The k-means working methodology is illustrated in the following example in which 12 instances are considered with their X and Y values. The task is to determine the optimal clusters out of the data.
|
Instance |
X |
Y |
|
1 |
7 |
8 |
|
2 |
2 |
4 |
|
3 |
6 |
4 |
|
4 |
3 |
2 |
|
5 |
6 |
5 |
|
6 |
5 |
7 |
|
7 |
3 |
3 |
|
8 |
1 |
4 |
|
9 |
5 |
4 |
|
10 |
7 |
7 |
|
11 |
7 |
6 |
|
12 |
2 |
1 |
After plotting the data points on a 2D chart, we can see that roughly two clusters are possible, where below-left is the first cluster and the top-right is another cluster, but in many practical cases there would be so many variables (or dimensions) that, we cannot simply visualize them. Hence, we need ...
