K-means clustering Algorithm for manually finding from observation:
Step 1: Take mean value
Step 2: Find nearest number of mean and put in cluster
Step 3: Repeat one and two until we get same mean
K={2,3,4,10,11,12,20,25,30}
k=2 [it means we have to create 2 clusters]
iter1:
m1=4 m2=12
k1={2,3,4} [according to nearest distance of 4]
so mean m1=3
k2={10,11,12,20,25,30}
m2=108/6=18
iter2:
k1={2,3,4,10}
m1=4.75==approc(5)
k2={11,12,20,25,30}
m2=19.6==approx(20)
Iter 3:
K1={2,3,4,10,11,12} K2={20,25,30}
m1=7 m2=25
k1={2,3,4,10,11,12} k2={20,25,30}
m1=7, m2=25
Same mean twice. Thus we are getting same mean we have to stop.
