fast_features.py

'''
               AAA               lllllll lllllll   iiii                      
              A:::A              l:::::l l:::::l  i::::i                     
             A:::::A             l:::::l l:::::l   iiii                      
            A:::::::A            l:::::l l:::::l                             
           A:::::::::A            l::::l  l::::l iiiiiii     eeeeeeeeeeee    
          A:::::A:::::A           l::::l  l::::l i:::::i   ee::::::::::::ee  
         A:::::A A:::::A          l::::l  l::::l  i::::i  e::::::eeeee:::::ee
        A:::::A   A:::::A         l::::l  l::::l  i::::i e::::::e     e:::::e
       A:::::A     A:::::A        l::::l  l::::l  i::::i e:::::::eeeee::::::e
      A:::::AAAAAAAAA:::::A       l::::l  l::::l  i::::i e:::::::::::::::::e 
     A:::::::::::::::::::::A      l::::l  l::::l  i::::i e::::::eeeeeeeeeee  
    A:::::AAAAAAAAAAAAA:::::A     l::::l  l::::l  i::::i e:::::::e           
   A:::::A             A:::::A   l::::::ll::::::li::::::ie::::::::e          
  A:::::A               A:::::A  l::::::ll::::::li::::::i e::::::::eeeeeeee  
 A:::::A                 A:::::A l::::::ll::::::li::::::i  ee:::::::::::::e  
AAAAAAA                   AAAAAAAlllllllllllllllliiiiiiii    eeeeeeeeeeeeee  

______         _                          ___  ______ _____     
|  ___|       | |                        / _ \ | ___ \_   _|  _ 
| |_ ___  __ _| |_ _   _ _ __ ___  ___  / /_\ \| |_/ / | |   (_)
|  _/ _ \/ _` | __| | | | '__/ _ \/ __| |  _  ||  __/  | |      
| ||  __/ (_| | |_| |_| | | |  __/\__ \ | | | || |    _| |_   _ 
\_| \___|\__,_|\__|\__,_|_|  \___||___/ \_| |_/\_|    \___/  (_)
                                                                
                                                                
 _____         _   
|_   _|       | |  
  | | _____  _| |_ 
  | |/ _ \ \/ / __|
  | |  __/>  <| |_ 
  \_/\___/_/\_\\__|
                   
		   
Featurize folders of text files if default_text_features = ['fast_features']

This is the Facebook FastText model:
https://fasttext.cc/docs/en/english-vectors.html
'''
import numpy as np

def fast_featurize(sentence,model):

    size=300
    sentences2=sentence.split()

    w2v_embed=list()
    for i in range(len(sentences2)):
        try:
            feature=model[sentences2[i]]
            print(feature)
            w2v_embed.append(feature)
        except:
            #pass if there is an error to not distort averages... :)
            pass

    out_embed=np.zeros(size)
    for j in range(len(w2v_embed)):
        out_embed=out_embed+np.array(w2v_embed[j])

    out_embed=(1/len(w2v_embed))*out_embed
    print(len(w2v_embed))
    features=out_embed
    labels=list()
    for i in range(len(features)):
        labels.append('fast_feature_%s'%(str(i+1)))

    return features, labels