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 RunAllKnnShogun(q):
totalTimer = Timer()
# Load input dataset.
# If the dataset contains two files then the second file is the query
# file.
try:
Log.Info("Loading dataset", self.verbose)
if len(self.dataset) == 2:
referenceData = np.genfromtxt(self.dataset[0],
delimiter=',')
queryData = np.genfromtxt(self.dataset[1], delimiter=',')
queryFeat = RealFeatures(queryFeat.T)
else:
referenceData = np.genfromtxt(self.dataset, delimiter=',')
# Labels are the last row of the dataset.
labels = MulticlassLabels(
referenceData[:, (referenceData.shape[1] - 1)])
referenceData = referenceData[:, :-1]
with totalTimer:
# Get all the parameters.
k = re.search("-k (\d+)", options)
if not k:
Log.Fatal(
"Required option: Number of furthest neighbors to find."
)
q.put(-1)
return -1
else:
k = int(k.group(1))
if (k < 1 or k > referenceData.shape[0]):
Log.Fatal("Invalid k: " + k.group(1) +
"; must be greater than 0" +
" and less or equal than " +
str(referenceData.shape[0]))
q.put(-1)
return -1
referenceFeat = RealFeatures(referenceData.T)
distance = EuclideanDistance(referenceFeat, referenceFeat)
# Perform All K-Nearest-Neighbors.
model = SKNN(k, distance, labels)
model.train()
if len(self.dataset) == 2:
out = model.apply(queryFeat).get_labels()
else:
out = model.apply(referenceFeat).get_labels()
except Exception as e:
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
def load_train(self):
ims, labels = self.load( self.test_images, self.test_labels)
self.test_images = ims
self.test_labels = labels
labels_numbers = MulticlassLabels(self.test_labels)
feats = RealFeatures(self.test_images.T)
dist = EuclideanDistance()
self.knn = KNN(self.k, dist, labels_numbers)
self.knn.train(feats)
def knn(train_features, train_labels, test_features, test_labels, k=1): from modshogun import KNN, MulticlassAccuracy, EuclideanDistance distance = EuclideanDistance(train_features, train_features) knn = KNN(k, distance, train_labels) knn.train() train_output = knn.apply() test_output = knn.apply(test_features) evaluator = MulticlassAccuracy() print 'KNN training error is %.4f' % ((1-evaluator.evaluate(train_output, train_labels))*100) print 'KNN test error is %.4f' % ((1-evaluator.evaluate(test_output, test_labels))*100)
def RunAllKnnShogun(q):
totalTimer = Timer()
# Load input dataset.
# If the dataset contains two files then the second file is the query
# file.
try:
Log.Info("Loading dataset", self.verbose)
if len(self.dataset) == 2:
referenceData = np.genfromtxt(self.dataset[0], delimiter=',')
queryData = np.genfromtxt(self.dataset[1], delimiter=',')
queryFeat = RealFeatures(queryFeat.T)
else:
referenceData = np.genfromtxt(self.dataset, delimiter=',')
# Labels are the last row of the dataset.
labels = MulticlassLabels(referenceData[:, (referenceData.shape[1] - 1)])
referenceData = referenceData[:,:-1]
with totalTimer:
# Get all the parameters.
k = re.search("-k (\d+)", options)
if not k:
Log.Fatal("Required option: Number of furthest neighbors to find.")
q.put(-1)
return -1
else:
k = int(k.group(1))
if (k < 1 or k > referenceData.shape[0]):
Log.Fatal("Invalid k: " + k.group(1) + "; must be greater than 0"
+ " and less or equal than " + str(referenceData.shape[0]))
q.put(-1)
return -1
referenceFeat = RealFeatures(referenceData.T)
distance = EuclideanDistance(referenceFeat, referenceFeat)
# Perform All K-Nearest-Neighbors.
model = SKNN(k, distance, labels)
model.train()
if len(self.dataset) == 2:
out = model.apply(queryFeat).get_labels()
else:
out = model.apply(referenceFeat).get_labels()
except Exception as e:
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
class Number_recognition:
def __init__(self, test_images, test_labels, k):
self.test_images = test_images;
self.test_labels = test_labels;
self.k = k;
def load(self, path_img, path_lbl):
with open(path_lbl, 'rb') as file:
magic, size = struct.unpack(">II", file.read(8))
if magic != 2049:
raise ValueError('Magic number mismatch, expected 2049,'
'got %d' % magic)
labels = array("B", file.read())
labels_result = np.zeros(shape=(size))
for i in xrange(size):
labels_result[i] = labels[i]
with open(path_img, 'rb') as file:
magic, size, rows, cols = struct.unpack(">IIII", file.read(16))
print "rows: " + str(rows) + " cols: " + str(cols)
if magic != 2051:
raise ValueError('Magic number mismatch, expected 2051,'
'got %d' % magic)
image_data = array("B", file.read())
images = np.zeros(shape=(size,rows*cols))
for i in xrange(size):
images[i][:] = image_data[i*rows*cols : (i+1)*rows*cols]
return images, labels_result
def load_train(self):
ims, labels = self.load( self.test_images, self.test_labels)
self.test_images = ims
self.test_labels = labels
labels_numbers = MulticlassLabels(self.test_labels)
feats = RealFeatures(self.test_images.T)
dist = EuclideanDistance()
self.knn = KNN(self.k, dist, labels_numbers)
self.knn.train(feats)
def predict(self, image):
feats_test = RealFeatures(image. T)
pred = self.knn.apply_multiclass(feats_test)
return pred[:]
def BuildModel(self, data, labels, options):
# Get all the parameters.
n = re.search("-n (\d+)", options)
self.n_neighbors = 5 if not n else int(n.group(1))
distance = EuclideanDistance(data, data)
from modshogun import KNN_KDTREE
knc = KNN(self.n_neighbors, distance, labels, KNN_KDTREE)
knc.set_leaf_size(30)
knc.train()
return knc
def assign_labels(data, centroids, ncenters):
from modshogun import EuclideanDistance
from modshogun import RealFeatures, MulticlassLabels
from modshogun import KNN
from numpy import arange
labels = MulticlassLabels(arange(0., ncenters))
fea = RealFeatures(data)
fea_centroids = RealFeatures(centroids)
distance = EuclideanDistance(fea_centroids, fea_centroids)
knn = KNN(1, distance, labels)
knn.train()
return knn.apply(fea)
def assign_labels(data, centroids, ncenters): from modshogun import EuclideanDistance from modshogun import RealFeatures, MulticlassLabels from modshogun import KNN from numpy import arange labels = MulticlassLabels(arange(0.,ncenters)) fea = RealFeatures(data) fea_centroids = RealFeatures(centroids) distance = EuclideanDistance(fea_centroids, fea_centroids) knn = KNN(1, distance, labels) knn.train() return knn.apply(fea)
def knn_classify(traindat, testdat, k=3):
from modshogun import KNN, MulticlassAccuracy, EuclideanDistance
train_features, train_labels = traindat.features, traindat.labels
distance = EuclideanDistance(train_features, train_features)
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 knn_classify(traindat, testdat, k=3): from modshogun import KNN, MulticlassAccuracy, EuclideanDistance train_features, train_labels = traindat.features, traindat.labels distance = EuclideanDistance(train_features, train_features) 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 BuildModel(self, data, labels, options):
# Get all the parameters.
if "k" in options:
n_neighbors = int(options.pop("k"))
else:
Log.Fatal("Required parameter 'k' not specified!")
raise Exception("missing parameter")
if len(options) > 0:
Log.Fatal("Unknown parameters: " + str(options))
raise Exception("unknown parameters")
distance = EuclideanDistance(data, data)
knc = KNN(self.n_neighbors, distance, labels, KNN_KDTREE)
knc.train()
return knc
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 classifier_knn_modular(train_fname=traindat,
test_fname=testdat,
label_train_fname=label_traindat,
k=3):
from modshogun import RealFeatures, MulticlassLabels, KNN, EuclideanDistance, CSVFile
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
distance = EuclideanDistance(feats_train, feats_train)
labels = MulticlassLabels(CSVFile(label_train_fname))
knn = KNN(k, distance, labels)
knn_train = knn.train()
output = knn.apply(feats_test).get_labels()
multiple_k = knn.classify_for_multiple_k()
return knn, knn_train, output, multiple_k
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_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 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 KNNAccuracy(distance, data, k, flag):
transformedData = np.dot(data[0], distance.T)
feat = RealFeatures(transformedData.T)
labels = MulticlassLabels(data[1].astype(np.float64))
dist = EuclideanDistance(feat, feat)
knn = KNN(k + 1, dist, labels)
knn.train(feat)
# Get nearest neighbors.
nn = knn.nearest_neighbors()
nn = np.delete(nn, 0, 0)
# Compute unique labels.
uniqueLabels = np.unique(labels)
# Keep count correct predictions.
count = 0
# Normalize labels
for i in range(data[0].shape[0]):
for j in range(len(uniqueLabels)):
if (labels[i] == uniqueLabels[j]):
labels[i] = j
break
for i in range(nn.shape[1]):
mapLabels = [0 for x in range(len(uniqueLabels))]
for j in range(nn.shape[0]):
if (flag):
distPoints = np.linalg.norm(data[0][nn[j][i], :] -
data[0][i, :])
# Add constant factor of 1 incase two points overlap
mapLabels[int(labels[nn[j, i]])] += 1 / (distPoints + 1)**2
else:
# Subtract a variable factor to avoid draw condition without
# affecting actual result.
mapLabels[int(labels[nn[j, i]])] += 1 - j * 1e-8
maxInd = np.argmax(mapLabels)
if (maxInd == labels[i]):
count += 1
accuracy = (count / nn.shape[1]) * 100
return accuracy
def run_knn(Xtrain,Ytrain,Xtest,Ytest):
prod_features = RealFeatures(Xtrain)
prod_labels = MulticlassLabels(Ytrain)
test_features = RealFeatures(Xtest)
test_labels = MulticlassLabels(Ytest)
if os.path.exists(".lmnn_model30000_5_reg05_cor20"):
print "Using LMNN distance"
lmnn = LMNN()
sf = SerializableAsciiFile(".lmnn_model30000_5_reg05_cor20", 'r')
lmnn.load_serializable(sf)
diagonal = np.diag(lmnn.get_linear_transform())
#print('%d out of %d elements are non-zero.' % (np.sum(diagonal != 0), diagonal.size))
#diagonal = lmnn.get_linear_transform()
np.set_printoptions(precision=1,threshold=1e10,linewidth=500)
#lmnn.set_diagonal(True)
dist = lmnn.get_distance()
else:
dist = EuclideanDistance()
# classifier
knn = KNN(K, dist, prod_labels)
#knn.set_use_covertree(True)
parallel = knn.get_global_parallel()
parallel.set_num_threads(4)
knn.set_global_parallel(parallel)
knn.train(prod_features)
print "Classifying test set..."
pred = knn.apply_multiclass(test_features)
print "Accuracy = %2.2f%%" % (100*np.mean(pred == Ytest))
cm = build_confusion_matrix(Ytest, pred, NCLASSES)
#save_confusion_matrix(cm)
#cm = load_confusion_matrix()
print "Confusion matrix: "
print cm
#plot_confusion_matrix(cm)
#results = predict_class_prob(pred, cm)
#nn = build_neighbours_matrix(knn, prod_labels)
#results = predict_class_from_neighbours(nn)
#print "Log loss: " + str(calculate_log_loss(results, Ytest))
#print_prediction_output(results)
return cm
def BuildModel(self, data, labels, options):
# Get all the parameters.
n = re.search("-n (\d+)", options)
self.n_neighbors = 5 if not n else int(n.group(1))
distance = EuclidianDistance(data, data)
knc = KNN(self.n_neighbors, distance, labels)
knc.train()
# Create and train the classifier.
knc = LibSvm(self.C, self.kernel, labels)
knc.train()
return knc
def knn(train_features, train_labels, test_features, test_labels, k=1):
from modshogun import KNN, MulticlassAccuracy, EuclideanDistance
distance = EuclideanDistance(train_features, train_features)
knn = KNN(k, distance, train_labels)
knn.train()
train_output = knn.apply()
test_output = knn.apply(test_features)
evaluator = MulticlassAccuracy()
print 'KNN training error is %.4f' % (
(1 - evaluator.evaluate(train_output, train_labels)) * 100)
print 'KNN test error is %.4f' % (
(1 - evaluator.evaluate(test_output, test_labels)) * 100)
def BuildModel(self, data, labels, options):
# Get all the parameters.
n = re.search("-n (\d+)", options)
self.n_neighbors = 5 if not n else int(n.group(1))
distance = EuclideanDistance(data, data)
from modshogun import KNN_KDTREE
knc = KNN(self.n_neighbors, distance, labels, KNN_KDTREE)
knc.set_leaf_size(30)
knc.train()
return knc
def BuildModel(self, data, labels, options):
# Get all the parameters.
n = re.search("-n (\d+)", options)
self.n_neighbors = 5 if not n else int(n.group(1))
distance = EuclidianDistance(data, data)
knc = KNN(self.n_neighbors, distance, labels)
knc.train()
# Create and train the classifier.
knc = LibSvm(self.C, self.kernel, labels)
knc.train()
return knc
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_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)
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()
knn.set_distance(lmnn.get_distance())
plot_data(x, y, axarr[1])
plot_neighborhood_graph(x, knn.nearest_neighbors(), axarr[1])
def evaluate(labels,
feats,
params={
'n_neighbors': 2,
'use_cover_tree': 'True',
'dist': 'Manhattan'
},
Nsplit=2):
"""
Run Cross-validation to evaluate the KNN.
Parameters
----------
labels: 2d array
Data set labels.
feats: array
Data set feats.
params: dictionary
Search scope parameters.
Nsplit: int, default = 2
The n for n-fold cross validation.
all_ks: range of int, default = range(1, 21)
Numbers of neighbors.
"""
k = params.get('n_neighbors')
use_cover_tree = params.get('use_cover_tree') == 'True'
if params.get('dist' == 'Euclidean'):
func_dist = EuclideanDistance
else:
func_dist = ManhattanMetric
split = CrossValidationSplitting(labels, Nsplit)
split.build_subsets()
accuracy = np.zeros(Nsplit)
acc_train = np.zeros(accuracy.shape)
time_test = np.zeros(accuracy.shape)
for i in range(Nsplit):
idx_train = split.generate_subset_inverse(i)
idx_test = split.generate_subset_indices(i)
feats.add_subset(idx_train)
labels.add_subset(idx_train)
dist = func_dist(feats, feats)
knn = KNN(k, dist, labels)
knn.set_store_model_features(True)
if use_cover_tree:
knn.set_knn_solver_type(KNN_COVER_TREE)
else:
knn.set_knn_solver_type(KNN_BRUTE)
knn.train()
evaluator = MulticlassAccuracy()
pred = knn.apply_multiclass()
acc_train[i] = evaluator.evaluate(pred, labels)
feats.remove_subset()
labels.remove_subset()
feats.add_subset(idx_test)
labels.add_subset(idx_test)
t_start = time.clock()
pred = knn.apply_multiclass(feats)
time_test[i] = (time.clock() - t_start) / labels.get_num_labels()
accuracy[i] = evaluator.evaluate(pred, labels)
feats.remove_subset()
labels.remove_subset()
print accuracy.mean()
return accuracy
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()
knn.set_distance(lmnn.get_distance())
plot_data(x, y, axarr[1])
plot_neighborhood_graph(x, knn.nearest_neighbors(), axarr[1])
from modshogun import EuclideanDistance, KNN, MulticlassLabels, CSVFile, RealFeatures
#![begin]
#![load_data]
trainf = CSVFile("../data/fm_train_real.dat")
feats_train = RealFeatures(trainf)
testf = CSVFile("../data/fm_test_real.dat")
feats_test = RealFeatures(testf)
train_labels = CSVFile("../data/label_train_multiclass.dat")
labels = MulticlassLabels(train_labels)
#![load_data]
#![choose_distance]
distance = EuclideanDistance(feats_train, feats_test)
#![choose_distance]
#![create_instance]
knn = KNN(3, distance, labels)
#![create_instance]
#![train_and_apply]
knn.train()
test_labels = knn.apply(feats_test)
output = test_labels.get_values()
print output
#![train_and_apply]
#![end]
# load LMNN
if os.path.exists(".lmnn_model30000_5_reg05_cor20"):
sf = SerializableAsciiFile(".lmnn_model30000_5_reg05_cor20", 'r')
lmnn = LMNN()
lmnn.load_serializable(sf)
diagonal = np.diag(lmnn.get_linear_transform())
print('%d out of %d elements are non-zero.' % (np.sum(diagonal != 0), diagonal.size))
#print diagonal
dist = lmnn.get_distance()
else:
dist = EuclideanDistance()
cm = load_confusion_matrix()
print cm
# classifier
knn = KNN(k, dist, prod_labels)
parallel = knn.get_global_parallel()
parallel.set_num_threads(4)
knn.set_global_parallel(parallel)
knn.train(prod_features)
print "Classifying test set..."
pred = knn.apply_multiclass(test_features)
results = predict_class_prob(pred, cm)
print_prediction_output(results)