Find clusters using k-means clustering algorithm if we have several objects (4 types of medicines) and each object have two attributes or features as shown in the table below.

Welcome back.

and 3 others joined a min ago.

14kviews

written 5.6 years ago by

teamques10 ★ 68k

• modified 4.8 years ago

The goal is to group these objects into k=2 group of medicine based on the two features (pH and weight index).

Object	Attribute 1 (X) Weight Index	Attribute 2 (Y) pH
Medicine A	1	1
Medicine B	2	1
Medicine C	4	3
Medicine D	5	4

data warehouse and mining

ADD COMMENT EDIT

1 Answer

1.7kviews

written 5.6 years ago by

teamques10 ★ 68k

• modified 5.2 years ago

Object	X	Y
A	1	1
B	2	1
C	4	3
D	5	4

enter image description here

K = 2

1] Obtain adjacency matrix.

-	A	B	C	D
A	0	-	-	-
B	1	0	-	-
C	$\sqrt{13}$	$\sqrt{8}$	0	-
D	5	$\sqrt{9}$	$\sqrt{2}$	0

2] Let $c_1$ = {A} & $c_2$ = {B}

$\therefore$ centroid of $c_1$ = {A} = { (1,1) }

" $c_2$ = {B} = { (2,1)}

enter image description here

3] $c_1$ = {A}

$c_2$ = { B, C, D}

$\therefore$ centroid of $c_1$ = {(1,1)}

" $c_2$ {( $\frac{2+4+5}{3}, \frac{1+3+4}{3} )$}

= {(3.67, 2.67)}

enter image description here

3] $c_1$ = {A , B}

$c_2$ = {C , D}

$\therefore$ centroid of $c_1$ = { (1.5, 1)}

" $c_2$ = {(4.5, 3.5)}

enter image description here

$\therefore$ $c_1$ = {A, B}

$c_2$ = { C, D}

$\because$ there is no change, these are the final clusters.

ADD COMMENT EDIT

Community

Content

Company