In [1]:

    

import pandas as pd


    

In [6]:

    

df = pd.read_csv("./the-simpsons-by-the-data/simpsons_script_lines.csv", usecols=['raw_text'])


    

In [7]:

    

df.shape


    

    
Out[7]:





(158271, 1)

In [9]:

    

df.head()


    

    
Out[9]:






  

    

      

      
raw_text
    
  
  

    

      
0
      
Miss Hoover: No, actually, it was a little of ...
    
    

      
1
      
Lisa Simpson: (NEAR TEARS) Where's Mr. Bergstrom?
    
    

      
2
      
Miss Hoover: I don't know. Although I'd sure l...
    
    

      
3
      
Lisa Simpson: That life is worth living.
    
    

      
4
      
Edna Krabappel-Flanders: The polls will be ope...
    
  

In [15]:

    

import os
cur_dir = os.curdir
os.chdir('../..')


    

In [17]:

    

os.chdir('./wv')


    

In [21]:

    

import embeddings
import wordvec


    

In [22]:

    

os.chdir(cur_dir)


    

In [23]:

    

wv_model = wordvec.create_wordvec_model(df, "raw_text")


    

In [ ]:

    




    

In [ ]:

    

dv_model = wordvec.create_docvec_model(df, "raw_text")