def compare_true_templates(): docs = doc.get_docs_nested(get_data_dir(sys.argv[2])) #confirm = cluster.PerfectCONFIRM(docs) confirm = cluster.BestPerfectCONFIRM(docs, lr=0.05) confirm.cluster() analyzer = metric.KnownClusterAnalyzer(confirm) analyzer.print_all() analyzer.draw_centers() analyzer.clusters[0].center.push_away(analyzer.clusters[1].center) print "PUSHING APART!" print print analyzer = metric.KnownClusterAnalyzer(confirm) analyzer.draw_centers() analyzer.print_all() print print
def get_acc_v_measure(clusters): class Mock: pass m = Mock() m.get_clusters = lambda: clusters analyzer = metric.KnownClusterAnalyzer(m) acc = analyzer.accuracy() v = analyzer.v_measure() return acc, v
def print_cluster_analysis(clusters): class Mock: pass m = Mock() m.get_clusters = lambda: clusters analyzer = metric.KnownClusterAnalyzer(m) analyzer.print_general_info() analyzer.print_label_conf_mat() analyzer.print_label_cluster_mat() analyzer.print_metric_info()
def print_analysis(instances, clusters): class Mock: pass m = Mock() m.get_clusters = lambda: clusters m.get_docs = lambda: instances analyzer = metric.KnownClusterAnalyzer(m) analyzer.print_general_info() analyzer.print_histogram_info() analyzer.print_label_conf_mat() analyzer.print_label_cluster_mat() analyzer.print_label_info() analyzer.print_metric_info()
def main(args):
if(len(args) != 2):
print "Usage: mds.py clustering.pkl"
print " C is the cluster in clustering.pkl to display"
sys.exit(0)
path = args[1]
print "Loading"
clusters = clustering = utils.load_obj(path)
#map(lambda c: c.set_label(), clustering)
for i in [5]:
clusters = reclusterWithOPTICS(clusters, i)
_docs = reduce(lambda x,y: x+y, map(lambda c: c.members, clusters))
confirm = BaseCONFIRM(_docs)
confirm.clusters = clusters
print "Original Number of Clusters:", len(clustering)
print "Final Number of Clusters:", len(clusters)
'''print reps
imgs = []
for idx in reps:
if idx == 0:
imgs.append(clustering[i].center)
else:
idx = idx -1
imgs.append(clustering[i].members[idx])
display(imgs)'''
#print len(selectWithHac(clustering))
#print streamSelector(clustering)
#print entropy(clustering)
#print "Analyzing"
analyzer = metric.KnownClusterAnalyzer(confirm)
analyzer.print_all()
print "User Queries:", QueryCount
def double_cluster_known():
docs = doc.get_docs_nested(get_data_dir(sys.argv[2]))
epsilon = float(sys.argv[3])
organizer = cluster.TemplateSorter(docs)
organizer.go(epsilon)
organizer.prune_clusters()
clusters = organizer.get_clusters()
print "Initial Clustering Complete"
print "Reclustering..."
centers = map(lambda x: x.center, clusters)
organizer.go(epsilon,templates=centers)
organizer.prune_clusters()
clusters = organizer.get_clusters()
print
print
analyzer = metric.KnownClusterAnalyzer(clusters)
analyzer.draw_centers()
analyzer.print_all()