def handle(self, dataset_id, *args, **options):
num_topics = options.get('num_topics')
name = options.get('name')
if not dataset_id:
raise CommandError("Dataset id is required.")
try:
dataset_id = int(dataset_id)
except ValueError:
raise CommandError("Dataset id must be a number.")
from msgvis.apps.enhance.tasks import default_topic_context, standard_topic_pipeline
context = default_topic_context(name, dataset_id=dataset_id)
standard_topic_pipeline(context, dataset_id=dataset_id, num_topics=int(num_topics))
def handle(self, dataset_id, *args, **options):
num_topics = options.get('num_topics')
name = options.get('name')
if not dataset_id:
raise CommandError("Dataset id is required.")
try:
dataset_id = int(dataset_id)
except ValueError:
raise CommandError("Dataset id must be a number.")
from msgvis.apps.enhance.tasks import default_topic_context, standard_topic_pipeline
context = default_topic_context(name, dataset_id=dataset_id)
dictionary = context.find_dictionary()
if dictionary is None:
dictionary = context.build_dictionary(dataset_id=dataset_id)
if not context.bows_exist(dictionary):
context.build_bows(dictionary)
def handle(self, dataset_id, *args, **options):
num_topics = options.get('num_topics')
name = options.get('name')
if not dataset_id:
raise CommandError("Dataset id is required.")
try:
dataset_id = int(dataset_id)
except ValueError:
raise CommandError("Dataset id must be a number.")
from msgvis.apps.enhance.tasks import default_topic_context, standard_topic_pipeline
context = default_topic_context(name, dataset_id=dataset_id)
dictionary = context.find_dictionary()
if dictionary is None:
dictionary = context.build_dictionary(dataset_id=dataset_id)
if not context.bows_exist(dictionary):
context.build_bows(dictionary)
def test_topic_modeling(self):
"""Generate some test messages and actually model topics"""
randomseed = 1
from numpy import random as nprandom
import random
nprandom.seed(randomseed)
random.seed(randomseed)
n_messages = 50
n_words = 5
num_topics = 2
topic_a_vocab = ['catskl', 'sshat', 'ssmarble']
topic_b_vocab = ['oppossum', 'lasso', 'amalgam']
total_words = len(topic_a_vocab) + len(topic_b_vocab)
english, created = corpus_models.Language.objects.get_or_create(
code='en', name="English")
for i in xrange(n_messages):
if i < n_messages / 2:
vocab = topic_a_vocab
else:
vocab = topic_b_vocab
self.dataset.message_set.create(
text=" ".join(random.choice(vocab) for w in xrange(n_words)),
language=english,
)
context = tasks.default_topic_context("test_topic_modeling",
dataset_id=self.dataset.id)
tasks.standard_topic_pipeline(context,
dataset_id=self.dataset.id,
num_topics=num_topics,
multicore=False)
dictionary = models.Dictionary.objects.get(name='test_topic_modeling')
# Check the basic stats of the dictionary
self.assertEquals(dictionary.num_docs, n_messages)
self.assertEquals(dictionary.num_pos, n_messages * n_words)
# Check the links to words
self.assertEquals(dictionary.words.count(), total_words)
# Check the links to topic models
self.assertEquals(dictionary.topicmodel_set.count(), 1)
topic_model = dictionary.topicmodel_set.first()
self.assertLess(topic_model.perplexity, -1)
# Check the number of topics
self.assertEquals(topic_model.topics.count(), num_topics)
topics = topic_model.topics.all()
topic_a = topics[0]
topic_b = topics[1]
# Should be the proper number of messages with positive topic probabilities
# The - 3 factor on the end allows a little wiggle room for randomness
# Count the messages that prefer each topic
from collections import defaultdict
topic_count = defaultdict(int)
for msg in self.dataset.message_set.all():
topic = topic_model.get_probable_topic(msg)
topic_count[topic] += 1
self.assertEquals(topic_count, {
topic_a: n_messages / 2,
topic_b: n_messages / 2,
})
# The words should be in the default topic names
for word in topic_a_vocab + topic_b_vocab:
self.assertTrue(word in topic_a.name or word in topic_b.name)