Iris Decision Tree

In [75]:

    

%matplotlib inline
from sklearn import datasets
from sklearn import tree
import pandas as pd
import numpy as np
import seaborn as sns
import random as rnd

iris = datasets.load_iris()

df = pd.DataFrame(data=np.c_[iris['data'], iris['target']],
                  columns=iris['feature_names'] + ['target'])

df.head()


    

    
Out[75]:






  

    

      

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

    

      
0
      
5.1
      
3.5
      
1.4
      
0.2
      
0.0
    
    

      
1
      
4.9
      
3.0
      
1.4
      
0.2
      
0.0
    
    

      
2
      
4.7
      
3.2
      
1.3
      
0.2
      
0.0
    
    

      
3
      
4.6
      
3.1
      
1.5
      
0.2
      
0.0
    
    

      
4
      
5.0
      
3.6
      
1.4
      
0.2
      
0.0
    
  

In [76]:

    

df.tail()


    

    
Out[76]:






  

    

      

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

    

      
145
      
6.7
      
3.0
      
5.2
      
2.3
      
2.0
    
    

      
146
      
6.3
      
2.5
      
5.0
      
1.9
      
2.0
    
    

      
147
      
6.5
      
3.0
      
5.2
      
2.0
      
2.0
    
    

      
148
      
6.2
      
3.4
      
5.4
      
2.3
      
2.0
    
    

      
149
      
5.9
      
3.0
      
5.1
      
1.8
      
2.0
    
  

In [77]:

    

df.describe()


    

    
Out[77]:






  

    

      

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

    

      
count
      
150.000000
      
150.000000
      
150.000000
      
150.000000
      
150.000000
    
    

      
mean
      
5.843333
      
3.054000
      
3.758667
      
1.198667
      
1.000000
    
    

      
std
      
0.828066
      
0.433594
      
1.764420
      
0.763161
      
0.819232
    
    

      
min
      
4.300000
      
2.000000
      
1.000000
      
0.100000
      
0.000000
    
    

      
25%
      
5.100000
      
2.800000
      
1.600000
      
0.300000
      
0.000000
    
    

      
50%
      
5.800000
      
3.000000
      
4.350000
      
1.300000
      
1.000000
    
    

      
75%
      
6.400000
      
3.300000
      
5.100000
      
1.800000
      
2.000000
    
    

      
max
      
7.900000
      
4.400000
      
6.900000
      
2.500000
      
2.000000
    
  

In [78]:

    

sns.set_style('whitegrid')
sns.pairplot(df, hue='target')


    

    
Out[78]:





<seaborn.axisgrid.PairGrid at 0x12a2eaf10>






    

In [79]:

    

X = iris.data[0:150, :]
X.shape


    

    
Out[79]:





(150, 4)

In [80]:

    

Y = iris.target[0:150]
Y.shape


    

    
Out[80]:





(150,)

In [81]:

    

setosa_index = rnd.randrange(0, 49)
test_setosa = [iris.data[setosa_index, :]]
X = np.delete(X, setosa_index, 0)
Y = np.delete(Y, setosa_index, 0)
test_setosa, iris.target_names[iris.target[setosa_index]], X.shape, Y.shape


    

    
Out[81]:





([array([ 4.4,  2.9,  1.4,  0.2])], 'setosa', (149, 4), (149,))

In [82]:

    

virginica_index = rnd.randrange(100, 150)
test_virginica = [iris.data[virginica_index, :]]
X = np.delete(X, virginica_index, 0)
Y = np.delete(Y, virginica_index, 0)
test_virginica, iris.target_names[iris.target[virginica_index]], X.shape, Y.shape


    

    
Out[82]:





([array([ 5.8,  2.7,  5.1,  1.9])], 'virginica', (148, 4), (148,))

In [83]:

    

versicolor_index = rnd.randrange(50, 99)
test_versicolor = [iris.data[versicolor_index, :]]
X = np.delete(X, versicolor_index, 0)
Y = np.delete(Y, versicolor_index, 0)
test_versicolor, iris.target_names[iris.target[versicolor_index]], X.shape, Y.shape


    

    
Out[83]:





([array([ 6.2,  2.2,  4.5,  1.5])], 'versicolor', (147, 4), (147,))

In [84]:

    

# Decision Tree Classifier Model
model_tree = tree.DecisionTreeClassifier()

# Training the model
model_tree.fit(X, Y)

pred_tree_setosa = model_tree.predict(test_setosa)
print('Decision Tree predicts {} for test_setosa'
      .format(iris.target_names[pred_tree_setosa]))


    

    




Decision Tree predicts ['setosa'] for test_setosa

In [85]:

    

pred_tree_virginica = model_tree.predict(test_virginica)
print('Decision Tree predicts {} for test_virginica'
      .format(iris.target_names[pred_tree_virginica]))


    

    




Decision Tree predicts ['virginica'] for test_virginica

In [86]:

    

pred_tree_versicolor = model_tree.predict(test_versicolor)
print('Decision Tree predicts {} for test_versicolor'
      .format(iris.target_names[pred_tree_versicolor]))


    

    




Decision Tree predicts ['versicolor'] for test_versicolor