def creating_cardinalities(self, min_cardinality=0, max_cardinality=float("+inf")):
"""Create the cardinality object for the learning step.
Args:
min_cardinality (int, optional): minimum value of cardinality to be selected. Defaults to 0.
max_cardinality (float, optional): maximum value of cardinality to be selected. Defaults to float("+inf").
"""
if self.one_model:
list_cardinalities_available = []
for event in self.counter:
cardinality = len(str(self.counter[event]))
min_cardinality = 3
max_cardinality = 8
if cardinality > min_cardinality and cardinality < max_cardinality:
list_cardinalities_available.append(cardinality)
self.set_cardinalities_available = set(list_cardinalities_available)
logger.info(str(len(self.set_cardinalities_available)) + " cardinalities available in this dataset")
self.list_cardinalities.append(Cardinality(cardinality=0, path_w2v=self.path_model_w2v, path_list_classes=self.path_list_classes, size=self.size, one_model=self.one_model, set_cardinalities=self.set_cardinalities_available))
else:
list_cardinalities_available = []
for event in self.counter:
list_cardinalities_available.append(len(str(self.counter[event])))
self.set_cardinalities_available = set(list_cardinalities_available)
logger.info(str(len(self.set_cardinalities_available)) + " cardinalities available in this dataset")
for cardinality in self.set_cardinalities_available:
if cardinality > min_cardinality and cardinality < max_cardinality:
self.list_cardinalities.append(Cardinality(cardinality=cardinality, path_w2v=self.path_model_w2v, path_list_classes=self.path_list_classes, size=self.size))
def setUp(self):
self.list_cardinalities = [
Cardinality(3, "", ""),
Cardinality(4, "", ""),
Cardinality(5, "", "")
]
self.lock = torch.multiprocessing.get_context('spawn').Lock()
self.model = LSTMLayer(num_classes=5)
def setUp(self):
self.cardinality = Cardinality(3, "", "")
self.cardinality.list_classes = [0, 0, 0, 1, 1, 2]
self.cardinality.counter = {
0: 100,
1: 100,
2: 100,
4: 100,
6: 1000,
5: 1000
}
self.cardinality.compute_position()
def test_loadfiles(self, mock_isfile):
mock_isfile.return_value = True
# without size
cardinality = Cardinality(3, "", "")
read_data = pickle.dumps({
'word2vec': -1,
'counter_patterns': {
"1": 1,
"10": 10,
"100": 100,
"1000": 1000,
"10000": 10000,
"100000": 100000
}
})
mockOpen = mock_open(read_data=read_data)
tf = tempfile.NamedTemporaryFile()
f = h5py.File(tf, 'w')
f.create_dataset("list_classes", data=[1, 2, 3, 4, 5])
f.close()
cardinality.path_list_classes = tf.name
with patch('builtins.open', mockOpen):
cardinality.load_files()
tf.close()
self.assertEqual(len(cardinality.counter), 6)
self.assertEqual(len(cardinality.list_classes), 5)
# with size
cardinality = Cardinality(3, "", "", size=2)
read_data = pickle.dumps({
'word2vec': -1,
'counter_patterns': {
"1": 1,
"10": 10,
"100": 100,
"1000": 1000,
"10000": 10000,
"100000": 100000
}
})
mockOpen = mock_open(read_data=read_data)
tf = tempfile.NamedTemporaryFile()
f = h5py.File(tf, 'w')
f.create_dataset("list_classes", data=[1, 2, 3, 4, 5])
f.close()
cardinality.path_list_classes = tf.name
with patch('builtins.open', mockOpen):
cardinality.load_files()
tf.close()
self.assertEqual(len(cardinality.counter), 6)
self.assertEqual(len(cardinality.list_classes), 2)
def test_train_model(self, mock_isfile):
mock_isfile.return_value = True
cardinality = Cardinality(3, "", "")
read_data = pickle.dumps({
'word2vec': {
"1": [1] * 20,
"2": [2] * 20,
"3": [3] * 20,
"4": [4] * 20,
"5": [5] * 20,
"6": [6] * 20,
"7": [7] * 20
},
'counter_patterns': {
1: 10,
2: 100,
3: 100,
4: 100,
6: 1000,
5: 1000
},
"LSTM": {
3: self.model.state_dict()
}
})
mockOpen = mock_open(read_data=read_data)
tf = tempfile.NamedTemporaryFile()
f = h5py.File(tf, 'w')
f.create_dataset("list_classes",
data=[
1, 1, 1, 2, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2,
1, 2, 1, 2, 3, 4, 5, 6
])
f.close()
cardinality.path_list_classes = tf.name
cardinality.counter = {1: 10, 2: 100, 3: 100, 4: 100, 6: 1000, 5: 1000}
with patch('builtins.open', mockOpen):
worker_single = Worker_single(batch_result=1,
cardinality=cardinality,
lock=self.lock,
batch_size=1)
dataloader = worker_single.create_dataloader()
worker_single.train(resuming=False)
worker_single.train(resuming=True)
def test_without_file(self, mock_isfile):
mock_isfile.return_value = True
cardinality = Cardinality(3, "", "")
read_data = pickle.dumps({
'word2vec': {
"1": [1] * 20,
"2": [2] * 20,
"3": [3] * 20,
"4": [4] * 20,
"5": [5] * 20,
"6": [6] * 20,
"7": [7] * 20
},
'counter_patterns': {
1: 10,
2: 100,
3: 100,
4: 100,
6: 1000,
5: 1000
},
"LSTM": {
3: self.model.state_dict()
}
})
mockOpen = mock_open(read_data=read_data)
tf = tempfile.NamedTemporaryFile()
f = h5py.File(tf, 'w')
f.create_dataset("list_classes",
data=[
1, 1, 1, 2, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2,
1, 2, 1, 2, 3, 4, 5, 6
])
f.close()
cardinality.path_list_classes = tf.name
cardinality.counter = {1: 10, 2: 100, 3: 100, 4: 100, 6: 1000, 5: 1000}
# No data
with self.assertRaises(Exception):
worker_single = Worker_single(cardinality=cardinality,
lock=self.lock,
batch_size=1)
worker_single.load_model()
def setUp(self):
self.lock = torch.multiprocessing.get_context('spawn').Lock()
self.model = LSTMLayer(num_classes=5)
cardinality = Cardinality(3, "", "")
cardinality.list_classes = [1,1,1,2,2,3,4,5,6]
cardinality.counter= {1:10, 2:100, 3:100, 4:100, 6:1000, 5:1000}
cardinality.compute_position()
self.result = Result(cardinality)
def test_creation(self):
cardinality = Cardinality(3, "", "", size=2)
read_data = pickle.dumps({
'word2vec': -1,
'counter_patterns': {
"1": 1,
"10": 10,
"100": 100,
"1000": 1000,
"10000": 10000,
"100000": 100000
}
})
mockOpen = mock_open(read_data=read_data)
tf = tempfile.NamedTemporaryFile()
f = h5py.File(tf, 'w')
f.create_dataset("list_classes", data=[1, 2, 3, 4, 5])
f.close()
cardinality.path_list_classes = tf.name
with patch('builtins.open', mockOpen):
cardinality.load_files()
self.cardinality = cardinality
worker_single = Worker_single(cardinality=self.cardinality,
lock=self.lock)
worker_single = Worker_single(cardinality=self.cardinality,
lock=self.lock,
stoppingcondition="timer")
worker_single = Worker_single(cardinality=self.cardinality,
lock=self.lock,
stoppingcondition="earlystopping")
worker_single = Worker_single(cardinality=self.cardinality,
lock=self.lock,
stoppingcondition="epoch")
with self.assertRaises(Exception):
worker_single = Worker_single(cardinality=self.cardinality,
lock=self.lock,
stoppingcondition="unimplemented")
tf.close()
def test_compute_position(self):
cardinality = Cardinality(3, "", "")
cardinality.list_classes = [1, 1, 1, 2, 2, 3, 4, 5, 6]
cardinality.counter = {1: 10, 2: 100, 3: 100, 4: 100, 6: 1000, 5: 1000}
cardinality.compute_position()
self.assertEqual(len(cardinality.set_classes_kept), 3)
self.assertEqual(list(cardinality.list_position), [3, 4, 5, 6])
self.assertEqual(cardinality.number_of_classes, 5)
self.assertEqual(len(cardinality), 4)
def test_compute_position_one_model(self):
cardinality = Cardinality(3,
"",
"",
one_model=True,
set_cardinalities=[1, 2, 3, 4, 5])
cardinality.list_classes = [1, 1, 1, 2, 2, 3, 4, 5, 6]
cardinality.counter = {1: 10, 2: 100, 3: 100, 4: 100, 6: 1000, 5: 1000}
cardinality.compute_position()
self.assertEqual(len(cardinality.set_classes_kept), 6)
self.assertEqual(list(cardinality.list_position),
[0, 1, 2, 3, 4, 5, 6, 7, 8])
self.assertEqual(cardinality.number_of_classes, 7)
self.assertEqual(len(cardinality), 9)
class UtilTest(unittest.TestCase):
def setUp(self):
self.cardinality = Cardinality(3, "", "")
self.cardinality.list_classes = [0, 0, 0, 1, 1, 2]
self.cardinality.counter = {
0: 100,
1: 100,
2: 100,
4: 100,
6: 1000,
5: 1000
}
self.cardinality.compute_position()
def test_creating(self):
result = Result(self.cardinality)
self.assertEqual(result.number_of_classes, 3)
def test_update(self):
result = Result(self.cardinality)
result.update(torch.Tensor([[0.4, 0.3], [0.3, 0.4], [0.4, 0.3],
[0.3, 0.4]]),
labels=[0, 1, 1, 0])
self.assertEqual(result.conf_matrix[0, 1], 1)
self.assertEqual(result.conf_matrix[1, 0], 1)
self.assertEqual(result.conf_matrix[1, 1], 1)
self.assertEqual(result.conf_matrix[0, 0], 1)
def test_compute(self):
result = Result(self.cardinality)
result.update(torch.Tensor([[0.4, 0.3], [0.3, 0.4], [0.4, 0.3],
[0.3, 0.4]]),
labels=[0, 1, 1, 0])
result.computing_result()
self.assertEqual(result.global_TP, 2)
self.assertEqual(result.global_FP, 2)
self.assertEqual(result.global_FN, 2)
self.assertEqual(result.macro_precision, 0.50)
self.assertEqual(result.macro_recall, 0.50)
self.assertTrue(math.isclose(result.micro_recall, 1 / 3))
self.assertTrue(math.isclose(result.micro_precision, 1 / 3))
def test_no_class(self):
result = Result(self.cardinality)
result.number_of_classes = 0
result.update(torch.Tensor([[0.4, 0.3], [0.3, 0.4], [0.4, 0.3],
[0.3, 0.4]]),
labels=[0, 1, 1, 0])
result.computing_result()
self.assertEqual(result.micro_precision, 0)
self.assertEqual(result.micro_recall, 0)
def test_print(self):
result = Result(self.cardinality, "Test")
result.number_of_classes = 0
result.update(torch.Tensor([[0.4, 0.3], [0.3, 0.4], [0.4, 0.3],
[0.3, 0.4]]),
labels=[0, 1, 1, 0])
result.computing_result()
result = Result(self.cardinality)
result.number_of_classes = 0
result.update(torch.Tensor([[0.4, 0.3], [0.3, 0.4], [0.4, 0.3],
[0.3, 0.4]]),
labels=[0, 1, 1, 0])
result.computing_result()
def test_results_normal(self):
result = Result(self.cardinality)
result.update(torch.Tensor([[0.4, 0.3], [0.3, 0.4], [0.4, 0.3],
[0.3, 0.4]]),
labels=[0, 1, 1, 0])
result_dump = pickle.dumps({
"Result": {
"1": {
"Test": result,
"Train": result
},
"2": {
"Test": result,
"Train": result
}
}
})
mockOpen = mock_open(read_data=result_dump)
with patch('builtins.open', mockOpen):
results = Results(path_model="model/", name_model="Test")
results.load_files()
results.compute_results(condition="Test")
self.assertEqual(results.global_TP, 4)
self.assertEqual(results.global_FP, 4)
self.assertEqual(results.global_FN, 4)
self.assertEqual(results.macro_precision, 0.50)
self.assertEqual(results.macro_recall, 0.50)
self.assertTrue(math.isclose(results.micro_recall, 1 / 3))
self.assertTrue(math.isclose(results.micro_precision, 1 / 3))
results.print_results()
def test_results_no_class(self):
result = Result(self.cardinality)
result.update(torch.Tensor([[0.4, 0.3], [0.3, 0.4], [0.4, 0.3],
[0.3, 0.4]]),
labels=[0, 1, 1, 0])
result.number_of_classes = 0
result_dump = pickle.dumps({
"Result": {
"1": {
"Test": result,
"Train": result
},
"2": {
"Test": result,
"Train": result
}
}
})
mockOpen = mock_open(read_data=result_dump)
with patch('builtins.open', mockOpen):
results = Results(path_model="model/", name_model="Test")
results.load_files()
results.compute_results(condition="Test")
self.assertEqual(results.global_TP, 0)
self.assertEqual(results.global_FP, 0)
self.assertEqual(results.global_FN, 0)
self.assertEqual(results.macro_precision, 0)
self.assertEqual(results.macro_recall, 0)
self.assertTrue(math.isclose(results.micro_recall, 0))
self.assertTrue(math.isclose(results.micro_precision, 0))
def test_create(self, mock_isfile):
mock_isfile.return_value = True
cardinality = Cardinality(3, "", "")
read_data = pickle.dumps({
'word2vec': {
"1": [1] * 20,
"2": [2] * 20,
"3": [3] * 20,
"4": [4] * 20,
"5": [5] * 20,
"6": [6] * 20,
"7": [7] * 20
},
'counter_patterns': {
1: 10,
2: 100,
3: 100,
4: 100,
6: 1000,
5: 1000
}
})
mockOpen = mock_open(read_data=read_data)
tf = tempfile.NamedTemporaryFile()
f = h5py.File(tf, 'w')
f.create_dataset("list_classes",
data=[
1, 1, 1, 2, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2,
1, 2, 1, 2, 3, 4, 5, 6
])
f.close()
cardinality.path_list_classes = tf.name
cardinality.counter = {1: 10, 2: 100, 3: 100, 4: 100, 6: 1000, 5: 1000}
# Test
with patch('builtins.open', mockOpen):
#cardinality.load_files()
worker_single = Worker_single(cardinality=cardinality,
lock=self.lock,
batch_size=1)
dataloader = worker_single.create_dataloader()
self.assertEqual(len(dataloader), 7) # 60% of 12
self.assertTrue(worker_single.dataset.loaded)
# Train
# Avoid to create a new object
worker_single.dataset.loaded = False
with patch('builtins.open', mockOpen):
#cardinality.load_files()
worker_single = Worker_single(cardinality=cardinality,
lock=self.lock,
batch_size=1)
dataloader = worker_single.create_dataloader(condition="Train")
self.assertEqual(len(dataloader), 5) # 40% of 12
worker_single.dataset.loaded = False
with patch('builtins.open', mockOpen):
#cardinality.load_files()
worker_single = Worker_single(cardinality=cardinality,
lock=self.lock,
batch_size=1)
dataloader = worker_single.create_dataloader(condition="Train",
subsample=True,
subsample_split=0.25)
self.assertEqual(len(dataloader), 1) # 25% of 40% of 12
tf.close()
def test_getitem(self):
cardinality = Cardinality(3, "", "")
cardinality.size_windows = 4
cardinality.list_classes = [
1, 1, 1, 2, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 3,
4, 5, 6
]
cardinality.counter = {1: 10, 2: 100, 3: 100, 4: 100, 6: 1000, 5: 1000}
cardinality.w2v = {
"1": [1] * 20,
"2": [2] * 20,
"3": [3] * 20,
"4": [4] * 20,
"5": [5] * 20,
"6": [6] * 20,
"7": [7] * 20
}
cardinality.list_position = range(len(cardinality.list_classes))
# Normal
output_getitem = cardinality.__getitem__(
len(cardinality.list_classes) - 1)
self.assertEqual(output_getitem['output'], 6)
self.assertEqual(len(list(output_getitem['input'][0])), 20)
self.assertEqual(len(list(output_getitem['input'])), 4)
# Invalid
output_getitem = cardinality.__getitem__(0)
self.assertListEqual(list(output_getitem['input']), [-1])
self.assertEqual(output_getitem['output'], -1)
# Invalid due to the same pattern
output_getitem = cardinality.__getitem__(1)
self.assertEqual(output_getitem['output'], -1)
self.assertListEqual(list(output_getitem['input']), [-1])
self.assertEqual(output_getitem['output'], -1)
# Padding
output_getitem = cardinality.__getitem__(5)
self.assertEqual(output_getitem['output'], 1)
self.assertEqual(len(list(output_getitem['input'][0])), 20)
self.assertEqual(len(list(output_getitem['input'])), 4)
def test_compute_position_void(self):
cardinality = Cardinality(3, "", "")
cardinality.list_classes = []
cardinality.counter = {1: 10, 2: 100, 3: 100, 4: 100, 6: 1000, 5: 1000}
cardinality.compute_position()
self.assertEqual(cardinality.number_of_classes, 0)