def run(argv):
parser = ArgumentParser()
parser.add_argument('vem_model', type=str, help='SAM VEM model to use features from')
parser.add_argument('-c', type=float, default=1.0, help='SVM C parameter')
options = parser.parse_args(argv[1:])
log.info('Loading SAM model %s' % options.vem_model)
sam_model = VEMModel.load(options.vem_model)
log.info('Making dataset')
dataset = make_dataset(sam_model)
metric = ClassificationError()
scores = []
for i in range(20):
train_data, test_data = dataset.split(p=0.90, seed=i)
topic_svm = TopicSVM(sam_model, C=options.c, normalize=True)
topic_svm.train(train_data)
predictions = topic_svm.predict(test_data)
score = metric(test_data.targets, predictions)
log.info(score)
scores.append(score)
log.info('Mean classification error: %g' % np.mean(scores))
def run(argv):
parser = ArgumentParser()
parser.add_argument('vem_model',
type=str,
help='SAM VEM model to use features from')
parser.add_argument('-c', type=float, default=1.0, help='SVM C parameter')
options = parser.parse_args(argv[1:])
log.info('Loading SAM model %s' % options.vem_model)
sam_model = VEMModel.load(options.vem_model)
log.info('Making dataset')
dataset = make_dataset(sam_model)
metric = ClassificationError()
scores = []
for i in range(20):
train_data, test_data = dataset.split(p=0.90, seed=i)
topic_svm = TopicSVM(sam_model, C=options.c, normalize=True)
topic_svm.train(train_data)
predictions = topic_svm.predict(test_data)
score = metric(test_data.targets, predictions)
log.info(score)
scores.append(score)
log.info('Mean classification error: %g' % np.mean(scores))
def run(self, options):
if os.path.exists(options.model):
print 'Loading model snapshot from %s' % options.model
model = VEMModel.load(options.model)
else:
# Initialize a model from scratch
print 'Initializing new model'
reader = CorpusReader(options.corpus, data_series='sam')
model = VEMModel(reader=reader, T=options.T)
while model.iteration < options.iterations:
print '** Iteration %d **' % model.iteration
model.run_one_iteration()
if model.iteration % SAVE_MODEL_INTERVAL == 0:
print 'Saving model snapshot...'
model.save(options.model)
if model.iteration % SAVE_TOPICS_INTERVAL == 0:
if options.write_topics:
print 'Saving topics to %s' % options.write_topics
with open(options.write_topics, 'w') as f:
model.write_topics(f)
if options.write_topic_weights:
print 'Saving topic weights to %s' % options.write_topic_weights
with open(options.write_topic_weights, 'w') as f:
model.write_topic_weights_arff(f)
if options.write_topics:
print 'Saving topics to %s' % options.write_topics
with open(options.write_topics, 'w') as f:
model.write_topics(f)
if options.write_topic_weights:
print 'Saving topic weights to %s' % options.write_topic_weights
with open(options.write_topic_weights, 'w') as f:
model.write_topic_weights_arff(f)
model.save(options.model)
def run(self, options):
if os.path.exists(options.model):
print 'Loading model snapshot from %s' % options.model
model = VEMModel.load(options.model)
else:
# Initialize a model from scratch
print 'Initializing new model'
reader = CorpusReader(options.corpus, data_series='sam')
model = VEMModel(reader=reader, T=options.T)
while model.iteration < options.iterations:
print '** Iteration %d **' % model.iteration
model.run_one_iteration()
if model.iteration % SAVE_MODEL_INTERVAL == 0:
print 'Saving model snapshot...'
model.save(options.model)
if model.iteration % SAVE_TOPICS_INTERVAL == 0:
if options.write_topics:
print 'Saving topics to %s' % options.write_topics
with open(options.write_topics, 'w') as f:
model.write_topics(f)
if options.write_topic_weights:
print 'Saving topic weights to %s' % options.write_topic_weights
with open(options.write_topic_weights, 'w') as f:
model.write_topic_weights_arff(f)
if options.write_topics:
print 'Saving topics to %s' % options.write_topics
with open(options.write_topics, 'w') as f:
model.write_topics(f)
if options.write_topic_weights:
print 'Saving topic weights to %s' % options.write_topic_weights
with open(options.write_topic_weights, 'w') as f:
model.write_topic_weights_arff(f)
model.save(options.model)
import numpy as np
from math_util import avk, deriv_avk
from optimize import check_grad
from corpus.corpus import CorpusReader
from vem.model import VEMModel
CORPUS_FILENAME = 'nips-425D.h5'
reader = CorpusReader(CORPUS_FILENAME, data_series='sam')
model = VEMModel(reader)
while True:
model.run_one_iteration()
model.print_topics()
def check_grads(model):
assert np.isfinite(model.l_alpha())
assert np.isfinite(model.l_valpha())
x = model.grad_l_vmu()
assert np.isfinite(x).all()
import pdb
try:
# Main update rules
print 'xi update:', check_grad(model, 'xi', model.l_xi,
model.grad_l_xi)
print 'valpha update:', check_grad(model, 'valpha', model.l_valpha,
model.grad_l_valpha)
import numpy as np
from math_util import avk, deriv_avk
from optimize import check_grad
from corpus.corpus import CorpusReader
from vem.model import VEMModel
CORPUS_FILENAME = 'nips-425D.h5'
reader = CorpusReader(CORPUS_FILENAME, data_series='sam')
model = VEMModel(reader)
while True:
model.run_one_iteration()
model.print_topics()
def check_grads(model):
assert np.isfinite(model.l_alpha())
assert np.isfinite(model.l_valpha())
x = model.grad_l_vmu()
assert np.isfinite(x).all()
import pdb
try:
# Main update rules
print 'xi update:', check_grad(model, 'xi', model.l_xi, model.grad_l_xi)
print 'valpha update:', check_grad(model, 'valpha', model.l_valpha, model.grad_l_valpha)
print 'alpha update:', check_grad(model, 'alpha', model.l_alpha, model.grad_l_alpha)
