In [1]:

    

from tensorglue.engine import RecommenderData
from tensorglue.tools.movielens import get_movielens_data
from tensorglue.tools.printing import print_frames


    

In [2]:

    

ml_data, ml_genres = get_movielens_data(get_genres=True)
#if you  have local copy of the movielens data you can use
#get_movielens_data(local_file="full_path_to_local_file", get_genres=True)


    

In [3]:

    

print_frames((ml_data.head(10), ml_genres.head(10)))


    

    
Out[3]:





    
 


  

    

      

      
userid
      
movieid
      
rating
    
  
  

    

      
0
      
1
      
122
      
5
    
    

      
1
      
1
      
185
      
5
    
    

      
2
      
1
      
231
      
5
    
    

      
3
      
1
      
292
      
5
    
    

      
4
      
1
      
316
      
5
    
    

      
5
      
1
      
329
      
5
    
    

      
6
      
1
      
355
      
5
    
    

      
7
      
1
      
356
      
5
    
    

      
8
      
1
      
362
      
5
    
    

      
9
      
1
      
364
      
5
    
  

 
 


  

    

      

      
movieid
      
movienm
      
genreid
    
  
  

    

      
0
      
1
      
Toy Story (1995)
      
Adventure
    
    

      
1
      
1
      
Toy Story (1995)
      
Animation
    
    

      
2
      
1
      
Toy Story (1995)
      
Children
    
    

      
3
      
1
      
Toy Story (1995)
      
Comedy
    
    

      
4
      
1
      
Toy Story (1995)
      
Fantasy
    
    

      
5
      
2
      
Jumanji (1995)
      
Adventure
    
    

      
6
      
2
      
Jumanji (1995)
      
Children
    
    

      
7
      
2
      
Jumanji (1995)
      
Fantasy
    
    

      
8
      
3
      
Grumpier Old Men (1995)
      
Comedy
    
    

      
9
      
3
      
Grumpier Old Men (1995)
      
Romance
    
  

 
    
    

In [4]:

    

simple_model = RecommenderData(ml_data, 'userid', 'movieid', 'rating')


    

In [5]:

    

simple_model._prepare_data(eval_num=3)


    

    




Unseen items found in the test set. Dropping...

In [6]:

    

simple_model.train_model('svd')


    

In [7]:

    

simple_model.evaluate()


    

    
Out[7]:





8284

In [8]:

    

simple_model.train_model('i2i')


    

In [9]:

    

simple_model.evaluate()


    

    
Out[9]:





8882

In [8]:

    

context_model = RecommenderData(ml_data, 'userid', 'movieid', 'rating',
                                  context_data=ml_genres.drop('movienm', 1))


    

In [9]:

    

context_model.arrange_by = context_model.fields.values


    

In [10]:

    

context_model._prepare_data(eval_num=3)


    

    




Unseen items found in the test set. Dropping...
Summarizing contextual values

In [11]:

    

context_model.train_model('svd')


    

In [12]:

    

context_model.evaluate()


    

    
Out[12]:





11419

In [13]:

    

context_model.arrange_by = context_model.fields.contextid


    

In [14]:

    

context_model._prepare_data(eval_num=3)


    

    




Unseen items found in the test set. Dropping...
Maximizing contextual values

In [15]:

    

context_model.train_model('tensor')


    

    




Step 1 of 25
growth of the core: 1.000000
Step 2 of 25
growth of the core: 0.121917
Step 3 of 25
growth of the core: 0.005939
Step 4 of 25
growth of the core: 0.000797
Core is no longer growing.
Done

In [16]:

    

context_model.evaluate()


    

    
Out[16]:





13014