def fitness(nodes, epochs):
nonlocal run_count, data_store, fl, fl_store, data_store, data_store_count, data_store_name
start_time = time.time()
run_count += 1
# run_kf for current trial of hyperparameters and return the score
hparams = create_hparams(nodes=nodes,
epochs=epochs,
loss=scoring,
learning_rate=0.001,
reg_l1=0.0005,
reg_l2=0,
verbose=0)
if plot_dir:
plot_name = '{}/{}_{}_run_{}'.format(plot_dir, model_mode,
scoring, run_count)
else:
plot_name = None
val_score, results_dict = run_kf(
model_mode=model_mode,
fl=fl,
fl_store=fl_store,
hparams=hparams,
scoring=scoring,
other_fl_dict=other_fl_dict,
write_excel_dir=None,
save_model_name=
f'{write_dir}/models/{scoring}_{model_mode}_run{run_count}',
plot_name=plot_name)
results_dict['info']['opt'] = {'nodes': nodes, 'epochs': epochs}
results_dict['info']['model_name'] = f'{write_dir}_run{run_count}'
# Save results
if (data_store_count - 1) % 5 == 0:
data_store = []
data_store_name += 5
data_store.append(results_dict)
with open(
'{}/data_store_{}.pkl'.format(data_store_dir,
data_store_name),
"wb") as file:
pickle.dump(data_store, file)
data_store_count += 1
end_time = time.time()
print(
f'**************************************************************************************************\n'
f'Run Number {run_count} \n'
f'nodes: {nodes}, epochs: {epochs}\n'
f'Time Taken: {end_time - start_time}\n'
f'*********************************************************************************************'
)
return val_score
def fitness(depth, num_est):
nonlocal run_count, data_store, fl, fl_store, data_store_count, data_store_name
start_time = time.time()
run_count += 1
# run_kf for single trial of hyperparameter
hparams = create_hparams(max_depth=depth,
num_est=num_est,
chain=chain)
val_score, results_dict = run_kf(
model_mode=model_mode,
fl=fl,
fl_store=fl_store,
hparams=hparams,
scoring=scoring,
other_fl_dict=other_fl_dict,
write_excel_dir=None,
save_model_name=
f'{write_dir}/models/{scoring}_{model_mode}_run{run_count}',
plot_name=None)
results_dict['info']['opt'] = {'depth': depth, 'num_est': num_est}
results_dict['info']['model_name'] = f'{write_dir}_run{run_count}'
# Save results in batches
if (data_store_count - 1) % 5 == 0:
data_store = []
data_store_name += 5
data_store.append(results_dict)
# Save data_store batch every trial in case hparam_opt accidentally terminates early (e.g. server shut down)
with open(
'{}/data_store_{}.pkl'.format(data_store_dir,
data_store_name),
"wb") as file:
pickle.dump(data_store, file)
data_store_count += 1
end_time = time.time()
print(
f'*************************************************************************************************\n'
f'Run Number {run_count} \n'
f'Depth {depth}, No. Estimators {num_est}\n'
f'Time Taken: {end_time - start_time}\n'
f'*********************************************************************************************'
)
return val_score
from own_package.models import create_hparams
from own_package.train_test import run_train_test
hparams = create_hparams(lstm_units=20, hidden_layers=[20], epochs=120, batch_size=128, learning_rate=0.001)
run_train_test(model_mode='LSTM', hparams=hparams, window_size=48, loader_file='./excel/results.xlsx',
save_model=True)
from own_package.features_labels_setup import load_data_to_fl, load_testset_to_fl
from own_package.models import create_hparams
from own_package.cross_validation import run_kf
from own_package.others import create_results_directory
def selector(case, **kwargs):
if case == 1:
# Run normal KF cross validation for a single hyperparameter
hparams = create_hparams()
model_mode = 'lr'
k_folds = 1
fl_dir = './excel/Data_loader_spline_full_onehot_R1_cut_CM3.xlsx'
other_names = ['ett30']
other_dir = ['./excel/ett30.xlsx']
# Load main training data
fl = load_data_to_fl(fl_dir,
normalise_labels=False,
norm_mask=[0, 1, 3, 4, 5])
fl_store = fl.create_kf(k_folds=k_folds, shuffle=True)
# Load other data to evaluate the model on. e.g. the separate test set
other_fl_dict = {
k: load_testset_to_fl(v,
norm_mask=[0, 1, 3, 4, 5],
scaler=fl.scaler)
for k, v in zip(other_names, other_dir)
}
write_dir = create_results_directory('./results/kf/kf_results',
folders=['models', 'plots'],
excels=['kf_results'])
write_excel = f'{write_dir}/kf_results.xlsx'
from own_package.features_labels_setup import load_data_to_fl, load_testset_to_fl
from own_package.models import create_hparams
from own_package.cross_validation import run_kf
from own_package.others import create_results_directory
def selector(case, **kwargs):
if case == 1:
# Run normal KF cross validation for a single hyperparameter
hparams = create_hparams(loss='mse',
learning_rate=0.001,
reg_l1=0.0005,
reg_l2=0.,
nodes=10,
max_depth=5,
num_est=5,
activation='relu',
epochs=100,
batch_size=16,
verbose=0)
model_mode = 'dtr'
k_folds = 3
fl_dir = './excel/Data_loader_Round13.xlsx'
other_names = ['ett30', 'ettI01']
other_dir = ['./excel/ett30.xlsx', './excel/ett30I01.xlsx']
data_augmentation = 'invariant'
numel = 10
# Load main training data
fl = load_data_to_fl(fl_dir,
normalise_labels=False,
norm_mask=[0, 1, 3, 4, 5])