In [1]:

    

import pandas as pd
%matplotlib inline
from sklearn import tree
import matplotlib.pyplot as plt
import numpy as np


    

In [2]:

    

sample_list = [0,250,36,'M',10,150,34,'F',2,90,10,'M',6,78,8,'F',4,20,1,'F',1,170,70,'M',8,160,41,'F',10,180,38,'M',6,200,45,'M']
df = pd.DataFrame(np.asarray(sample_list).reshape(9,4),
                    index=['Homer','Marge','Bart','Lisa','Maggie','Abe','Selma','Otto','Krusty'],columns = ['hair_length','weight','age','class'])


    

In [3]:

    

df


    

    
Out[3]:






  

    

      

      
hair_length
      
weight
      
age
      
class
    
  
  

    

      
Homer
      
0
      
250
      
36
      
M
    
    

      
Marge
      
10
      
150
      
34
      
F
    
    

      
Bart
      
2
      
90
      
10
      
M
    
    

      
Lisa
      
6
      
78
      
8
      
F
    
    

      
Maggie
      
4
      
20
      
1
      
F
    
    

      
Abe
      
1
      
170
      
70
      
M
    
    

      
Selma
      
8
      
160
      
41
      
F
    
    

      
Otto
      
10
      
180
      
38
      
M
    
    

      
Krusty
      
6
      
200
      
45
      
M
    
  

In [4]:

    

x = df[['hair_length','weight','age']].as_matrix() # the attributes
x


    

    
Out[4]:





array([['0', '250', '36'],
       ['10', '150', '34'],
       ['2', '90', '10'],
       ['6', '78', '8'],
       ['4', '20', '1'],
       ['1', '170', '70'],
       ['8', '160', '41'],
       ['10', '180', '38'],
       ['6', '200', '45']], dtype=object)

In [5]:

    

y = df['class'].as_matrix() # the attributes
y


    

    
Out[5]:





array(['M', 'F', 'M', 'F', 'F', 'M', 'F', 'M', 'M'], dtype=object)

In [7]:

    

dt = tree.DecisionTreeClassifier()


    

In [8]:

    

dt = dt.fit(x,y)


    

In [13]:

    




    

    
Out[13]:





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

In [15]:

    

from sklearn.cross_validation import cross_val_score


    

In [16]:

    

# http://scikit-learn.org/stable/modules/cross_validation.html#computing-cross-validated-metrics
scores = cross_val_score(dt,x,y,cv=5) #We're passing in our values and getting an array of values back


    

    




c:\users\dongjin\envs\03stat\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)

In [17]:

    

np.mean(scores) #here we get our average result


    

    
Out[17]:





0.80000000000000004

In [23]:

    

x_test = np.asarray([0,250,36])


    

In [24]:

    

predicted= dt.predict(x_test)


    

    




c:\users\dongjin\envs\03stat\lib\site-packages\sklearn\utils\validation.py:386: DeprecationWarning: Passing 1d arrays as data is deprecated in 0.17 and willraise ValueError in 0.19. Reshape your data either using X.reshape(-1, 1) if your data has a single feature or X.reshape(1, -1) if it contains a single sample.
  DeprecationWarning)

In [25]:

    

predicted


    

    
Out[25]:





array(['M'], dtype=object)

In [ ]: