TiDE
Time-series Dense Encoder (TiDE
) is a MLP-based univariate time-series forecasting model. TiDE
uses Multi-layer Perceptrons (MLPs) in an encoder-decoder model for long-term time-series forecasting. In addition, this model can handle exogenous inputs.
1. Auxiliary Functions
1.1 MLP residual
An MLP block with a residual connection.
source
MLPResidual
MLPResidual (input_dim, hidden_size, output_dim, dropout, layernorm)
MLPResidual
2. Model
source
TiDE
TiDE (h, input_size, hidden_size=512, decoder_output_dim=32, temporal_decoder_dim=128, dropout=0.3, layernorm=True, num_encoder_layers=1, num_decoder_layers=1, temporal_width=4, futr_exog_list=None, hist_exog_list=None, stat_exog_list=None, exclude_insample_y=False, loss=MAE(), valid_loss=None, max_steps:int=1000, learning_rate:float=0.001, num_lr_decays:int=-1, early_stop_patience_steps:int=-1, val_check_steps:int=100, batch_size:int=32, valid_batch_size:Optional[int]=None, windows_batch_size=1024, inference_windows_batch_size=1024, start_padding_enabled=False, step_size:int=1, scaler_type:str='identity', random_seed:int=1, num_workers_loader:int=0, drop_last_loader:bool=False, optimizer=None, optimizer_kwargs=None, lr_scheduler=None, lr_scheduler_kwargs=None, **trainer_kwargs)
*TiDE
Time-series Dense Encoder
(TiDE
)
is a MLP-based univariate time-series forecasting model.
TiDE
uses Multi-layer Perceptrons (MLPs) in an encoder-decoder model for
long-term time-series forecasting.
Parameters:
h
: int, forecast horizon.
input_size
: int,
considered autorregresive inputs (lags), y=[1,2,3,4] input_size=2 ->
lags=[1,2].
hidden_size
: int=1024, number of units for the dense
MLPs.
decoder_output_dim
: int=32, number of units for the output
of the decoder.
temporal_decoder_dim
: int=128, number of units for
the hidden sizeof the temporal decoder.
dropout
: float=0.0,
dropout rate between (0, 1) .
layernorm
: bool=True, if True uses
Layer Normalization on the MLP residual block outputs.
num_encoder_layers
: int=1, number of encoder layers.
num_decoder_layers
: int=1, number of decoder layers.
temporal_width
: int=4, lower temporal projected dimension.
futr_exog_list
: str list, future exogenous columns.
hist_exog_list
: str list, historic exogenous columns.
stat_exog_list
: str list, static exogenous columns.
loss
: PyTorch module, instantiated train loss class from losses
collection.
valid_loss
: PyTorch module=loss
, instantiated valid loss class from
losses
collection.
max_steps
: int=1000, maximum number of training steps.
learning_rate
: float=1e-3, Learning rate between (0, 1).
num_lr_decays
: int=-1, Number of learning rate decays, evenly
distributed across max_steps.
early_stop_patience_steps
: int=-1,
Number of validation iterations before early stopping.
val_check_steps
: int=100, Number of training steps between every
validation loss check.
batch_size
: int=32, number of different
series in each batch.
step_size
: int=1, step size between each
window of temporal data.
scaler_type
: str=‘identity’, type of
scaler for temporal inputs normalization see temporal
scalers.
random_seed
: int=1, random_seed for pytorch initializer and numpy
generators.
num_workers_loader
: int=os.cpu_count(), workers to be
used by TimeSeriesDataLoader
.
drop_last_loader
: bool=False, if
True TimeSeriesDataLoader
drops last non-full batch.
alias
: str,
optional, Custom name of the model.
optimizer
: Subclass of
‘torch.optim.Optimizer’, optional, user specified optimizer instead of
the default choice (Adam).
optimizer_kwargs
: dict, optional, list
of parameters used by the user specified optimizer
.
lr_scheduler
: Subclass of ‘torch.optim.lr_scheduler.LRScheduler’,
optional, user specified lr_scheduler instead of the default choice
(StepLR).
lr_scheduler_kwargs
: dict, optional, list of parameters
used by the user specified lr_scheduler
.
**trainer_kwargs
: int,
keyword trainer arguments inherited from PyTorch Lighning’s
trainer.
TiDE.fit
TiDE.fit (dataset, val_size=0, test_size=0, random_seed=None, distributed_config=None)
*Fit.
The fit
method, optimizes the neural network’s weights using the
initialization parameters (learning_rate
, windows_batch_size
, …) and
the loss
function as defined during the initialization. Within fit
we use a PyTorch Lightning Trainer
that inherits the initialization’s
self.trainer_kwargs
, to customize its inputs, see PL’s trainer
arguments.
The method is designed to be compatible with SKLearn-like classes and in particular to be compatible with the StatsForecast library.
By default the model
is not saving training checkpoints to protect
disk memory, to get them change enable_checkpointing=True
in
__init__
.
Parameters:
dataset
: NeuralForecast’s
TimeSeriesDataset
,
see
documentation.
val_size
: int, validation size for temporal cross-validation.
random_seed
: int=None, random_seed for pytorch initializer and numpy
generators, overwrites model.__init__’s.
test_size
: int, test
size for temporal cross-validation.
*
TiDE.predict
TiDE.predict (dataset, test_size=None, step_size=1, random_seed=None, **data_module_kwargs)
*Predict.
Neural network prediction with PL’s Trainer
execution of
predict_step
.
Parameters:
dataset
: NeuralForecast’s
TimeSeriesDataset
,
see
documentation.
test_size
: int=None, test size for temporal cross-validation.
step_size
: int=1, Step size between each window.
random_seed
:
int=None, random_seed for pytorch initializer and numpy generators,
overwrites model.__init__’s.
**data_module_kwargs
: PL’s
TimeSeriesDataModule args, see
documentation.*
3. Usage Examples
import pandas as pd
import matplotlib.pyplot as plt
from neuralforecast import NeuralForecast
from neuralforecast.models import TiDE
from neuralforecast.losses.pytorch import GMM, DistributionLoss
from neuralforecast.utils import AirPassengersPanel, AirPassengersStatic
Y_train_df = AirPassengersPanel[AirPassengersPanel.ds<AirPassengersPanel['ds'].values[-12]] # 132 train
Y_test_df = AirPassengersPanel[AirPassengersPanel.ds>=AirPassengersPanel['ds'].values[-12]].reset_index(drop=True) # 12 test
fcst = NeuralForecast(
models=[
TiDE(h=12,
input_size=24,
loss=GMM(n_components=7, return_params=True, level=[80,90]),
max_steps=500,
scaler_type='standard',
futr_exog_list=['y_[lag12]'],
hist_exog_list=None,
stat_exog_list=['airline1'],
),
],
freq='M'
)
fcst.fit(df=Y_train_df, static_df=AirPassengersStatic)
forecasts = fcst.predict(futr_df=Y_test_df)
# Plot quantile predictions
Y_hat_df = forecasts.reset_index(drop=False).drop(columns=['unique_id','ds'])
plot_df = pd.concat([Y_test_df, Y_hat_df], axis=1)
plot_df = pd.concat([Y_train_df, plot_df])
plot_df = plot_df[plot_df.unique_id=='Airline1'].drop('unique_id', axis=1)
plt.plot(plot_df['ds'], plot_df['y'], c='black', label='True')
plt.plot(plot_df['ds'], plot_df['TiDE-median'], c='blue', label='median')
plt.fill_between(x=plot_df['ds'][-12:],
y1=plot_df['TiDE-lo-90'][-12:].values,
y2=plot_df['TiDE-hi-90'][-12:].values,
alpha=0.4, label='level 90')
plt.legend()
plt.grid()