Created
August 18, 2017 09:04
-
-
Save Couhp/6722b33fd9ce212dcc5f345354915278 to your computer and use it in GitHub Desktop.
LDA by python
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
# -*- coding: utf-8 -*- | |
from nltk.tokenize import RegexpTokenizer | |
from nltk.stem.porter import PorterStemmer | |
from gensim import corpora, models | |
import gensim | |
from os import listdir | |
from os.path import isfile, join | |
import time | |
import logging | |
log_number = open("LDA_Log/Logging","r").read() | |
update_log = open("LDA_Log/Logging","w") | |
update_log.writelines(str(int(log_number) + 1)) | |
update_log.close() | |
#logging.basicConfig(filename='LDA_Log/lda_model_' + log_number + '.log', format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO) | |
tokenizer = RegexpTokenizer(r'\w+') | |
# create sample documents | |
mypath = "training" | |
listFile = [f for f in listdir(mypath) if isfile(join(mypath, f))] | |
# compile sample documents into a list | |
doc_set = [] | |
start_time = time.time() | |
for inputFile in listFile : | |
f = open(join(mypath,inputFile), "r") | |
inputStr = f.read() | |
if len(inputStr) < 30 : | |
inputStr += " " + inputStr | |
doc_set.append(inputStr) | |
end_time = time.time() | |
print ("Time load : ", (end_time - start_time)*1000 , " ms") | |
print ("The number of documents", len(doc_set)) | |
# loop through document list | |
texts = [] | |
for doc in doc_set: | |
# clean and tokenize document string | |
texts.append(doc.split(" ")) | |
# add tokens to list | |
# texts.append(stemmed_tokens) | |
# turn our tokenized documents into a id <-> term dictionary | |
dictionary = corpora.Dictionary(texts) | |
dictionary.save("dictionary.dict") | |
# convert tokenized documents into a document-term matrix | |
corpus = [dictionary.doc2bow(text) for text in texts] | |
# generate LDA model | |
start_time = time.time() | |
ldamodel = gensim.models.ldamulticore.LdaMulticore(corpus, num_topics = 380, id2word = dictionary, passes = 10,eval_every=5, workers=5) | |
end_time = time.time() | |
print ("Time load : ", (end_time - start_time) , " s") | |
topics = ldamodel.print_topics(num_topics=-1) | |
for topic in topics : | |
print ("Topic : ", topic) | |
ldamodel.save("ldamodel.model") #Save the model for next time.... | |
# data = texts[1] | |
# a = ldamodel[data] | |
# print a | |
# for i in range(5) : | |
# data = ldamodel.get_document_topics(corpus[i]) | |
# print (data) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment