notebook.community

Edit and run



In [25]:

    
#importing libraries
import numpy as np
import pandas as pd
from sklearn.naive_bayes import BernoulliNB, GaussianNB
from sklearn.cross_validation import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import LabelEncoder
import warnings 
warnings.simplefilter('ignore')



In [26]:

    
dataframe=pd.read_csv('http://archive.ics.uci.edu/ml/machine-learning-databases/chess/king-rook-vs-king-pawn/kr-vs-kp.data')
dataframe.shape









    Out[26]:





(3195, 37)



In [34]:

    
headers = [x for x in range(0,37)]
dataframe.columns=headers



In [35]:

    
dataframe.sample(5)









    Out[35]:






  
    
      
      0
      1
      2
      3
      4
      5
      6
      7
      8
      9
      ...
      27
      28
      29
      30
      31
      32
      33
      34
      35
      36
    
  
  
    
      985
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      ...
      0
      0
      0
      0
      0
      1
      1
      1
      0
      0
    
    
      1141
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      ...
      0
      0
      0
      0
      0
      1
      1
      1
      0
      0
    
    
      1844
      1
      0
      0
      0
      1
      1
      1
      1
      1
      0
      ...
      0
      0
      0
      0
      0
      0
      0
      1
      0
      1
    
    
      749
      0
      0
      0
      0
      1
      1
      1
      0
      0
      0
      ...
      0
      0
      0
      0
      0
      0
      0
      1
      0
      1
    
    
      1061
      0
      0
      0
      0
      0
      0
      0
      0
      0
      0
      ...
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
    
  

5 rows × 37 columns



In [36]:

    
encoder=LabelEncoder()
for x in dataframe:
    dataframe[x]=encoder.fit_transform(dataframe[x])



In [37]:

    
dataframe.sample(5)









    Out[37]:






  
    
      
      0
      1
      2
      3
      4
      5
      6
      7
      8
      9
      ...
      27
      28
      29
      30
      31
      32
      33
      34
      35
      36
    
  
  
    
      2596
      0
      0
      0
      0
      1
      1
      0
      1
      1
      1
      ...
      0
      0
      0
      1
      0
      1
      0
      0
      0
      0
    
    
      1839
      0
      0
      0
      1
      0
      1
      1
      1
      1
      0
      ...
      0
      0
      0
      0
      0
      0
      1
      1
      0
      1
    
    
      2195
      0
      1
      0
      1
      0
      0
      0
      0
      1
      0
      ...
      0
      0
      0
      1
      1
      0
      0
      0
      0
      1
    
    
      2572
      0
      0
      0
      0
      1
      1
      1
      0
      0
      1
      ...
      0
      0
      0
      0
      0
      1
      1
      0
      0
      0
    
    
      1715
      0
      0
      0
      0
      0
      0
      0
      0
      1
      0
      ...
      0
      0
      0
      1
      0
      0
      0
      1
      0
      1
    
  

5 rows × 37 columns



In [38]:

    
features=dataframe.columns[:-1]
target=dataframe.columns[-1]



In [44]:

    
train,test=train_test_split(dataframe,test_size=0.4)



In [45]:

    
gnb= BernoulliNB()
gnb=gnb.fit(train[features],train[target])
predict=gnb.predict(test[features])
accu=accuracy_score(test[target],predict)*100
accu









    Out[45]:





86.150234741784033



In [46]:

    
gnb=GaussianNB()
gnb=gnb.fit(train[features],train[target])
gaupredict=gnb.predict(test[features])
gauaccu=accuracy_score(test[target],gaupredict)*100
gauaccu









    Out[46]:





61.424100156494518



In [ ]:

	0	4	5	6	7	8	...	32	33	34	36
985	0	0	1	0	0	0	...	1	1	1	0
1141	0	0	1	0	0	0	...	1	1	1	0
1844	1	1	1	1	1	1	...	0	0	1	1
749	0	1	1	1	0	0	...	0	0	1	1
1061	0	0	0	0	0	0	...	0	1	0	0

	1	3	4	5	6	7	8	9	...	30	31	32	33	34	36
2596	0	0	1	1	0	1	1	1	...	1	0	1	0	0	0
1839	0	1	0	1	1	1	1	0	...	0	0	0	1	1	1
2195	1	1	0	0	0	0	1	0	...	1	1	0	0	0	1
2572	0	0	1	1	1	0	0	1	...	0	0	1	1	0	0
1715	0	0	0	0	0	0	1	0	...	1	0	0	0	1	1