def test_evaluate(self):
numpy_optimizer = NumpyBigramOptimizer(self.statistics,
self.vocabulary)
theano_optimizer = TheanoBigramOptimizer(self.statistics,
self.vocabulary)
word_id = numpy_optimizer.get_word_id('d')
orig_class_id = numpy_optimizer.get_word_class(word_id)
new_class_id = 1 if orig_class_id != 1 else 0
orig_ll = numpy_optimizer.log_likelihood()
self.assertTrue(
numpy.isclose(orig_ll, theano_optimizer.log_likelihood()))
ll_diff = numpy_optimizer._evaluate(word_id, new_class_id)
self.assertTrue(
numpy.isclose(ll_diff,
theano_optimizer._evaluate(word_id, new_class_id)))
numpy_optimizer._move(word_id, new_class_id)
new_ll = numpy_optimizer.log_likelihood()
self.assertFalse(numpy.isclose(orig_ll, new_ll))
self.assertTrue(numpy.isclose(orig_ll + ll_diff, new_ll))
theano_optimizer._move(word_id, new_class_id)
self.assertTrue(
numpy.isclose(new_ll, theano_optimizer.log_likelihood()))
def test_evaluate(self):
numpy_optimizer = NumpyBigramOptimizer(self.statistics, self.vocabulary)
theano_optimizer = TheanoBigramOptimizer(self.statistics, self.vocabulary)
word_id = numpy_optimizer.get_word_id('d')
orig_class_id = numpy_optimizer.get_word_class(word_id)
new_class_id = 1 if orig_class_id != 1 else 0
orig_ll = numpy_optimizer.log_likelihood()
self.assertTrue(numpy.isclose(orig_ll, theano_optimizer.log_likelihood()))
ll_diff = numpy_optimizer._evaluate(word_id, new_class_id)
self.assertTrue(numpy.isclose(ll_diff, theano_optimizer._evaluate(word_id, new_class_id)))
numpy_optimizer._move(word_id, new_class_id)
new_ll = numpy_optimizer.log_likelihood()
self.assertFalse(numpy.isclose(orig_ll, new_ll))
self.assertTrue(numpy.isclose(orig_ll + ll_diff, new_ll))
theano_optimizer._move(word_id, new_class_id)
self.assertTrue(numpy.isclose(new_ll, theano_optimizer.log_likelihood()))
