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

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 [ ]: