def evaluation_clustering(features=fea, ground_truth=gnd_raw, ncenters=10):
from shogun.Evaluation import ClusteringAccuracy, ClusteringMutualInformation
from shogun.Features import MulticlassLabels
from shogun.Mathematics import Math
# reproducable results
Math.init_random(1)
centroids = run_clustering(features, ncenters)
gnd_hat = assign_labels(features, centroids, ncenters)
gnd = MulticlassLabels(ground_truth)
AccuracyEval = ClusteringAccuracy()
AccuracyEval.best_map(gnd_hat, gnd)
accuracy = AccuracyEval.evaluate(gnd_hat, gnd)
#print(('Clustering accuracy = %.4f' % accuracy))
MIEval = ClusteringMutualInformation()
mutual_info = MIEval.evaluate(gnd_hat, gnd)
#print(('Clustering mutual information = %.4f' % mutual_info))
# TODO mutual information does not work with serialization
#return gnd, gnd_hat, accuracy, MIEval, mutual_info
return gnd, gnd_hat, accuracy
def evaluation_clustering (features=fea, ground_truth=gnd_raw, ncenters=10):
from shogun.Evaluation import ClusteringAccuracy, ClusteringMutualInformation
from shogun.Features import MulticlassLabels
from shogun.Mathematics import Math
# reproducable results
Math.init_random(1)
centroids = run_clustering(features, ncenters)
gnd_hat = assign_labels(features, centroids, ncenters)
gnd = MulticlassLabels(ground_truth)
AccuracyEval = ClusteringAccuracy()
AccuracyEval.best_map(gnd_hat, gnd)
accuracy = AccuracyEval.evaluate(gnd_hat, gnd)
#print(('Clustering accuracy = %.4f' % accuracy))
MIEval = ClusteringMutualInformation()
mutual_info = MIEval.evaluate(gnd_hat, gnd)
#print(('Clustering mutual information = %.4f' % mutual_info))
# TODO mutual information does not work with serialization
#return gnd, gnd_hat, accuracy, MIEval, mutual_info
return gnd, gnd_hat, accuracy
def evaluation_clustering_simple(n_data=100, sqrt_num_blobs=4, distance=5):
from shogun.Evaluation import ClusteringAccuracy, ClusteringMutualInformation
from shogun.Features import MulticlassLabels, GaussianBlobsDataGenerator
from shogun.Mathematics import Math
# reproducable results
Math.init_random(1)
# produce sone Gaussian blobs to cluster
ncenters = sqrt_num_blobs**2
stretch = 1
angle = 1
gen = GaussianBlobsDataGenerator(sqrt_num_blobs, distance, stretch, angle)
features = gen.get_streamed_features(n_data)
X = features.get_feature_matrix()
# compute approximate "ground truth" labels via taking the closest blob mean
coords = array(range(0, sqrt_num_blobs * distance, distance))
idx_0 = [abs(coords - x).argmin() for x in X[0]]
idx_1 = [abs(coords - x).argmin() for x in X[1]]
ground_truth = array(
[idx_0[i] * sqrt_num_blobs + idx_1[i] for i in range(n_data)],
dtype="float64")
#for label in unique(ground_truth):
# indices=ground_truth==label
# plot(X[0][indices], X[1][indices], 'o')
#show()
centroids = run_clustering(features, ncenters)
gnd_hat = assign_labels(features, centroids, ncenters)
gnd = MulticlassLabels(ground_truth)
AccuracyEval = ClusteringAccuracy()
AccuracyEval.best_map(gnd_hat, gnd)
accuracy = AccuracyEval.evaluate(gnd_hat, gnd)
# in this case we know that the clustering has to be very good
#print(('Clustering accuracy = %.4f' % accuracy))
assert (accuracy > 0.8)
MIEval = ClusteringMutualInformation()
mutual_info = MIEval.evaluate(gnd_hat, gnd)
#print(('Clustering mutual information = %.4f' % mutual_info))
# TODO add multiclass labels and MI once the serialization works
#return gnd, accuracy, mutual_info
return accuracy
def evaluation_clustering_simple (n_data=100, sqrt_num_blobs=4, distance=5):
from shogun.Evaluation import ClusteringAccuracy, ClusteringMutualInformation
from shogun.Features import MulticlassLabels, GaussianBlobsDataGenerator
from shogun.Mathematics import Math
# reproducable results
Math.init_random(1)
# produce sone Gaussian blobs to cluster
ncenters=sqrt_num_blobs**2
stretch=1
angle=1
gen=GaussianBlobsDataGenerator(sqrt_num_blobs, distance, stretch, angle)
features=gen.get_streamed_features(n_data)
X=features.get_feature_matrix()
# compute approximate "ground truth" labels via taking the closest blob mean
coords=array(range(0,sqrt_num_blobs*distance,distance))
idx_0=[abs(coords -x).argmin() for x in X[0]]
idx_1=[abs(coords -x).argmin() for x in X[1]]
ground_truth=array([idx_0[i]*sqrt_num_blobs + idx_1[i] for i in range(n_data)], dtype="float64")
#for label in unique(ground_truth):
# indices=ground_truth==label
# plot(X[0][indices], X[1][indices], 'o')
#show()
centroids = run_clustering(features, ncenters)
gnd_hat = assign_labels(features, centroids, ncenters)
gnd = MulticlassLabels(ground_truth)
AccuracyEval = ClusteringAccuracy()
AccuracyEval.best_map(gnd_hat, gnd)
accuracy = AccuracyEval.evaluate(gnd_hat, gnd)
# in this case we know that the clustering has to be very good
#print(('Clustering accuracy = %.4f' % accuracy))
assert(accuracy>0.8)
MIEval = ClusteringMutualInformation()
mutual_info = MIEval.evaluate(gnd_hat, gnd)
#print(('Clustering mutual information = %.4f' % mutual_info))
# TODO add multiclass labels and MI once the serialization works
#return gnd, accuracy, mutual_info
return accuracy
def evaluation_clustering (features=fea, ground_truth=gnd_raw, ncenters=10):
from shogun.Evaluation import ClusteringAccuracy, ClusteringMutualInformation
from shogun.Features import MulticlassLabels
centroids = run_clustering(features, ncenters)
gnd_hat = assign_labels(features, centroids, ncenters)
gnd = MulticlassLabels(ground_truth)
AccuracyEval = ClusteringAccuracy()
AccuracyEval.best_map(gnd_hat, gnd)
accuracy = AccuracyEval.evaluate(gnd_hat, gnd)
#print(('Clustering accuracy = %.4f' % accuracy))
MIEval = ClusteringMutualInformation()
mutual_info = MIEval.evaluate(gnd_hat, gnd)
#print(('Clustering mutual information = %.4f' % mutual_info))
return gnd, accuracy, mutual_info
def evaluation_clustering(features=fea, ground_truth=gnd_raw, ncenters=10):
from shogun.Evaluation import ClusteringAccuracy, ClusteringMutualInformation
from shogun.Features import MulticlassLabels
centroids = run_clustering(features, ncenters)
gnd_hat = assign_labels(features, centroids, ncenters)
gnd = MulticlassLabels(ground_truth)
AccuracyEval = ClusteringAccuracy()
AccuracyEval.best_map(gnd_hat, gnd)
accuracy = AccuracyEval.evaluate(gnd_hat, gnd)
#print(('Clustering accuracy = %.4f' % accuracy))
MIEval = ClusteringMutualInformation()
mutual_info = MIEval.evaluate(gnd_hat, gnd)
#print(('Clustering mutual information = %.4f' % mutual_info))
return gnd, accuracy, mutual_info
return kmeans.get_cluster_centers()
def assign_labels(data, centroids):
from shogun.Classifier import KNN
from numpy import arange
labels = Labels(arange(1.,11.))
fea = RealFeatures(data)
fea_centroids = RealFeatures(centroids)
distance = EuclidianDistance(fea_centroids, fea_centroids)
knn = KNN(1, distance, labels)
knn.train()
return knn.apply(fea)
if __name__ == '__main__':
(fea, gnd_raw) = prepare_data()
centroids = run_clustering(fea, 10)
gnd_hat = assign_labels(fea, centroids)
gnd = Labels(gnd_raw)
AccuracyEval = ClusteringAccuracy()
AccuracyEval.best_map(gnd_hat, gnd)
accuracy = AccuracyEval.evaluate(gnd_hat, gnd)
print(('Clustering accuracy = %.4f' % accuracy))
MIEval = ClusteringMutualInformation()
mutual_info = MIEval.evaluate(gnd_hat, gnd)
print(('Clustering mutual information = %.4f' % mutual_info))
def assign_labels(data, centroids):
from shogun.Classifier import KNN
from numpy import arange
labels = Labels(arange(1., 11.))
fea = RealFeatures(data)
fea_centroids = RealFeatures(centroids)
distance = EuclidianDistance(fea_centroids, fea_centroids)
knn = KNN(1, distance, labels)
knn.train()
return knn.apply(fea)
if __name__ == '__main__':
(fea, gnd_raw) = prepare_data()
centroids = run_clustering(fea, 10)
gnd_hat = assign_labels(fea, centroids)
gnd = Labels(gnd_raw)
AccuracyEval = ClusteringAccuracy()
AccuracyEval.best_map(gnd_hat, gnd)
accuracy = AccuracyEval.evaluate(gnd_hat, gnd)
print(('Clustering accuracy = %.4f' % accuracy))
MIEval = ClusteringMutualInformation()
mutual_info = MIEval.evaluate(gnd_hat, gnd)
print(('Clustering mutual information = %.4f' % mutual_info))
