​
BaseAuto

 BaseAuto (cls_model, h, loss, valid_loss, config,
           search_alg=<ray.tune.search.basic_variant.BasicVariantGenerator
           object at 0x7f95d4cc5f90>, num_samples=10, cpus=4, gpus=0,
           refit_with_val=False, verbose=False, alias=None, backend='ray',
           callbacks=None)

*Class for Automatic Hyperparameter Optimization, it builds on top of ray to give access to a wide variety of hyperparameter optimization tools ranging from classic grid search, to Bayesian optimization and HyperBand algorithm.

The validation loss to be optimized is defined by the config['loss'] dictionary value, the config also contains the rest of the hyperparameter search space.

It is important to note that the success of this hyperparameter optimization heavily relies on a strong correlation between the validation and test periods.*

TypeDefaultDetails
cls_modelPyTorch/PyTorchLightning modelSee neuralforecast.models collection here.
hintForecast horizon
lossPyTorch moduleInstantiated train loss class from losses collection.
valid_lossPyTorch moduleInstantiated valid loss class from losses collection.
configdict or callableDictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict.
search_algBasicVariantGenerator<ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7f95d4cc5f90>For ray see https://docs.ray.io/en/latest/tune/api_docs/suggestion.html
For optuna see https://optuna.readthedocs.io/en/stable/reference/samplers/index.html.
num_samplesint10Number of hyperparameter optimization steps/samples.
cpusint4Number of cpus to use during optimization. Only used with ray tune.
gpusint0Number of gpus to use during optimization, default all available. Only used with ray tune.
refit_with_valboolFalseRefit of best model should preserve val_size.
verboseboolFalseTrack progress.
aliasNoneTypeNoneCustom name of the model.
backendstrrayBackend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’.
callbacksNoneTypeNoneList of functions to call during the optimization process.
ray reference: https://docs.ray.io/en/latest/tune/tutorials/tune-metrics.html
optuna reference: https://optuna.readthedocs.io/en/stable/tutorial/20_recipes/007_optuna_callback.html

​
BaseAuto.fit

 BaseAuto.fit (dataset, val_size=0, test_size=0, random_seed=None,
               distributed_config=None)

*BaseAuto.fit

Perform the hyperparameter optimization as specified by the BaseAuto configuration dictionary config.

The optimization is performed on the TimeSeriesDataset using temporal cross validation with the validation set that sequentially precedes the test set.

Parameters:
dataset: NeuralForecast’s TimeSeriesDataset see details here
val_size: int, size of temporal validation set (needs to be bigger than 0).
test_size: int, size of temporal test set (default 0).
random_seed: int=None, random_seed for hyperparameter exploration algorithms, not yet implemented.
Returns:
self: fitted instance of BaseAuto with best hyperparameters and results
.*

​
BaseAuto.predict

 BaseAuto.predict (dataset, step_size=1, **data_kwargs)

*BaseAuto.predict

Predictions of the best performing model on validation.

Parameters:
dataset: NeuralForecast’s TimeSeriesDataset see details here
step_size: int, steps between sequential predictions, (default 1).
**data_kwarg: additional parameters for the dataset module.
random_seed: int=None, random_seed for hyperparameter exploration algorithms (not implemented).
Returns:
y_hat: numpy predictions of the NeuralForecast model.
*

class RayLogLossesCallback(tune.Callback):
    def on_trial_complete(self, iteration, trials, trial, **info):
        result = trial.last_result
        print(40 * '-' + 'Trial finished' + 40 * '-')
        print(f'Train loss: {result["train_loss"]:.2f}. Valid loss: {result["loss"]:.2f}')
        print(80 * '-')

config = {
    "hidden_size": tune.choice([512]),
    "num_layers": tune.choice([3, 4]),
    "input_size": 12,
    "max_steps": 10,
    "val_check_steps": 5
}
auto = BaseAuto(h=12, loss=MAE(), valid_loss=MSE(), cls_model=MLP, config=config, num_samples=2, cpus=1, gpus=0, callbacks=[RayLogLossesCallback()])
auto.fit(dataset=dataset)
y_hat = auto.predict(dataset=dataset)
assert mae(Y_test_df['y'].values, y_hat[:, 0]) < 200

def config_f(trial):
    return {
        "hidden_size": trial.suggest_categorical('hidden_size', [512]),
        "num_layers": trial.suggest_categorical('num_layers', [3, 4]),
        "input_size": 12,
        "max_steps": 10,
        "val_check_steps": 5
    }

class OptunaLogLossesCallback:
    def __call__(self, study, trial):
        metrics = trial.user_attrs['METRICS']
        print(40 * '-' + 'Trial finished' + 40 * '-')
        print(f'Train loss: {metrics["train_loss"]:.2f}. Valid loss: {metrics["loss"]:.2f}')
        print(80 * '-')

auto2 = BaseAuto(h=12, loss=MAE(), valid_loss=MSE(), cls_model=MLP, config=config_f, search_alg=optuna.samplers.RandomSampler(), num_samples=2, backend='optuna', callbacks=[OptunaLogLossesCallback()])
auto2.fit(dataset=dataset)
assert isinstance(auto2.results, optuna.Study)
y_hat2 = auto2.predict(dataset=dataset)
assert mae(Y_test_df['y'].values, y_hat2[:, 0]) < 200

​
References

NumPy EvaluationBaseRecurrent