def test_scoring_logreg_tune_correct(data_fixture, request):
train_data, test_data = request.getfixturevalue(data_fixture)
train_data.features = Scaling().fit(train_data.features).apply(
train_data.features)
test_data.features = Scaling().fit(test_data.features).apply(
test_data.features)
logreg = Model(model_type='logit')
model, _ = logreg.fit(train_data)
test_predicted = logreg.predict(fitted_model=model, data=test_data)
test_roc_auc = roc_auc(y_true=test_data.target, y_score=test_predicted)
logreg_for_tune = Model(model_type='logit')
model_tuned, _ = logreg_for_tune.fine_tune(
train_data, iterations=50, max_lead_time=timedelta(minutes=0.1))
test_predicted_tuned = logreg_for_tune.predict(fitted_model=model_tuned,
data=test_data)
test_roc_auc_tuned = roc_auc(y_true=test_data.target,
y_score=test_predicted_tuned)
roc_threshold = 0.6
assert round(test_roc_auc_tuned, 2) >= round(test_roc_auc,
2) > roc_threshold
def test_classification_manual_tuning_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = Scaling().fit(data.features).apply(data.features)
train_data, test_data = train_test_data_setup(data=data)
knn = Model(model_type='knn')
model, _ = knn.fit(data=train_data)
test_predicted = knn.predict(fitted_model=model, data=test_data)
knn_for_tune = Model(model_type='knn')
knn_for_tune.params = {'n_neighbors': 1}
model, _ = knn_for_tune.fit(data=train_data)
test_predicted_tuned = knn_for_tune.predict(fitted_model=model,
data=test_data)
assert not np.array_equal(test_predicted, test_predicted_tuned)
def main(args):
if args.gpu < 0:
cuda = False
else:
cuda = True
torch.cuda.set_device(args.gpu)
default_path = create_default_path()
print('\n*** Set default saving/loading path to:', default_path)
if args.dataset == AIFB or args.dataset == MUTAG:
module = importlib.import_module(MODULE.format('dglrgcn'))
data = module.load_dglrgcn(args.data_path)
data = to_cuda(data) if cuda else data
mode = NODE_CLASSIFICATION
elif args.dataset == MUTAGENICITY or args.dataset == PTC_MR or args.dataset == PTC_MM or args.dataset == PTC_FR or args.dataset == PTC_FM:
module = importlib.import_module(MODULE.format('dortmund'))
data = module.load_dortmund(args.data_path)
data = to_cuda(data) if cuda else data
mode = GRAPH_CLASSIFICATION
else:
raise ValueError('Unable to load dataset', args.dataset)
print_graph_stats(data[GRAPH])
config_params = read_params(args.config_fpath, verbose=True)
# create GNN model
model = Model(g=data[GRAPH],
config_params=config_params[0],
n_classes=data[N_CLASSES],
n_rels=data[N_RELS] if N_RELS in data else None,
n_entities=data[N_ENTITIES] if N_ENTITIES in data else None,
is_cuda=cuda,
mode=mode)
if cuda:
model.cuda()
# 1. Training
app = App()
learning_config = {
'lr': args.lr,
'n_epochs': args.n_epochs,
'weight_decay': args.weight_decay,
'batch_size': args.batch_size,
'cuda': cuda
}
print('\n*** Start training ***\n')
app.train(data, config_params[0], learning_config, default_path, mode=mode)
# 2. Testing
print('\n*** Start testing ***\n')
app.test(data, default_path, mode=mode)
# 3. Delete model
remove_model(default_path)
def test_node_factory_log_reg_correct(data_setup):
model_type = 'logit'
node = PrimaryNode(model_type=model_type)
expected_model = Model(model_type=model_type).__class__
actual_model = node.model.__class__
assert node.__class__ == PrimaryNode
assert expected_model == actual_model
def test_node_factory_log_reg_correct(data_setup):
model_type = ModelTypesIdsEnum.logit
node = NodeGenerator().primary_node(model_type=model_type)
expected_model = Model(model_type=model_type).__class__
actual_model = node.model.__class__
assert node.__class__ == PrimaryNode
assert expected_model == actual_model
def test_pca_model_removes_redunant_features_correct():
n_informative = 5
data = classification_dataset_with_redunant_features(
n_samples=1000, n_features=100, n_informative=n_informative)
train_data, test_data = train_test_data_setup(data=data)
pca = Model(model_type='pca_data_model')
_, train_predicted = pca.fit(data=train_data)
assert train_predicted.shape[1] < data.features.shape[1]
def test_log_clustering_fit_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = Scaling().fit(data.features).apply(data.features)
train_data, test_data = train_test_data_setup(data=data)
kmeans = Model(model_type=ModelTypesIdsEnum.kmeans)
_, train_predicted = kmeans.fit(data=train_data)
assert all(np.unique(train_predicted) == [0, 1])
def test_log_regression_fit_correct(classification_dataset):
data = classification_dataset
data.features = Scaling().fit(data.features).apply(data.features)
train_data, test_data = train_test_data_setup(data=data)
log_reg = Model(model_type=ModelTypesIdsEnum.logit)
_, train_predicted = log_reg.fit(data=train_data)
roc_on_train = roc_auc(y_true=train_data.target, y_score=train_predicted)
roc_threshold = 0.95
assert roc_on_train >= roc_threshold
def test_qda_fit_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = Scaling().fit(data.features).apply(data.features)
train_data, test_data = train_test_data_setup(data=data)
qda = Model(model_type=ModelTypesIdsEnum.qda)
_, train_predicted = qda.fit(data=train_data)
roc_on_train = roc_auc(y_true=train_data.target, y_score=train_predicted)
roc_threshold = 0.95
assert roc_on_train >= roc_threshold
def test_lda_fit_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = Scaling().fit(data.features).apply(data.features)
train_data, test_data = train_test_data_setup(data=data)
lda = Model(model_type='lda')
_, train_predicted = lda.fit(data=train_data)
roc_on_train = get_roc_auc(train_data, train_predicted)
roc_threshold = 0.95
assert roc_on_train >= roc_threshold
def test_log_regression_fit_correct(classification_dataset):
data = classification_dataset
data.features = Scaling().fit(data.features).apply(data.features)
train_data, test_data = train_test_data_setup(data=data)
log_reg = Model(model_type='logit')
_, train_predicted = log_reg.fit(data=train_data)
roc_on_train = get_roc_auc(train_data, train_predicted)
roc_threshold = 0.95
assert roc_on_train >= roc_threshold
def test_knn_classification_tune_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = Scaling().fit(data.features).apply(data.features)
train_data, test_data = train_test_data_setup(data=data)
knn = Model(model_type='knn')
model, _ = knn.fit(data=train_data)
test_predicted = knn.predict(fitted_model=model, data=test_data)
roc_on_test = roc_auc(y_true=test_data.target, y_score=test_predicted)
knn_for_tune = Model(model_type='knn')
model, _ = knn_for_tune.fine_tune(data=train_data,
iterations=10,
max_lead_time=timedelta(minutes=1))
test_predicted_tuned = knn.predict(fitted_model=model, data=test_data)
roc_on_test_tuned = roc_auc(y_true=test_data.target,
y_score=test_predicted_tuned)
roc_threshold = 0.6
assert roc_on_test_tuned > roc_on_test > roc_threshold
def test_pca_manual_tuning_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = Scaling().fit(data.features).apply(data.features)
train_data, test_data = train_test_data_setup(data=data)
pca = Model(model_type='pca_data_model')
model, _ = pca.fit(data=train_data)
test_predicted = pca.predict(fitted_model=model, data=test_data)
pca_for_tune = Model(model_type='pca_data_model')
pca_for_tune.params = {
'svd_solver': 'randomized',
'iterated_power': 'auto',
'dim_reduction_expl_thr': 0.7,
'dim_reduction_min_expl': 0.001
}
model, _ = pca_for_tune.fit(data=train_data)
test_predicted_tuned = pca_for_tune.predict(fitted_model=model,
data=test_data)
assert not np.array_equal(test_predicted, test_predicted_tuned)
def fit_template(chain_template, classes, with_gaussian=False, skip_fit=False):
templates_by_models = []
for model_template in itertools.chain.from_iterable(chain_template):
model_instance = Model(model_type=model_template.model_type)
model_template.model_instance = model_instance
templates_by_models.append((model_template, model_instance))
if skip_fit:
return
for template, instance in templates_by_models:
samples, features_amount = template.input_shape
if with_gaussian:
features, target = gauss_quantiles(samples_amount=samples,
features_amount=features_amount,
classes_amount=classes)
else:
options = {
'informative': features_amount,
'redundant': 0,
'repeated': 0,
'clusters_per_class': 1
}
features, target = synthetic_dataset(
samples_amount=samples,
features_amount=features_amount,
classes_amount=classes,
features_options=options)
target = np.expand_dims(target, axis=1)
data_train = InputData(idx=np.arange(0, samples),
features=features,
target=target,
data_type=DataTypesEnum.table,
task=Task(TaskTypesEnum.classification))
preproc_data = copy(data_train)
preprocessor = Normalization().fit(preproc_data.features)
preproc_data.features = preprocessor.apply(preproc_data.features)
print(f'Fit {instance}')
fitted_model, predictions = instance.fit(data=preproc_data)
template.fitted_model = fitted_model
template.data_fit = preproc_data
template.preprocessor = preprocessor
def test_arima_tune_correct():
data = get_synthetic_ts_data()
train_data, test_data = train_test_data_setup(data=data)
arima_for_tune = Model(model_type='arima')
model, _ = arima_for_tune.fine_tune(data=train_data,
iterations=5,
max_lead_time=timedelta(minutes=0.1))
test_predicted_tuned = arima_for_tune.predict(fitted_model=model,
data=test_data)
rmse_on_test_tuned = mse(y_true=test_data.target,
y_pred=test_predicted_tuned,
squared=False)
rmse_threshold = np.std(test_data.target)
assert rmse_on_test_tuned < rmse_threshold
def test_max_lead_time_in_tune_process(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = Scaling().fit(data.features).apply(data.features)
train_data, test_data = train_test_data_setup(data=data)
start = datetime.now()
knn_for_tune = Model(model_type='knn')
model, _ = knn_for_tune.fine_tune(data=train_data,
max_lead_time=timedelta(minutes=0.05),
iterations=100)
test_predicted_tuned = knn_for_tune.predict(fitted_model=model,
data=test_data)
roc_on_test_tuned = roc_auc(y_true=test_data.target,
y_score=test_predicted_tuned)
roc_threshold = 0.6
spent_time = (datetime.now() - start).seconds
assert roc_on_test_tuned > roc_threshold
assert spent_time == 3
def test_rf_class_tune_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = Scaling().fit(data.features).apply(data.features)
train_data, test_data = train_test_data_setup(data=data)
rf = Model(model_type='rf')
model, _ = rf.fit(train_data)
test_predicted = rf.predict(fitted_model=model, data=test_data)
test_roc_auc = roc_auc(y_true=test_data.target, y_score=test_predicted)
model_tuned, _ = rf.fine_tune(data=train_data,
iterations=12,
max_lead_time=timedelta(minutes=0.1))
test_predicted_tuned = rf.predict(fitted_model=model_tuned, data=test_data)
test_roc_auc_tuned = roc_auc(y_true=test_data.target,
y_score=test_predicted_tuned)
roc_threshold = 0.7
assert test_roc_auc_tuned != test_roc_auc
assert test_roc_auc_tuned > roc_threshold
def __init__(self, model_type: str):
model = Model(model_type=model_type)
super().__init__(nodes_from=None, model=model)
def train(self, data, model_config, learning_config, save_path='', mode=NODE_CLASSIFICATION):
loss_fcn = torch.nn.CrossEntropyLoss()
labels = data[LABELS]
# initialize graph
if mode == NODE_CLASSIFICATION:
train_mask = data[TRAIN_MASK]
val_mask = data[VAL_MASK]
dur = []
# create GNN model
self.model = Model(g=data[GRAPH],
config_params=model_config,
n_classes=data[N_CLASSES],
n_rels=data[N_RELS] if N_RELS in data else None,
n_entities=data[N_ENTITIES] if N_ENTITIES in data else None,
is_cuda=learning_config['cuda'],
mode=mode)
optimizer = torch.optim.Adam(self.model.parameters(),
lr=learning_config['lr'],
weight_decay=learning_config['weight_decay'])
for epoch in range(learning_config['n_epochs']):
self.model.train()
if epoch >= 3:
t0 = time.time()
# forward
logits = self.model(None)
loss = loss_fcn(logits[train_mask], labels[train_mask])
optimizer.zero_grad()
loss.backward()
optimizer.step()
if epoch >= 3:
dur.append(time.time() - t0)
val_acc, val_loss = self.model.eval_node_classification(labels, val_mask)
print("Epoch {:05d} | Time(s) {:.4f} | Train loss {:.4f} | Val accuracy {:.4f} | "
"Val loss {:.4f}".format(epoch,
np.mean(dur),
loss.item(),
val_acc,
val_loss))
self.early_stopping(val_loss, self.model, save_path)
if self.early_stopping.early_stop:
print("Early stopping")
break
elif mode == GRAPH_CLASSIFICATION:
self.accuracies = np.zeros(10)
graphs = data[GRAPH] # load all the graphs
# debug purposes: reshuffle all the data before the splitting
random_indices = list(range(len(graphs)))
random.shuffle(random_indices)
graphs = [graphs[i] for i in random_indices]
labels = labels[random_indices]
K = 10
for k in range(K): # K-fold cross validation
# create GNN model
self.model = Model(g=data[GRAPH],
config_params=model_config,
n_classes=data[N_CLASSES],
n_rels=data[N_RELS] if N_RELS in data else None,
n_entities=data[N_ENTITIES] if N_ENTITIES in data else None,
is_cuda=learning_config['cuda'],
mode=mode)
optimizer = torch.optim.Adam(self.model.parameters(),
lr=learning_config['lr'],
weight_decay=learning_config['weight_decay'])
if learning_config['cuda']:
self.model.cuda()
print('\n\n\nProcess new k')
start = int(len(graphs)/K) * k
end = int(len(graphs)/K) * (k+1)
# testing batch
testing_graphs = graphs[start:end]
self.testing_labels = labels[start:end]
self.testing_batch = dgl.batch(testing_graphs)
# training batch
training_graphs = graphs[:start] + graphs[end:]
training_labels = labels[list(range(0, start)) + list(range(end+1, len(graphs)))]
training_samples = list(map(list, zip(training_graphs, training_labels)))
training_batches = DataLoader(training_samples,
batch_size=learning_config['batch_size'],
shuffle=True,
collate_fn=collate)
dur = []
for epoch in range(learning_config['n_epochs']):
self.model.train()
if epoch >= 3:
t0 = time.time()
losses = []
training_accuracies = []
for iter, (bg, label) in enumerate(training_batches):
logits = self.model(bg)
loss = loss_fcn(logits, label)
losses.append(loss.item())
_, indices = torch.max(logits, dim=1)
correct = torch.sum(indices == label)
training_accuracies.append(correct.item() * 1.0 / len(label))
optimizer.zero_grad()
loss.backward()
optimizer.step()
if epoch >= 3:
dur.append(time.time() - t0)
val_acc, val_loss = self.model.eval_graph_classification(self.testing_labels, self.testing_batch)
print("Epoch {:05d} | Time(s) {:.4f} | Train acc {:.4f} | Train loss {:.4f} "
"| Val accuracy {:.4f} | Val loss {:.4f}".format(epoch,
np.mean(dur) if dur else 0,
np.mean(training_accuracies),
np.mean(losses),
val_acc,
val_loss))
is_better = self.early_stopping(val_loss, self.model, save_path)
if is_better:
self.accuracies[k] = val_acc
if self.early_stopping.early_stop:
print("Early stopping")
break
self.early_stopping.reset()
else:
raise RuntimeError
def __init__(self, model_type: ModelTypesIdsEnum):
model = Model(model_type=model_type)
super().__init__(nodes_from=None, model=model)
def __init__(self, model_type: str, nodes_from: Optional[List['Node']] = None):
model = Model(model_type=model_type)
nodes_from = [] if nodes_from is None else nodes_from
super().__init__(nodes_from=nodes_from, model=model)
def __init__(self, nodes_from: Optional[List['Node']], model_type: str,
manual_preprocessing_func: Optional[Callable] = None):
self.nodes_from = nodes_from
self.model = Model(model_type=model_type)
self.cache = FittedModelCache(self)
self.manual_preprocessing_func = manual_preprocessing_func
def __init__(self, nodes_from: Optional[List['Node']],
model_type: ModelTypesIdsEnum):
model = Model(model_type=model_type)
nodes_from = [] if nodes_from is None else nodes_from
super().__init__(nodes_from=nodes_from, model=model)