AutoModels
NeuralForecast contains user-friendly implementations of neural forecasting models that allow for easy transition of computing capabilities (GPU/CPU), computation parallelization, and hyperparameter tuning.
All the NeuralForecast models are “global” because we train them with
all the series from the input pd.DataFrame data Y_df
, yet the
optimization objective is, momentarily, “univariate” as it does not
consider the interaction between the output predictions across time
series. Like the StatsForecast library, core.NeuralForecast
allows you
to explore collections of models efficiently and contains functions for
convenient wrangling of input and output pd.DataFrames predictions.
First we load the AirPassengers dataset such that you can run all the examples.
1. Automatic Forecasting
A. RNN-Based
source
AutoRNN
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc000ecd6f0> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoLSTM
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc00006ded0> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoGRU
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0011b8190> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoTCN
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0002a4190> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoDeepAR
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | DistributionLoss | DistributionLoss() | Instantiated train loss class from losses collection. |
valid_loss | MQLoss | MQLoss() | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc00005df00> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoDilatedRNN
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc00029fc70> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoBiTCN
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0000395d0> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
B. MLP-Based
source
AutoMLP
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc00004e080> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoNBEATS
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc02a71fb20> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoNBEATSx
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc000005e40> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoNHITS
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc000014520> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoDLinear
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0001eea40> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoNLinear
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0001c6620> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoTiDE
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0003d5840> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoDeepNPTS
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0000074c0> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
C. KAN-Based
source
AutoKAN
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0003c6350> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
D. Transformer-Based
source
AutoTFT
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc00039dd80> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoVanillaTransformer
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc00003bf70> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoInformer
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0001b8040> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoAutoformer
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0001455d0> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoFEDformer
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0003d4370> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoPatchTST
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc000194790> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoiTransformer
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
n_series | |||
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0001617e0> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
E. CNN Based
source
AutoTimesNet
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc000184100> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
F. Multivariate
source
AutoStemGNN
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
n_series | |||
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc00016f850> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoHINT
*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.*
Type | Default | Details | |
---|---|---|---|
cls_model | PyTorch/PyTorchLightning model | See neuralforecast.models collection here. | |
h | int | Forecast horizon | |
loss | PyTorch module | Instantiated train loss class from losses collection. | |
valid_loss | PyTorch module | Instantiated valid loss class from losses collection. | |
S | |||
config | dict or callable | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. | |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc000f4d990> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoTSMixer
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
n_series | |||
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc000f4c640> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoTSMixerx
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
n_series | |||
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc000f4c310> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoMLPMultivariate
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
n_series | |||
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc02a8259c0> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoSOFTS
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
n_series | |||
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc000134c40> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoTimeMixer
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
n_series | |||
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc0001372b0> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |
source
AutoRMoK
*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.*
Type | Default | Details | |
---|---|---|---|
h | int | Forecast horizon | |
n_series | |||
loss | MAE | MAE() | Instantiated train loss class from losses collection. |
valid_loss | NoneType | None | Instantiated valid loss class from losses collection. |
config | NoneType | None | Dictionary with ray.tune defined search space or function that takes an optuna trial and returns a configuration dict. |
search_alg | BasicVariantGenerator | <ray.tune.search.basic_variant.BasicVariantGenerator object at 0x7fc00025d750> | 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_samples | int | 10 | Number of hyperparameter optimization steps/samples. |
refit_with_val | bool | False | Refit of best model should preserve val_size. |
cpus | int | 4 | Number of cpus to use during optimization. Only used with ray tune. |
gpus | int | 0 | Number of gpus to use during optimization, default all available. Only used with ray tune. |
verbose | bool | False | Track progress. |
alias | NoneType | None | Custom name of the model. |
backend | str | ray | Backend to use for searching the hyperparameter space, can be either ‘ray’ or ‘optuna’. |
callbacks | NoneType | None | List 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 |