Data Science Lab Exercise (Naïve Bayes) Solution

    • Create text file for the following data and load data through Pandas libraries

    • Build your own Naïve Bayes classifier model using steps below

    • Class: P(C) = Nc/N

    • e.g., P(No) = 7/10,

    • For discrete attributes:

P(Ai | Ck) = |Aik|/ Nck

where |Aik| is number of instances having attribute Ai and belongs to class Ck

Examples:

P(Status=Married|No) = 4/7

P(Refund=Yes|Yes)=0


•
Normal distribution:



categoricalcategorical           continuous  class


2   ij2






One for each (Ai,ci) pair










( A
)2







1

iij







P( Ai | c j )

e
2  ij2


















For (Income, Class=No):

Tid
Refund
Marital
Taxable
Evade





Status
Income


If Class=No










sample mean = 110



1
Yes
Single
125K
No

sample variance = 2975

2
No
Married
100K
No











•  Once Trained, test your model for the
3
No
Single
70K
No

cases below




4
Yes
Married
120K
No












X1 = {Refund = Yes, Status = Divorced,
5
No
Divorced
95K
Yes

Income = 90K, Evade = ?}

6
No
Married
60K
No

X2 = {Refund = No, Status = Married,
7
Yes
Divorced
220K
No

Income = 60K, Evade = ?}




















8
No
Single
85K
Yes






9
No
Married
75K
No






10
No
Single
90K
Yes