def load_data(num_train_samples=7291, m_data_dict=data_dict):
from modshogun import RealFeatures, MulticlassLabels
import numpy
train_vec = m_data_dict['yTr'][0][:num_train_samples].astype(numpy.float64)
train_labels = MulticlassLabels(train_vec)
test_vec = m_data_dict['yTe'][0].astype(numpy.float64)
test_labels = MulticlassLabels(test_vec)
print "#train_labels = " + str(train_labels.get_num_labels())
print "#test_labels = " + str(test_labels.get_num_labels())
train_mat = m_data_dict['xTr'][:, :num_train_samples].astype(numpy.float64)
train_features = RealFeatures(train_mat)
test_mat = m_data_dict['xTe'].astype(numpy.float64)
test_features = RealFeatures(test_mat)
print "#train_vectors = " + str(train_features.get_num_vectors())
print "#test_vectors = " + str(test_features.get_num_vectors())
print "data dimension = " + str(test_features.get_num_features())
return train_features, train_labels, test_features, test_labels
def load_data(num_train_samples=7291, m_data_dict=data_dict): from modshogun import RealFeatures, MulticlassLabels import numpy train_vec = m_data_dict['yTr'][0][:num_train_samples].astype(numpy.float64) train_labels = MulticlassLabels(train_vec) test_vec = m_data_dict['yTe'][0].astype(numpy.float64) test_labels = MulticlassLabels(test_vec) print "#train_labels = " + str(train_labels.get_num_labels()) print "#test_labels = " + str(test_labels.get_num_labels()) train_mat = m_data_dict['xTr'][:,:num_train_samples].astype(numpy.float64) train_features = RealFeatures(train_mat) test_mat = m_data_dict['xTe'].astype(numpy.float64) test_features = RealFeatures(test_mat) print "#train_vectors = " + str(train_features.get_num_vectors()) print "#test_vectors = " + str(test_features.get_num_vectors()) print "data dimension = " + str(test_features.get_num_features()) return train_features, train_labels, test_features, test_labels
def metric_lmnn_statistics(
k=3,
fname_features="../../data/fm_train_multiclass_digits.dat.gz",
fname_labels="../../data/label_train_multiclass_digits.dat",
):
try:
from modshogun import LMNN, CSVFile, RealFeatures, MulticlassLabels, MSG_DEBUG
import matplotlib.pyplot as pyplot
except ImportError:
print "Error importing modshogun or other required modules. Please, verify their installation."
return
features = RealFeatures(load_compressed_features(fname_features).T)
labels = MulticlassLabels(CSVFile(fname_labels))
# print 'number of examples = %d' % features.get_num_vectors()
# print 'number of features = %d' % features.get_num_features()
assert features.get_num_vectors() == labels.get_num_labels()
# train LMNN
lmnn = LMNN(features, labels, k)
lmnn.set_correction(100)
# lmnn.io.set_loglevel(MSG_DEBUG)
print "Training LMNN, this will take about two minutes..."
lmnn.train()
print "Training done!"
# plot objective obtained during training
statistics = lmnn.get_statistics()
pyplot.plot(statistics.obj.get())
pyplot.grid(True)
pyplot.xlabel("Iterations")
pyplot.ylabel("LMNN objective")
pyplot.title("LMNN objective during training for the multiclass digits data set")
pyplot.show()
def metric_lmnn_statistics(
k=3,
fname_features='../../data/fm_train_multiclass_digits.dat.gz',
fname_labels='../../data/label_train_multiclass_digits.dat'):
try:
from modshogun import LMNN, CSVFile, RealFeatures, MulticlassLabels, MSG_DEBUG
import matplotlib.pyplot as pyplot
except ImportError:
print 'Error importing modshogun or other required modules. Please, verify their installation.'
return
features = RealFeatures(load_compressed_features(fname_features).T)
labels = MulticlassLabels(CSVFile(fname_labels))
# print 'number of examples = %d' % features.get_num_vectors()
# print 'number of features = %d' % features.get_num_features()
assert (features.get_num_vectors() == labels.get_num_labels())
# train LMNN
lmnn = LMNN(features, labels, k)
lmnn.set_correction(100)
# lmnn.io.set_loglevel(MSG_DEBUG)
print 'Training LMNN, this will take about two minutes...'
lmnn.train()
print 'Training done!'
# plot objective obtained during training
statistics = lmnn.get_statistics()
pyplot.plot(statistics.obj.get())
pyplot.grid(True)
pyplot.xlabel('Iterations')
pyplot.ylabel('LMNN objective')
pyplot.title(
'LMNN objective during training for the multiclass digits data set')
pyplot.show()
axis.scatter(xi[:,0], xi[:,1], s=50, facecolors='none', edgecolors=COLS[idx])
def plot_neighborhood_graph(x, nn, axis):
for i in xrange(x.shape[0]):
xs = [x[i,0], x[nn[1,i], 0]]
ys = [x[i,1], x[nn[1,i], 1]]
axis.plot(xs, ys, COLS[int(y[i])])
figure, axarr = pyplot.subplots(3, 1)
x, y = sandwich_data()
features = RealFeatures(x.T)
labels = MulticlassLabels(y)
print('%d vectors with %d features' % (features.get_num_vectors(), features.get_num_features()))
assert(features.get_num_vectors() == labels.get_num_labels())
distance = EuclideanDistance(features, features)
k = 2
knn = KNN(k, distance, labels)
plot_data(x, y, axarr[0])
plot_neighborhood_graph(x, knn.nearest_neighbors(), axarr[0])
axarr[0].set_aspect('equal')
axarr[0].set_xlim(-6, 4)
axarr[0].set_ylim(-3, 2)
lmnn = LMNN(features, labels, k)
lmnn.set_maxiter(10000)
lmnn.train()
L = lmnn.get_linear_transform()
def plot_neighborhood_graph(x, nn, axis):
for i in xrange(x.shape[0]):
xs = [x[i, 0], x[nn[1, i], 0]]
ys = [x[i, 1], x[nn[1, i], 1]]
axis.plot(xs, ys, COLS[int(y[i])])
figure, axarr = pyplot.subplots(3, 1)
x, y = sandwich_data()
features = RealFeatures(x.T)
labels = MulticlassLabels(y)
print('%d vectors with %d features' %
(features.get_num_vectors(), features.get_num_features()))
assert (features.get_num_vectors() == labels.get_num_labels())
distance = EuclideanDistance(features, features)
k = 2
knn = KNN(k, distance, labels)
plot_data(x, y, axarr[0])
plot_neighborhood_graph(x, knn.nearest_neighbors(), axarr[0])
axarr[0].set_aspect('equal')
axarr[0].set_xlim(-6, 4)
axarr[0].set_ylim(-3, 2)
lmnn = LMNN(features, labels, k)
lmnn.set_maxiter(10000)
lmnn.train()
L = lmnn.get_linear_transform()
