def do_compute(reference_txt, pre_clustering_txt, groundtruth_npy):
# load reference clusters
reference = Clustering.load(reference_txt)
# load hypothesis clusters
hypothesis = Clustering.load(pre_clustering_txt)
# number of hypothesis clusters
nPreClusters = len(hypothesis.clusters)
preClusters = sorted(hypothesis.clusters)
# groundtruth[i, j] contains
# 1 if all elements in clusters i and j are in the same cluster
# 0 if elements in clusters i and j are not in the same cluster
# -1 if either cluster i or j is not pure
groundtruth = np.empty((nPreClusters, nPreClusters), dtype=int)
# clustersRef[c] contains reference cluster for pure hypothesis cluster c
# in case c is not pure, clustersRef[c] is None
clustersRef = {}
for c in preClusters:
r = set([reference[i] for i in hypothesis.clusters[c]])
if len(r) == 1:
clustersRef[c] = r.pop()
else:
clustersRef[c] = None
for k, ci in enumerate(preClusters):
if clustersRef[ci] is None:
groundtruth[ci, :] = -1
groundtruth[:, ci] = -1
continue
for cj in preClusters[k:]:
if clustersRef[cj] is not None:
groundtruth[ci, cj] = clustersRef[ci] == clustersRef[cj]
groundtruth[cj, ci] = groundtruth[ci, cj]
# save groundtruth matrix
np.save(groundtruth_npy, groundtruth)
def do_it(image_txt, features_npy, clustering_txt, output_npy):
# load image list
with open(image_txt, 'r') as f:
images = [int(line.strip()) for line in f.readlines()]
image2index = {image: index for index, image in enumerate(images)}
# load hypothesis clusters
clustering = Clustering.load(clustering_txt)
clusters = sorted(clustering.clusters)
# load features
features = np.load(features_npy)
# L2 normalization (for later dot product)
features = (features.T / np.sqrt(np.sum((features**2), axis=1))).T
# find centroid image for every cluster
centroid = {}
for c, cluster in enumerate(clusters):
# list of images in current cluster
_images = clustering.clusters[cluster]
# corresponding indices in features matrix
_indices = [image2index[image] for image in _images]
# compute distance matrix between
# all images of current cluster
_features = features[_indices, :]
_distance = 1. - np.dot(_features, _features.T)
# find centroid image
i = np.argmin(np.sum(_distance, axis=0))
centroid[cluster] = _images[i]
print 'image %s is centroid of cluster %s' % (centroid[cluster],
cluster)
# centroid indices in features matrix
_indices = [image2index[centroid[cluster]] for cluster in clusters]
# compute distance matrix between all centroids
_features = features[_indices, :]
_distance = 1. - np.dot(_features, _features.T)
# save distance matrix
with open(output_npy, 'wb') as f:
np.save(f, _distance)
def do_it(image_txt, features_npy, clustering_txt, output_npy):
# load image list
with open(image_txt, 'r') as f:
images = [int(line.strip()) for line in f.readlines()]
image2index = {image: index for index, image in enumerate(images)}
# load hypothesis clusters
clustering = Clustering.load(clustering_txt)
clusters = sorted(clustering.clusters)
# load features
features = np.load(features_npy)
# L2 normalization (for later dot product)
features = (features.T / np.sqrt(np.sum((features ** 2), axis=1))).T
# find centroid image for every cluster
centroid = {}
for c, cluster in enumerate(clusters):
# list of images in current cluster
_images = clustering.clusters[cluster]
# corresponding indices in features matrix
_indices = [image2index[image] for image in _images]
# compute distance matrix between
# all images of current cluster
_features = features[_indices, :]
_distance = 1. - np.dot(_features, _features.T)
# find centroid image
i = np.argmin(np.sum(_distance, axis=0))
centroid[cluster] = _images[i]
print 'image %s is centroid of cluster %s' % (centroid[cluster], cluster)
# centroid indices in features matrix
_indices = [image2index[centroid[cluster]] for cluster in clusters]
# compute distance matrix between all centroids
_features = features[_indices, :]
_distance = 1. - np.dot(_features, _features.T)
# save distance matrix
with open(output_npy, 'wb') as f:
np.save(f, _distance)
for k, v in cluster.iteritems():
for photo in v:
file.write("%d\t%d\n" % (photo, k))
file.close()
print "Loading json into memory..."
dictionary = readjson(
"/vol/corpora4/mediaeval/2014/SED_2014_Dev_Metadata.json")
print "...Done !"
clusterU = clusterUser(dictionary, fileID)
clusterD = clusterDate(dictionary, fileID, clusterU)
print_result_file(clusterD, fileOUT)
reference = Clustering.load(fileREF)
hypothesis = Clustering.load(fileOUT)
images = []
for c in clusterD.values():
for i in range(0, len(c)):
images.append(c[i])
h = homogeneity(reference, hypothesis, images)
print h
c = completeness(reference, hypothesis, images)
print c
file = open(filename, "w")
for k, v in cluster.iteritems():
for photo in v:
file.write("%d\t%d\n" % (photo, k))
file.close()
print "Loading json into memory..."
dictionary = readjson("/vol/corpora4/mediaeval/2014/SED_2014_Dev_Metadata.json")
print "...Done !"
clusterU = clusterUser(dictionary, fileID)
clusterD = clusterDate(dictionary, fileID, clusterU)
print_result_file(clusterD, fileOUT)
reference = Clustering.load(fileREF)
hypothesis = Clustering.load(fileOUT)
images = []
for c in clusterD.values():
for i in range (0, len(c)):
images.append(c[i])
h = homogeneity(reference, hypothesis, images)
print h
c = completeness(reference, hypothesis, images)
print c
