How to Do It

Experiment – 5

AIM: study and analysis of “Clustering Task” “K-Means Clustering Algorithm”

Database:

@relation training_campaign

@attribute age {young,middle,old}
@attribute income {low,nominal,high}
@attribute train {yes,no}

@data
young,low,yes
young,nominal,yes
young,high,yes
middle,low,yes
middle,nominal,yes
middle,high,no
old,low,yes
old,nominal,no
old,high,no

Clusterer output:

=== Run information ===

Scheme:       weka.clusterers.SimpleKMeans -N 2 -S 10
Relation:     training_campaign
Instances:     9
Attributes:   3
              age
              income
              train
Test mode:     evaluate on training data

=== Model and evaluation on training set ===

kMeans
======

Number of iterations: 2
Within cluster sum of squared errors: 12.0

Cluster centroids:

Cluster 0
Mean/Mode:   young low yes
Std Devs:   N/A   N/A   N/A  
Cluster 1
Mean/Mode:   middle low yes
Std Devs:   N/A   N/A   N/A  

Clustered Instances

0       6 ( 67%)
1       3 ( 33%)

Clustered Database:

@relation training_campaign_clustered

@attribute Instance_number numeric
@attribute age {young,middle,old}
@attribute income {low,nominal,high}
@attribute train {yes,no}
@attribute Cluster {cluster0,cluster1}

@data
0,young,low,yes,cluster0
1,young,nominal,yes,cluster0
2,young,high,yes,cluster0
3,middle,low,yes,cluster1
4,middle,nominal,yes,cluster1
5,middle,high,no,cluster1
6,old,low,yes,cluster0
7,old,nominal,no,cluster0
8,old,high,no,cluster0

Clusterer output for Clustered Database:

=== Run information ===

Scheme:       weka.clusterers.SimpleKMeans -N 2 -S 10
Relation:     training_campaign_clustered
Instances:     9
Attributes:   5
              Instance_number
              age
              income
              train
              Cluster
Test mode:     evaluate on training data

=== Model and evaluation on training set ===

kMeans
======

Number of iterations: 2
Within cluster...