Data preprocessing

In [1]:

    

# Importing the dataset
dataset=read.csv('Data.csv')
dataset


    

    






Country
Age
Salary
Purchased

	
France 
44     
72000  
No     
	
Spain  
27     
48000  
Yes    
	
Germany
30     
54000  
No     
	
Spain  
38     
61000  
No     
	
Germany
40     
   NA  
Yes    
	
France 
35     
58000  
Yes    
	
Spain  
NA     
52000  
No     
	
France 
48     
79000  
Yes    
	
Germany
50     
83000  
No     
	
France 
37     
67000  
Yes    

In [2]:

    

# Taking care of missing values
dataset$Age=ifelse(is.na(dataset$Age),
                  ave(dataset$Age,FUN=function(x) mean(x,na.rm=TRUE)),
                      dataset$Age)
dataset$Salary= ifelse(is.na(dataset$Salary),
                  ave(dataset$Salary,FUN=function(x) mean(x,na.rm=TRUE)),
                      dataset$Salary)
dataset


    

    






Country
Age
Salary
Purchased

	
France  
44.00000
72000.00
No      
	
Spain   
27.00000
48000.00
Yes     
	
Germany 
30.00000
54000.00
No      
	
Spain   
38.00000
61000.00
No      
	
Germany 
40.00000
63777.78
Yes     
	
France  
35.00000
58000.00
Yes     
	
Spain   
38.77778
52000.00
No      
	
France  
48.00000
79000.00
Yes     
	
Germany 
50.00000
83000.00
No      
	
France  
37.00000
67000.00
Yes     

In [3]:

    

# Encoding Categorical variables
dataset$Country=factor(dataset$Country,
                      levels=c('France','Spain','Germany'),
                      labels=c(1,2,3))
dataset


    

    






Country
Age
Salary
Purchased

	
1       
44.00000
72000.00
No      
	
2       
27.00000
48000.00
Yes     
	
3       
30.00000
54000.00
No      
	
2       
38.00000
61000.00
No      
	
3       
40.00000
63777.78
Yes     
	
1       
35.00000
58000.00
Yes     
	
2       
38.77778
52000.00
No      
	
1       
48.00000
79000.00
Yes     
	
3       
50.00000
83000.00
No      
	
1       
37.00000
67000.00
Yes     

In [5]:

    

dataset$Purchased=factor(dataset$Purchased,levels=c('No','Yes'),labels=c(0,1))
dataset


    

    






Country
Age
Salary
Purchased

	
1       
44.00000
72000.00
0       
	
2       
27.00000
48000.00
1       
	
3       
30.00000
54000.00
0       
	
2       
38.00000
61000.00
0       
	
3       
40.00000
63777.78
1       
	
1       
35.00000
58000.00
1       
	
2       
38.77778
52000.00
0       
	
1       
48.00000
79000.00
1       
	
3       
50.00000
83000.00
0       
	
1       
37.00000
67000.00
1       

In [12]:

    

# Splitting train set and test set
library(caTools)
set.seed(2001)
split=sample.split(dataset$Purchased,SplitRatio=0.8)
#help(sample.split)
split
training_set=subset(dataset,split==TRUE)
test_set=subset(dataset,split==FALSE)


    

    






	
FALSE
	
TRUE
	
TRUE
	
TRUE
	
TRUE
	
TRUE
	
TRUE
	
FALSE
	
TRUE
	
TRUE








    






Country
Age
Salary
Purchased

	
1
1    
44   
72000
0    
	
8
1    
48   
79000
1    

In [15]:

    

# Feature scaling (optional)
## Note : A factor is not a numeric variable
training_set[,2:3]=scale(training_set[,2:3])
test_set[,2:3]=scale(test_set[,2:3])
test_set


    

    






Country
Age
Salary
Purchased

	
1
1         
-0.7071068
-0.7071068
0         
	
8
1         
 0.7071068
 0.7071068
1         

In [ ]: