In [10]:

    

import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
from sklearn.tree import DecisionTreeClassifier
from sklearn.cross_validation import train_test_split
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.datasets import load_iris
from sklearn.tree import export_graphviz

import pydot
import graphviz


    

In [2]:

    

dataset_iris = load_iris()

df = pd.DataFrame(data=dataset_iris.data, columns=dataset_iris.feature_names)


    

In [3]:

    

df.head(5)


    

    
Out[3]:







  

    

      

      
sepal length (cm)
      
sepal width (cm)
      
petal length (cm)
      
petal width (cm)
    
  
  

    

      
0
      
5.1
      
3.5
      
1.4
      
0.2
    
    

      
1
      
4.9
      
3.0
      
1.4
      
0.2
    
    

      
2
      
4.7
      
3.2
      
1.3
      
0.2
    
    

      
3
      
4.6
      
3.1
      
1.5
      
0.2
    
    

      
4
      
5.0
      
3.6
      
1.4
      
0.2
    
  

In [4]:

    

X_train, X_test, Y_train, Y_test = train_test_split(dataset_iris.data, 
                                                    dataset_iris.target, 
                                                    test_size = 0.33)


    

In [5]:

    

clf = DecisionTreeClassifier(max_depth= None,
                             max_features = None,
                             criterion = 'entropy',
                             min_samples_leaf = 1,
                             min_samples_split = 2)

model = clf.fit(X_train, Y_train)
predicts = model.predict(X_test)


    

In [6]:

    

print(confusion_matrix(Y_test, predicts))


    

    




[[18  0  0]
 [ 0 13  0]
 [ 0  2 17]]

In [7]:

    

print('Acuracia com dados de teste: ', accuracy_score(Y_test, predicts))


    

    




Acuracia com dados de teste:  0.96

In [8]:

    

output = '/home/avinicius/workspace/machine-learning/tree.dot'


    

In [9]:

    

export_graphviz(clf, out_file=output, feature_names=dataset_iris.feature_names)

with open(output) as file:
    dot_graph = file.read()
    
graphviz.Source(dot_graph)


    

    
Out[9]:

In [ ]: