Last active
August 29, 2015 14:08
-
-
Save KayneWest/dc005e9e596e77496395 to your computer and use it in GitHub Desktop.
word2vec_model.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from string import translate,maketrans,punctuation | |
from itertools import chain | |
from nltk import PunktSentenceTokenizer | |
import datetime | |
import re | |
def log(msg): | |
print("{} {}".format(str(datetime.datetime.now()), msg)) | |
def removeNonAscii(s): | |
return "".join(filter(lambda x: ord(x)<128, s)) | |
# keeps -, +, # in words | |
punctuation = punctuation.replace('-','').replace('+','').replace('#','') | |
#makes a C translation dictionary converting punctuations to white spaces | |
Trans = maketrans(punctuation, ' '*len(punctuation)) | |
#splits text into sentences' | |
tknr = PunktSentenceTokenizer() | |
#fast ngrammer if you end up using it for phrases | |
def ngrammer2(l,n): | |
temp = [" ".join(l[i:i+n]) for i in xrange(0,len(l)) if len(l[i:i+n])==n] | |
return temp | |
print 'Loading the post data' | |
import pickle | |
s=pickle.load(open("title_and_job.p","rb")) | |
x_train_RAW=[] | |
for i in s: | |
if len(i.values()[0])>=30: | |
title=i.keys()[0] | |
for q in i.values()[0]: | |
x_train_RAW.append(q.encode('utf-8')) | |
#can use the ngrammer here if you want to look at phrase similarity | |
#I get rid of html characters from this corpus | |
def spliter(jobpost): | |
sentences2=[] | |
s=tknr.tokenize(jobpost) | |
cleaned_words = [list(translate(re.sub(r'[0-9]|\-|\\~|\`|\@|\$|\%|\^|\&|\*|\(|\)|\_|\=|\[|\]|\\|\<|\<|\>|\?|\/|\;|\\.',' ',sentence).lower().encode('utf-8'),Trans).split()) for sentence in s] | |
#two_three_ngrams = [ngrammer2(sent,num) for num in [1,2,3] for sent in cleaned_words] | |
for U in cleaned_words: | |
sentences2.append(U) | |
sentences2=list(chain(*sentences2)) | |
return sentences2 | |
#i always do this, not sure why. | |
import random | |
random.shuffle(x_train_RAW) | |
#going to multiprocess the tokenizer to make it faster | |
from multiprocessing import Pool,cpu_count | |
pool=Pool(cpu_count()) | |
print 'starting to sentence tokenize' | |
x_train_RAW=filter(None,pool.map(spliter,x_train_RAW)) | |
import gensim | |
from multiprocessing import cpu_count | |
model = gensim.models.Word2Vec(x_train_RAW, size=100, window=5, min_count=5, workers=cpu_count()) | |
pickle.dump(model,open('model.p','wb')) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment