def run_metocean_forecasting_problem(train_file_path,
test_file_path,
forecast_length=1,
max_window_size=32,
is_visualise=False):
# specify the task to solve
task_to_solve = Task(
TaskTypesEnum.ts_forecasting,
TsForecastingParams(forecast_length=forecast_length,
max_window_size=max_window_size))
full_path_train = os.path.join(str(project_root()), train_file_path)
dataset_to_train = InputData.from_csv(full_path_train,
task=task_to_solve,
data_type=DataTypesEnum.ts)
# a dataset for a final validation of the composed model
full_path_test = os.path.join(str(project_root()), test_file_path)
dataset_to_validate = InputData.from_csv(full_path_test,
task=task_to_solve,
data_type=DataTypesEnum.ts)
chain_simple = TsForecastingChain(PrimaryNode('linear'))
chain_simple.fit(input_data=dataset_to_train, verbose=False)
rmse_on_valid_simple = calculate_validation_metric(
chain_simple.predict(dataset_to_validate),
dataset_to_validate,
f'full-simple_{forecast_length}',
is_visualise=is_visualise)
print(f'RMSE simple: {rmse_on_valid_simple}')
chain_composite_lstm = get_composite_chain()
chain_composite_lstm.fit(input_data=dataset_to_train, verbose=False)
rmse_on_valid_lstm_only = calculate_validation_metric(
chain_composite_lstm.predict(dataset_to_validate),
dataset_to_validate,
f'full-lstm-only_{forecast_length}',
is_visualise=is_visualise)
print(f'RMSE LSTM composite: {rmse_on_valid_lstm_only}')
return rmse_on_valid_simple
def run_metocean_forecasting_problem(train_file_path,
test_file_path,
forecast_length=1,
max_window_size=64,
with_visualisation=True):
# specify the task to solve
task_to_solve = Task(
TaskTypesEnum.ts_forecasting,
TsForecastingParams(forecast_length=forecast_length,
max_window_size=max_window_size,
return_all_steps=False))
full_path_train = os.path.join(str(project_root()), train_file_path)
dataset_to_train = InputData.from_csv(full_path_train,
task=task_to_solve,
data_type=DataTypesEnum.ts)
# a dataset for a final validation of the composed model
full_path_test = os.path.join(str(project_root()), test_file_path)
dataset_to_validate = InputData.from_csv(full_path_test,
task=task_to_solve,
data_type=DataTypesEnum.ts)
metric_function = MetricsRepository().metric_by_id(
RegressionMetricsEnum.RMSE)
time_limit_min = 10
available_model_types = [
'linear', 'ridge', 'lasso', 'rfr', 'dtreg', 'knnreg', 'svr'
]
if max_window_size == 1:
# unit test model
available_model_types = ['linear', 'ridge']
time_limit_min = 0.001
# each possible single-model chain
for model in available_model_types:
chain = TsForecastingChain(PrimaryNode(model))
chain.fit(input_data=dataset_to_train, verbose=False)
calculate_validation_metric(chain.predict(dataset_to_validate),
dataset_to_validate,
is_visualise=with_visualisation,
label=model)
# static multiscale chain
multiscale_chain = get_composite_multiscale_chain()
multiscale_chain.fit(input_data=dataset_to_train, verbose=False)
calculate_validation_metric(multiscale_chain.predict(dataset_to_validate),
dataset_to_validate,
is_visualise=with_visualisation,
label='Fixed multiscale')
# static all-in-one ensemble chain
ens_chain = get_ensemble_chain()
ens_chain.fit(input_data=dataset_to_train, verbose=False)
calculate_validation_metric(ens_chain.predict(dataset_to_validate),
dataset_to_validate,
is_visualise=with_visualisation,
label='Ensemble composite')
# optimized ensemble chain
composer_requirements = GPComposerRequirements(
primary=available_model_types,
secondary=available_model_types,
max_arity=5,
max_depth=2,
pop_size=10,
num_of_generations=10,
crossover_prob=0.8,
mutation_prob=0.8,
max_lead_time=datetime.timedelta(minutes=time_limit_min),
add_single_model_chains=False)
builder = GPComposerBuilder(task=task_to_solve).with_requirements(
composer_requirements).with_metrics(metric_function)
composer = builder.build()
chain = composer.compose_chain(data=dataset_to_train, is_visualise=False)
chain.fit_from_scratch(input_data=dataset_to_train, verbose=False)
if with_visualisation:
ComposerVisualiser.visualise(chain)
calculate_validation_metric(chain.predict(dataset_to_validate),
dataset_to_validate,
is_visualise=with_visualisation,
label='Automated ensemble')
# optimized multiscale chain
available_model_types_primary = ['trend_data_model', 'residual_data_model']
available_model_types_secondary = [
'linear', 'ridge', 'lasso', 'rfr', 'dtreg', 'knnreg', 'svr'
]
available_model_types_all = available_model_types_primary + available_model_types_secondary
composer_requirements = GPComposerRequirements(
primary=available_model_types_all,
secondary=available_model_types_secondary,
max_arity=5,
max_depth=2,
pop_size=10,
num_of_generations=30,
crossover_prob=0.8,
mutation_prob=0.8,
max_lead_time=datetime.timedelta(minutes=time_limit_min))
builder = GPComposerBuilder(task=task_to_solve).with_requirements(
composer_requirements).with_metrics(
metric_function).with_initial_chain(multiscale_chain)
composer = builder.build()
chain = composer.compose_chain(data=dataset_to_train, is_visualise=False)
chain.fit_from_scratch(input_data=dataset_to_train, verbose=False)
if with_visualisation:
visualiser = ChainVisualiser()
visualiser.visualise(chain)
rmse_on_valid = calculate_validation_metric(
chain.predict(dataset_to_validate),
dataset_to_validate,
is_visualise=with_visualisation,
label='Automated multiscale')
return rmse_on_valid