def test_compute_prediction(self):
model = Mljar(project=self.proj_title,
experiment=self.expt_title,
algorithms=['rfc'],
metric='logloss',
validation_kfolds=3,
tuning_mode='Normal',
single_algorithm_time_limit=1)
self.assertTrue(model is not None)
# fit models and wait till all models are trained
model.fit(X=self.X, y=self.y, dataset_title='My dataset')
# get project id
project_id = model.project.hid
# get model id
model_id = model.selected_algorithm.hid
dc = DatasetClient(project_id)
init_datasets_cnt = len(dc.get_datasets())
# compute predictions
pred = Mljar.compute_prediction(self.X, model_id, project_id)
# compute score
score = self.mse(pred, self.y)
self.assertTrue(score < 0.9)
# check if dataset was removed
self.assertEqual(init_datasets_cnt, len(dc.get_datasets()))
# run predictions again, but keep dataset
pred = Mljar.compute_prediction(self.X,
model_id,
project_id,
keep_dataset=True)
self.assertEqual(init_datasets_cnt + 1,
len(dc.get_datasets())) # should be one more
def test_add_dataset_for_prediction(self):
# setup dataset client
dc = DatasetClient(self.project.hid)
self.assertNotEqual(dc, None)
# get datasets, there should be none
datasets = dc.get_datasets()
self.assertEqual(len(datasets), 0)
# add dataset
my_dataset = dc.add_dataset_if_not_exists(self.X, None)
self.assertNotEqual(my_dataset, None)
# get datasets
datasets = dc.get_datasets()
self.assertEqual(len(datasets), 1)
my_dataset_2 = dc.get_dataset(my_dataset.hid)
self.assertEqual(my_dataset.hid, my_dataset_2.hid)
self.assertEqual(my_dataset.title, my_dataset_2.title)
def test_add_existing_dataset(self):
# setup dataset client
dc = DatasetClient(self.project.hid)
self.assertNotEqual(dc, None)
# get initial number of datasets
init_datasets_cnt = len(dc.get_datasets())
# add dataset
dc.add_dataset_if_not_exists(self.X, self.y)
# get datasets
datasets = dc.get_datasets()
self.assertEqual(len(datasets), init_datasets_cnt + 1)
# add the same dataset
# it shouldn't be added
dc.add_dataset_if_not_exists(self.X, self.y)
# number of all datasets in project should be 1
datasets = dc.get_datasets()
self.assertEqual(len(datasets), init_datasets_cnt + 1)
def test_create_and_delete(self):
# setup dataset client
dc = DatasetClient(self.project.hid)
self.assertNotEqual(dc, None)
# get initial number of datasets
init_datasets_cnt = len(dc.get_datasets())
# add dataset
my_dataset_1 = dc.add_dataset_if_not_exists(self.X, self.y)
my_dataset_2 = dc.add_dataset_if_not_exists(self.X, y=None)
# get datasets
datasets = dc.get_datasets()
self.assertEqual(len(datasets), init_datasets_cnt + 2)
# delete added dataset
dc.delete_dataset(my_dataset_1.hid)
# check number of datasets
datasets = dc.get_datasets()
self.assertEqual(len(datasets), init_datasets_cnt + 1)
def test_add_dataset_for_training(self):
# setup dataset client
dc = DatasetClient(self.project.hid)
self.assertNotEqual(dc, None)
# get datasets, there should be none
datasets = dc.get_datasets()
self.assertEqual(len(datasets), 0)
# add dataset
my_dataset = dc.add_dataset_if_not_exists(self.X, self.y)
self.assertNotEqual(my_dataset, None)
# get datasets
datasets = dc.get_datasets()
self.assertEqual(len(datasets), 1)
my_dataset_2 = dc.get_dataset(my_dataset.hid)
self.assertEqual(my_dataset.hid, my_dataset_2.hid)
self.assertEqual(my_dataset.title, my_dataset_2.title)
# test __str__ method
self.assertTrue('id' in str(my_dataset_2))
self.assertTrue('title' in str(my_dataset_2))
self.assertTrue('file' in str(my_dataset_2))