Python PenguinAggregation.__num_gold_clusters__ Exemples

Exemple #1

Fichier : clusterCompare2.py Projet : JiaminXuan/aggregation

        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 len([z1 for (z1,z2) in zip(Z1,Z2) if z1 > z2])/float(len(Z1))
print len([z1 for (z1,z2) in zip(Z1,Z2) if z1 < z2])/float(len(Z1))
print len([z1 for (z1,z2) in zip(Z1,Z2) if z1 == z2])/float(len(Z1))

plt.plot(Z2,Z1,'.',color="black")
plt.xlabel("Number of Clusters Found by Divisive K-Means")
plt.ylabel("Number of Clusters Found by Agglomerative Clustering")
plt.plot([0,max(max(Z1),max(Z2))+10],[0,max(max(Z1),max(Z2))+10],"--",color="black")
plt.xlim((0,max(max(Z1),max(Z2))+10))
plt.ylim((0,max(max(Z1),max(Z2))+10))
plt.show()

Exemple #2

Fichier : clusterCompare2.py Projet : lelou6666/aggregation

    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 len([z1 for (z1, z2) in zip(Z1, Z2) if z1 > z2]) / float(len(Z1))
print len([z1 for (z1, z2) in zip(Z1, Z2) if z1 < z2]) / float(len(Z1))
print len([z1 for (z1, z2) in zip(Z1, Z2) if z1 == z2]) / float(len(Z1))

plt.plot(Z2, Z1, '.', color="black")
plt.xlabel("Number of Clusters Found by Divisive K-Means")
plt.ylabel("Number of Clusters Found by Agglomerative Clustering")
plt.plot([0, max(max(Z1), max(Z2)) + 10], [0, max(max(Z1), max(Z2)) + 10],
         "--",
         color="black")
plt.xlim((0, max(max(Z1), max(Z2)) + 10))
plt.ylim((0, max(max(Z1), max(Z2)) + 10))
plt.show()

Exemple #3

Fichier : clusterCompare.py Projet : lelou6666/aggregation

    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))
print len([z1 for (z1, z2) in zip(Z1, Z2) if z1 < z2]) / float(len(Z1))
print len([z1 for (z1, z2) in zip(Z1, Z2) if z1 == z2]) / float(len(Z1))

plt.plot(Z2, Z1, '.', color="black")
plt.xlabel("Number of Clusters Found by Divisive K-Means")
plt.ylabel("Number of Clusters Found by Agglomerative Clustering")
plt.plot([0, max(max(Z1), max(Z2)) + 10], [0, max(max(Z1), max(Z2)) + 10],
         "--",
         color="black")
plt.xlim((0, max(max(Z1), max(Z2)) + 10))
plt.ylim((0, max(max(Z1), max(Z2)) + 10))
plt.show()

Exemple #4

Fichier : clusterCompare.py Projet : alexbfree/aggregation

    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))
print len([z1 for (z1, z2) in zip(Z1, Z2) if z1 < z2]) / float(len(Z1))
print len([z1 for (z1, z2) in zip(Z1, Z2) if z1 == z2]) / float(len(Z1))

plt.plot(Z2, Z1, ".", color="black")
plt.xlabel("Number of Clusters Found by Divisive K-Means")
plt.ylabel("Number of Clusters Found by Agglomerative Clustering")
plt.plot([0, max(max(Z1), max(Z2)) + 10], [0, max(max(Z1), max(Z2)) + 10], "--", color="black")
plt.xlim((0, max(max(Z1), max(Z2)) + 10))
plt.ylim((0, max(max(Z1), max(Z2)) + 10))
plt.show()
#
# plt.plot(X1,Y1,"+",color="black",label="Agglomerative")