In [1]:

    

#Decision Trees are excellent tools for data inspection


    

In [3]:

    

#Data preparation


    

In [6]:

    

Data<-read.csv("http://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data",header=F)#import


    

In [7]:

    

names(Data)<-c("age","workclass","fnlwgt","education", "educationnum", "maritalstatus", "occupation", "relationship", "race", "sex", "capitalgain", "capitalloss", 
               "hoursperweek", "nativecountry", "response")#assign names for columns


    

In [8]:

    

str(Data)#look at the structure of the dataset


    

    




'data.frame':	32561 obs. of  15 variables:
 $ age          : int  39 50 38 53 28 37 49 52 31 42 ...
 $ workclass    : Factor w/ 9 levels " ?"," Federal-gov",..: 8 7 5 5 5 5 5 7 5 5 ...
 $ fnlwgt       : int  77516 83311 215646 234721 338409 284582 160187 209642 45781 159449 ...
 $ education    : Factor w/ 16 levels " 10th"," 11th",..: 10 10 12 2 10 13 7 12 13 10 ...
 $ educationnum : int  13 13 9 7 13 14 5 9 14 13 ...
 $ maritalstatus: Factor w/ 7 levels " Divorced"," Married-AF-spouse",..: 5 3 1 3 3 3 4 3 5 3 ...
 $ occupation   : Factor w/ 15 levels " ?"," Adm-clerical",..: 2 5 7 7 11 5 9 5 11 5 ...
 $ relationship : Factor w/ 6 levels " Husband"," Not-in-family",..: 2 1 2 1 6 6 2 1 2 1 ...
 $ race         : Factor w/ 5 levels " Amer-Indian-Eskimo",..: 5 5 5 3 3 5 3 5 5 5 ...
 $ sex          : Factor w/ 2 levels " Female"," Male": 2 2 2 2 1 1 1 2 1 2 ...
 $ capitalgain  : int  2174 0 0 0 0 0 0 0 14084 5178 ...
 $ capitalloss  : int  0 0 0 0 0 0 0 0 0 0 ...
 $ hoursperweek : int  40 13 40 40 40 40 16 45 50 40 ...
 $ nativecountry: Factor w/ 42 levels " ?"," Cambodia",..: 40 40 40 40 6 40 24 40 40 40 ...
 $ response     : Factor w/ 2 levels " <=50K"," >50K": 1 1 1 1 1 1 1 2 2 2 ...

In [9]:

    

Data<-Data[,c(1:13,15)]#remove the factor with more than 42 levels


    

In [10]:

    

set.seed(100)


    

In [11]:

    

train<-sample(1:nrow(Data),0.8*nrow(Data))


    

In [12]:

    

traindata<-Data[train,]


    

In [13]:

    

testdata<-Data[-train,]


    

In [14]:

    

head(traindata)


    

    
Out[14]:





age
workclass
fnlwgt
education
educationnum
maritalstatus
occupation
relationship
race
sex
capitalgain
capitalloss
hoursperweek
response

	
10022
45
 Private
161819
 11th
7
 Separated
 Adm-clerical
 Unmarried
 Black
 Female
0
0
25
 <=50K
	
8390
24
 Private
153082
 HS-grad
9
 Never-married
 Sales
 Not-in-family
 White
 Male
0
0
30
 <=50K
	
17984
33
 Private
181091
 10th
6
 Divorced
 Craft-repair
 Not-in-family
 White
 Male
0
0
35
 <=50K
	
1836
23
 Private
64292
 HS-grad
9
 Never-married
 Adm-clerical
 Not-in-family
 White
 Female
0
0
40
 <=50K
	
15255
21
 Private
347292
 HS-grad
9
 Never-married
 Craft-repair
 Not-in-family
 White
 Male
0
0
40
 <=50K
	
15750
49
 Federal-gov
128990
 Bachelors
13
 Married-civ-spouse
 Prof-specialty
 Husband
 White
 Male
0
0
40
 >50K

In [ ]: