Knn classification

KNN Classification
Algorithm


What’s in it for you?

Why do we need KNN?
What is KNN?
How do we choose the factor ‘K’?
When do we use KNN?
How does KNN Algorithm work?
Use Case: Predict whether a person will have
diabetes or not


Why KNN?
By
By now,
now, we
we all
all know
know
Machine
Machine learning
learning models
models
makes
makes predictions
predictions by
by
learning

learning from
from the
the past
past
data
data available
available
Machine Learning Model

Input value

Predicted Output


Is that a dog?


No dear, you can
differentiate
between a cat
and a dog based
on their
characteristics


CATS

DOGS

Sharp Claws, uses to climb

Dull Claws

Smaller length of ears

Bigger length of ears

Meows and purrs

Barks

Doesn’t love to play around

Loves to run around

No dear, you can
differentiate
between a cat
and a dog based
on their
characteristics


DOGS

Sharpness of claws 

CATS

Length of ears 

No dear, you can
differentiate
between a cat
and a dog based
on their
characteristics


Now tell me if it
is a cat or a dog?


DOGS

Sharpness of claws 

CATS

Length of ears 

Now tell me if
it’s a cat or a
dog?


It’s features are more like
cats, it must be a cat!

DOGS

Sharp of claws 

CATS

Length of ears 


Why KNN?
Because
Because KNN
KNN is
is based
based on
on
feature
feature similarity,
similarity, we
we can
can
do
do classification
classification using
using KNN
KNN
Classifier!
Classifier!
KNN

Input value

Predicted Output


What is KNN?


What is KNN Algorithm?
KNN – K Nearest Neighbors, is one of the simplest Supervised Machine Learning
algorithm mostly used for

Classification
It classifies a data point based on how its
neighbors are classified


What is KNN Algorithm?

Sulphur Dioxide Level 

KNN stores all available cases
and classifies new cases based
on a similarity measure

RED or WHITE?

Chloride Level 

What is KNN Algorithm?

Sulphur Dioxide Level 

But, what is K?

RED or WHITE?

Chloride Level 


What is KNN Algorithm?
 k in KNN is a parameter that
refers to the number of nearest
neighbors to include in the
majority voting process

Sulphur Dioxide Level 

K=5

RED or WHITE?

Chloride Level 


What is KNN Algorithm?
A data point is classified by
majority votes from its 5
nearest neighbors

Sulphur Dioxide Level 

K=5

RED or WHITE?

Chloride Level 


What is KNN Algorithm?
Here, the unknown point would
be classified as red, since 4 out
of 5 neighbors are red

Sulphur Dioxide Level 

K=5

RED

Chloride Level 


How do we choose ‘k’?