In [2]:

    

from CPT import *
import pandas as pd


    

In [5]:

    

train_df = pd.read_csv("train.csv")
train_df


    

    
Out[5]:







  

    

      

      
1
      
2
      
3
      
4
      
5
      
6
      
7
      
9
    
  
  

    

      
'A'
      
'B'
      
'C'
      
'D'
      
'E'
      
'F'
      
'G'
      
'H'
      
'I'
    
    

      
'A'
      
'B'
      
'C'
      
'D'
      
'E'
      
'F'
      
'X'
      
'Y'
      
'Z'
    
    

      
'A'
      
'B'
      
'C'
      
'D'
      
'E'
      
'F'
      
'M'
      
'N'
      
'O'
    
    

      
'A'
      
'B'
      
'C'
      
'D'
      
'E'
      
'F'
      
'G'
      
'H'
      
'Y'
    
    

      
'A'
      
'B'
      
'C'
      
'D'
      
'E'
      
'F'
      
'G'
      
'H'
      
'X'
    
    

      
'E'
      
'F'
      
'S'
      
'M'
      
'I'
      
'L'
      
'I'
      
'N'
      
'G'
    
    

      
'S'
      
'M'
      
'I'
      
'L'
      
'I'
      
'N'
      
'G'
      
'E'
      
'F'
    
    

      
'S'
      
'M'
      
'I'
      
'L'
      
'E'
      
'B'
      
'A'
      
'T'
      
'F'
    
  

In [6]:

    

test_df = pd.read_csv("test.csv")
test_df


    

    
Out[6]:







  

    

      

      
1
      
2
      
3
    
  
  

    

      
0
      
'A'
      
'B'
      
'C'
    
    

      
1
      
'S'
      
'M'
      
'I'
    
    

      
2
      
'X'
      
'A'
      
'Z'
    
  

In [7]:

    

model = CPT()
train, test = model.load_files("train.csv", "test.csv")
model.train(train)


    

    
Out[7]:





True

In [8]:

    

predictions = model.predict(train,test,2,1)


    

    




100%|██████████| 3/3 [00:00<00:00, 2702.52it/s]

In [9]:

    

predictions


    

    
Out[9]:





[["'D'"], ["'N'"], []]