Last active
January 3, 2018 15:22
-
-
Save msubhash/468390e22ed660a1eafdae62a33c965c to your computer and use it in GitHub Desktop.
Word2Vec on Catalog description
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 gensim.models import Phrases | |
from gensim.models import Word2Vec | |
from nltk.tokenize import RegexpTokenizer | |
from nltk.corpus import stopwords | |
import re | |
sentences = [] | |
fname = "model.mm" | |
input_file="stories_15k.txt" | |
#Remove stop words. Not doing all the data cleaning here. | |
def preprocess(sentence): | |
sentence = sentence.lower() | |
tokenizer = RegexpTokenizer(r'\w+') | |
tokens = tokenizer.tokenize(sentence) | |
filtered_words = [w for w in tokens if not w in stopwords.words('english')] | |
return " ".join(filtered_words) | |
with open(input_file) as f: | |
data = f.readlines() | |
#preprocess - remove stop words. | |
for sentence in data: | |
sentences.append(sentence) | |
#Initialize model | |
model = Word2Vec([s.split() for s in sentences], size=100, window=5, min_count=5, workers=4) | |
#Save the model | |
model.save(fname) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment