0% found this document useful (0 votes)
394 views5 pages

K-Means Clustering Numerical Example

Uploaded by

Aakash Bhat
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
394 views5 pages

K-Means Clustering Numerical Example

Uploaded by

Aakash Bhat
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

K-means

Clusterirg
Data Point

2 2

2 5
6

|2
13

cetrids
Randomly select two
C; = (2, 3)
- (6, )
Dut Euclidean dis tance
Now find
D=

Data Point Cluster


2 3
2

2. 2 3
Je-2+ (s3)
3 5 5123

5 Jo 5
12-04

13 1345
Euclidean
Eudlidean to distane to cluste
Data Point dittane

|.4| 860

72|
2 3 2
2
593 J.4)
2
3
1:21
6 9 2
|2.0 4 5
5 lo |2 2-.
565
13
l3-45

mea n
taki ny the
Vbdate Centids
each clus tey
data poins
and 2
data þoint
are

COts ter |
Mean (+2), (2+3)&)
2 2

Nens Centoidl G =|5, 2:5

data poi nt Ye 3, 4 5, 6

Mean (5+6+ lo +n) 9


(8++12 +13)

-] 8, lo 5)
2
Nous find out Nen arsgned clusters
the nens Centn'ds
besed upon

Data Point
15 25 Jo -5
0:707
2
0707
2 3
2
6519
8
3

I2:74
5
13 14.15

ertoid G, [S, 25)


Eucli di nean olis tance for
for Data Point I= J(s-°r (a5-2)=
t= (65-2*+ (25-3) oo7

(5- )+ -8)-
(a5-8) -st(-s9
3=

(:5-9) )ks
5-(15-)+ (215- )=J((n9 J72- 25+ o s
IC25 =12:79

2 14 I5
Euclidan diztane tor centid (8, lo5]

J(8-I) +(io5- 2) = 49 + 722s

W(3-2) +(o5-3) (9+(19*


92:5-60

8) (a5)
(8-5 )+ (oS -1s-25-30

(2)+(us)
44 2 s
25

(8- jo) (1o:5-I2)2)i(f

Vo-n)+(ws- 1s).e(aj.

Euclidean Eu cei dean 3.90


Data Point dstance for diatanu for
cleetr
070 7
2
960
2 2
2 2
30
3 2S 2
6
2
|2:74 25
|2
5 I4.1S 3.90
13
6
Calelated fo
For thìs da taset We have
terations.

both the
And
cluots ae Aame So we amigna

Data toi nts I, 2

cluster 2 Date Poirg 3,4,s,6

the value 6
both Ccnes

amijndl clusters are olfener then

tuke
ansipnel clete
data þol nts ntil thy con ve

cluste

You might also like