels, n, num_constraints)
# Test sparse graph inputs.
for graph in ((W, scipy.sparse.csr_matrix(W))):
sdml = SDML().fit(self.iris_points, graph)
csep = class_separation(sdml.transform(), self.iris_labels)
self.assertLess(csep, 0.25)
def test_sdml_raises_warning_msg_installed_skggm(self):
"""Tests that the right warning message is raised if someone tries to
use SDML but has not installed skggm, and that the algorithm fails to
converge"""
# TODO: remove if we don't need skggm anymore
# case on which we know that skggm's graphical lasso fails
# because it will return non finite values
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., 50.], [0., -60]]])
y_pairs = [1, -1]
sdml = SDML(use_cov=False, balance_param=100, verbose=True)
msg = ("There was a problem in SDML when using skggm's graphical "
"lasso solver.")
with pytest.raises(RuntimeError) as raised_error:
sdml.fit(pairs, y_pairs)
assert msg == str(raised_error.value)
def test_raises_no_warning_installed_skggm(self):
# otherwise we should be able to instantiate and fit SDML and it
# should raise no error and no ConvergenceWarning
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., -55.], [0., -60]]])
y_pairs = [1, -1]
X, y = make_classification(random_state=42)
with pytest.warns(None) as records:
sdml = SDML(prior='covariance')
sdml.fit(pairs, y_pairs)
for record in records:
assert record.category is not ConvergenceWarning
with pytest.warns(None) as records:
sdml_supervised = SDML_Supervised(prior='identity', balance_param=1e-5)
sdml_supervised.fit(X, y)
for record in records:
assert record.category is not ConvergenceWarning
def test_sdml_raises_warning_msg_installed_skggm(self):
"""Tests that the right warning message is raised if someone tries to
use SDML but has not installed skggm, and that the algorithm fails to
converge"""
# TODO: remove if we don't need skggm anymore
# case on which we know that skggm's graphical lasso fails
# because it will return non finite values
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., 50.], [0., -60]]])
y_pairs = [1, -1]
sdml = SDML(use_cov=False, balance_param=100, verbose=True)
msg = ("There was a problem in SDML when using skggm's graphical "
"lasso solver.")
with pytest.raises(RuntimeError) as raised_error:
sdml.fit(pairs, y_pairs)
assert msg == str(raised_error.value)
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 test_sdml_raises_warning_non_psd(self):
"""Tests that SDML raises a warning on a toy example where we know the
pseudo-covariance matrix is not PSD"""
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., 50.], [0., -60]]])
y = [1, -1]
sdml = SDML(use_cov=True, sparsity_param=0.01, balance_param=0.5)
msg = ("Warning, the input matrix of graphical lasso is not "
"positive semi-definite (PSD). The algorithm may diverge, "
"and lead to degenerate solutions. "
"To prevent that, try to decrease the balance parameter "
"`balance_param` and/or to set use_cov=False.")
with pytest.warns(ConvergenceWarning) as raised_warning:
try:
sdml.fit(pairs, y)
except Exception:
pass
# we assert that this warning is in one of the warning raised by the
# estimator
assert msg in list(map(lambda w: str(w.message), raised_warning))
def test_sdml_raises_warning_non_psd(self):
"""Tests that SDML raises a warning on a toy example where we know the
pseudo-covariance matrix is not PSD"""
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., 50.], [0., -60]]])
y = [1, -1]
sdml = SDML(use_cov=True, sparsity_param=0.01, balance_param=0.5)
msg = ("Warning, the input matrix of graphical lasso is not "
"positive semi-definite (PSD). The algorithm may diverge, "
"and lead to degenerate solutions. "
"To prevent that, try to decrease the balance parameter "
"`balance_param` and/or to set use_cov=False.")
with pytest.warns(ConvergenceWarning) as raised_warning:
try:
sdml.fit(pairs, y)
except Exception:
pass
# we assert that this warning is in one of the warning raised by the
# estimator
assert msg in list(map(lambda w: str(w.message), raised_warning))
def test_sdml_raises_warning_msg_not_installed_skggm(self):
"""Tests that the right warning message is raised if someone tries to
use SDML but has not installed skggm, and that the algorithm fails to
converge"""
# TODO: remove if we don't need skggm anymore
# case on which we know that scikit-learn's graphical lasso fails
# because it will return a non SPD matrix
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., 50.], [0., -60]]])
y_pairs = [1, -1]
sdml = SDML(use_cov=False, balance_param=100, verbose=True)
msg = ("There was a problem in SDML when using scikit-learn's graphical "
"lasso solver. skggm's graphical lasso can sometimes converge on "
"non SPD cases where scikit-learn's graphical lasso fails to "
"converge. Try to install skggm and rerun the algorithm (see "
"the README.md for the right version of skggm).")
with pytest.raises(RuntimeError) as raised_error:
sdml.fit(pairs, y_pairs)
assert msg == str(raised_error.value)
def test_sdml_raises_warning_msg_not_installed_skggm(self):
"""Tests that the right warning message is raised if someone tries to
use SDML but has not installed skggm, and that the algorithm fails to
converge"""
# TODO: remove if we don't need skggm anymore
# case on which we know that scikit-learn's graphical lasso fails
# because it will return a non SPD matrix
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., 50.], [0., -60]]])
y_pairs = [1, -1]
sdml = SDML(prior='identity', balance_param=100, verbose=True)
msg = ("There was a problem in SDML when using scikit-learn's graphical "
"lasso solver. skggm's graphical lasso can sometimes converge on "
"non SPD cases where scikit-learn's graphical lasso fails to "
"converge. Try to install skggm and rerun the algorithm (see "
"the README.md for the right version of skggm).")
with pytest.raises(RuntimeError) as raised_error:
sdml.fit(pairs, y_pairs)
assert msg == str(raised_error.value)
def metricLearning(data):
df_label = pd.read_csv('../TestAndLearn/data/outcome_labels.csv')
#print("df_label", '\n', df_label)
#get unique row ids
rowIDLIst = pd.concat([df_label.id1, df_label.id2],
axis=0).unique().tolist()
print("rowIDLIst", '\n', rowIDLIst)
#connectivity graph
cmatrix = np.zeros([len(rowIDLIst), len(rowIDLIst)])
#print("as_Matrix", '\n', df_label.as_matrix)
for lbl in df_label.as_matrix():
#print ("rowIDLIst.index(lbl[0])", rowIDLIst.index(lbl[0]),"rowIDLIst.index(lbl[1])",rowIDLIst.index(lbl[1]))
cmatrix[rowIDLIst.index(lbl[0])][rowIDLIst.index(lbl[1])] = int(lbl[2])
cmatrix[rowIDLIst.index(lbl[1])][rowIDLIst.index(lbl[0])] = int(lbl[2])
print("cmatrix.shape", '\n', cmatrix.shape)
trainedData = []
for rid in rowIDLIst:
row = data.iloc[[rid]]
#print "row","\n",row
#print "rowType","\n",type(row)
trainedData.append(row)
#print "LentrainedData","\n", len(trainedData)
#print "typetrainedData1", '\n', len(trainedData)
trainedData = pd.concat(trainedData, axis=0).as_matrix()
print("trainedData.shape", "\n", trainedData.shape)
#print "trainedData2", "\n", trainedData
metric = SDML().fit(trainedData, cmatrix)
newData = metric.transform(data)
return newData
def test_raises_no_warning_installed_skggm(self):
# otherwise we should be able to instantiate and fit SDML and it
# should raise no warning
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., -55.], [0., -60]]])
y_pairs = [1, -1]
X, y = make_classification(random_state=42)
with pytest.warns(None) as record:
sdml = SDML()
sdml.fit(pairs, y_pairs)
assert len(record) == 0
with pytest.warns(None) as record:
sdml = SDML_Supervised(use_cov=False, balance_param=1e-5)
sdml.fit(X, y)
assert len(record) == 0
def test_raises_no_warning_installed_skggm(self):
# otherwise we should be able to instantiate and fit SDML and it
# should raise no warning
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., -55.], [0., -60]]])
y_pairs = [1, -1]
X, y = make_classification(random_state=42)
with pytest.warns(None) as record:
sdml = SDML()
sdml.fit(pairs, y_pairs)
assert len(record) == 0
with pytest.warns(None) as record:
sdml = SDML_Supervised(use_cov=False, balance_param=1e-5)
sdml.fit(X, y)
assert len(record) == 0
def test_tiwafer():
num_constraints = 1500
print "Loading Data...."
tiwafer_data = load_data_sdml()
sim_pairs = tiwafer_data.sim_pairs
diff_pairs = tiwafer_data.diff_pairs
sorted_ids = tiwafer_data.sortedIds
ti_data = np.array(tiwafer_data.data)
labels = np.array(tiwafer_data.target)
print "Done Loading Data.\nLearning Distance Metric...."
num_points = len(sorted_ids)
W = prepare_constraints_old(labels, num_points, num_constraints)
sdml = SDML()
# W = prepare_constraints(sorted_ids, sim_pairs, diff_pairs)
sdml.fit(ti_data, W)
W_metric = sdml.metric()
cPickle.dump(W_metric, open('W_metric_sdml.p', 'wb'))
W_trans = sdml.transformer()
with open('W_trans_sdml.p', 'wb') as handle:
cPickle.dump(W_trans, handle)
# 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(use_cov=False, 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),
(NCA(), build_classification), (RCA(), build_classification),
(ITML_Supervised(max_iter=5), build_classification),
(LSML_Supervised(), build_classification),
(MMC_Supervised(max_iter=5), build_classification),
(RCA_Supervised(num_chunks=10), build_classification),
(SDML_Supervised(use_cov=False,
balance_param=1e-5), build_classification)]
ids_classifiers = list(
def fit(self, X, y):
num_constraints = NUM_CONSTRAINTS
constraints = SDML.prepare_constraints(y, len(X), num_constraints)
return super(SDML_sk, self).fit(X, constraints)
# 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),
(NCA(), build_classification), (RCA(), build_classification),
(ITML_Supervised(max_iter=5), build_classification),
(LSML_Supervised(), build_classification),
(MMC_Supervised(max_iter=5), build_classification),
(RCA_Supervised(num_chunks=5), build_classification),
(SDML_Supervised(prior='identity',
balance_param=1e-5), build_classification)]
ids_classifiers = list(
#print ("lbl[0]",lbl[0])
#print ("lbl[1]",lbl[1])
#print ("lbl[2]",lbl[2])
#print ("rowIDLIst.index(lbl[0])", rowIDLIst.index(lbl[0]),"rowIDLIst.index(lbl[1])",rowIDLIst.index(lbl[1]))
cmatrix[rowIDLIst.index(lbl[0])][rowIDLIst.index(lbl[1])] = int(lbl[2])
cmatrix[rowIDLIst.index(lbl[1])][rowIDLIst.index(lbl[0])] = int(lbl[2])
print "cmatrix.shape", '\n', cmatrix.shape
trainedData = []
for rid in rowIDLIst:
row = df_reperent.iloc[[rid]]
#print "row","\n",row
#print "rowType","\n",type(row)
trainedData.append(row)
#print "LentrainedData","\n", len(trainedData)
#print "typetrainedData1", '\n', len(trainedData)
trainedData = pd.concat(trainedData, axis=0).as_matrix()
print "trainedData.shape", "\n", trainedData.shape
#print "trainedData2", "\n", trainedData
metric = SDML().fit(trainedData, cmatrix)
newData = metric.transform(df_reperent)
print type(newData)
print newData.shape
# 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),
(NCA(), build_classification), (RCA(), build_classification),
(ITML_Supervised(max_iter=5), build_classification),
(LSML_Supervised(), build_classification),
(MMC_Supervised(max_iter=5), build_classification),
(RCA_Supervised(num_chunks=10), build_classification),
(SDML_Supervised(), build_classification)]
ids_classifiers = list(
map(lambda x: x.__class__.__name__,
