def testMaxModelsOnDisc2(ensemble_backend):
# Test for Extreme scenarios
# Make sure that the best predictions are kept
ensbuilder = EnsembleBuilder(
backend=ensemble_backend,
dataset_name="TEST",
task_type=BINARY_CLASSIFICATION,
metric=roc_auc,
seed=0, # important to find the test files
ensemble_nbest=50,
max_models_on_disc=10000.0,
)
ensbuilder.read_preds = {}
for i in range(50):
ensbuilder.read_scores['pred' + str(i)] = {
'ens_score': i * 10,
'num_run': i,
'loaded': 1,
"seed": 1,
"disc_space_cost_mb": 50 * i,
}
ensbuilder.read_preds['pred' + str(i)] = {Y_ENSEMBLE: True}
sel_keys = ensbuilder.get_n_best_preds()
assert ['pred49', 'pred48', 'pred47'] == sel_keys
# Make sure at least one model is kept alive
ensbuilder.max_models_on_disc = 0.0
sel_keys = ensbuilder.get_n_best_preds()
assert ['pred49'] == sel_keys
def testPerformanceRangeThresholdMaxBest(self):
to_test = ((0.0, 1, 1), (0.0, 1.0, 4), (0.1, 2, 2), (0.3, 4, 3),
(0.5, 1, 1), (0.6, 10, 2), (0.8, 0.5, 1), (1, 1.0, 1))
for performance_range_threshold, ensemble_nbest, exp in to_test:
ensbuilder = EnsembleBuilder(
backend=self.backend,
dataset_name="TEST",
task_type=1, # Binary Classification
metric=roc_auc,
limit=-1, # not used,
seed=0, # important to find the test files
ensemble_nbest=ensemble_nbest,
performance_range_threshold=performance_range_threshold,
max_models_on_disc=None,
)
ensbuilder.read_preds = {
'A': {'ens_score': 1, 'num_run': 1, 0: True, 'loaded': -1, "seed": 1},
'B': {'ens_score': 2, 'num_run': 2, 0: True, 'loaded': -1, "seed": 1},
'C': {'ens_score': 3, 'num_run': 3, 0: True, 'loaded': -1, "seed": 1},
'D': {'ens_score': 4, 'num_run': 4, 0: True, 'loaded': -1, "seed": 1},
'E': {'ens_score': 5, 'num_run': 5, 0: True, 'loaded': -1, "seed": 1},
}
sel_keys = ensbuilder.get_n_best_preds()
self.assertEqual(len(sel_keys), exp)
def testPerformanceRangeThresholdMaxBest(ensemble_backend,
performance_range_threshold,
ensemble_nbest, exp):
ensbuilder = EnsembleBuilder(
backend=ensemble_backend,
dataset_name="TEST",
task_type=BINARY_CLASSIFICATION,
metric=roc_auc,
seed=0, # important to find the test files
ensemble_nbest=ensemble_nbest,
performance_range_threshold=performance_range_threshold,
max_models_on_disc=None,
)
ensbuilder.read_scores = {
'A': {
'ens_score': 1,
'num_run': 1,
'loaded': -1,
"seed": 1
},
'B': {
'ens_score': 2,
'num_run': 2,
'loaded': -1,
"seed": 1
},
'C': {
'ens_score': 3,
'num_run': 3,
'loaded': -1,
"seed": 1
},
'D': {
'ens_score': 4,
'num_run': 4,
'loaded': -1,
"seed": 1
},
'E': {
'ens_score': 5,
'num_run': 5,
'loaded': -1,
"seed": 1
},
}
ensbuilder.read_preds = {
key: {key_2: True
for key_2 in (Y_ENSEMBLE, Y_VALID, Y_TEST)}
for key in ensbuilder.read_scores
}
sel_keys = ensbuilder.get_n_best_preds()
assert len(sel_keys) == exp
def testMaxModelsOnDisc(self):
ensemble_nbest = 4
for (test_case, exp) in [
# If None, no reduction
(None, 2),
# If Int, limit only on exceed
(4, 2),
(1, 1),
# If Float, translate float to # models.
# below, mock of each file is 100 Mb and
# 4 files .model and .npy (test/val/pred) exist
(700.0, 1),
(800.0, 2),
(9999.0, 2),
]:
ensbuilder = EnsembleBuilder(
backend=self.backend,
dataset_name="TEST",
task_type=1, # Binary Classification
metric=roc_auc,
limit=-1, # not used,
seed=0, # important to find the test files
ensemble_nbest=ensemble_nbest,
max_models_on_disc=test_case,
)
with unittest.mock.patch('os.path.getsize') as mock:
mock.return_value = 100 * 1024 * 1024
ensbuilder.score_ensemble_preds()
sel_keys = ensbuilder.get_n_best_preds()
self.assertEqual(len(sel_keys), exp)
# Test for Extreme scenarios
# Make sure that the best predictions are kept
ensbuilder = EnsembleBuilder(
backend=self.backend,
dataset_name="TEST",
task_type=1, # Binary Classification
metric=roc_auc,
limit=-1, # not used,
seed=0, # important to find the test files
ensemble_nbest=50,
max_models_on_disc=10000.0,
)
ensbuilder.read_preds = {}
for i in range(50):
ensbuilder.read_preds['pred' + str(i)] = {
'ens_score': i * 10,
'num_run': i,
0: True,
'loaded': 1,
"seed": 1,
"disc_space_cost_mb": 50 * i,
}
sel_keys = ensbuilder.get_n_best_preds()
self.assertListEqual(['pred49', 'pred48', 'pred47', 'pred46'],
sel_keys)
# Make sure at least one model is kept alive
ensbuilder.max_models_on_disc = 0.0
sel_keys = ensbuilder.get_n_best_preds()
self.assertListEqual(['pred49'], sel_keys)
