维基百科语料中的词语相似度探索

......
INFO: 53665431  Pampapaul
INFO: 53665433  Charles Frederick Zimpel
INFO: Finished 11-process extraction of 5375019 articles in 8363.5s (642.7 art/s)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: Pan Yang (panyangnlp@gmail.com)
# Copyright 2017 @ Yu Zhen
 
import gensim
import logging
import multiprocessing
import os
import re
import sys
 
from pattern.en import tokenize
from time import time
 
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',
                    level=logging.INFO)
 
 
def cleanhtml(raw_html):
    cleanr = re.compile('<.*?>')
    cleantext = re.sub(cleanr, ' ', raw_html)
    return cleantext
 
 
class MySentences(object):
    def __init__(self, dirname):
        self.dirname = dirname
 
    def __iter__(self):
        for root, dirs, files in os.walk(self.dirname):
            for filename in files:
                file_path = root + '/' + filename
                for line in open(file_path):
                    sline = line.strip()
                    if sline == "":
                        continue
                    rline = cleanhtml(sline)
                    tokenized_line = ' '.join(tokenize(rline))
                    is_alpha_word_line = [word for word in
                                          tokenized_line.lower().split()
                                          if word.isalpha()]
                    yield is_alpha_word_line
 
 
if __name__ == '__main__':
    if len(sys.argv) != 2:
        print "Please use python train_with_gensim.py data_path"
        exit()
    data_path = sys.argv[1]
    begin = time()
 
    sentences = MySentences(data_path)
    model = gensim.models.Word2Vec(sentences,
                                   size=200,
                                   window=10,
                                   min_count=10,
                                   workers=multiprocessing.cpu_count())
    model.save("data/model/word2vec_gensim")
    model.wv.save_word2vec_format("data/model/word2vec_org",
                                  "data/model/vocabulary",
                                  binary=False)
 
    end = time()
    print "Total procesing time: %d seconds" % (end - begin)

2017-04-22 14:31:04,703 : INFO : collecting all words and their counts
2017-04-22 14:31:04,704 : INFO : PROGRESS: at sentence #0, processed 0 words, keeping 0 word types
2017-04-22 14:31:06,442 : INFO : PROGRESS: at sentence #10000, processed 480546 words, keeping 33925 word types
2017-04-22 14:31:08,104 : INFO : PROGRESS: at sentence #20000, processed 983240 words, keeping 51765 word types
2017-04-22 14:31:09,685 : INFO : PROGRESS: at sentence #30000, processed 1455218 words, keeping 64982 word types
2017-04-22 14:31:11,349 : INFO : PROGRESS: at sentence #40000, processed 1957479 words, keeping 76112 word types
......
2017-04-23 02:50:59,844 : INFO : worker thread finished; awaiting finish of 2 more threads                                                                      2017-04-23 02:50:59,844 : INFO : worker thread finished; awaiting finish of 1 more threads                                                                      2017-04-23 02:50:59,854 : INFO : worker thread finished; awaiting finish of 0 more threads                                                                      2017-04-23 02:50:59,854 : INFO : training on 8903084745 raw words (6742578791 effective words) took 37805.2s, 178351 effective words/s                          
2017-04-23 02:50:59,855 : INFO : saving Word2Vec object under data/model/word2vec_gensim, separately None                                                       
2017-04-23 02:50:59,855 : INFO : not storing attribute syn0norm                 
2017-04-23 02:50:59,855 : INFO : storing np array 'syn0' to data/model/word2vec_gensim.wv.syn0.npy                                                              
2017-04-23 02:51:00,241 : INFO : storing np array 'syn1neg' to data/model/word2vec_gensim.syn1neg.npy                                                           
2017-04-23 02:51:00,574 : INFO : not storing attribute cum_table                
2017-04-23 02:51:13,886 : INFO : saved data/model/word2vec_gensim               
2017-04-23 02:51:13,886 : INFO : storing vocabulary in data/model/vocabulary    
2017-04-23 02:51:17,480 : INFO : storing 868777x200 projection weights into data/model/word2vec_org                                                             
Total procesing time: 44476 seconds

textminer@textminer:/opt/wiki/data$ ipython
Python 2.7.12 (default, Nov 19 2016, 06:48:10) 
Type "copyright", "credits" or "license" for more information.
 
IPython 2.4.1 -- An enhanced Interactive Python.
?         -> Introduction and overview of IPython's features.
%quickref -> Quick reference.
help      -> Python's own help system.
object?   -> Details about 'object', use 'object??' for extra details.
 
In [1]: from gensim.models import Word2Vec
 
In [2]: en_wiki_word2vec_model = Word2Vec.load('data/model/word2vec_gensim')

In [3]: en_wiki_word2vec_model.most_similar('word')
Out[3]: 
[('phrase', 0.8129693269729614),
 ('meaning', 0.7311851978302002),
 ('words', 0.7010501623153687),
 ('adjective', 0.6805518865585327),
 ('noun', 0.6461974382400513),
 ('suffix', 0.6440576314926147),
 ('verb', 0.6319557428359985),
 ('loanword', 0.6262609958648682),
 ('proverb', 0.6240501403808594),
 ('pronunciation', 0.6105246543884277)]

In [4]: en_wiki_word2vec_model.most_similar('similarity')
Out[4]: 
[('similarities', 0.8517599701881409),
 ('resemblance', 0.786037266254425),
 ('resemblances', 0.7496883869171143),
 ('affinities', 0.6571112275123596),
 ('differences', 0.6465682983398438),
 ('dissimilarities', 0.6212711930274963),
 ('correlation', 0.6071442365646362),
 ('dissimilarity', 0.6062943935394287),
 ('variation', 0.5970577001571655),
 ('difference', 0.5928016901016235)]

In [5]: en_wiki_word2vec_model.most_similar('nlp')
Out[5]: 
[('neurolinguistic', 0.6698148250579834),
 ('psycholinguistic', 0.6388964056968689),
 ('connectionism', 0.6027182936668396),
 ('semantics', 0.5866401195526123),
 ('connectionist', 0.5865628719329834),
 ('bandler', 0.5837364196777344),
 ('phonics', 0.5733655691146851),
 ('psycholinguistics', 0.5613113641738892),
 ('bootstrapping', 0.559638261795044),
 ('psychometrics', 0.5555593967437744)]

In [6]: en_wiki_word2vec_model.most_similar('learn')
Out[6]: 
[('teach', 0.7533557415008545),
 ('understand', 0.71148681640625),
 ('discover', 0.6749690771102905),
 ('learned', 0.6599283218383789),
 ('realize', 0.6390970349311829),
 ('find', 0.6308424472808838),
 ('know', 0.6171890497207642),
 ('tell', 0.6146825551986694),
 ('inform', 0.6008728742599487),
 ('instruct', 0.5998791456222534)]

In [7]: en_wiki_word2vec_model.most_similar('man')
Out[7]: 
[('woman', 0.7243080735206604),
 ('boy', 0.7029494047164917),
 ('girl', 0.6441491842269897),
 ('stranger', 0.63275545835495),
 ('drunkard', 0.6136815547943115),
 ('gentleman', 0.6122575998306274),
 ('lover', 0.6108279228210449),
 ('thief', 0.609005331993103),
 ('beggar', 0.6083744764328003),
 ('person', 0.597919225692749)]

In [8]: en_wiki_word2vec_model.most_similar(positive=['woman', 'king'], negative=['man'], topn=1)
Out[8]: [('queen', 0.7752252817153931)]
 
In [9]: en_wiki_word2vec_model.similarity('woman', 'man')
Out[9]: 0.72430799548282099
 
In [10]: en_wiki_word2vec_model.doesnt_match("breakfast cereal dinner lunch".split())
Out[10]: 'cereal'