def serialize(self):
BleiCorpus.serialize(self.corpus_path, self, id2word=self.reviews_dictionary)
return self
def serialize(self):
BleiCorpus.serialize(self.corpus_path,
self,
id2word=self.reviews_dictionary)
return self
def serialize(self):
u'''Serialize corpus'''
BleiCorpus.serialize(self.corpus_path, self, \
id2word=self.corpus_dictionary)
return self
print "pos-tag", nelem
folder = 'models_unigram_topics_all_pos'
dictionary_path = folder + "/dictionary.dict"
corpus_path = folder + "/corpus.lda-c"
lda_num_topics = 250
lda_model_path = folder + "/lda_model_" + str(lda_num_topics) + "_topics.lda"
print "created paths"
dictionary = corpora.Dictionary(review["words"] for review in corpus_list)
dictionary.filter_extremes(keep_n=10000)
dictionary.compactify()
corpora.Dictionary.save(dictionary, dictionary_path)
corpus = [dictionary.doc2bow(review["words"]) for review in corpus_list]
BleiCorpus.serialize(corpus_path, corpus, id2word=dictionary)
corpus = corpora.BleiCorpus(corpus_path)
print "running lda"
lda = gensim.models.LdaMulticore(corpus,
num_topics=lda_num_topics,
id2word=dictionary,
minimum_probability=0.,
workers=8)
lda.save(lda_model_path)
print "done lda"
dictionary = corpora.Dictionary.load(dictionary_path)
corpus = corpora.BleiCorpus(corpus_path)
lda = LdaMulticore.load(lda_model_path)
i = 0
def handle(self, *args, **options):
super(Command, self).handle(self, *args, **options)
#Create temporary directory to write the corpus LDA-C files
temp_dir_path = tempfile.mkdtemp()
corpus_path = temp_dir_path + "/corpus.lda-c"
lda_num_topics = 50
for database in self.selected_dbs:
print "Processing database " + database
#Building dictionary
print "Building dictionary"
dictionary = Dictionary()
queryset = Comment.objects.using(database).exclude(
text__isnull=True)
self.pbar_setup(maxval=queryset.count())
for comment in queryset_iterator(queryset, chunksize=50):
dictionary.add_documents(
[[word.word for word in comment.text.word_set.all()]])
self.pbar_increment()
self.pbar_destroy()
dictionary.filter_extremes(keep_n=10000)
dictionary.compactify()
#Serialize corpus
print "Serializing corpus"
corpus = Corpus(
queryset_iterator(Comment.objects.using(database).all(),
chunksize=50), dictionary)
BleiCorpus.serialize(corpus_path, corpus, id2word=dictionary)
#Train
print "Training..."
bleicorpus = BleiCorpus(corpus_path)
lda = gensim.models.LdaModel(bleicorpus,
num_topics=lda_num_topics,
id2word=dictionary)
#Saving
print "Saving results to DB"
lda_db_obj, created = Algorithm.objects.using(
database).get_or_create(name='LDA')
#Removing previous results
lda_db_obj.result_set.all().delete()
#Looping through results and saving to DB
i = 0
for topic in lda.show_topics(num_topics=lda_num_topics):
Result.objects.using(database).create(sequence=i,
value=str(topic),
algorithm=lda_db_obj)
i += 1
#Remove temporary directory
#Check first if it's not the current working directory, as removing it
# would be a disaster! ;)
if os.getcwd() != temp_dir_path:
#Just remove it if it's a temp dir
shutil.rmtree(temp_dir_path)
else:
#If it's the current working directory, just remove the uneeded files
map(os.remove, glob.glob('corpus.lda-c*'))
self.stdout.write(self.style.SUCCESS('Command executed succesfully'))
def serialize(self):
# serialize(serializer, fname, corpus, id2word=None, index_fname=None, progress_cnt=None, labels=None, metadata=False)
# Iterate through the document stream corpus, saving the documents to fname and recording byte offset of each document. Save the resulting index structure to file index_fname (or fname.index is not set).
BleiCorpus.serialize(self.corpus_path, self, id2word=self.tag_dictionary)
return self
def serialize(self):
u'''Serialize corpus'''
BleiCorpus.serialize(self.corpus_path, self, \
id2word=self.corpus_dictionary)
return self
