def metric_lmnn_modular(train_fname=traindat,
test_fname=testdat,
label_train_fname=label_traindat,
k=3):
try:
from modshogun import RealFeatures, MulticlassLabels, LMNN, KNN, CSVFile
except ImportError:
return
# wrap features and labels into Shogun objects
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
labels = MulticlassLabels(CSVFile(label_train_fname))
# LMNN
lmnn = LMNN(feats_train, labels, k)
lmnn.train()
lmnn_distance = lmnn.get_distance()
# perform classification with KNN
knn = KNN(k, lmnn_distance, labels)
knn.train()
output = knn.apply(feats_test).get_labels()
return lmnn, output
def main():
# Get training file name from the command line
traindatafile = sys.argv[1]
# The training file is in libSVM format
with open(traindatafile, mode="r") as myFile:
lines = myFile.readlines()
random.shuffle(lines)
open("tempdata.dat", 'w').writelines(lines)
tr_data = load_svmlight_file("tempdata.dat")
#To randomly select 5000 points
Xtr = tr_data[0].toarray()
# Converts sparse matrices to dense
Ytr = tr_data[1]
# The trainig labels
Xtr = Xtr[:5000]
Ytr = Ytr[:5000]
# Cast data to Shogun format to work with LMNN
features = RealFeatures(Xtr.T)
labels = MulticlassLabels(Ytr.astype(np.float64))
#print(Xtr.shape)
### Do magic stuff here to learn the best metric you can ###
kmax = 25 #inductive bias
values = list(range(1, kmax + 1))
k = predict(Xtr, Ytr, values)
# Number of target neighbours per example - tune this using validation
#print(k)
# Initialize the LMNN package
print("K : "),
print(k)
k = 5
lmnn = LMNN(features, labels, k)
init_transform = np.eye(Xtr.shape[1])
# Choose an appropriate timeout
lmnn.set_maxiter(25000)
lmnn.train(init_transform)
# Let LMNN do its magic and return a linear transformation
# corresponding to the Mahalanobis metric it has learnt
L = lmnn.get_linear_transform()
M = np.matrix(np.dot(L.T, L))
print("LMNN done")
#print(M)
# Save the model for use in testing phase
# Warning: do not change this file name
np.save("model.npy", M)
def diagonal_lmnn(features, labels, k=3, max_iter=10000):
from modshogun import LMNN, MSG_DEBUG
import numpy
lmnn = LMNN(features, labels, k)
# lmnn.io.set_loglevel(MSG_DEBUG)
lmnn.set_diagonal(True)
lmnn.set_maxiter(max_iter)
lmnn.train(numpy.eye(features.get_num_features()))
return lmnn
def test_LMNN():
X = np.eye(80)
Y = np.array([i for j in range(4) for i in range(20)])
feats = RealFeatures(X.T)
labs = MulticlassLabels(Y.astype(np.float64))
arr = LMNN(feats, labs, 2)
arr.train()
L = arr.get_linear_transform()
X_proj = np.dot(L, X.T)
test_x = np.eye(80)[0:20:]
test = RealFeatures(test_x.T)
test_proj = np.dot(L, test_x.T)
pdb.set_trace()
def main():
# Get training file name from the command line
traindatafile = sys.argv[1]
# The training file is in libSVM format
tr_data = load_svmlight_file(traindatafile);
Xtr = tr_data[0].toarray(); # Converts sparse matrices to dense
Ytr = tr_data[1]; # The trainig labels
Indices_array = np.arange(Ytr.shape[0]);
np.random.shuffle(Indices_array);
Xtr = Xtr[Indices_array];
Xtr = Xtr[:6000];
Ytr = Ytr[Indices_array];
Ytr = Ytr[:6000];
# Cast data to Shogun format to work with LMNN
features = RealFeatures(Xtr.T)
labels = MulticlassLabels(Ytr.astype(np.float64))
### Do magic stuff here to learn the best metric you can ###
# Number of target neighbours per example - tune this using validation
k = 10
# Initialize the LMNN package
lmnn = LMNN(features, labels, k)
init_transform = np.eye(Xtr.shape[1])
# Choose an appropriate timeout
lmnn.set_maxiter(200000)
lmnn.train(init_transform)
# Let LMNN do its magic and return a linear transformation
# corresponding to the Mahalanobis metric it has learnt
L = lmnn.get_linear_transform()
M = np.matrix(np.dot(L.T, L))
# Save the model for use in testing phase
# Warning: do not change this file name
np.save("model.npy", M)
def main():
# Get training file name from the command line
traindatafile = sys.argv[1]
# The training file is in libSVM format
tr_data = load_svmlight_file(traindatafile)
print("loaded data")
init_transform = np.eye(tr_data[0].toarray().shape[1])
print(init_transform)
Xtr = tr_data[0][:6000].toarray()
# Converts sparse matrices to dense
Ytr = tr_data[1][:6000]
# The trainig labels
# Cast data to Shogun format to work with LMNN
features = RealFeatures(Xtr.T)
labels = MulticlassLabels(Ytr.astype(np.float64))
### Do magic stuff here to learn the best metric you can ###
# Number of target neighbours per example - tune this using validation
k = 21
# Initialize the LMNN package
print("starting lmnn train....")
lmnn = LMNN(features, labels, k)
# Choose an appropriate timeout
lmnn.set_maxiter(3000)
lmnn.train(init_transform)
# Let LMNN do its magic and return a linear transformation
# corresponding to the Mahalanobis metric it has learnt
L = lmnn.get_linear_transform()
M = np.matrix(np.dot(L.T, L))
print(M)
# Save the model for use in testing phase
# Warning: do not change this file name
statistics = lmnn.get_statistics()
pyplot.plot(statistics.obj.get())
pyplot.grid(True)
pyplot.xlabel('Number of iterations')
pyplot.ylabel('LMNN objective')
pyplot.show()
np.save("model.npy", M)
def lmnn(train_features, train_labels, test_features, test_labels, k=1):
from modshogun import LMNN, KNN, MSG_DEBUG, MulticlassAccuracy
import numpy
# dummy = LMNN()
# dummy.io.set_loglevel(MSG_DEBUG)
lmnn = LMNN(train_features, train_labels, k)
lmnn.train()
distance = lmnn.get_distance()
knn = KNN(k, distance, train_labels)
knn.train()
train_output = knn.apply()
test_output = knn.apply(test_features)
evaluator = MulticlassAccuracy()
print 'LMNN training error is %.4f' % (
(1 - evaluator.evaluate(train_output, train_labels)) * 100)
print 'LMNN test error is %.4f' % (
(1 - evaluator.evaluate(test_output, test_labels)) * 100)
def lmnn_classify(traindat, testdat, k=3):
from modshogun import LMNN, KNN, MulticlassAccuracy, MSG_DEBUG
train_features, train_labels = traindat.features, traindat.labels
lmnn = LMNN(train_features, train_labels, k)
lmnn.set_maxiter(1200)
lmnn.io.set_loglevel(MSG_DEBUG)
lmnn.train()
distance = lmnn.get_distance()
knn = KNN(k, distance, train_labels)
knn.train()
test_features, test_labels = testdat.features, testdat.labels
predicted_labels = knn.apply(test_features)
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(predicted_labels, test_labels)
err = 1 - acc
return err
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 lmnn_diagonal(train_features,
train_labels,
test_features,
test_labels,
k=1):
from modshogun import LMNN, KNN, MSG_DEBUG, MulticlassAccuracy
import numpy
lmnn = LMNN(train_features, train_labels, k)
lmnn.set_diagonal(True)
lmnn.train()
distance = lmnn.get_distance()
knn = KNN(k, distance, train_labels)
knn.train()
train_output = knn.apply()
test_output = knn.apply(test_features)
evaluator = MulticlassAccuracy()
print 'LMNN-diagonal training error is %.4f' % (
(1 - evaluator.evaluate(train_output, train_labels)) * 100)
print 'LMNN-diagonal test error is %.4f' % (
(1 - evaluator.evaluate(test_output, test_labels)) * 100)
def main():
Xtr, Ytr = gettrainData()
Xtr = Xtr[:len(Xtr) // 6]
Ytr = Ytr[:len(Ytr) // 6]
# Cast data to Shogun format to work with LMNN
features = RealFeatures(Xtr.T)
labels = MulticlassLabels(Ytr.astype(np.float64))
print(2.1)
### Do magic stuff here to learn the best metric you can ###
# Number of target neighbours per example - tune this using validation
k = 10
# Initialize the LMNN package
lmnn = LMNN(features, labels, k)
print(2.2)
init_transform = np.eye(Xtr.shape[1])
print(2.3)
# Choose an appropriate timeout
lmnn.set_maxiter(8000)
print(2.4)
lmnn.train(init_transform)
print(2.5)
# Let LMNN do its magic and return a linear transformation
# corresponding to the Mahalanobis metric it has learnt
L = lmnn.get_linear_transform()
print(2.6)
M = np.matrix(np.dot(L.T, L))
print(2.7)
# Save the model for use in testing phase
# Warning: do not change this file name
np.save("model2.npy", M)
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()
knn.set_distance(lmnn.get_distance())
plot_data(x, y, axarr[1])
plot_neighborhood_graph(x, knn.nearest_neighbors(), axarr[1])
axarr[1].set_aspect('equal')
axarr[1].set_xlim(-6, 4)
axarr[1].set_ylim(-3, 2)
xL = numpy.dot(x, L.T) ## to see the data after the linear transformation
features = RealFeatures(xL.T)
distance = EuclideanDistance(features, features)
knn.set_distance(distance)
