def main():
with open('seq2seq.json', 'r') as f:
conf_paths = json.load(f)
train_manager = TrainManager(4)
name = get_timestamp()
random_seed = np.random.randint(1, int(1e5))
window = 'hourly'
for fold_idx in range(5):
for is_working in range(2):
for input_days in range(1, 8):
conf_path = np.random.choice(
conf_paths[str(input_days)][str(is_working)])
with open(conf_path.replace('.h5', '.json'), 'r') as f:
conf = json.load(f)
conf['window'] = window
conf['input_days'] = input_days
conf['only_working_day'] = is_working
conf['fold_idx'] = fold_idx
conf['random_seed'] = random_seed
# conf['verbose'] = False
# conf['train_conf']['train_kwargs']['verbose'] = 0
conf['models_dir'] = os.path.join(DATASET_PATH, 'models',
'2018_10_29_seq2seq',
'%s_cv%i' % (name, fold_idx))
train_manager.submit(train_single_model, conf)
def main_parallel():
"""
This will train 4 models in parallel using 2 gpus.
"""
train_manager = TrainManager(4)
name = get_timestamp()
random_seed = np.random.randint(1, int(1e5))
window = 'hourly'
for fold_idx in range(5):
for is_working in range(2):
for input_days in range(1, 8):
conf = _get_random_conf(input_days, is_working)
conf['window'] = window
conf['input_days'] = input_days
conf['only_working_day'] = is_working
conf['fold_idx'] = fold_idx
conf['random_seed'] = random_seed
conf['models_dir'] = os.path.join(DATASET_PATH, 'models',
'seq2seq',
'%s_cv%i' % (name, fold_idx))
train_manager.submit(train_single_model, conf)
def main_sequential():
"""
This will train one model each time (not in parallel)
"""
progress_bar = tqdm(desc='Training seq2seq', total=(5 * 2 * 7))
name = get_timestamp()
random_seed = np.random.randint(1, int(1e5))
window = 'hourly'
for fold_idx in range(5):
for is_working in range(2):
for input_days in range(1, 8):
conf = _get_random_conf(input_days, is_working)
conf['window'] = window
conf['input_days'] = input_days
conf['only_working_day'] = is_working
conf['fold_idx'] = fold_idx
conf['random_seed'] = random_seed
conf['models_dir'] = os.path.join(DATASET_PATH, 'models',
'seq2seq',
'%s_cv%i' % (name, fold_idx))
train_single_model(conf)
progress_bar.update()
def main():
with open('frankenstein.json', 'r') as f:
conf_paths = json.load(f)
train_manager = TrainManager(4)
name = get_timestamp()
random_seed = np.random.randint(1, int(1e5))
for fold_idx in range(5):
for window in ['daily', 'weekly']:
for input_days in range(1, 8):
conf_path = np.random.choice(
conf_paths[window][str(input_days)])
with open(conf_path.replace('.h5', '.json'), 'r') as f:
conf = json.load(f)
conf['window'] = window
conf['input_days'] = input_days
conf['fold_idx'] = fold_idx
conf['random_seed'] = random_seed
conf['verbose'] = False
conf['train_conf']['train_kwargs']['verbose'] = 0
conf['models_dir'] = os.path.join(DATASET_PATH, 'models',
'2018_10_29_frankenstein',
'%s_cv%i' % (name, fold_idx))
train_manager.submit(train_single_model, conf)
def main():
model_conf = {
'encoding': {
'is_day_off': [{'layer': 'Dense', 'units': 32, 'activation': 'relu'}],
'metadata_ohe': [{'layer': 'Dense', 'units': 8, 'activation': 'relu'}],
'data_trend': [{'layer': 'Dense', 'units': 16, 'activation': 'relu'}],
'metadata_days_off': [{'layer': 'Dense', 'units': 8, 'activation': 'relu'}],
},
'weights': [{'layer': 'Dense', 'units': 32, 'activation': 'relu'},
{'layer': 'Dense', 'units': 16, 'activation': 'relu'}],
'repeat_weights': False,
}
train_conf = {
'optimizer_kwargs': {'lr': 1e-3, 'clipvalue': 10},
'train_kwargs': dict(batch_size=8, epochs=5000, verbose=0),
'callbacks': {
'EarlyStopping': {
'patience': 25, 'mode': 'min', 'verbose': 0, 'monitor': 'val_loss',
'min_delta': 0.0001},
'ReduceLROnPlateau': {
'patience': 0, 'factor': 0.95, 'mode': 'min', 'verbose': 0,
'monitor': 'loss'},
'ModelCheckpointRAM': {
'mode': 'min', 'verbose': 0, 'monitor': 'val_loss'},
},
}
name = get_timestamp()
print(name)
conf = {
'windows': ['hourly', 'daily', 'weekly'],
'input_days': list(range(1, 8)),
'fold_idxs': list(range(5)),
'remove_inputs': ['temperature', 'temperature_normed', 'cluster_id_ohe'],
'max_workers': 8,
'verbose': False,
'models_dir': os.path.join(
DATASET_PATH, 'models', '2018_10_11_architecture_exploration', name),
'train_conf': train_conf,
'model_conf': model_conf,
}
simple_train_manager(conf)
n_models_trained = 1
while 1:
model_conf = {
'encoding': {
'is_day_off': _create_layers(np.random.choice([8, 16, 32, 64])),
'metadata_ohe': _create_layers(np.random.choice([4, 8, 16])),
'data_trend': _create_layers(np.random.choice([8, 16, 32])),
'metadata_days_off': _create_layers(np.random.choice([4, 8, 16])),
},
'weights': _create_layers(
np.random.choice([8, 16, 32, 64], size=np.random.randint(1, 4))),
'repeat_weights': False,
}
conf['model_conf'] = model_conf
name = get_timestamp()
print(name)
print('Number of models trained: %i' % n_models_trained)
n_models_trained += 1
conf['models_dir'] = os.path.join(
DATASET_PATH, 'models', '2018_10_11_architecture_exploration', name)
print(conf['models_dir'])
simple_train_manager(conf)