def test_itml(self):
def_kwargs = {
'convergence_threshold': 0.001,
'gamma': 1.0,
'max_iter': 1000,
'preprocessor': None,
'prior': 'identity',
'random_state': None,
'verbose': False
}
nndef_kwargs = {'gamma': 0.5}
merged_kwargs = sk_repr_kwargs(def_kwargs, nndef_kwargs)
self.assertEqual(remove_spaces(str(metric_learn.ITML(gamma=0.5))),
remove_spaces(f"ITML({merged_kwargs})"))
def_kwargs = {
'convergence_threshold': 0.001,
'gamma': 1.0,
'max_iter': 1000,
'num_constraints': None,
'preprocessor': None,
'prior': 'identity',
'random_state': None,
'verbose': False
}
nndef_kwargs = {'num_constraints': 7}
merged_kwargs = sk_repr_kwargs(def_kwargs, nndef_kwargs)
self.assertEqual(
remove_spaces(str(
metric_learn.ITML_Supervised(num_constraints=7))),
remove_spaces(f"ITML_Supervised({merged_kwargs})"))
def test_itml(self):
self.assertEqual(remove_spaces(str(metric_learn.ITML(gamma=0.5))),
remove_spaces("ITML(gamma=0.5)"))
self.assertEqual(
remove_spaces(str(
metric_learn.ITML_Supervised(num_constraints=7))),
remove_spaces("ITML_Supervised(num_constraints=7)"))
def test_itml(self):
self.assertEqual(str(metric_learn.ITML()), """
ITML(A0=None, convergence_threshold=0.001, gamma=1.0, max_iter=1000,
preprocessor=None, verbose=False)
""".strip('\n'))
self.assertEqual(str(metric_learn.ITML_Supervised()), """
ITML_Supervised(A0=None, bounds=None, convergence_threshold=0.001, gamma=1.0,
max_iter=1000, num_constraints=None, num_labeled='deprecated',
preprocessor=None, verbose=False)
""".strip('\n'))
def test_itml(self):
self.assertEqual(
remove_spaces(str(metric_learn.ITML())),
remove_spaces("""
ITML(A0='deprecated', convergence_threshold=0.001, gamma=1.0,
max_iter=1000, preprocessor=None, prior='identity', random_state=None,
verbose=False)
"""))
self.assertEqual(
remove_spaces(str(metric_learn.ITML_Supervised())),
remove_spaces("""
ITML_Supervised(A0='deprecated', bounds='deprecated',
convergence_threshold=0.001, gamma=1.0,
max_iter=1000, num_constraints=None, num_labeled='deprecated',
preprocessor=None, prior='identity', random_state=None, verbose=False)
"""))
def test_string_repr(self):
# we don't test LMNN here because it could be python_LMNN
self.assertEqual(str(metric_learn.Covariance()), "Covariance()")
self.assertEqual(str(metric_learn.NCA()),
"NCA(learning_rate=0.01, max_iter=100, num_dims=None)")
self.assertEqual(str(metric_learn.LFDA()),
"LFDA(dim=None, k=7, metric='weighted')")
self.assertEqual(str(metric_learn.ITML()), """
ITML(convergence_threshold=0.001, gamma=1.0, max_iters=1000, verbose=False)
""".strip('\n'))
self.assertEqual(str(metric_learn.ITML_Supervised()), """
ITML_Supervised(A0=None, bounds=None, convergence_threshold=0.001, gamma=1.0,
max_iters=1000, num_constraints=None, num_labeled=inf,
verbose=False)
""".strip('\n'))
self.assertEqual(str(metric_learn.LSML()),
"LSML(max_iter=1000, tol=0.001, verbose=False)")
self.assertEqual(str(metric_learn.LSML_Supervised()), """
LSML_Supervised(max_iter=1000, num_constraints=None, num_labeled=inf,
prior=None, tol=0.001, verbose=False, weights=None)
""".strip('\n'))
self.assertEqual(str(metric_learn.SDML()), """
SDML(balance_param=0.5, sparsity_param=0.01, use_cov=True, verbose=False)
""".strip('\n'))
self.assertEqual(str(metric_learn.SDML_Supervised()), """
SDML_Supervised(balance_param=0.5, num_constraints=None, num_labeled=inf,
sparsity_param=0.01, use_cov=True, verbose=False)
""".strip('\n'))
self.assertEqual(str(metric_learn.RCA()), "RCA(dim=None)")
self.assertEqual(str(metric_learn.RCA_Supervised()),
"RCA_Supervised(chunk_size=2, dim=None, num_chunks=100)")
self.assertEqual(str(metric_learn.MLKR()), """
MLKR(A0=None, alpha=0.0001, epsilon=0.01, max_iter=1000, num_dims=None)
""".strip('\n'))
###################################################################### # Information Theoretic Metric Learning # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ # # ITML uses a regularizer that automatically enforces a Semi-Definite # Positive Matrix condition - the LogDet divergence. It uses soft # must-link or cannot-link constraints, and a simple algorithm based on # Bregman projections. Unlike LMNN, ITML will implicitly enforce points from # the same class to belong to the same cluster, as you can see below. # # - See more in the :ref:`User Guide <itml>` # - See more in the documentation of the class :py:class:`ITML # <metric_learn.ITML>` itml = metric_learn.ITML_Supervised() X_itml = itml.fit_transform(X, y) plot_tsne(X_itml, y) ###################################################################### # Mahalanobis Metric for Clustering # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ # # MMC is an algorithm that will try to minimize the distance between similar # points, while ensuring that the sum of distances between dissimilar points is # higher than a threshold. This is done by optimizing a cost function # subject to an inequality constraint. # # - See more in the :ref:`User Guide <mmc>` # - See more in the documentation of the class :py:class:`MMC
import numpy as np
from sklearn.datasets import load_iris
import metric_learn
CLASSES = {
'Covariance':
metric_learn.Covariance(),
'ITML_Supervised':
metric_learn.ITML_Supervised(num_constraints=200),
'LFDA':
metric_learn.LFDA(k=2, dim=2),
'LMNN':
metric_learn.LMNN(k=5, learn_rate=1e-6, verbose=False),
'LSML_Supervised':
metric_learn.LSML_Supervised(num_constraints=200),
'MLKR':
metric_learn.MLKR(),
'NCA':
metric_learn.NCA(max_iter=700, n_components=2),
'RCA_Supervised':
metric_learn.RCA_Supervised(dim=2, num_chunks=30, chunk_size=2),
'SDML_Supervised':
metric_learn.SDML_Supervised(num_constraints=1500)
}
class IrisDataset(object):
params = [sorted(CLASSES)]
param_names = ['alg']
