def setUp(self):
dataset_filepath = config.ROOT + '/python/test/resource/NFLX_dataset_public_raw.py'
dataset = import_python_file(dataset_filepath)
np.random.seed(0)
info_dict = {
'missing_probability': 0.1,
}
self.dataset_reader = MissingDataRawDatasetReader(dataset, input_dict=info_dict)
def test_observer_content_aware_subjective_model_missingdata(self):
dataset = import_python_file(self.dataset_filepath)
np.random.seed(0)
info_dict = {
'missing_probability': 0.1,
}
dataset_reader = MissingDataRawDatasetReader(dataset, input_dict=info_dict)
subjective_model = MaximumLikelihoodEstimationModel(dataset_reader)
result = subjective_model.run_modeling()
self.assertAlmostEquals(np.sum(result['content_bias']), 0, places=4)
self.assertAlmostEquals(np.var(result['content_bias']), 0, places=4)
self.assertAlmostEquals(np.sum(result['content_ambiguity']), 3.9104244772977128, places=4)
self.assertAlmostEquals(np.var(result['content_ambiguity']), 0.0037713583509767193, places=4)
self.assertAlmostEquals(np.sum(result['observer_bias']), -0.21903272050455846, places=4)
self.assertAlmostEquals(np.var(result['observer_bias']), 0.084353684687185043, places=4)
self.assertAlmostEquals(np.sum(result['observer_inconsistency']), 9.8168943054654481, places=4)
self.assertAlmostEquals(np.var(result['observer_inconsistency']), 0.028159236075789944, places=4)
self.assertAlmostEquals(np.sum(result['quality_scores']), 280.05548186797336, places=4)
self.assertAlmostEquals(np.var(result['quality_scores']), 1.4339487982797514, places=4)
np.random.seed(0)
info_dict = {
'missing_probability': 0.5,
}
dataset_reader = MissingDataRawDatasetReader(dataset, input_dict=info_dict)
subjective_model = MaximumLikelihoodEstimationModel(dataset_reader)
result = subjective_model.run_modeling()
self.assertAlmostEquals(np.sum(result['content_bias']), 0, places=4)
self.assertAlmostEquals(np.var(result['content_bias']), 0, places=4)
self.assertAlmostEquals(np.sum(result['content_ambiguity']), 2.63184284168883, places=4)
self.assertAlmostEquals(np.var(result['content_ambiguity']), 0.019164097909450246, places=4)
self.assertAlmostEquals(np.sum(result['observer_bias']), 0.2263148440748638, places=4)
self.assertAlmostEquals(np.var(result['observer_bias']), 0.070613033112114504, places=4)
self.assertAlmostEquals(np.sum(result['observer_inconsistency']), 12.317917502439435, places=4)
self.assertAlmostEquals(np.var(result['observer_inconsistency']), 0.029455722248727296, places=4)
self.assertAlmostEquals(np.sum(result['quality_scores']), 280.29962156788139, places=4)
self.assertAlmostEquals(np.var(result['quality_scores']), 1.4717366222424826, places=4)
class MissingDatasetReaderTest(unittest.TestCase):
def setUp(self):
dataset_filepath = config.ROOT + '/python/test/resource/NFLX_dataset_public_raw.py'
dataset = import_python_file(dataset_filepath)
np.random.seed(0)
info_dict = {
'missing_probability': 0.1,
}
self.dataset_reader = MissingDataRawDatasetReader(dataset, input_dict=info_dict)
def test_opinion_score_2darray(self):
os_2darray = self.dataset_reader.opinion_score_2darray
self.assertTrue(np.isnan(np.mean(os_2darray)))
self.assertEquals(np.isnan(os_2darray).sum(), 201)
def test_to_dataset(self):
dataset = self.dataset_reader.to_dataset()
old_scores = [dis_video['os'] for dis_video in self.dataset_reader.dataset.dis_videos]
new_scores = [dis_video['os'] for dis_video in dataset.dis_videos]
self.assertNotEquals(old_scores, new_scores)
def run_one_missing_prob(missing_prob, dataset, seed):
np.random.seed(seed)
info_dict = {
'missing_probability': missing_prob,
}
dataset_reader = MissingDataRawDatasetReader(dataset,
input_dict=info_dict)
subjective_model = model_class(dataset_reader)
try:
result = subjective_model.run_modeling(normalize_final=False)
except ValueError as e:
print 'Warning: {}, return result None'.format(e)
result = None
return dataset_reader, result
def test_observer_aware_subjective_model_missingdata(self):
dataset = import_python_file(self.dataset_filepath)
np.random.seed(0)
info_dict = {
'missing_probability': 0.1,
}
dataset_reader = MissingDataRawDatasetReader(dataset, input_dict=info_dict)
subjective_model = MaximumLikelihoodEstimationModelReduced(dataset_reader)
result = subjective_model.run_modeling()
self.assertAlmostEquals(np.sum(result['observer_bias']), -0.18504017984241944, places=4)
self.assertAlmostEquals(np.var(result['observer_bias']), 0.087350553292201705, places=4)
self.assertAlmostEquals(np.sum(result['observer_inconsistency']), 15.520738471447299, places=4)
self.assertAlmostEquals(np.var(result['observer_inconsistency']), 0.010940587327083341, places=4)
self.assertAlmostEquals(np.sum(result['quality_scores']), 279.94975274863879, places=4)
self.assertAlmostEquals(np.var(result['quality_scores']), 1.4325574378911554, places=4)
np.random.seed(0)
info_dict = {
'missing_probability': 0.5,
}
dataset_reader = MissingDataRawDatasetReader(dataset, input_dict=info_dict)
subjective_model = MaximumLikelihoodEstimationModelReduced(dataset_reader)
result = subjective_model.run_modeling()
self.assertAlmostEquals(np.sum(result['observer_bias']), 0.057731868199093525, places=4)
self.assertAlmostEquals(np.var(result['observer_bias']), 0.081341845650928557, places=4)
self.assertAlmostEquals(np.sum(result['observer_inconsistency']), 14.996238224489693, places=4)
self.assertAlmostEquals(np.var(result['observer_inconsistency']), 0.013666025579465165, places=4)
self.assertAlmostEquals(np.sum(result['quality_scores']), 280.67100837103203, places=4)
self.assertAlmostEquals(np.var(result['quality_scores']), 1.4637917512768972, places=4)
