def RunKMeansShogun(q):
import numpy as np
from shogun.Distance import EuclideanDistance
from shogun.Features import RealFeatures
from shogun import Clustering
from shogun.Mathematics import Math_init_random
totalTimer = Timer()
if seed:
Math_init_random(seed.group(1))
try:
data = np.genfromtxt(self.dataset, delimiter=',')
dataFeat = RealFeatures(data.T)
distance = EuclideanDistance(dataFeat, dataFeat)
# Create the K-Means object and perform K-Means clustering.
with totalTimer:
model = Clustering.KMeans(int(clusters.group(1)),
distance)
model.set_max_iter(maxIterations)
model.train()
labels = model.apply().get_labels()
centers = model.get_cluster_centers()
except Exception as e:
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
def classifier_larank_modular(fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
C=0.9,
num_threads=1,
num_iter=5):
from shogun.Features import RealFeatures, Labels
from shogun.Kernel import GaussianKernel
from shogun.Classifier import LaRank
from shogun.Mathematics import Math_init_random
Math_init_random(17)
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
width = 2.1
kernel = GaussianKernel(feats_train, feats_train, width)
epsilon = 1e-5
labels = Labels(label_train_multiclass)
svm = LaRank(C, kernel, labels)
#svm.set_tau(1e-3)
svm.set_batch_mode(False)
#svm.io.enable_progress()
svm.set_epsilon(epsilon)
svm.train()
out = svm.apply(feats_train).get_labels()
predictions = svm.apply()
return predictions, svm, predictions.get_labels()
def run_clustering(data, k):
from shogun.Clustering import KMeans
from shogun.Mathematics import Math_init_random
Math_init_random(42)
fea = RealFeatures(data)
distance = EuclidianDistance(fea, fea)
kmeans = KMeans(k, distance)
print("Running clustering...")
kmeans.train()
return kmeans.get_cluster_centers()
def clustering_kmeans_modular(fm_train=traindat, k=3):
from shogun.Distance import EuclidianDistance
from shogun.Features import RealFeatures
from shogun.Clustering import KMeans
from shogun.Mathematics import Math_init_random
Math_init_random(17)
feats_train = RealFeatures(fm_train)
distance = EuclidianDistance(feats_train, feats_train)
kmeans = KMeans(k, distance)
kmeans.train()
out_centers = kmeans.get_cluster_centers()
kmeans.get_radiuses()
return out_centers, kmeans
def features_director_dot_modular(fm_train_real, fm_test_real,
label_train_twoclass, C, epsilon):
from shogun.Features import RealFeatures, SparseRealFeatures, BinaryLabels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC_DUAL
from shogun.Mathematics import Math_init_random
Math_init_random(17)
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = BinaryLabels(label_train_twoclass)
dfeats_train = NumpyFeatures(fm_train_real)
dfeats_test = NumpyFeatures(fm_test_real)
dlabels = BinaryLabels(label_train_twoclass)
print feats_train.get_computed_dot_feature_matrix()
print dfeats_train.get_computed_dot_feature_matrix()
svm = LibLinear(C, feats_train, labels)
svm.set_liblinear_solver_type(L2R_L2LOSS_SVC_DUAL)
svm.set_epsilon(epsilon)
svm.set_bias_enabled(True)
svm.train()
svm.set_features(feats_test)
svm.apply().get_labels()
predictions = svm.apply()
dfeats_train.__disown__()
dfeats_train.parallel.set_num_threads(1)
dsvm = LibLinear(C, dfeats_train, dlabels)
dsvm.set_liblinear_solver_type(L2R_L2LOSS_SVC_DUAL)
dsvm.set_epsilon(epsilon)
dsvm.set_bias_enabled(True)
dsvm.train()
dfeats_test.__disown__()
dfeats_test.parallel.set_num_threads(1)
dsvm.set_features(dfeats_test)
dsvm.apply().get_labels()
dpredictions = dsvm.apply()
return predictions, svm, predictions.get_labels()
def classifier_liblinear_modular(fm_train_real, fm_test_real,
label_train_twoclass, C, epsilon):
from shogun.Features import RealFeatures, SparseRealFeatures, Labels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC_DUAL
from shogun.Mathematics import Math_init_random
Math_init_random(17)
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = Labels(label_train_twoclass)
svm = LibLinear(C, feats_train, labels)
svm.set_liblinear_solver_type(L2R_L2LOSS_SVC_DUAL)
svm.set_epsilon(epsilon)
svm.set_bias_enabled(True)
svm.train()
svm.set_features(feats_test)
svm.apply().get_labels()
predictions = svm.apply()
return predictions, svm, predictions.get_labels()
def classifier_multiclassocas_modular(num_vec=10,
num_class=3,
distance=15,
width=2.1,
C=1,
epsilon=1e-5,
seed=1):
from shogun.Features import RealFeatures, MulticlassLabels
from shogun.Classifier import MulticlassOCAS
from shogun.Mathematics import Math_init_random
# reproducible results
random.seed(seed)
Math_init_random(seed)
# generate some training data where each class pair is linearly separable
label_train = array([mod(x, num_class) for x in range(num_vec)],
dtype="float64")
label_test = array([mod(x, num_class) for x in range(num_vec)],
dtype="float64")
fm_train = array(random.randn(num_class, num_vec))
fm_test = array(random.randn(num_class, num_vec))
for i in range(len(label_train)):
fm_train[label_train[i], i] += distance
fm_test[label_test[i], i] += distance
feats_train = RealFeatures(fm_train)
feats_test = RealFeatures(fm_test)
labels = MulticlassLabels(label_train)
classifier = MulticlassOCAS(C, feats_train, labels)
classifier.train()
out = classifier.apply(feats_test).get_labels()
#print label_test
#print out
return out, classifier
def classifier_larank_modular (num_vec,num_class,distance,C=0.9,num_threads=1,num_iter=5,seed=1): from shogun.Features import RealFeatures, MulticlassLabels from shogun.Kernel import GaussianKernel from shogun.Classifier import LaRank from shogun.Mathematics import Math_init_random # reproducible results Math_init_random(seed) random.seed(seed) # generate some training data where each class pair is linearly separable label_train=array([mod(x,num_class) for x in range(num_vec)],dtype="float64") label_test=array([mod(x,num_class) for x in range(num_vec)],dtype="float64") fm_train=array(random.randn(num_class,num_vec)) fm_test=array(random.randn(num_class,num_vec)) for i in range(len(label_train)): fm_train[label_train[i],i]+=distance fm_test[label_test[i],i]+=distance feats_train=RealFeatures(fm_train) feats_test=RealFeatures(fm_test) width=2.1 kernel=GaussianKernel(feats_train, feats_train, width) epsilon=1e-5 labels=MulticlassLabels(label_train) svm=LaRank(C, kernel, labels) #svm.set_tau(1e-3) svm.set_batch_mode(False) #svm.io.enable_progress() svm.set_epsilon(epsilon) svm.train() out=svm.apply(feats_test).get_labels() predictions = svm.apply() return predictions, svm, predictions.get_labels()