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_preprocessor_weakly_supervised(preprocessor, tuples, y_tuples):
"""Tests different ways to use the preprocessor argument: an array,
a class callable, and a function callable, with a weakly supervised
algorithm
"""
nca = ITML(preprocessor=preprocessor)
nca.fit(tuples, y_tuples)
def test_preprocessor_weakly_supervised(preprocessor, tuples, y_tuples): """Tests different ways to use the preprocessor argument: an array, a class callable, and a function callable, with a weakly supervised algorithm """ nca = ITML(preprocessor=preprocessor) nca.fit(tuples, y_tuples)
def test_iris(self):
num_constraints = 200
n = self.iris_points.shape[0]
C = ITML.prepare_constraints(self.iris_labels, n, num_constraints)
itml = ITML().fit(self.iris_points, C, verbose=False)
csep = class_separation(itml.transform(), self.iris_labels)
self.assertLess(csep, 0.4) # it's not great
def test_iris(self):
num_constraints = 200
n = self.iris_points.shape[0]
C = ITML.prepare_constraints(self.iris_labels, n, num_constraints)
itml = ITML().fit(self.iris_points, C, verbose=False)
csep = class_separation(itml.transform(), self.iris_labels)
self.assertLess(csep, 0.4) # it's not great
def doClustering(X = None, y = None, initial = False, silent = True, numClusters = 4):
takekmeans = True
takeoptics = False
if not silent: print("- doClustering")
X, y = rd.readTransformedData()
# metric learning
X2 = X.iloc[:, 0:].values
if initial == False:
votesX, votesY = rd.readFeedbackData()
pairs = []
for index, row in votesX.iterrows():
pairs.append((X2[row["id_punkt1"]], X2[row["id_punkt2"]]))
a = votesY
itml = ITML()
itml.fit(pairs, a)
if not silent: print("Transform")
X2 = itml.transform(X2)
if takekmeans == True:
# Compute kMeans
# print("numCluster",numClusters)
# number_clusters = numClusters
kmeans = KMeans(n_clusters=numClusters , random_state=0).fit(X2)
labels = kmeans.labels_
labels_true = y
core_samples_mask = [0] * len(y)
elif takeoptics == True:
opt = OPTICS(min_samples=30, xi=.05)
# opt = OPTICS(min_samples=50, xi=.05, min_cluster_size=.05)
opt.fit(X2)
labels = opt.labels_
labels_true = y
core_samples_mask = [0] * len(y)
else:
# Compute DBSCAN
# db = DBSCAN(eps=0.1, min_samples=10).fit(X2)
db = DBSCAN(eps=0.6, min_samples=5).fit(X2)
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
labels = db.labels_
labels_true = y
writeClusteringResult(X2, labels, labels_true, core_samples_mask)
if not silent: print("+ doClustering")
return 1
def test_bounds_parameters_valid(bounds):
"""Asserts that we can provide any array-like of two elements as bounds,
and that the attribute bound_ is a numpy array"""
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., 50.], [0., -60]]])
y_pairs = [1, -1]
itml = ITML()
itml.fit(pairs, y_pairs, bounds=bounds)
X = np.array([[0, 0], [0, 1], [2, 0], [2, 1]])
y = np.array([1, 0, 1, 0])
itml_supervised = ITML_Supervised()
itml_supervised.fit(X, y, bounds=bounds)
def test_bounds_parameters_valid(bounds): """Asserts that we can provide any array-like of two elements as bounds, and that the attribute bound_ is a numpy array""" pairs = np.array([[[-10., 0.], [10., 0.]], [[0., 50.], [0., -60]]]) y_pairs = [1, -1] itml = ITML() itml.fit(pairs, y_pairs, bounds=bounds) X = np.array([[0, 0], [0, 1], [2, 0], [2, 1]]) y = np.array([1, 0, 1, 0]) itml_supervised = ITML_Supervised() itml_supervised.fit(X, y, bounds=bounds)
def test_bounds_parameters_invalid(bounds):
"""Assert that if a non array-like is put for bounds, or an array-like
of length different than 2, an error is returned"""
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., 50.], [0., -60]]])
y_pairs = [1, -1]
itml = ITML()
with pytest.raises(Exception):
itml.fit(pairs, y_pairs, bounds=bounds)
X = np.array([[0, 0], [0, 1], [2, 0], [2, 1]])
y = np.array([1, 0, 1, 0])
itml_supervised = ITML_Supervised()
with pytest.raises(Exception):
itml_supervised.fit(X, y, bounds=bounds)
def test_bounds_parameters_invalid(bounds):
"""Assert that if a non array-like is put for bounds, or an array-like
of length different than 2, an error is returned"""
pairs = np.array([[[-10., 0.], [10., 0.]], [[0., 50.], [0., -60]]])
y_pairs = [1, -1]
itml = ITML()
with pytest.raises(Exception):
itml.fit(pairs, y_pairs, bounds=bounds)
X = np.array([[0, 0], [0, 1], [2, 0], [2, 1]])
y = np.array([1, 0, 1, 0])
itml_supervised = ITML_Supervised()
with pytest.raises(Exception):
itml_supervised.fit(X, y, bounds=bounds)
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 constructSimilartyMatrixITML(self, k=5):
print 'Now doing itml'
num_constraints = 100
itml = ITML()
C = ITML.prepare_constraints(self.y_train,
self.trainVectorsPCA.shape[0],
num_constraints)
itml.fit(self.trainVectorsPCA, C, verbose=True)
self.L_itml = itml.transformer()
name = 'itml/ITML transformer matrix with dataset shape ' + str(
self.trainVectorsPCA.shape)
print 'L itml shape is ', self.L_itml.shape
np.save(name, self.L_itml)
# Input data transformed to the metric space by X*L.T
self.transformedTrainITML = copy(itml.transform(self.trainVectorsPCA))
self.transformedTestITML = copy(itml.transform(self.testVectorsPCA))
self.transformedAllITML = copy(itml.transform(self.allDataPCA))
# now we can simply calculate the eucledian distances on the above transformed dataset
#Visualizing the dataset by TSNE
projectedDigits = TSNE(random_state=randomState).fit_transform(
self.transformedTrainITML)
plt.scatter(projectedDigits[:, 0],
projectedDigits[:, 1],
c=self.y_train)
plt.title(
'ITML Transformed Train set projected to 2 Dimensions by TSNE with k='
+ str(k) + ' and num_constraints = ' + str(num_constraints))
plt.savefig(pp, format='pdf')
self.pwdis = copy(
pairwise_distances(self.transformedAllITML, metric='euclidean'))
self.D = np.zeros(self.pwdis.shape)
for i in range(0, self.pwdis.shape[0]):
l1 = self.pwdis[i].tolist()
#print 'l1 is ',l1,'\n\n'
allnearestNeighbours = sorted(range(len(l1)), key=lambda i: l1[i])
#now set the all the weights except for k+1 to 0
self.pwdis[i, allnearestNeighbours[k:]] = 0
self.D[i, i] = sum(self.pwdis[i])
print 'accuracy for ITML\n'
self.labelPropogation()
def constructSimilartyMatrixITML(self,k=5):
print 'Now doing itml'
num_constraints=100
itml=ITML()
C = ITML.prepare_constraints(self.y_train, self.trainVectorsPCA.shape[0], num_constraints)
itml.fit(self.trainVectorsPCA, C, verbose=True)
self.L_itml=itml.transformer()
name='itml/ITML transformer matrix with dataset shape '+str(self.trainVectorsPCA.shape)
print 'L itml shape is ',self.L_itml.shape
np.save(name,self.L_itml)
# Input data transformed to the metric space by X*L.T
self.transformedTrainITML=copy(itml.transform(self.trainVectorsPCA))
self.transformedTestITML=copy(itml.transform(self.testVectorsPCA))
self.transformedAllITML=copy(itml.transform(self.allDataPCA))
# now we can simply calculate the eucledian distances on the above transformed dataset
#Visualizing the dataset by TSNE
projectedDigits = TSNE(random_state=randomState).fit_transform(self.transformedTrainITML)
plt.scatter(projectedDigits[:,0],projectedDigits[:,1],c=self.y_train)
plt.title('ITML Transformed Train set projected to 2 Dimensions by TSNE with k='+str(k)+' and num_constraints = '+str(num_constraints))
plt.savefig(pp,format='pdf')
self.pwdis=copy(pairwise_distances(self.transformedAllITML,metric='euclidean'))
self.D=np.zeros(self.pwdis.shape)
for i in range(0,self.pwdis.shape[0]):
l1=self.pwdis[i].tolist()
#print 'l1 is ',l1,'\n\n'
allnearestNeighbours=sorted(range(len(l1)),key=lambda i : l1[i])
#now set the all the weights except for k+1 to 0
self.pwdis[i,allnearestNeighbours[k:]]=0
self.D[i,i]=sum(self.pwdis[i])
print 'accuracy for ITML\n'
self.labelPropogation()
def constructSimilartyMatrixITML(self):
print 'Now doing itml'
counter = 1
ks = [
3, 5, 7, 10, 12, 15, 20, 22, 25, 27, 30, 33, 35, 37, 40, 43, 45,
47, 50, 53, 55, 57, 60, 65
]
constraints = [80, 100, 120, 150, 180, 200]
constraints = [100]
for k in ks:
for num_constraints in constraints:
itml = ITML()
self.y_train = self.y_train.reshape(-1, )
C = ITML.prepare_constraints(self.y_train,
self.trainVectorsPCA.shape[0],
num_constraints)
itml.fit(self.trainVectorsPCA, C, verbose=True)
self.L_itml = copy(itml.transformer())
name = 'itml/ITML transformer matrix with dataset shape ' + str(
self.trainVectorsPCA.shape) + ' and k=' + str(
k) + ' and num_constraints=' + str(num_constraints)
#print 'L itml shape is ',self.L_itml.shape
np.save(name, self.L_itml)
# Input data transformed to the metric space by X*L.T
self.transformedTrainITML = copy(
itml.transform(self.trainVectorsPCA))
self.transformedTestITML = copy(
itml.transform(self.testVectorsPCA))
self.transformedAllITML = copy(itml.transform(self.allDataPCA))
# now we can simply calculate the eucledian distances on the above transformed dataset
#Visualizing the dataset by TSNE
projectedDigits = TSNE(random_state=randomState).fit_transform(
self.transformedAllITML)
print 'projectedDigits is ', projectedDigits.shape
plt.figure()
plt.scatter(projectedDigits[:, 0],
projectedDigits[:, 1],
c=self.labels)
plt.title(
'ITML Transformed ALL set projected to 2 Dimensions by TSNE with'
+ str(k) + ' and num_constraints=' + str(num_constraints))
plt.savefig(pp, format='pdf')
#plt.show()
plt.close()
self.pwdis = copy(
pairwise_distances(self.transformedAllITML,
metric='euclidean'))
#sigmas=[1,2.5,2,2.5,3,3.5,4,4.5,5]
#for sigma in sigmas:
self.D = np.zeros(self.pwdis.shape)
for i in range(0, self.pwdis.shape[0]):
l1 = self.pwdis[i].tolist()
#print 'l1 is ',l1,'\n\n'
allnearestNeighbours = sorted(range(len(l1)),
key=lambda i: l1[i])
#now set the all the weights except for k+1 to 0
#since we exponentiated the distances with the minus sign we need to set the lowest weights to 0, so everything except for the last k go to 0
self.pwdis[i, allnearestNeighbours[k:]] = 0
self.D[i, i] = sum(self.pwdis[i])
print 'accuracy for ITML for k= ', k, ' and num_constraints=' + str(
num_constraints), '\n'
self.labelPropogation()
def fit(self, X, y):
num_constraints = NUM_CONSTRAINTS
constraints = ITML.prepare_constraints(y, len(X), num_constraints)
return super(ITML_sk, self).fit(X, constraints)
# 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),
(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),
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),
(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)]
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),
(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',
import numpy as np
from metric_learn import ITML
from sklearn.datasets import load_iris
from scipy.sparse import rand
x = rand(10, 10)
print 'S is ', x.todense()
x = x.todense()
mat1 = np.zeros(x.shape)
for i in range(0, mat1.shape[0]):
mat1[i, i] = 112.0
for j in range(0, mat1.shape[1]):
if i == j:
continue
mat1[i, j] = x[i, j]
print 'mat1 is ', mat1
y = np.ones((10, ))
y[5:] = 0
itml = ITML()
print 'X is ', mat1.shape, ' y is ', y.shape
num_constraints = 5
C = ITML.prepare_constraints(y, mat1.shape[0], num_constraints)
itml.fit(mat1, C, verbose=False)
xl = itml.transform(mat1)
print 'xl is ', xl
t0 = time()
pca = RandomizedPCA(n_components=n_components, whiten=True).fit(X_train)
print("done in %0.3fs" % (time() - t0))
eigenfaces = pca.components_.reshape((n_components, h, w))
print("Projecting the input data on the eigenfaces orthonormal basis")
t0 = time()
X_train_pca = pca.transform(X_train)
X_test_pca = pca.transform(X_test)
print("done in %0.3fs" % (time() - t0))
# Try LMNN here.
print("Trying ITML")
param_grid = {''}
itml = ITML(num_constraints=200)
X_tr = itml.fit(X_train_pca, y_train).transform(X_train_pca)
X_te = itml.transform(X_test_pca)
acc, y_pred = classifier.sk_nearest_neighbour(X_tr, y_train, X_te, y_test)
print("accuracy = %s",acc)
print(classification_report(y_test, y_pred, target_names=target_names))
print(confusion_matrix(y_test, y_pred, labels=range(n_classes)))
###############################################################################
# Train a SVM classification model
print("Fitting the classifier to the training set")
t0 = time()
param_grid = {'C': [1e3, 5e3, 1e4, 5e4, 1e5],
y_lims = (y_center - max_diff / 2 - margin,
y_center + max_diff / 2 + margin)
x_lims = (x_center - max_diff / 2 - margin,
x_center + max_diff / 2 + margin)
plt.figure()
for i, edge in enumerate(pairs):
plt.plot(edge[:, 0],
edge[:, 1],
c='green' if y_pairs[i] == 1 else 'red',
alpha=0.3)
plt.scatter(pairs[:, 0, 0], pairs[:, 0, 1], c='b')
plt.scatter(pairs[:, 1, 0], pairs[:, 1, 1], c='b')
plt.xlim(*x_lims)
plt.ylim(*y_lims)
plt.axis('equal')
plt.savefig(name)
plot_points(pairs, y_pairs, 'pairs_without_metric')
mmc = ITML()
mmc.fit(pairs, y_pairs)
X_e = mmc.transform(X)
pairs = X_e[c].copy()
plot_points(pairs, y_pairs, 'pairs_with_metric')
import numpy as np from metric_learn import ITML from sklearn.datasets import load_iris iris_data = load_iris() X = iris_data['data'] Y = iris_data['target'] print 'Y is ',Y.shape print 'X.shape is ',X.shape itml = ITML() num_constraints = 200 C = ITML.prepare_constraints(Y, X.shape[0], num_constraints) itml.fit(X, C, verbose=False) x2=itml.transform(X) print 'x2 is ',x2 l=itml.transformer() print '\n\n\nafter transforming is ',np.dot(X,l.T)
# 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(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),
import numpy as np from metric_learn import ITML from sklearn.datasets import load_iris iris_data = load_iris() X = iris_data['data'] Y = iris_data['target'] print 'Y is ', Y.shape print 'X.shape is ', X.shape itml = ITML() num_constraints = 200 C = ITML.prepare_constraints(Y, X.shape[0], num_constraints) itml.fit(X, C, verbose=False) x2 = itml.transform(X) print 'x2 is ', x2 l = itml.transformer() print '\n\n\nafter transforming is ', np.dot(X, l.T)
