def fit(model,
train,
test,
num_boost_round=360,
verbose_eval=1,
export=False,
training_params=None,
export_params=None,
**kwargs):
if not use_gpu():
print_errors('XGBoost can only be executed on a GPU for the moment',
do_exit=True)
training_params = {} if training_params is None else training_params
export_params = {} if export_params is None else export_params
d_test = xgb.DMatrix(np.asarray(test.get_vectors()),
label=np.asarray(test.labels))
if not validation_only:
print_h1('Training: ' + special_parameters.setup_name)
print_info("get vectors...")
X = np.asarray(train.get_vectors())
y = np.asarray(train.labels)
d_train = xgb.DMatrix(X, label=y)
gpu_id = first_device().index
kwargs['verbosity'] = verbose_level()
kwargs['gpu_id'] = gpu_id
eval_list = [(d_test, 'eval'), (d_train, 'train')]
print_info("fit model...")
bst = xgb.train(kwargs,
d_train,
num_boost_round=num_boost_round,
verbose_eval=verbose_eval,
evals=eval_list,
xgb_model=model)
print_info("Save model...")
save_model(bst)
else:
bst = load_model()
print_h1('Validation/Export: ' + special_parameters.setup_name)
predictions = bst.predict(d_test, ntree_limit=bst.best_ntree_limit)
res = validate(predictions,
np.array(test.labels),
training_params['metrics']
if 'metrics' in training_params else tuple(),
final=True)
print_notification(res, end='')
if export:
export_results(test, predictions, **export_params)
def fit(model,
train,
test,
export=False,
nb_classes=4520,
training_params=None,
export_params=None,
save=True):
training_params = {} if training_params is None else training_params
export_params = {} if export_params is None else export_params
clf = model
if not validation_only:
print_h1('Training: ' + setup_name)
print_info("get vectors...")
X = np.array(train.get_vectors())
y = np.array(train.labels)
print_info("fit model...")
clf.fit(X, y)
if save:
save_model(clf)
print_h1('Validation/Export: ' + setup_name)
restricted_predictions = clf.predict_proba(np.array(test.get_vectors()))
predictions = np.zeros((restricted_predictions.shape[0], nb_classes))
predictions[:, clf.classes_] = restricted_predictions
res = validate(predictions,
np.array(test.labels),
training_params['metrics']
if 'metrics' in training_params else tuple(),
final=True)
print_notification(res, end='')
if export:
export_results(test, predictions, **export_params)
def fit(model_z,
train,
test,
val=None,
training_params=None,
predict_params=None,
validation_params=None,
export_params=None,
optim_params=None,
model_selection_params=None):
"""
This function is the core of an experiment. It performs the ml procedure as well as the call to validation.
:param training_params: parameters for the training procedure
:param val: validation set
:param test: the test set
:param train: The training set
:param optim_params:
:param export_params:
:param validation_params:
:param predict_params:
:param model_z: the model that should be trained
:param model_selection_params:
"""
# configuration
training_params, predict_params, validation_params, export_params, optim_params, \
cv_params = merge_dict_set(
training_params, TRAINING_PARAMS,
predict_params, PREDICT_PARAMS,
validation_params, VALIDATION_PARAMS,
export_params, EXPORT_PARAMS,
optim_params, OPTIM_PARAMS,
model_selection_params, MODEL_SELECTION_PARAMS
)
train_loader, test_loader, val_loader = _dataset_setup(
train, test, val, **training_params)
statistics_path = output_path('metric_statistics.dump')
metrics_stats = Statistics(
model_z, statistics_path, **
cv_params) if cv_params.pop('cross_validation') else None
validation_path = output_path('validation.txt')
# training parameters
optim = optim_params.pop('optimizer')
iterations = training_params.pop('iterations')
gamma = training_params.pop('gamma')
loss = training_params.pop('loss')
log_modulo = training_params.pop('log_modulo')
val_modulo = training_params.pop('val_modulo')
first_epoch = training_params.pop('first_epoch')
# callbacks for ml tests
vcallback = validation_params.pop(
'vcallback') if 'vcallback' in validation_params else None
if iterations is None:
print_errors(
'Iterations must be set',
exception=TrainingConfigurationException('Iterations is None'))
# before ml callback
if vcallback is not None and special_parameters.train and first_epoch < max(
iterations):
init_callbacks(vcallback, val_modulo,
max(iterations) // val_modulo, train_loader.dataset,
model_z)
max_iterations = max(iterations)
if special_parameters.train and first_epoch < max(iterations):
print_h1('Training: ' + special_parameters.setup_name)
loss_logs = [] if first_epoch < 1 else load_loss('loss_train')
loss_val_logs = [] if first_epoch < 1 else load_loss('loss_validation')
opt = create_optimizer(model_z.parameters(), optim, optim_params)
scheduler = MultiStepLR(opt, milestones=list(iterations), gamma=gamma)
# number of batches in the ml
epoch_size = len(train_loader)
# one log per epoch if value is -1
log_modulo = epoch_size if log_modulo == -1 else log_modulo
epoch = 0
for epoch in range(max_iterations):
if epoch < first_epoch:
# opt.step()
_skip_step(scheduler, epoch)
continue
# saving epoch to enable restart
export_epoch(epoch)
model_z.train()
# printing new epoch
print_h2('-' * 5 + ' Epoch ' + str(epoch + 1) + '/' +
str(max_iterations) + ' (lr: ' + str(scheduler.get_lr()) +
') ' + '-' * 5)
running_loss = 0.0
for idx, data in enumerate(train_loader):
# get the inputs
inputs, labels = data
# wrap labels in Variable as input is managed through a decorator
# labels = model_z.p_label(labels)
if use_gpu():
labels = labels.cuda()
# zero the parameter gradients
opt.zero_grad()
outputs = model_z(inputs)
loss_value = loss(outputs, labels)
loss_value.backward()
opt.step()
# print math
running_loss += loss_value.item()
if idx % log_modulo == log_modulo - 1: # print every log_modulo mini-batches
print('[%d, %5d] loss: %.5f' %
(epoch + 1, idx + 1, running_loss / log_modulo))
# tensorboard support
add_scalar('Loss/train', running_loss / log_modulo)
loss_logs.append(running_loss / log_modulo)
running_loss = 0.0
# end of epoch update of learning rate scheduler
scheduler.step(epoch + 1)
# saving the model and the current loss after each epoch
save_checkpoint(model_z, optimizer=opt)
# validation of the model
if epoch % val_modulo == val_modulo - 1:
validation_id = str(int((epoch + 1) / val_modulo))
# validation call
predictions, labels, loss_val = predict(
model_z, val_loader, loss, **predict_params)
loss_val_logs.append(loss_val)
res = '\n[validation_id:' + validation_id + ']\n' + validate(
predictions,
labels,
validation_id=validation_id,
statistics=metrics_stats,
**validation_params)
# save statistics for robust cross validation
if metrics_stats:
metrics_stats.save()
print_notification(res)
if special_parameters.mail == 2:
send_email(
'Results for XP ' + special_parameters.setup_name +
' (epoch: ' + str(epoch + 1) + ')', res)
if special_parameters.file:
save_file(
validation_path,
'Results for XP ' + special_parameters.setup_name +
' (epoch: ' + str(epoch + 1) + ')', res)
# checkpoint
save_checkpoint(model_z,
optimizer=opt,
validation_id=validation_id)
# callback
if vcallback is not None:
run_callbacks(vcallback, (epoch + 1) // val_modulo)
# save loss
save_loss(
{ # // log_modulo * log_modulo in case log_modulo does not divide epoch_size
'train': (loss_logs, log_modulo),
'validation':
(loss_val_logs,
epoch_size // log_modulo * log_modulo * val_modulo)
},
ylabel=str(loss))
# saving last epoch
export_epoch(epoch +
1) # if --restart is set, the train will not be executed
# callback
if vcallback is not None:
finish_callbacks(vcallback)
# final validation
if special_parameters.evaluate or special_parameters.export:
print_h1('Validation/Export: ' + special_parameters.setup_name)
if metrics_stats is not None:
# change the parameter states of the model to best model
metrics_stats.switch_to_best_model()
predictions, labels, val_loss = predict(model_z,
test_loader,
loss,
validation_size=-1,
**predict_params)
if special_parameters.evaluate:
res = validate(predictions,
labels,
statistics=metrics_stats,
**validation_params,
final=True)
print_notification(res, end='')
if special_parameters.mail >= 1:
send_email(
'Final results for XP ' + special_parameters.setup_name,
res)
if special_parameters.file:
save_file(
validation_path,
'Final results for XP ' + special_parameters.setup_name,
res)
if special_parameters.export:
export_results(test_loader.dataset, predictions, **export_params)
return metrics_stats
def fit(train,
test,
validation=None,
validation_params=None,
export_params=None,
model_name='model',
**kwargs):
"""
Fit a light GBM model. If validation_only or export is True, then the training is not performed and the model is
loaded.
:param model_name:
:param export_params:
:param validation_params:
:param train:
:param test:
:param validation:
:param kwargs:
:return:
"""
nb_labels = _nb_labels(train, test, validation)
train_data = _to_lgb_dataset(train)
test_data = _to_lgb_dataset(test)
val_data = test_data if validation is None else _to_lgb_dataset(validation)
if not (special_parameters.validation_only or special_parameters.export):
print_h1('Training: ' + special_parameters.setup_name)
num_round = 10
param = kwargs
merge_smooth(param, _default_params)
param['num_class'] = nb_labels
bst = lgb.train(param, train_data, num_round, valid_sets=[val_data])
bst.save_model(output_path('models/{}.bst'.format(model_name)))
else:
bst = lgb.Booster(
model_file=output_path('models/{}.bst'.format(model_name)))
print_h1('Validation/Export: ' + special_parameters.setup_name)
testset, labels = test.numpy()
predictions = bst.predict(testset)
# validation
if special_parameters.validation_only or not special_parameters.export:
res = validate(
predictions,
labels,
**({} if validation_params is None else validation_params),
final=True)
print_notification(res, end='')
if special_parameters.mail >= 1:
send_email('Final results for XP ' + special_parameters.setup_name,
res)
if special_parameters.file:
save_file(output_path('validation.txt'),
'Final results for XP ' + special_parameters.setup_name,
res)
if special_parameters.export:
export_results(test, predictions,
**({} if export_params is None else export_params))