#print nonEmpty,index
agglomerative.__readin_subject__(subject,read_in_gold=True)#,users_to_skip=["caitlin.black"])
dkmeans.__readin_subject__(subject,read_in_gold=True)
numClusters,time_to_cluster = agglomerative.__cluster_subject__(subject)
if numClusters == 0:
continue
print nonEmpty
nonEmpty += 1
if nonEmpty == 30:
break
accuracy1 = agglomerative.__accuracy__(subject)
X1.append(numClusters)
Y1.append(time_to_cluster)
Z1.append(accuracy1)
numClusters2,time_to_cluster = dkmeans.__cluster_subject__(subject, clusterAlg2,fix_distinct_clusters=True)
accuracy2 = dkmeans.__accuracy__(subject)
X2.append(numClusters2)
Y2.append(time_to_cluster)
Z2.append(accuracy2)
#dkmeans.__outliers__(subject)
print accuracy1,accuracy2,dkmeans.__num_gold_clusters__(subject)
#print numMarkings,numMarkings2
#print nonEmpty,index
agglomerative.__readin_subject__(
subject, read_in_gold=True) #,users_to_skip=["caitlin.black"])
dkmeans.__readin_subject__(subject, read_in_gold=True)
numClusters, time_to_cluster = agglomerative.__cluster_subject__(subject)
if numClusters == 0:
continue
print nonEmpty
nonEmpty += 1
if nonEmpty == 20:
break
accuracy1 = agglomerative.__accuracy__(subject)
X1.append(numClusters)
Y1.append(time_to_cluster)
Z1.append(accuracy1)
numClusters2, time_to_cluster = dkmeans.__cluster_subject__(
subject, clusterAlg2, fix_distinct_clusters=True)
accuracy2 = dkmeans.__accuracy__(subject)
X2.append(numClusters2)
Y2.append(time_to_cluster)
Z2.append(accuracy2)
#dkmeans.__outliers__(subject)
print accuracy1, accuracy2, dkmeans.__num_gold_clusters__(subject)
#print nonEmpty,index
penguin.__readin_subject__(
subject, read_in_gold=True) #,users_to_skip=["caitlin.black"])
numClusters, time_to_cluster = penguin.__cluster_subject__(
subject, clusterAlg)
if numClusters == 0:
continue
print nonEmpty
nonEmpty += 1
if nonEmpty == 50:
break
accuracy1 = penguin.__accuracy__(subject)
X1.append(numClusters)
Y1.append(time_to_cluster)
Z1.append(accuracy1)
numClusters2, time_to_cluster = penguin.__cluster_subject__(
subject, clusterAlg2, fix_distinct_clusters=True)
accuracy2 = penguin.__accuracy__(subject)
X2.append(numClusters2)
Y2.append(time_to_cluster)
Z2.append(accuracy2)
print accuracy1, accuracy2, penguin.__num_gold_clusters__(subject)
#print numMarkings,numMarkings2
# subject = "APZ000173v"
subject = subject_ids[index]
# print nonEmpty,index
penguin.__readin_subject__(subject, read_in_gold=True) # ,users_to_skip=["caitlin.black"])
numClusters, time_to_cluster = penguin.__cluster_subject__(subject, clusterAlg)
if numClusters == 0:
continue
print nonEmpty
nonEmpty += 1
if nonEmpty == 50:
break
accuracy1 = penguin.__accuracy__(subject)
X1.append(numClusters)
Y1.append(time_to_cluster)
Z1.append(accuracy1)
numClusters2, time_to_cluster = penguin.__cluster_subject__(subject, clusterAlg2, fix_distinct_clusters=True)
accuracy2 = penguin.__accuracy__(subject)
X2.append(numClusters2)
Y2.append(time_to_cluster)
Z2.append(accuracy2)
print accuracy1, accuracy2, penguin.__num_gold_clusters__(subject)
# print numMarkings,numMarkings2
print len([z1 for (z1, z2) in zip(Z1, Z2) if z1 > z2]) / float(len(Z1))
