Scribd
Upload
34 views15 pages

K-Means Clustering Algorithm Explained

The document discusses different clustering algorithms including K-means clustering which partitions observations into K clusters where each observation belongs to the cluster with the nearest mean. It then provides an example of applying K-means clustering to a dataset with 12 observations grouped into 2 clusters. The document also covers hierarchical clustering which forms clusters progressively by linking observations together in a tree structure.

Uploaded by

nanugupta633
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
34 views15 pages

K-Means Clustering Algorithm Explained

The document discusses different clustering algorithms including K-means clustering which partitions observations into K clusters where each observation belongs to the cluster with the nearest mean. It then provides an example of applying K-means clustering to a dataset with 12 observations grouped into 2 clusters. The document also covers hierarchical clustering which forms clusters progressively by linking observations together in a tree structure.

Uploaded by

nanugupta633
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

2

Umite 101|@
K=2 lustey
luateu
A%ouatoa kue Miutngo
M
ON
SHOT
Algomtht
tuo (2) clustees sng
K-Meenu

#femae
Eucldea ditau = J e-H) (Xu - w, ) 2.

Wheu,
XH ’chsestved value
H ontuoid yalie
ohseyed Value
Centtat Walue
Now, we Aave
Skblnihalje tuwe lustees

þeusons wernt
I85
2
56
3
l68
|19 68
5. 182 12
6 I86
180
8
9. )83 84
88
I80
12

efang
Comtuaid
186 t2(185 12)
66. (h0, S6)
NOw olout wutt lste
4 aucl peson 2. C
e to add d peuson Centsustdvo
the elther Hhu

o that we Cuotitdeam. dislaue


2.

didauc

dislamet
Ls chseed values (Xn,X) ’ Us8, 6o)
Ls lontuntd Nalutaof f H,,w,) ’ (185,12)
(163-185 )? + (12-6o)2 J 289 +l49 =J433
=|20-80

hot

{233
Vaue hange the
mean Calucahng the
I70 +l63
2
S6tG069,53)
Dato:

WContuatd cdusles Hllmowl


2 (35,12) C,’1,
169 (163,53) G2,3

t step-2 ferr peucn-4

>(14-1A9) + L63-12) J36+lt 52


]s2
’.7-2)
(ù) Ed of
’lotOO =|200)44)

fI,41

betome
(32 ((S2,7o)
S? (l69,S? )

Qloove

(2-182) ( 12-70) ’2
S365 9.1

So,

18/07/2023 08:09
data
clasaitt mean
Considey vaue
Vales
andl
and

Data= t e,3,4, Jo, 1, (2, 20, 25 30 3.


Someb
M)= y M22.
ck valuo Yo os chekk
Kauge s ke maue hai ya. I2 Ke
Meae ha

f 2,3, 4
gi0en) I0,11, 12,2o, 2s, 303
take mean Vauo

(K) Meaz 3 (ke)m = L8.

K,= b ) ,)2,2O, 2S,20j.

K(Mean) 45 K,( Mean) 19.6


Date:

Mean Ck)
Meamea)
slebyt K, 239,19,11, 123 K 20,2203
MeOMk,)

Lame me
haue togtop hese.

k, - 2124,lo, l1,1

PEGASUS 18 7/2023 08:0


4) Aglomesatie datetisg
L Botom

IA

lishage
e tikage tehnlque(Mideo)
t 7ablo 4
PO
B9 O
P3 1
PuG5

shebl 2 i8 Smatlust distanc


So, maku cluileu
betweew

min PC,B1) Check i gin talel)


min 9,8]
Imin = &
Tabt
min (P, Ce,P]). So,tabe otu be
min C(e,)i).
min= 3
6 S
-MTY
nratmdteotu ton

male
musutey.

mn , t
Tant-3)
0)

3
5
togethr
P

miC,fa),(B,8, ).

mig 9, , l o , 6 9, 8J
mw
Pege No.
Date:
vAnljesfioclouoom

Nou
value Combin the
drstaee

Me Masi mum Value e


hataha
H 2,3,S
-MIRA
Pago No,
Date:
[Link]

Remoug a oud
aud maleos (E
L

TIO
34
200
35
Ja 3 5

Steb TAemse 1
ubpot
2 Ls Glven o Mese
oansoge
5 3).
B) 23s
2SV.
G) L 13s V
Hhe min L 23sV.
L l2?.
male þai of to. D) (ab slyp),
l,2,3,S3.
Llemcet Suppos
la. 23
4 Owteal
E4,54 4 2sy.
d.
e
233
s}
2/y S0Y.
Yy=oates
Laeha ab
rthege (2,3,5) haha hai a wke
Rdes
Supprt Confsclew
(2^3)455
2.3^5) 9
2

|3^5)’3 2
2/2 loo.
S.
’(3^s) 2
3’(2^5) 2(2 66
2

onldane
Rule1-(243)
A B.

4sCAu)

Rulo 2 and

243)-5
3 b
a
ems
C) Rmove
b)
(a
4 d
3
3 D
Root Tem
5
dacd
ab 3
dc
dabc 2
dmaveLems 3
þoa the aceona4
to edc
2
ems TID
he in
Tews wUte
Min
hull ==ngde Root
No. Pags
te Roat (d Root

A) C)
(C:V(b:)
(C)

Root)

(a:2

l’2t)

b+)+)

You might also like