In [1]:

    

import os
import pandas as pd
import math
import numpy as np
from sklearn.tree import DecisionTreeClassifier


    

In [2]:

    

headers = ["buying", "maint", "doors", "persons","lug_boot", "safety", "class"]
data = pd.read_csv("car_data.csv", header=None, names=headers)

data = data.sample(frac=1).reset_index(drop=True) # shuffle


    

In [3]:

    

for h in headers:
    data[h] = data[h].astype('category')
    data[h] = data[h].cat.codes

data.set_index("class", inplace=True)
data.head()


    

    
Out[3]:







  

    

      

      
buying
      
maint
      
doors
      
persons
      
lug_boot
      
safety
    
    

      
class
      

      

      

      

      

      

    
  
  

    

      
2
      
1
      
1
      
3
      
0
      
2
      
0
    
    

      
2
      
1
      
2
      
0
      
2
      
2
      
0
    
    

      
2
      
0
      
1
      
0
      
2
      
1
      
1
    
    

      
0
      
1
      
0
      
0
      
1
      
2
      
2
    
    

      
2
      
0
      
1
      
2
      
0
      
2
      
1
    
  

In [4]:

    

size = len(data)
train_size = int(math.floor(size * 0.7))
train_data = data[:train_size]
test_data = data[train_size:]


    

In [5]:

    

#Usando critério gini
d_tree = DecisionTreeClassifier(criterion="gini")
d_tree.fit(train_data, train_data.index)


    

    
Out[5]:





DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')

In [6]:

    

d_tree.predict(test_data.iloc[:, 0:6])
d_tree.score(test_data, test_data.index)


    

    
Out[6]:





0.96917148362235073

In [7]:

    

d_tree2 = DecisionTreeClassifier(criterion="entropy")
d_tree2.fit(train_data, train_data.index)


    

    
Out[7]:





DecisionTreeClassifier(class_weight=None, criterion='entropy', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')

In [8]:

    

d_tree2.predict(test_data.iloc[:, 0:6])
d_tree2.score(test_data, test_data.index)


    

    
Out[8]:





0.97687861271676302

In [ ]: