

In [1]:

    
%load_ext autoreload
%autoreload 2



In [2]:

    
import word2vec



In [3]:

    
import numpy as np



In [4]:

    
model = word2vec.load('/Users/danielfrg/Downloads/text8.bin')

Cosine



In [5]:

    
%%timeit
indexes, metrics = model.cosine('word', n=10)









    



10 loops, best of 3: 22.9 ms per loop



In [6]:

    
%%timeit
indexes, metrics = model.cosine('socks', n=10)
model.generate_response(indexes, metrics)









    



10 loops, best of 3: 22.8 ms per loop



In [7]:

    
%%timeit
indexes, metrics = model.cosine('word', n=5000)









    



10 loops, best of 3: 26.2 ms per loop



In [8]:

    
%%timeit
indexes, metrics = model.cosine('word', n=5000)
model.generate_response(indexes, metrics)









    



10 loops, best of 3: 26.4 ms per loop

Analogy



In [9]:

    
%%timeit
indexes, metrics = model.analogy(pos=['paris', 'germany'], neg=['france'], n=10)









    



10 loops, best of 3: 27.5 ms per loop



In [10]:

    
%%timeit
indexes, metrics = model.analogy(pos=['paris', 'germany'], neg=['france'], n=10)
model.generate_response(indexes, metrics)









    



10 loops, best of 3: 31.9 ms per loop



In [11]:

    
%%timeit
indexes, metrics = model.analogy(pos=['paris', 'germany'], neg=['france'], n=5000)









    



10 loops, best of 3: 28.6 ms per loop



In [12]:

    
%%timeit
indexes, metrics = model.analogy(pos=['paris', 'germany'], neg=['france'], n=5000)
model.generate_response(indexes, metrics)









    



10 loops, best of 3: 29.7 ms per loop



In [13]:

    
%%timeit
indexes, metrics = model.analogy(pos=['paris', 'germany'], neg=['france'], n=5000)
model.generate_response(indexes, metrics).tolist()









    



10 loops, best of 3: 26.7 ms per loop

Cluster



In [14]:

    
clusters = word2vec.load_clusters('/Users/danielfrg/Downloads/text8-clusters.txt')



In [15]:

    
model.clusters = clusters



In [16]:

    
%%timeit
indexes, metrics = model.analogy(pos=['paris', 'germany'], neg=['france'], n=10)
model.generate_response(indexes, metrics)









    



10 loops, best of 3: 26.3 ms per loop



In [17]:

    
%%timeit
indexes, metrics = model.analogy(pos=['paris', 'germany'], neg=['france'], n=5000)
model.generate_response(indexes, metrics)









    



10 loops, best of 3: 28.5 ms per loop



In [18]:

    
%%timeit
indexes, metrics = model.analogy(pos=['paris', 'germany'], neg=['france'], n=5000)
model.generate_response(indexes, metrics).tolist()









    



10 loops, best of 3: 28.7 ms per loop



In [ ]: